{"schema":"fast-research.authors/2","retrievedAt":"2026-10-19","year":2025,"yearField":"DBLP yearOfPublication","listSource":"https://gaplab.cuhk.edu.cn/slow_research/#statement","bibliographySource":"https://sparql.dblp.org/","population":120,"countedAuthors":111,"unresolvedAuthors":9,"authorPaperIncidences":2705,"uniqueDblpKeys":2523,"median":20,"namedLabEntries":90,"teamGroups":113,"preprintCountedAuthors":105,"preprintUnresolvedAuthors":15,"preprintAuthorPaperIncidences":2151,"uniqueArxivIds":2008,"preprintMedian":18,"notes":["All author positions count; this is not a lab-output or quality metric.","Null counts are missing, not zero. Verified subsets for mixed identities are excluded from aggregates.","Conference workshops are included. CoRR, informal and identified non-research/editorial/homonym records are excluded.","Publication year can differ from conference year. Distinct DBLP keys may include conference/journal versions of the same underlying research."],"authors":[{"index":0,"name":"Jon Barron","nameZh":"Jon Barron","role":"Senior Research Scientist","affiliation":"Google Research","source":"DBLP official SPARQL","profileUrl":"https://dblp.org/pid/30/9988","identifier":"30/9988","identityEvidence":[{"url":"https://dblp.org/pid/30/9988","evidence":"DBLP 唯一同名作者档案；通过作者/机构主页与发表题名交叉核对。"},{"url":"https://jonbarron.info/","evidence":"作者/机构页面与该 DBLP 档案交叉匹配的题名示例：MIRA: Mental Imagery for Robotic Affordances.；AligNeRF: High-Fidelity Neural Radiance Fields via Alignment-Aware Training.","matchedPaperKeys":["conf/corl/LinFZBDMSGI22","conf/cvpr/0001HMXBWX23"]},{"url":"https://research.google/people/jonathanbarron/","evidence":"Google Research 的 Jonathan T. Barron 档案指向 jonbarron.info；确认 Jon Barron 与 DBLP Jonathan T. Barron 的姓名对应。"}],"count2025":10,"conference2025":8,"journal2025":2,"preprint2025":4,"status":"verified","notes":"声明采用 Jon Barron；DBLP 使用 Jonathan T. Barron。Google Research 官方人物页与作者主页交叉确认。","retrievedAt":"2026-10-19","yearPolicy":"DBLP yearOfPublication = 2025","queryUrl":"https://sparql.dblp.org/sparql?query=PREFIX%20dblp%3A%20%3Chttps%3A//dblp.org/rdf/schema%23%3E%20PREFIX%20xsd%3A%20%3Chttp%3A//www.w3.org/2001/XMLSchema%23%3E%20SELECT%20%3Fpub%20%3Ftitle%20%3Ftype%20%3Fvenue%20WHERE%20%7B%20%3Fpub%20dblp%3AauthoredBy%20%3Chttps%3A//dblp.org/pid/30/9988%3E%3B%20dblp%3AyearOfPublication%20%222025%22%5E%5Exsd%3AgYear%3B%20dblp%3Atitle%20%3Ftitle%3B%20a%20%3Ftype%20.%20OPTIONAL%20%7B%20%3Fpub%20dblp%3ApublishedIn%20%3Fvenue%20%7D%20%7D&format=json","papers":[{"key":"conf/cvpr/AlzayerHBHSV25","title":"Generative Multiview Relighting for 3D Reconstruction under Extreme Illumination Variation.","type":"Inproceedings","venue":"CVPR","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/CVPR52734.2025.01021","sourceUrl":"https://dblp.org/rec/conf/cvpr/AlzayerHBHSV25","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Alzayer_Generative_Multiview_Relighting_for_3D_Reconstruction_under_Extreme_Illumination_Variation_CVPR_2025_paper.html","pages":"10933-10942"},{"key":"conf/cvpr/TrevithickPHVWA25","title":"SimVS: Simulating World Inconsistencies for Robust View Synthesis.","type":"Inproceedings","venue":"CVPR","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/CVPR52734.2025.01535","sourceUrl":"https://dblp.org/rec/conf/cvpr/TrevithickPHVWA25","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Trevithick_SimVS_Simulating_World_Inconsistencies_for_Robust_View_Synthesis_CVPR_2025_paper.html","pages":"16464-16474"},{"key":"conf/cvpr/WuGPTZBH25","title":"CAT4D: Create Anything in 4D with Multi-View Video Diffusion Models.","type":"Inproceedings","venue":"CVPR","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/CVPR52734.2025.02427","sourceUrl":"https://dblp.org/rec/conf/cvpr/WuGPTZBH25","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Wu_CAT4D_Create_Anything_in_4D_with_Multi-View_Video_Diffusion_Models_CVPR_2025_paper.html","pages":"26057-26068"},{"key":"conf/eccv/AttalVMHBOS24","title":"Flash Cache: Reducing Bias in Radiance Cache Based Inverse Rendering.","type":"Inproceedings","venue":"ECCV (28)","year":2025,"yearOfPublication":2025,"yearOfEvent":2024,"doi":"https://doi.org/10.1007/978-3-031-73390-1_2","sourceUrl":"https://dblp.org/rec/conf/eccv/AttalVMHBOS24","documentUrl":"https://doi.org/10.1007/978-3-031-73390-1_2","pages":"20-36"},{"key":"conf/eccv/SrinivasanGVBM24","title":"Nuvo: Neural UV Mapping for Unruly 3D Representations.","type":"Inproceedings","venue":"ECCV (39)","year":2025,"yearOfPublication":2025,"yearOfEvent":2024,"doi":"https://doi.org/10.1007/978-3-031-72933-1_2","sourceUrl":"https://dblp.org/rec/conf/eccv/SrinivasanGVBM24","documentUrl":"https://doi.org/10.1007/978-3-031-72933-1_2","pages":"18-34"},{"key":"conf/iccv/MaiHKVFXKBZ25","title":"EVER: Exact Volumetric Ellipsoid Rendering for Real-Time View Synthesis.","type":"Inproceedings","venue":"ICCV","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/ICCV51701.2025.00469","sourceUrl":"https://dblp.org/rec/conf/iccv/MaiHKVFXKBZ25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.00469","pages":"4930-4939"},{"key":"conf/iccv/SzymanowiczZSGBHMBH25","title":"Bolt3D: Generating 3D Scenes in Seconds.","type":"Inproceedings","venue":"ICCV","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/ICCV51701.2025.02304","sourceUrl":"https://dblp.org/rec/conf/iccv/SzymanowiczZSGBHMBH25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.02304","pages":"24846-24857"},{"key":"conf/nips/NiemeyerMROTTBT25","title":"Learning Neural Exposure Fields for View Synthesis.","type":"Inproceedings","venue":"NeurIPS","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":null,"sourceUrl":"https://dblp.org/rec/conf/nips/NiemeyerMROTTBT25","documentUrl":"http://papers.nips.cc/paper_files/paper/2025/hash/c55e6792923cc16fd6ed5c3f672420a5-Abstract-Conference.html","pages":null},{"key":"journals/pami/HedmanSMRBD25","title":"Baking Neural Radiance Fields for Real-Time View Synthesis.","type":"Article","venue":"IEEE Trans. Pattern Anal. Mach. Intell.","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.1109/TPAMI.2024.3381001","sourceUrl":"https://dblp.org/rec/journals/pami/HedmanSMRBD25","documentUrl":"https://doi.org/10.1109/TPAMI.2024.3381001","pages":"3310-3321"},{"key":"journals/pami/VerbinHMZBS25","title":"Ref-NeRF: Structured View-Dependent Appearance for Neural Radiance Fields.","type":"Article","venue":"IEEE Trans. Pattern Anal. Mach. Intell.","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.1109/TPAMI.2024.3360018","sourceUrl":"https://dblp.org/rec/journals/pami/VerbinHMZBS25","documentUrl":"https://doi.org/10.1109/TPAMI.2024.3360018","pages":"9426-9437"}],"preprints":[{"key":"journals/corr/abs-2502-10647","title":"A Power Transform.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2502.10647","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2502-10647","documentUrl":"https://doi.org/10.48550/ARXIV.2502.10647","pages":null,"arxivId":"2502.10647","arxivUrl":"https://arxiv.org/abs/2502.10647"},{"key":"journals/corr/abs-2503-14445","title":"Bolt3D: Generating 3D Scenes in Seconds.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2503.14445","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-14445","documentUrl":"https://doi.org/10.48550/ARXIV.2503.14445","pages":null,"arxivId":"2503.14445","arxivUrl":"https://arxiv.org/abs/2503.14445"},{"key":"journals/corr/abs-2510-08279","title":"Learning Neural Exposure Fields for View Synthesis.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2510.08279","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-08279","documentUrl":"https://doi.org/10.48550/ARXIV.2510.08279","pages":null,"arxivId":"2510.08279","arxivUrl":"https://arxiv.org/abs/2510.08279"},{"key":"journals/corr/abs-2512-04076","title":"Radiance Meshes for Volumetric Reconstruction.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2512.04076","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-04076","documentUrl":"https://doi.org/10.48550/ARXIV.2512.04076","pages":null,"arxivId":"2512.04076","arxivUrl":"https://arxiv.org/abs/2512.04076"}],"excludedFormal":[],"labName":null,"labUrl":null,"labEvidence":"本轮检查本人主页及团队检索，确认 Google Research 任职，但未确认当前具名 Lab；不把公司研究机构直接改写为个人团队。","labSourceUrl":"https://jonbarron.info/","affiliationZh":"Google Research","sourceWarning":false,"excludedOther":[],"excludedHomonyms":[],"unassignedCandidates":[],"knownPreprintMinimum2025":null,"excludedMisattributed":[],"displayNotes":"原名单写作 Jon Barron，对应 DBLP 档案 Jonathan T. Barron，已经 Google Research 人物页与个人主页交叉确认。2025 年正式记录 10 条（会议 8、期刊 2），所有作者位置均计入；预印本 4 条单列，不加总。","labDisplayNotes":"个人主页确认其任职于 Google Research，但未见具名的个人团队；不把公司研究部门当作 Lab，图中以「姓名及合作者」单列。"},{"index":1,"name":"Angela Dai","nameZh":"Angela Dai","role":"Associate Professor","affiliation":"Technical University of Munich","source":"DBLP official SPARQL","profileUrl":"https://dblp.org/pid/149/1202","identifier":"149/1202","identityEvidence":[{"url":"https://dblp.org/pid/149/1202","evidence":"DBLP 档案名 Angela Dai；机构/履历：Stanford University, USA；TU Munich, Germany"}],"count2025":14,"conference2025":13,"journal2025":1,"preprint2025":13,"status":"verified","notes":"身份已通过机构/个人主页或 DBLP 机构信息核对；篇数为数据库记录统计，不表示每篇均由本人主导。","retrievedAt":"2026-10-19","yearPolicy":"DBLP yearOfPublication = 2025","queryUrl":"https://sparql.dblp.org/sparql?query=PREFIX%20dblp%3A%20%3Chttps%3A//dblp.org/rdf/schema%23%3E%20PREFIX%20xsd%3A%20%3Chttp%3A//www.w3.org/2001/XMLSchema%23%3E%20SELECT%20%3Fpub%20%3Ftitle%20%3Ftype%20%3Fvenue%20WHERE%20%7B%20%3Fpub%20dblp%3AauthoredBy%20%3Chttps%3A//dblp.org/pid/149/1202%3E%3B%20dblp%3AyearOfPublication%20%222025%22%5E%5Exsd%3AgYear%3B%20dblp%3Atitle%20%3Ftitle%3B%20a%20%3Ftype%20.%20OPTIONAL%20%7B%20%3Fpub%20dblp%3ApublishedIn%20%3Fvenue%20%7D%20%7D&format=json","papers":[{"key":"conf/cvpr/BokhovkinMTD25","title":"SceneFactor: Factored Latent 3D Diffusion for Controllable 3D Scene Generation.","type":"Inproceedings","venue":"CVPR","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/CVPR52734.2025.00067","sourceUrl":"https://dblp.org/rec/conf/cvpr/BokhovkinMTD25","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Bokhovkin_SceneFactor_Factored_Latent_3D_Diffusion_for_Controllable_3D_Scene_Generation_CVPR_2025_paper.html","pages":"628-639"},{"key":"conf/cvpr/ErkocG0NDW0Z25","title":"PrEditor3D: Fast and Precise 3D Shape Editing.","type":"Inproceedings","venue":"CVPR","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/CVPR52734.2025.00068","sourceUrl":"https://dblp.org/rec/conf/cvpr/ErkocG0NDW0Z25","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Erkoc_PrEditor3D_Fast_and_Precise_3D_Shape_Editing_CVPR_2025_paper.html","pages":"640-649"},{"key":"conf/cvpr/GaoSLD25","title":"MeshArt: Generating Articulated Meshes with Structure-Guided Transformers.","type":"Inproceedings","venue":"CVPR","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/CVPR52734.2025.00066","sourceUrl":"https://dblp.org/rec/conf/cvpr/GaoSLD25","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Gao_MeshArt_Generating_Articulated_Meshes_with_Structure-Guided_Transformers_CVPR_2025_paper.html","pages":"618-627"},{"key":"conf/cvpr/Meng0ND25","title":"LT3SD: Latent Trees for 3D Scene Diffusion.","type":"Inproceedings","venue":"CVPR","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/CVPR52734.2025.00069","sourceUrl":"https://dblp.org/rec/conf/cvpr/Meng0ND25","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Meng_LT3SD_Latent_Trees_for_3D_Scene_Diffusion_CVPR_2025_paper.html","pages":"650-660"},{"key":"conf/cvpr/ZhangLD25","title":"DNF: Unconditional 4D Generation with Dictionary-based Neural Fields.","type":"Inproceedings","venue":"CVPR","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/CVPR52734.2025.02426","sourceUrl":"https://dblp.org/rec/conf/cvpr/ZhangLD25","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Zhang_DNF_Unconditional_4D_Generation_with_Dictionary-based_Neural_Fields_CVPR_2025_paper.html","pages":"26047-26056"},{"key":"conf/humanoids/TaouilZDK25","title":"Physically Consistent Humanoid Loco-Manipulation Using Latent Diffusion Models.","type":"Inproceedings","venue":"Humanoids","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/HUMANOIDS65713.2025.11203092","sourceUrl":"https://dblp.org/rec/conf/humanoids/TaouilZDK25","documentUrl":"https://doi.org/10.1109/HUMANOIDS65713.2025.11203092","pages":"1-8"},{"key":"conf/iccv/AnejaSKTDN25","title":"GaussianSpeech: Audio-Driven Personalized 3D Gaussian Avatars.","type":"Inproceedings","venue":"ICCV","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/ICCV51701.2025.01214","sourceUrl":"https://dblp.org/rec/conf/iccv/AnejaSKTDN25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.01214","pages":"13065-13075"},{"key":"conf/iccv/BoudjoghraLD25","title":"ScanEdit: Hierarchically-Guided Functional 3D Scan Editing.","type":"Inproceedings","venue":"ICCV","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/ICCV51701.2025.02516","sourceUrl":"https://dblp.org/rec/conf/iccv/BoudjoghraLD25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.02516","pages":"27105-27115"},{"key":"conf/iccv/LiELSRDN25","title":"MeshPad: Interactive Sketch-Conditioned Artist-Reminiscent Mesh Generation and Editing.","type":"Inproceedings","venue":"ICCV","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/ICCV51701.2025.01506","sourceUrl":"https://dblp.org/rec/conf/iccv/LiELSRDN25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.01506","pages":"16227-16237"},{"key":"conf/iccv/LiuHND25","title":"QuickSplat: Fast 3D Surface Reconstruction via Learned Gaussian Initialization.","type":"Inproceedings","venue":"ICCV","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/ICCV51701.2025.02585","sourceUrl":"https://dblp.org/rec/conf/iccv/LiuHND25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.02585","pages":"27851-27861"},{"key":"conf/iccv/PiersonLDO25","title":"DiffuMatch: Category-Agnostic Spectral Diffusion Priors for Robust Non-Rigid Shape Matching.","type":"Inproceedings","venue":"ICCV","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/ICCV51701.2025.00544","sourceUrl":"https://dblp.org/rec/conf/iccv/PiersonLDO25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.00544","pages":"5745-5756"},{"key":"conf/iccv/YeshwanthRD25","title":"ExCap3d: Expressive 3D Scene Understanding via Object Captioning with Varying Detail.","type":"Inproceedings","venue":"ICCV","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/ICCV51701.2025.02015","sourceUrl":"https://dblp.org/rec/conf/iccv/YeshwanthRD25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.02015","pages":"21699-21709"},{"key":"conf/iclr/BoudjoghraDLCA025","title":"Open-YOLO 3D: Towards Fast and Accurate Open-Vocabulary 3D Instance Segmentation.","type":"Inproceedings","venue":"ICLR","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":null,"sourceUrl":"https://dblp.org/rec/conf/iclr/BoudjoghraDLCA025","documentUrl":"https://openreview.net/forum?id=CRmiX0v16e","pages":null},{"key":"journals/ral/TaouilAKDBTS25","title":"Non-Gaited Legged Locomotion With Monte-Carlo Tree Search and Supervised Learning.","type":"Article","venue":"IEEE Robotics Autom. Lett.","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.1109/LRA.2024.3519908","sourceUrl":"https://dblp.org/rec/journals/ral/TaouilAKDBTS25","documentUrl":"https://doi.org/10.1109/LRA.2024.3519908","pages":"1265-1272"}],"preprints":[{"key":"journals/corr/abs-2502-05118","title":"Use of Winsome Robots for Understanding Human Feedback (UWU).","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2502.05118","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2502-05118","documentUrl":"https://doi.org/10.48550/ARXIV.2502.05118","pages":null,"arxivId":"2502.05118","arxivUrl":"https://arxiv.org/abs/2502.05118"},{"key":"journals/corr/abs-2503-01425","title":"MeshPad: Interactive Sketch-Conditioned Artist-Designed Mesh Generation and Editing.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2503.01425","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-01425","documentUrl":"https://doi.org/10.48550/ARXIV.2503.01425","pages":null,"arxivId":"2503.01425","arxivUrl":"https://arxiv.org/abs/2503.01425"},{"key":"journals/corr/abs-2503-15996","title":"Animating the Uncaptured: Humanoid Mesh Animation with Video Diffusion Models.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2503.15996","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-15996","documentUrl":"https://doi.org/10.48550/ARXIV.2503.15996","pages":null,"arxivId":"2503.15996","arxivUrl":"https://arxiv.org/abs/2503.15996"},{"key":"journals/corr/abs-2503-17044","title":"ExCap3D: Expressive 3D Scene Understanding via Object Captioning with Varying Detail.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2503.17044","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-17044","documentUrl":"https://doi.org/10.48550/ARXIV.2503.17044","pages":null,"arxivId":"2503.17044","arxivUrl":"https://arxiv.org/abs/2503.17044"},{"key":"journals/corr/abs-2503-17400","title":"TripNet: Learning Large-scale High-fidelity 3D Car Aerodynamics with Triplane Networks.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2503.17400","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-17400","documentUrl":"https://doi.org/10.48550/ARXIV.2503.17400","pages":null,"arxivId":"2503.17400","arxivUrl":"https://arxiv.org/abs/2503.17400"},{"key":"journals/corr/abs-2503-23315","title":"AI Agents in Engineering Design: A Multi-Agent Framework for Aesthetic and Aerodynamic Car Design.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2503.23315","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-23315","documentUrl":"https://doi.org/10.48550/ARXIV.2503.23315","pages":null,"arxivId":"2503.23315","arxivUrl":"https://arxiv.org/abs/2503.23315"},{"key":"journals/corr/abs-2504-15049","title":"ScanEdit: Hierarchically-Guided Functional 3D Scan Editing.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2504.15049","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2504-15049","documentUrl":"https://doi.org/10.48550/ARXIV.2504.15049","pages":null,"arxivId":"2504.15049","arxivUrl":"https://arxiv.org/abs/2504.15049"},{"key":"journals/corr/abs-2504-16843","title":"Physically Consistent Humanoid Loco-Manipulation using Latent Diffusion Models.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2504.16843","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2504-16843","documentUrl":"https://doi.org/10.48550/ARXIV.2504.16843","pages":null,"arxivId":"2504.16843","arxivUrl":"https://arxiv.org/abs/2504.16843"},{"key":"journals/corr/abs-2505-05591","title":"QuickSplat: Fast 3D Surface Reconstruction via Learned Gaussian Initialization.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2505.05591","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-05591","documentUrl":"https://doi.org/10.48550/ARXIV.2505.05591","pages":null,"arxivId":"2505.05591","arxivUrl":"https://arxiv.org/abs/2505.05591"},{"key":"journals/corr/abs-2505-07396","title":"TUM2TWIN: Introducing the Large-Scale Multimodal Urban Digital Twin Benchmark Dataset.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2505.07396","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-07396","documentUrl":"https://doi.org/10.48550/ARXIV.2505.07396","pages":null,"arxivId":"2505.07396","arxivUrl":"https://arxiv.org/abs/2505.07396"},{"key":"journals/corr/abs-2506-07209","title":"HOI-PAGE: Zero-Shot Human-Object Interaction Generation with Part Affordance Guidance.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2506.07209","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-07209","documentUrl":"https://doi.org/10.48550/ARXIV.2506.07209","pages":null,"arxivId":"2506.07209","arxivUrl":"https://arxiv.org/abs/2506.07209"},{"key":"journals/corr/abs-2507-23715","title":"DiffuMatch: Category-Agnostic Spectral Diffusion Priors for Robust Non-rigid Shape Matching.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2507.23715","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2507-23715","documentUrl":"https://doi.org/10.48550/ARXIV.2507.23715","pages":null,"arxivId":"2507.23715","arxivUrl":"https://arxiv.org/abs/2507.23715"},{"key":"journals/corr/abs-2511-07142","title":"ProcGen3D: Learning Neural Procedural Graph Representations for Image-to-3D Reconstruction.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2511.07142","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2511-07142","documentUrl":"https://doi.org/10.48550/ARXIV.2511.07142","pages":null,"arxivId":"2511.07142","arxivUrl":"https://arxiv.org/abs/2511.07142"}],"excludedFormal":[],"labName":"3D AI Lab","labUrl":"http://www.3dunderstanding.org/","labEvidence":"本人原 Stanford 地址重定向至该实验室；Team 页明确 Angela Dai 在 TUM 领导 3D AI Lab。","labSourceUrl":"http://www.3dunderstanding.org/team.html","affiliationZh":"Technical University of Munich","sourceWarning":false,"excludedOther":[],"excludedHomonyms":[],"unassignedCandidates":[],"knownPreprintMinimum2025":null,"excludedMisattributed":[],"displayNotes":"身份已经机构或个人主页核对。2025 年正式记录 14 条（会议 13、期刊 1），所有作者位置均计入，不表示主导或贡献份额；预印本 13 条单列，不加总。","labDisplayNotes":"3D AI Lab 的 Team 页写明她在 TUM 领导该实验室，本人旧 Stanford 地址也重定向到此，据此归组。名称为检索时的公开关联，不代表 2025 年全年的团队边界。"},{"index":2,"name":"Mingyu Ding","nameZh":"Mingyu Ding","role":"Assistant Professor","affiliation":"University of North Carolina at Chapel Hill","source":"DBLP official SPARQL","profileUrl":"https://dblp.org/pid/188/5243","identifier":"188/5243","identityEvidence":[{"url":"https://dblp.org/pid/188/5243","evidence":"DBLP 唯一同名作者档案；通过作者/机构主页与发表题名交叉核对。"},{"url":"https://dingmyu.github.io/","evidence":"作者/机构页面与该 DBLP 档案交叉匹配的题名示例：CoorDex: Coordinating Body and Hand Priors for Continuous Dexterous Humanoid Loco-Manipulation.；Learning Action Priors for Cross-embodiment Robot Manipulation.","matchedPaperKeys":["journals/corr/abs-2606-23680","journals/corr/abs-2606-26095"]}],"count2025":20,"conference2025":14,"journal2025":6,"preprint2025":20,"status":"verified","notes":"DBLP 档案的早年记录存在疑似同名混入（非本统计年度）；本次已检查 2025 正式记录题名，均为机器人、计算机视觉或相关 AI 研究。统计仍是 DBLP 档案口径，非逐篇贡献审计。","retrievedAt":"2026-10-19","yearPolicy":"DBLP yearOfPublication = 2025","queryUrl":"https://sparql.dblp.org/sparql?query=PREFIX%20dblp%3A%20%3Chttps%3A//dblp.org/rdf/schema%23%3E%20PREFIX%20xsd%3A%20%3Chttp%3A//www.w3.org/2001/XMLSchema%23%3E%20SELECT%20%3Fpub%20%3Ftitle%20%3Ftype%20%3Fvenue%20WHERE%20%7B%20%3Fpub%20dblp%3AauthoredBy%20%3Chttps%3A//dblp.org/pid/188/5243%3E%3B%20dblp%3AyearOfPublication%20%222025%22%5E%5Exsd%3AgYear%3B%20dblp%3Atitle%20%3Ftitle%3B%20a%20%3Ftype%20.%20OPTIONAL%20%7B%20%3Fpub%20dblp%3ApublishedIn%20%3Fvenue%20%7D%20%7D&format=json","papers":[{"key":"conf/cvpr/GeXJPTLDJZ25","title":"CompGS: Unleashing 2D Compositionality for Compositional Text-to-3D via Dynamically Optimizing 3D Gaussians.","type":"Inproceedings","venue":"CVPR","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/CVPR52734.2025.01725","sourceUrl":"https://dblp.org/rec/conf/cvpr/GeXJPTLDJZ25","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Ge_CompGS_Unleashing_2D_Compositionality_for_Compositional_Text-to-3D_via_Dynamically_Optimizing_CVPR_2025_paper.html","pages":"18509-18520"},{"key":"conf/cvpr/LiangMWCSZTLD25","title":"DexHandDiff: Interaction-aware Diffusion Planning for Adaptive Dexterous Manipulation.","type":"Inproceedings","venue":"CVPR","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/CVPR52734.2025.00170","sourceUrl":"https://dblp.org/rec/conf/cvpr/LiangMWCSZTLD25","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Liang_DexHandDiff_Interaction-aware_Diffusion_Planning_for_Adaptive_Dexterous_Manipulation_CVPR_2025_paper.html","pages":"1745-1755"},{"key":"conf/cvpr/MuCCPLGLYZXLXDL25","title":"RoboTwin: Dual-Arm Robot Benchmark with Generative Digital Twins.","type":"Inproceedings","venue":"CVPR","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/CVPR52734.2025.02575","sourceUrl":"https://dblp.org/rec/conf/cvpr/MuCCPLGLYZXLXDL25","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Mu_RoboTwin_Dual-Arm_Robot_Benchmark_with_Generative_Digital_Twins_CVPR_2025_paper.html","pages":"27649-27660"},{"key":"conf/iccv/ChenGTLGDSL25","title":"Moto: Latent Motion Token as the Bridging Language for Learning Robot Manipulation from Videos.","type":"Inproceedings","venue":"ICCV","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/ICCV51701.2025.01837","sourceUrl":"https://dblp.org/rec/conf/iccv/ChenGTLGDSL25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.01837","pages":"19752-19763"},{"key":"conf/iclr/0002XPZHPDTZ25","title":"X-Drive: Cross-modality Consistent Multi-Sensor Data Synthesis for Driving Scenarios.","type":"Inproceedings","venue":"ICLR","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":null,"sourceUrl":"https://dblp.org/rec/conf/iclr/0002XPZHPDTZ25","documentUrl":"https://openreview.net/forum?id=IEMmEd5Jgm","pages":null},{"key":"conf/iclr/XiaHQZWZCCDLWY25","title":"MMIE: Massive Multimodal Interleaved Comprehension Benchmark for Large Vision-Language Models.","type":"Inproceedings","venue":"ICLR","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":null,"sourceUrl":"https://dblp.org/rec/conf/iclr/XiaHQZWZCCDLWY25","documentUrl":"https://openreview.net/forum?id=HnhNRrLPwm","pages":null},{"key":"conf/icml/LiFGZLXYTZ0DZ25","title":"WOMD-Reasoning: A Large-Scale Dataset for Interaction Reasoning in Driving.","type":"Inproceedings","venue":"ICML","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":null,"sourceUrl":"https://dblp.org/rec/conf/icml/LiFGZLXYTZ0DZ25","documentUrl":"https://proceedings.mlr.press/v267/li25l.html","pages":null},{"key":"conf/icra/JacobsonXDXTZW25","title":"TrajSSL: Trajectory-Enhanced Semi-Supervised 3D Object Detection.","type":"Inproceedings","venue":"ICRA","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/ICRA55743.2025.11128266","sourceUrl":"https://dblp.org/rec/conf/icra/JacobsonXDXTZW25","documentUrl":"https://doi.org/10.1109/ICRA55743.2025.11128266","pages":"9558-9565"},{"key":"conf/icra/TangPZZYLTDF25","title":"Embodiment-agnostic Action Planning via Object-Part Scene Flow.","type":"Inproceedings","venue":"ICRA","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/ICRA55743.2025.11127873","sourceUrl":"https://dblp.org/rec/conf/icra/TangPZZYLTDF25","documentUrl":"https://doi.org/10.1109/ICRA55743.2025.11127873","pages":"2086-2093"},{"key":"conf/icra/ZhangWCWLMTDZ25","title":"Physics-Aware Robotic Palletization With Online Masking Inference.","type":"Inproceedings","venue":"ICRA","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/ICRA55743.2025.11128204","sourceUrl":"https://dblp.org/rec/conf/icra/ZhangWCWLMTDZ25","documentUrl":"https://doi.org/10.1109/ICRA55743.2025.11128204","pages":"6139-6145"},{"key":"conf/iros/FangYZZBSD25","title":"ReBot: Scaling Robot Learning with Real-to-Sim-to-Real Robotic Video Synthesis.","type":"Inproceedings","venue":"IROS","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/IROS60139.2025.11246305","sourceUrl":"https://dblp.org/rec/conf/iros/FangYZZBSD25","documentUrl":"https://doi.org/10.1109/IROS60139.2025.11246305","pages":"11351-11358"},{"key":"conf/iros/GuoXZZTDZ25","title":"PhyGrasp: Generalizing Robotic Grasping with Physics-informed Large Multimodal Models.","type":"Inproceedings","venue":"IROS","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/IROS60139.2025.11246481","sourceUrl":"https://dblp.org/rec/conf/iros/GuoXZZTDZ25","documentUrl":"https://doi.org/10.1109/IROS60139.2025.11246481","pages":"14915-14922"},{"key":"conf/iros/SongCTZXD25","title":"P2 Explore: Efficient Exploration in Unknown Cluttered Environment with Floor Plan Prediction.","type":"Inproceedings","venue":"IROS","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/IROS60139.2025.11247205","sourceUrl":"https://dblp.org/rec/conf/iros/SongCTZXD25","documentUrl":"https://doi.org/10.1109/IROS60139.2025.11247205","pages":"13090-13096"},{"key":"conf/nips/TongWCJQHGXZXDR25","title":"MJ-Video: Benchmarking and Rewarding Video Generation with Fine-Grained Video Preference.","type":"Inproceedings","venue":"NeurIPS","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":null,"sourceUrl":"https://dblp.org/rec/conf/nips/TongWCJQHGXZXDR25","documentUrl":"http://papers.nips.cc/paper_files/paper/2025/hash/71ad539a57b1fd49b19e5c80070cb8b9-Abstract-Conference.html","pages":null},{"key":"journals/csur/SunZXLCQXDLGWWCYRFHYLLL25","title":"A Survey of Reasoning with Foundation Models: Concepts, Methodologies, and Outlook.","type":"Article","venue":"ACM Comput. Surv.","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.1145/3729218","sourceUrl":"https://dblp.org/rec/journals/csur/SunZXLCQXDLGWWCYRFHYLLL25","documentUrl":"https://doi.org/10.1145/3729218","pages":"278:1-278:43"},{"key":"journals/pami/ChenDYLDTTG25","title":"Compositional Physical Reasoning of Objects and Events From Videos.","type":"Article","venue":"IEEE Trans. Pattern Anal. Mach. Intell.","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.1109/TPAMI.2025.3574322","sourceUrl":"https://dblp.org/rec/journals/pami/ChenDYLDTTG25","documentUrl":"https://doi.org/10.1109/TPAMI.2025.3574322","pages":"7689-7703"},{"key":"journals/pami/LuXDZYTY25","title":"Sel4FT: Annotation Selection for Pretraining-Finetuning With Distribution Shift.","type":"Article","venue":"IEEE Trans. Pattern Anal. Mach. Intell.","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.1109/TPAMI.2025.3591018","sourceUrl":"https://dblp.org/rec/journals/pami/LuXDZYTY25","documentUrl":"https://doi.org/10.1109/TPAMI.2025.3591018","pages":"9922-9937"},{"key":"journals/ral/LiuXHSDZT25","title":"Language-Driven Policy Distillation for Cooperative Driving in Multi-Agent Reinforcement Learning.","type":"Article","venue":"IEEE Robotics Autom. Lett.","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.1109/LRA.2025.3551098","sourceUrl":"https://dblp.org/rec/journals/ral/LiuXHSDZT25","documentUrl":"https://doi.org/10.1109/LRA.2025.3551098","pages":"4292-4299"},{"key":"journals/ral/YangZDBS25","title":"BOSS: Benchmark for Observation Space Shift in Long-Horizon Task.","type":"Article","venue":"IEEE Robotics Autom. Lett.","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.1109/LRA.2025.3585390","sourceUrl":"https://dblp.org/rec/journals/ral/YangZDBS25","documentUrl":"https://doi.org/10.1109/LRA.2025.3585390","pages":"8882-8889"},{"key":"journals/tvt/FangLDCLHS25","title":"Towards Interactive and Learnable Cooperative Driving Automation: A Large Language Model-Driven Decision-Making Framework.","type":"Article","venue":"IEEE Trans. Veh. Technol.","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.1109/TVT.2025.3552922","sourceUrl":"https://dblp.org/rec/journals/tvt/FangLDCLHS25","documentUrl":"https://doi.org/10.1109/TVT.2025.3552922","pages":"11894-11905"}],"preprints":[{"key":"journals/corr/abs-2501-09783","title":"GeoManip: Geometric Constraints as General Interfaces for Robot Manipulation.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2501.09783","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2501-09783","documentUrl":"https://doi.org/10.48550/ARXIV.2501.09783","pages":null,"arxivId":"2501.09783","arxivUrl":"https://arxiv.org/abs/2501.09783"},{"key":"journals/corr/abs-2502-01719","title":"MJ-VIDEO: Fine-Grained Benchmarking and Rewarding Video Preferences in Video Generation.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2502.01719","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2502-01719","documentUrl":"https://doi.org/10.48550/ARXIV.2502.01719","pages":null,"arxivId":"2502.01719","arxivUrl":"https://arxiv.org/abs/2502.01719"},{"key":"journals/corr/abs-2502-13443","title":"Physics-Aware Robotic Palletization with Online Masking Inference.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2502.13443","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2502-13443","documentUrl":"https://doi.org/10.48550/ARXIV.2502.13443","pages":null,"arxivId":"2502.13443","arxivUrl":"https://arxiv.org/abs/2502.13443"},{"key":"journals/corr/abs-2502-15679","title":"BOSS: Benchmark for Observation Space Shift in Long-Horizon Task.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2502.15679","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2502-15679","documentUrl":"https://doi.org/10.48550/ARXIV.2502.15679","pages":null,"arxivId":"2502.15679","arxivUrl":"https://arxiv.org/abs/2502.15679"},{"key":"journals/corr/abs-2503-14526","title":"ReBot: Scaling Robot Learning with Real-to-Sim-to-Real Robotic Video Synthesis.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2503.14526","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-14526","documentUrl":"https://doi.org/10.48550/ARXIV.2503.14526","pages":null,"arxivId":"2503.14526","arxivUrl":"https://arxiv.org/abs/2503.14526"},{"key":"journals/corr/abs-2503-22122","title":"REMAC: Self-Reflective and Self-Evolving Multi-Agent Collaboration for Long-Horizon Robot Manipulation.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2503.22122","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-22122","documentUrl":"https://doi.org/10.48550/ARXIV.2503.22122","pages":null,"arxivId":"2503.22122","arxivUrl":"https://arxiv.org/abs/2503.22122"},{"key":"journals/corr/abs-2504-13059","title":"RoboTwin: Dual-Arm Robot Benchmark with Generative Digital Twins.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2504.13059","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2504-13059","documentUrl":"https://doi.org/10.48550/ARXIV.2504.13059","pages":null,"arxivId":"2504.13059","arxivUrl":"https://arxiv.org/abs/2504.13059"},{"key":"journals/corr/abs-2505-02152","title":"Interleave-VLA: Enhancing Robot Manipulation with Interleaved Image-Text Instructions.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2505.02152","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-02152","documentUrl":"https://doi.org/10.48550/ARXIV.2505.02152","pages":null,"arxivId":"2505.02152","arxivUrl":"https://arxiv.org/abs/2505.02152"},{"key":"journals/corr/abs-2505-12744","title":"Incentivizing Multimodal Reasoning in Large Models for Direct Robot Manipulation.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2505.12744","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-12744","documentUrl":"https://doi.org/10.48550/ARXIV.2505.12744","pages":null,"arxivId":"2505.12744","arxivUrl":"https://arxiv.org/abs/2505.12744"},{"key":"journals/corr/abs-2506-17667","title":"PhysUniBench: An Undergraduate-Level Physics Reasoning Benchmark for Multimodal Models.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2506.17667","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-17667","documentUrl":"https://doi.org/10.48550/ARXIV.2506.17667","pages":null,"arxivId":"2506.17667","arxivUrl":"https://arxiv.org/abs/2506.17667"},{"key":"journals/corr/abs-2508-03526","title":"CollaBot: Vision-Language Guided Simultaneous Collaborative Manipulation.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2508.03526","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-03526","documentUrl":"https://doi.org/10.48550/ARXIV.2508.03526","pages":null,"arxivId":"2508.03526","arxivUrl":"https://arxiv.org/abs/2508.03526"},{"key":"journals/corr/abs-2508-17380","title":"Mimicking the Physicist's Eye:A VLM-centric Approach for Physics Formula Discovery.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2508.17380","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-17380","documentUrl":"https://doi.org/10.48550/ARXIV.2508.17380","pages":null,"arxivId":"2508.17380","arxivUrl":"https://arxiv.org/abs/2508.17380"},{"key":"journals/corr/abs-2510-04860","title":"Alignment Tipping Process: How Self-Evolution Pushes LLM Agents Off the Rails.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2510.04860","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-04860","documentUrl":"https://doi.org/10.48550/ARXIV.2510.04860","pages":null,"arxivId":"2510.04860","arxivUrl":"https://arxiv.org/abs/2510.04860"},{"key":"journals/corr/abs-2510-05213","title":"VER: Vision Expert Transformer for Robot Learning via Foundation Distillation and Dynamic Routing.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2510.05213","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-05213","documentUrl":"https://doi.org/10.48550/ARXIV.2510.05213","pages":null,"arxivId":"2510.05213","arxivUrl":"https://arxiv.org/abs/2510.05213"},{"key":"journals/corr/abs-2510-20809","title":"Real Deep Research for AI, Robotics and Beyond.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2510.20809","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-20809","documentUrl":"https://doi.org/10.48550/ARXIV.2510.20809","pages":null,"arxivId":"2510.20809","arxivUrl":"https://arxiv.org/abs/2510.20809"},{"key":"journals/corr/abs-2511-12485","title":"ARCHE: A Novel Task to Evaluate LLMs on Latent Reasoning Chain Extraction.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2511.12485","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2511-12485","documentUrl":"https://doi.org/10.48550/ARXIV.2511.12485","pages":null,"arxivId":"2511.12485","arxivUrl":"https://arxiv.org/abs/2511.12485"},{"key":"journals/corr/abs-2511-19315","title":"Rethinking Intermediate Representation for VLM-based Robot Manipulation.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2511.19315","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2511-19315","documentUrl":"https://doi.org/10.48550/ARXIV.2511.19315","pages":null,"arxivId":"2511.19315","arxivUrl":"https://arxiv.org/abs/2511.19315"},{"key":"journals/corr/abs-2511-19433","title":"Mixture of Horizons in Action Chunking.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2511.19433","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2511-19433","documentUrl":"https://doi.org/10.48550/ARXIV.2511.19433","pages":null,"arxivId":"2511.19433","arxivUrl":"https://arxiv.org/abs/2511.19433"},{"key":"journals/corr/abs-2511-19900","title":"Agent0-VL: Exploring Self-Evolving Agent for Tool-Integrated Vision-Language Reasoning.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2511.19900","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2511-19900","documentUrl":"https://doi.org/10.48550/ARXIV.2511.19900","pages":null,"arxivId":"2511.19900","arxivUrl":"https://arxiv.org/abs/2511.19900"},{"key":"journals/corr/abs-2512-18007","title":"Robotic VLA Benefits from Joint Learning with Motion Image Diffusion.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2512.18007","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-18007","documentUrl":"https://doi.org/10.48550/ARXIV.2512.18007","pages":null,"arxivId":"2512.18007","arxivUrl":"https://arxiv.org/abs/2512.18007"}],"excludedFormal":[],"sourceWarning":true,"labName":"Intelligent Dexterous Embodied AI Lab (IDEAL)","labUrl":"https://ideal.cs.unc.edu/","labEvidence":"个人主页的 Lab Website 明确链接该网站；实验室页标题及页尾写出全称，并列 PI Homepage 和 md@cs.unc.edu。","labSourceUrl":"https://ideal.cs.unc.edu/","affiliationZh":"University of North Carolina at Chapel Hill","excludedOther":[],"excludedHomonyms":[],"unassignedCandidates":[],"knownPreprintMinimum2025":null,"excludedMisattributed":[],"displayNotes":"身份已核对。DBLP 档案的早年记录疑有同名混入，但不在本统计年度；2025 年的正式记录已逐条查看题名，均为机器人、视觉或相关 AI 研究。计入 20 条（会议 14、期刊 6）；预印本 20 条单列。","labDisplayNotes":"个人主页的 Lab Website 指向 IDEAL，实验室页列其为 PI，据此归组。这反映检索时的公开关联，不代表 2025 全年的归属。"},{"index":3,"name":"Chen Feng","nameZh":"Chen Feng","role":"Associate Professor","affiliation":"New York University","source":"DBLP official SPARQL","profileUrl":"https://dblp.org/pid/01/161-2","identifier":"01/161-2","identityEvidence":[{"url":"https://dblp.org/pid/01/161-2","evidence":"DBLP 档案名 Chen Feng 0002；机构/履历：Mitsubishi Electric Research Laboratories, Cambridge, MA, USA；New York University, Department of Civil and Urban Engineering, Mechanical and Aerospace Engineering, NY, USA；University of Michigan, Department of Civil and Environmental Engineering, Ann Arbor, MI, USA"},{"url":"https://api.crossref.org/works/10.1109/TASE.2025.3616634","evidence":"Publisher-deposited Crossref metadata identifies HUST Chen Feng, ORCID 0000-0003-0756-1700; target is NYU Chen Feng, ORCID 0000-0003-3211-1576. The other ORCID has a verified hust.edu.cn address.","matchedPaperKeys":["journals/tase/FengCXC25"]},{"url":"https://api.crossref.org/works/10.1109/TGRS.2025.3597777","evidence":"Publisher-deposited Crossref metadata assigns Chen Feng to HUST with ORCID 0000-0003-0756-1700, not the NYU signatory.","matchedPaperKeys":["journals/tgrs/DuFXC25"]},{"url":"https://ai4ce.github.io/publications","evidence":"Author or laboratory publication page: counted formal-paper titles matched after punctuation/case normalization. Additional title variants and missing entries were checked separately below.","matchedPaperKeys":["conf/cvpr/0003LJSYZAZF25","conf/iccv/ChenDZSZHYZSF25","conf/iccv/HanJLWIYLWPFL25","conf/iccv/LiJCXTWFZMIFZ25","conf/iccv/LiTCZFL25","conf/icra/FangSHTWZHYFZ25","conf/icra/PanHCLF25","conf/iros/WangZDFF25","journals/ral/ChenCLLDWF25"]},{"url":"https://openaccess.thecvf.com/content/ICCV2025W/HCV/papers/Chen_Human-Inspired_Summarization_Cluster_Scene_Videos_into_Diverse_Frames_ICCVW_2025_paper.pdf","evidence":"Original first page assigns Chen Feng to New York University and cfeng@nyu.edu.","matchedPaperKeys":["conf/iccv/ChenZSYJF25"]},{"url":"https://openaccess.thecvf.com/content/ICCV2025W/WDFM-AD/papers/Yang_Distillation_Improves_Visual_Place_Recognition_for_Low_Quality_Images_ICCVW_2025_paper.pdf","evidence":"Original first page assigns Chen Feng to New York University and cfeng@nyu.edu; project belongs to AI4CE.","matchedPaperKeys":["conf/iccv/YangJHWRF25"]},{"url":"https://orcid.org/0000-0003-0756-1700","evidence":"The excluded HUST researcher has verified hust.edu.cn and hgtech.com.cn addresses and lists the two excluded papers."}],"count2025":11,"conference2025":10,"journal2025":1,"preprint2025":null,"status":"verified_manual","notes":"身份已通过机构/个人主页或 DBLP 机构信息核对；篇数为数据库记录统计，不表示每篇均由本人主导。 发现同名误归后，全部正式候选用本人论文列表、论文原文或正确 ORCID 重新核对。预印本候选保留于 unassignedCandidates；null 不表示零篇。","retrievedAt":"2026-10-19","yearPolicy":"DBLP yearOfPublication = 2025","queryUrl":"https://sparql.dblp.org/sparql?query=PREFIX%20dblp%3A%20%3Chttps%3A//dblp.org/rdf/schema%23%3E%20PREFIX%20xsd%3A%20%3Chttp%3A//www.w3.org/2001/XMLSchema%23%3E%20SELECT%20%3Fpub%20%3Ftitle%20%3Ftype%20%3Fvenue%20WHERE%20%7B%20%3Fpub%20dblp%3AauthoredBy%20%3Chttps%3A//dblp.org/pid/01/161-2%3E%3B%20dblp%3AyearOfPublication%20%222025%22%5E%5Exsd%3AgYear%3B%20dblp%3Atitle%20%3Ftitle%3B%20a%20%3Ftype%20.%20OPTIONAL%20%7B%20%3Fpub%20dblp%3ApublishedIn%20%3Fvenue%20%7D%20%7D&format=json","papers":[{"key":"conf/cvpr/0003LJSYZAZF25","title":"CityWalker: Learning Embodied Urban Navigation from Web-Scale Videos.","type":"Inproceedings","venue":"CVPR","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/CVPR52734.2025.00645","sourceUrl":"https://dblp.org/rec/conf/cvpr/0003LJSYZAZF25","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Liu_CityWalker_Learning_Embodied_Urban_Navigation_from_Web-Scale_Videos_CVPR_2025_paper.html","pages":"6875-6885"},{"key":"conf/iccv/ChenDZSZHYZSF25","title":"Co-VisiON: Co-Visibility ReasONing on Sparse Image Sets of Indoor Scenes.","type":"Inproceedings","venue":"ICCVW","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/ICCVW69036.2025.00504","sourceUrl":"https://dblp.org/rec/conf/iccv/ChenDZSZHYZSF25","documentUrl":"https://doi.org/10.1109/ICCVW69036.2025.00504","pages":"4861-4871"},{"key":"conf/iccv/ChenZSYJF25","title":"Human-Inspired Summarization: Cluster Scene Videos into Diverse Frames.","type":"Inproceedings","venue":"ICCVW","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/ICCVW69036.2025.00505","sourceUrl":"https://dblp.org/rec/conf/iccv/ChenZSYJF25","documentUrl":"https://doi.org/10.1109/ICCVW69036.2025.00505","pages":"4872-4882"},{"key":"conf/iccv/HanJLWIYLWPFL25","title":"Extrapolated Urban View Synthesis Benchmark.","type":"Inproceedings","venue":"ICCV","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/ICCV51701.2025.02667","sourceUrl":"https://dblp.org/rec/conf/iccv/HanJLWIYLWPFL25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.02667","pages":"28718-28728"},{"key":"conf/iccv/LiJCXTWFZMIFZ25","title":"GARF: Learning Generalizable 3D Reassembly for Real-World Fractures.","type":"Inproceedings","venue":"ICCV","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/ICCV51701.2025.00541","sourceUrl":"https://dblp.org/rec/conf/iccv/LiJCXTWFZMIFZ25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.00541","pages":"5711-5721"},{"key":"conf/iccv/LiTCZFL25","title":"Adversarial Exploitation of Data Diversity Improves Visual Localization.","type":"Inproceedings","venue":"ICCV","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/ICCV51701.2025.02492","sourceUrl":"https://dblp.org/rec/conf/iccv/LiTCZFL25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.02492","pages":"26848-26858"},{"key":"conf/iccv/YangJHWRF25","title":"Distillation Improves Visual Place Recognition for Low Quality Images.","type":"Inproceedings","venue":"ICCVW","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/ICCVW69036.2025.00474","sourceUrl":"https://dblp.org/rec/conf/iccv/YangJHWRF25","documentUrl":"https://doi.org/10.1109/ICCVW69036.2025.00474","pages":"4560-4569"},{"key":"conf/icra/FangSHTWZHYFZ25","title":"Fusionsense: Bridging Common Sense, Vision, and Touch for Robust Sparse-View Reconstruction.","type":"Inproceedings","venue":"ICRA","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/ICRA55743.2025.11128188","sourceUrl":"https://dblp.org/rec/conf/icra/FangSHTWZHYFZ25","documentUrl":"https://doi.org/10.1109/ICRA55743.2025.11128188","pages":"15798-15805"},{"key":"conf/icra/PanHCLF25","title":"NYC-Event-VPR: A Large-Scale High-Resolution Event-Based Visual Place Recognition Dataset in Dense Urban Environments.","type":"Inproceedings","venue":"ICRA","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/ICRA55743.2025.11128789","sourceUrl":"https://dblp.org/rec/conf/icra/PanHCLF25","documentUrl":"https://doi.org/10.1109/ICRA55743.2025.11128789","pages":"4657-4664"},{"key":"conf/iros/WangZDFF25","title":"VLM See, Robot Do: Human Demo Video to Robot Action Plan via Vision Language Model.","type":"Inproceedings","venue":"IROS","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/IROS60139.2025.11246682","sourceUrl":"https://dblp.org/rec/conf/iros/WangZDFF25","documentUrl":"https://doi.org/10.1109/IROS60139.2025.11246682","pages":"17215-17222"},{"key":"journals/ral/ChenCLLDWF25","title":"Self-Supervised Place Recognition by Refining Temporal and Featural Pseudo Labels From Panoramic Data.","type":"Article","venue":"IEEE Robotics Autom. Lett.","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.1109/LRA.2024.3495584","sourceUrl":"https://dblp.org/rec/journals/ral/ChenCLLDWF25","documentUrl":"https://doi.org/10.1109/LRA.2024.3495584","pages":"248-255"}],"preprints":[],"excludedFormal":[],"excludedHomonyms":[{"key":"journals/tase/FengCXC25","title":"One-Shot Cross-Domain Instance Detection With Universal Representation.","type":"Article","venue":"IEEE Trans Autom. Sci. Eng.","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.1109/TASE.2025.3616634","sourceUrl":"https://dblp.org/rec/journals/tase/FengCXC25","documentUrl":"https://doi.org/10.1109/TASE.2025.3616634","pages":"22003-22017","exclusionReason":"Publisher-deposited Crossref metadata identifies HUST Chen Feng, ORCID 0000-0003-0756-1700; target is NYU Chen Feng, ORCID 0000-0003-3211-1576. The other ORCID has a verified hust.edu.cn address.","exclusionSource":"https://api.crossref.org/works/10.1109/TASE.2025.3616634"},{"key":"journals/tgrs/DuFXC25","title":"CODNet: Infrared Small-Target Detection by Mitigating the Curse of Dimensionality.","type":"Article","venue":"IEEE Trans. Geosci. Remote. Sens.","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.1109/TGRS.2025.3597777","sourceUrl":"https://dblp.org/rec/journals/tgrs/DuFXC25","documentUrl":"https://doi.org/10.1109/TGRS.2025.3597777","pages":"1-14","exclusionReason":"Publisher-deposited Crossref metadata assigns Chen Feng to HUST with ORCID 0000-0003-0756-1700, not the NYU signatory.","exclusionSource":"https://api.crossref.org/works/10.1109/TGRS.2025.3597777"}],"sourceWarning":true,"preprintStatus":"partial_identity_review","unassignedCandidates":[{"key":"journals/corr/abs-2501-10604","title":"When language and vision meet road safety: leveraging multimodal large language models for video-based traffic accident analysis.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2501.10604","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2501-10604","documentUrl":"https://doi.org/10.48550/ARXIV.2501.10604","pages":null,"reviewStatus":"Preprint identity not separately audited after mixed-profile contamination was detected; excluded from reported totals."},{"key":"journals/corr/abs-2504-05400","title":"GARF: Learning Generalizable 3D Reassembly for Real-World Fractures.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2504.05400","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2504-05400","documentUrl":"https://doi.org/10.48550/ARXIV.2504.05400","pages":null,"reviewStatus":"Preprint identity not separately audited after mixed-profile contamination was detected; excluded from reported totals."},{"key":"journals/corr/abs-2506-09930","title":"From Intention to Execution: Probing the Generalization Boundaries of Vision-Language-Action Models.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2506.09930","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-09930","documentUrl":"https://doi.org/10.48550/ARXIV.2506.09930","pages":null,"reviewStatus":"Preprint identity not separately audited after mixed-profile contamination was detected; excluded from reported totals."},{"key":"journals/corr/abs-2506-16805","title":"Co-VisiON: Co-Visibility ReasONing on Sparse Image Sets of Indoor Scenes.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2506.16805","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-16805","documentUrl":"https://doi.org/10.48550/ARXIV.2506.16805","pages":null,"reviewStatus":"Preprint identity not separately audited after mixed-profile contamination was detected; excluded from reported totals."},{"key":"journals/corr/abs-2509-11090","title":"End-to-End Visual Autonomous Parking via Control-Aided Attention.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2509.11090","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-11090","documentUrl":"https://doi.org/10.48550/ARXIV.2509.11090","pages":null,"reviewStatus":"Preprint identity not separately audited after mixed-profile contamination was detected; excluded from reported totals."},{"key":"journals/corr/abs-2511-20351","title":"Thinking in 360°: Humanoid Visual Search in the Wild.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2511.20351","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2511-20351","documentUrl":"https://doi.org/10.48550/ARXIV.2511.20351","pages":null,"reviewStatus":"Preprint identity not separately audited after mixed-profile contamination was detected; excluded from reported totals."},{"key":"journals/corr/abs-2511-20620","title":"Wanderland: Geometrically Grounded Simulation for Open-World Embodied AI.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2511.20620","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2511-20620","documentUrl":"https://doi.org/10.48550/ARXIV.2511.20620","pages":null,"reviewStatus":"Preprint identity not separately audited after mixed-profile contamination was detected; excluded from reported totals."}],"labName":"AI4CE Lab","labUrl":"https://ai4ce.github.io/","labEvidence":"实验室主页写明 AI4CE Lab at New York University，并说明 Dr. Feng 的 CREO 共同主任身份和联系方式 cfeng。","labSourceUrl":"https://ai4ce.github.io/","affiliationZh":"New York University","excludedOther":[],"knownPreprintMinimum2025":null,"excludedMisattributed":[{"key":"journals/tase/FengCXC25","title":"One-Shot Cross-Domain Instance Detection With Universal Representation.","type":"Article","venue":"IEEE Trans Autom. Sci. Eng.","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.1109/TASE.2025.3616634","sourceUrl":"https://dblp.org/rec/journals/tase/FengCXC25","documentUrl":"https://doi.org/10.1109/TASE.2025.3616634","pages":"22003-22017","exclusionReason":"Publisher-deposited Crossref metadata identifies HUST Chen Feng, ORCID 0000-0003-0756-1700; target is NYU Chen Feng, ORCID 0000-0003-3211-1576. The other ORCID has a verified hust.edu.cn address.","exclusionSource":"https://api.crossref.org/works/10.1109/TASE.2025.3616634"},{"key":"journals/tgrs/DuFXC25","title":"CODNet: Infrared Small-Target Detection by Mitigating the Curse of Dimensionality.","type":"Article","venue":"IEEE Trans. Geosci. Remote. Sens.","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.1109/TGRS.2025.3597777","sourceUrl":"https://dblp.org/rec/journals/tgrs/DuFXC25","documentUrl":"https://doi.org/10.1109/TGRS.2025.3597777","pages":"1-14","exclusionReason":"Publisher-deposited Crossref metadata assigns Chen Feng to HUST with ORCID 0000-0003-0756-1700, not the NYU signatory.","exclusionSource":"https://api.crossref.org/works/10.1109/TGRS.2025.3597777"}],"displayNotes":"曾发现同名误归，已用本人论文列表、论文原文或正确的 ORCID 逐条重核全部正式候选。计入 11 条（会议 10、期刊 1）。预印本候选尚未完成归属，暂不给出总数，这不是零。","labDisplayNotes":"AI4CE Lab 主页写明实验室位于 NYU，并列出其联系方式，据此归组。分组只含本人参与的记录，不是全组产量。"},{"index":4,"name":"Jun Gao","nameZh":"Jun Gao","role":"Assistant Professor","affiliation":"University of Michigan","source":"DBLP official SPARQL","profileUrl":"https://dblp.org/pid/82/4977-4","identifier":"82/4977-4","identityEvidence":[{"url":"https://dblp.org/pid/82/4977-4","evidence":"DBLP 档案名 Jun Gao 0004；机构/履历：University of Toronto, Canada"},{"url":"https://j-lab.ai/","evidence":"作者主页说明任职 University of Michigan，同时说明博士毕业于 University of Toronto，与 DBLP Jun Gao 0004 的 Toronto 履历一致；主页 2025 新闻列出 Difix3D+，与该 DBLP 档案相符。"}],"count2025":5,"conference2025":5,"journal2025":0,"preprint2025":8,"status":"verified","notes":"身份已通过机构/个人主页或 DBLP 机构信息核对；篇数为数据库记录统计，不表示每篇均由本人主导。","retrievedAt":"2026-10-19","yearPolicy":"DBLP yearOfPublication = 2025","queryUrl":"https://sparql.dblp.org/sparql?query=PREFIX%20dblp%3A%20%3Chttps%3A//dblp.org/rdf/schema%23%3E%20PREFIX%20xsd%3A%20%3Chttp%3A//www.w3.org/2001/XMLSchema%23%3E%20SELECT%20%3Fpub%20%3Ftitle%20%3Ftype%20%3Fvenue%20WHERE%20%7B%20%3Fpub%20dblp%3AauthoredBy%20%3Chttps%3A//dblp.org/pid/82/4977-4%3E%3B%20dblp%3AyearOfPublication%20%222025%22%5E%5Exsd%3AgYear%3B%20dblp%3Atitle%20%3Ftitle%3B%20a%20%3Ftype%20.%20OPTIONAL%20%7B%20%3Fpub%20dblp%3ApublishedIn%20%3Fvenue%20%7D%20%7D&format=json","papers":[{"key":"conf/cvpr/LiangGLMHL00VFW25","title":"Diffusion Renderer: Neural Inverse and Forward Rendering with Video Diffusion Models.","type":"Inproceedings","venue":"CVPR","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/CVPR52734.2025.02428","sourceUrl":"https://dblp.org/rec/conf/cvpr/LiangGLMHL00VFW25","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Liang_Diffusion_Renderer_Neural_Inverse_and_Forward_Rendering_with_Video_Diffusion_CVPR_2025_paper.html","pages":"26069-26080"},{"key":"conf/cvpr/RenSHLLN00F025","title":"GEN3C: 3D-Informed World-Consistent Video Generation with Precise Camera Control.","type":"Inproceedings","venue":"CVPR","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/CVPR52734.2025.00574","sourceUrl":"https://dblp.org/rec/conf/cvpr/RenSHLLN00F025","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Ren_GEN3C_3D-Informed_World-Consistent_Video_Generation_with_Precise_Camera_Control_CVPR_2025_paper.html","pages":"6121-6132"},{"key":"conf/cvpr/Wu0TR0SFGL25","title":"DIFIX3D+: Improving 3D Reconstructions with Single-Step Diffusion Models.","type":"Inproceedings","venue":"CVPR","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/CVPR52734.2025.02424","sourceUrl":"https://dblp.org/rec/conf/cvpr/Wu0TR0SFGL25","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Wu_DIFIX3D_Improving_3D_Reconstructions_with_Single-Step_Diffusion_Models_CVPR_2025_paper.html","pages":"26024-26035"},{"key":"conf/iccv/LiuUXSFSG25","title":"PartField: Learning 3D Feature Fields for Part Segmentation and Beyond.","type":"Inproceedings","venue":"ICCV","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/ICCV51701.2025.00905","sourceUrl":"https://dblp.org/rec/conf/iccv/LiuUXSFSG25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.00905","pages":"9704-9715"},{"key":"conf/iccv/LuRYSWGWCCFH25","title":"InfiniCube: Unbounded and Controllable Dynamic 3D Driving Scene Generation with World-Guided Video Models.","type":"Inproceedings","venue":"ICCV","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/ICCV51701.2025.02532","sourceUrl":"https://dblp.org/rec/conf/iccv/LuRYSWGWCCFH25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.02532","pages":"27272-27283"}],"preprints":[{"key":"journals/corr/abs-2501-18590","title":"DiffusionRenderer: Neural Inverse and Forward Rendering with Video Diffusion Models.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2501.18590","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2501-18590","documentUrl":"https://doi.org/10.48550/ARXIV.2501.18590","pages":null,"arxivId":"2501.18590","arxivUrl":"https://arxiv.org/abs/2501.18590"},{"key":"journals/corr/abs-2503-01774","title":"Difix3D+: Improving 3D Reconstructions with Single-Step Diffusion Models.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2503.01774","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-01774","documentUrl":"https://doi.org/10.48550/ARXIV.2503.01774","pages":null,"arxivId":"2503.01774","arxivUrl":"https://arxiv.org/abs/2503.01774"},{"key":"journals/corr/abs-2503-03751","title":"GEN3C: 3D-Informed World-Consistent Video Generation with Precise Camera Control.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2503.03751","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-03751","documentUrl":"https://doi.org/10.48550/ARXIV.2503.03751","pages":null,"arxivId":"2503.03751","arxivUrl":"https://arxiv.org/abs/2503.03751"},{"key":"journals/corr/abs-2504-11451","title":"PARTFIELD: Learning 3D Feature Fields for Part Segmentation and Beyond.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2504.11451","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2504-11451","documentUrl":"https://doi.org/10.48550/ARXIV.2504.11451","pages":null,"arxivId":"2504.11451","arxivUrl":"https://arxiv.org/abs/2504.11451"},{"key":"journals/corr/abs-2506-09042","title":"Cosmos-Drive-Dreams: Scalable Synthetic Driving Data Generation with World Foundation Models.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2506.09042","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-09042","documentUrl":"https://doi.org/10.48550/ARXIV.2506.09042","pages":null,"arxivId":"2506.09042","arxivUrl":"https://arxiv.org/abs/2506.09042"},{"key":"journals/corr/abs-2508-10934","title":"ViPE: Video Pose Engine for 3D Geometric Perception.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2508.10934","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-10934","documentUrl":"https://doi.org/10.48550/ARXIV.2508.10934","pages":null,"arxivId":"2508.10934","arxivUrl":"https://arxiv.org/abs/2508.10934"},{"key":"journals/corr/abs-2509-19296","title":"Lyra: Generative 3D Scene Reconstruction via Video Diffusion Model Self-Distillation.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2509.19296","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-19296","documentUrl":"https://doi.org/10.48550/ARXIV.2509.19296","pages":null,"arxivId":"2509.19296","arxivUrl":"https://arxiv.org/abs/2509.19296"},{"key":"journals/corr/abs-2510-04290","title":"ChronoEdit: Towards Temporal Reasoning for Image Editing and World Simulation.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2510.04290","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-04290","documentUrl":"https://doi.org/10.48550/ARXIV.2510.04290","pages":null,"arxivId":"2510.04290","arxivUrl":"https://arxiv.org/abs/2510.04290"}],"excludedFormal":[],"labName":null,"labUrl":null,"labEvidence":"本人主页使用 j-lab.ai 域名，但正文仅称 my group；未找到明确团队命名，不从域名推造 J-Lab 名称。","labSourceUrl":"https://j-lab.ai/","affiliationZh":"University of Michigan","sourceWarning":false,"excludedOther":[],"excludedHomonyms":[],"unassignedCandidates":[],"knownPreprintMinimum2025":null,"excludedMisattributed":[],"displayNotes":"身份已经机构或个人主页核对。2025 年正式记录 5 条，均为会议论文，所有作者位置均计入；预印本 8 条单列，不加总。","labDisplayNotes":"本人主页使用 j-lab.ai 域名，但正文只称 my group；不从域名推出 J-Lab 这一名称，图中以「姓名及合作者」单列。"},{"index":5,"name":"Andreas Geiger","nameZh":"Andreas Geiger","role":"Professor","affiliation":"University of Tübingen","source":"DBLP official SPARQL","profileUrl":"https://dblp.org/pid/40/5825-1","identifier":"40/5825-1","identityEvidence":[{"url":"https://dblp.org/pid/40/5825-1","evidence":"DBLP 档案名 Andreas Geiger 0001；机构/履历：Karlsruhe Institute of Technology (KIT), Karlsruhe, Germany；Max Planck Institute for Intelligent Systems, Tübingen, Germany；University of Tübingen, Department of Computer Science, Germany"}],"count2025":23,"conference2025":21,"journal2025":2,"preprint2025":23,"status":"verified","notes":"身份已通过机构/个人主页或 DBLP 机构信息核对；篇数为数据库记录统计，不表示每篇均由本人主导。","retrievedAt":"2026-10-19","yearPolicy":"DBLP yearOfPublication = 2025","queryUrl":"https://sparql.dblp.org/sparql?query=PREFIX%20dblp%3A%20%3Chttps%3A//dblp.org/rdf/schema%23%3E%20PREFIX%20xsd%3A%20%3Chttp%3A//www.w3.org/2001/XMLSchema%23%3E%20SELECT%20%3Fpub%20%3Ftitle%20%3Ftype%20%3Fvenue%20WHERE%20%7B%20%3Fpub%20dblp%3AauthoredBy%20%3Chttps%3A//dblp.org/pid/40/5825-1%3E%3B%20dblp%3AyearOfPublication%20%222025%22%5E%5Exsd%3AgYear%3B%20dblp%3Atitle%20%3Ftitle%3B%20a%20%3Ftype%20.%20OPTIONAL%20%7B%20%3Fpub%20dblp%3ApublishedIn%20%3Fvenue%20%7D%20%7D&format=json","papers":[{"key":"conf/3dim/LiCHPGP25","title":"Unimotion: Unifying 3D Human Motion Synthesis and Understanding.","type":"Inproceedings","venue":"3DV","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/3DV66043.2025.00027","sourceUrl":"https://dblp.org/rec/conf/3dim/LiCHPGP25","documentUrl":"https://doi.org/10.1109/3DV66043.2025.00027","pages":"240-249"},{"key":"conf/acl/FlickeAIPSCKHSS25","title":"Scholar Inbox: Personalized Paper Recommendations for Scientists.","type":"Inproceedings","venue":"ACL (3)","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.18653/V1/2025.ACL-DEMO.30","sourceUrl":"https://dblp.org/rec/conf/acl/FlickeAIPSCKHSS25","documentUrl":"https://doi.org/10.18653/V1/2025.ACL-DEMO.30","pages":"307-317"},{"key":"conf/cvpr/EspositoCRBPSRZ25","title":"Volumetric Surfaces: Representing Fuzzy Geometries with Layered Meshes.","type":"Inproceedings","venue":"CVPR","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/CVPR52734.2025.01991","sourceUrl":"https://dblp.org/rec/conf/cvpr/EspositoCRBPSRZ25","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Esposito_Volumetric_Surfaces_Representing_Fuzzy_Geometries_with_Layered_Meshes_CVPR_2025_paper.html","pages":"21370-21380"},{"key":"conf/cvpr/LuCZZHY0L25","title":"UrbanCAD: Towards Highly Controllable and Photorealistic 3D Vehicles for Urban Scene Simulation.","type":"Inproceedings","venue":"CVPR","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/CVPR52734.2025.02563","sourceUrl":"https://dblp.org/rec/conf/cvpr/LuCZZHY0L25","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Lu_UrbanCAD_Towards_Highly_Controllable_and_Photorealistic_3D_Vehicles_for_Urban_CVPR_2025_paper.html","pages":"27519-27530"},{"key":"conf/cvpr/Miao0BYZ0L0L25","title":"EVolSplat: Efficient Volume-based Gaussian Splatting for Urban View Synthesis.","type":"Inproceedings","venue":"CVPR","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/CVPR52734.2025.01054","sourceUrl":"https://dblp.org/rec/conf/cvpr/Miao0BYZ0L0L25","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Miao_EVolSplat_Efficient_Volume-based_Gaussian_Splatting_for_Urban_View_Synthesis_CVPR_2025_paper.html","pages":"11286-11296"},{"key":"conf/cvpr/WuXH0C25","title":"GenFusion: Closing the Loop between Reconstruction and Generation via Videos.","type":"Inproceedings","venue":"CVPR","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/CVPR52734.2025.00570","sourceUrl":"https://dblp.org/rec/conf/cvpr/WuXH0C25","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Wu_GenFusion_Closing_the_Loop_between_Reconstruction_and_Generation_via_Videos_CVPR_2025_paper.html","pages":"6078-6088"},{"key":"conf/cvpr/XuPWBB0P25","title":"DepthSplat: Connecting Gaussian Splatting and Depth.","type":"Inproceedings","venue":"CVPR","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/CVPR52734.2025.01534","sourceUrl":"https://dblp.org/rec/conf/cvpr/XuPWBB0P25","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Xu_DepthSplat_Connecting_Gaussian_Splatting_and_Depth_CVPR_2025_paper.html","pages":"16453-16463"},{"key":"conf/cvpr/YangSLS0L25","title":"Prometheus: 3D-Aware Latent Diffusion Models for Feed-Forward Text-to-3D Scene Generation.","type":"Inproceedings","venue":"CVPR","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/CVPR52734.2025.00272","sourceUrl":"https://dblp.org/rec/conf/cvpr/YangSLS0L25","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Yang_Prometheus_3D-Aware_Latent_Diffusion_Models_for_Feed-Forward_Text-to-3D_Scene_Generation_CVPR_2025_paper.html","pages":"2857-2869"},{"key":"conf/eccv/BaurMG24","title":"LISO: Lidar-Only Self-supervised 3D Object Detection.","type":"Inproceedings","venue":"ECCV (86)","year":2025,"yearOfPublication":2025,"yearOfEvent":2024,"doi":"https://doi.org/10.1007/978-3-031-73016-0_15","sourceUrl":"https://dblp.org/rec/conf/eccv/BaurMG24","documentUrl":"https://doi.org/10.1007/978-3-031-73016-0_15","pages":"253-270"},{"key":"conf/eccv/ChenXETG24","title":"LaRa: Efficient Large-Baseline Radiance Fields.","type":"Inproceedings","venue":"ECCV (11)","year":2025,"yearOfPublication":2025,"yearOfEvent":2024,"doi":"https://doi.org/10.1007/978-3-031-73247-8_20","sourceUrl":"https://dblp.org/rec/conf/eccv/ChenXETG24","documentUrl":"https://doi.org/10.1007/978-3-031-73247-8_20","pages":"338-355"},{"key":"conf/eccv/ChenXZZPGCC24","title":"MVSplat: Efficient 3D Gaussian Splatting from Sparse Multi-view Images.","type":"Inproceedings","venue":"ECCV (21)","year":2025,"yearOfPublication":2025,"yearOfEvent":2024,"doi":"https://doi.org/10.1007/978-3-031-72664-4_21","sourceUrl":"https://dblp.org/rec/conf/eccv/ChenXZZPGCC24","documentUrl":"https://doi.org/10.1007/978-3-031-72664-4_21","pages":"370-386"},{"key":"conf/eccv/ChittaDG24","title":"SLEDGE: Synthesizing Driving Environments with Generative Models and Rule-Based Traffic.","type":"Inproceedings","venue":"ECCV (4)","year":2025,"yearOfPublication":2025,"yearOfEvent":2024,"doi":"https://doi.org/10.1007/978-3-031-73235-5_4","sourceUrl":"https://dblp.org/rec/conf/eccv/ChittaDG24","documentUrl":"https://doi.org/10.1007/978-3-031-73235-5_4","pages":"57-74"},{"key":"conf/eccv/MiaoHBQLGL24","title":"Efficient Depth-Guided Urban View Synthesis.","type":"Inproceedings","venue":"ECCV (30)","year":2025,"yearOfPublication":2025,"yearOfEvent":2024,"doi":"https://doi.org/10.1007/978-3-031-73404-5_6","sourceUrl":"https://dblp.org/rec/conf/eccv/MiaoHBQLGL24","documentUrl":"https://doi.org/10.1007/978-3-031-73404-5_6","pages":"90-107"},{"key":"conf/eccv/SimaRCCZXBLGL24","title":"DriveLM: Driving with Graph Visual Question Answering.","type":"Inproceedings","venue":"ECCV (52)","year":2025,"yearOfPublication":2025,"yearOfEvent":2024,"doi":"https://doi.org/10.1007/978-3-031-72943-0_15","sourceUrl":"https://dblp.org/rec/conf/eccv/SimaRCCZXBLGL24","documentUrl":"https://doi.org/10.1007/978-3-031-72943-0_15","pages":"256-274"},{"key":"conf/iccv/ChenCXGC25","title":"Easi3R: Estimating Disentangled Motion from DUSt3R Without Training.","type":"Inproceedings","venue":"ICCV","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/ICCV51701.2025.00856","sourceUrl":"https://dblp.org/rec/conf/iccv/ChenCXGC25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.00856","pages":"9158-9168"},{"key":"conf/iccv/DongDSBG25","title":"MoGA: 3D Generative Avatar Prior for Monocular Gaussian Avatar Reconstruction.","type":"Inproceedings","venue":"ICCV","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/ICCV51701.2025.01236","sourceUrl":"https://dblp.org/rec/conf/iccv/DongDSBG25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.01236","pages":"13304-13314"},{"key":"conf/iccv/HavrylovHZG25","title":"Benchmarking Feature Upsampling Methods for Vision Foundation Models Using Interactive Segmentation.","type":"Inproceedings","venue":"ICCVW","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/ICCVW69036.2025.00028","sourceUrl":"https://dblp.org/rec/conf/iccv/HavrylovHZG25","documentUrl":"https://doi.org/10.1109/ICCVW69036.2025.00028","pages":"210-219"},{"key":"conf/iccv/HuangCHGZ25","title":"LoftUp: Learning a Coordinate-Based Feature Upsampler for Vision Foundation Models.","type":"Inproceedings","venue":"ICCV","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/ICCV51701.2025.00924","sourceUrl":"https://dblp.org/rec/conf/iccv/HuangCHGZ25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.00924","pages":"9913-9923"},{"key":"conf/iclr/MiyatoL0W25","title":"Artificial Kuramoto Oscillatory Neurons.","type":"Inproceedings","venue":"ICLR","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":null,"sourceUrl":"https://dblp.org/rec/conf/iclr/MiyatoL0W25","documentUrl":"https://openreview.net/forum?id=nwDRD4AMoN","pages":null},{"key":"conf/nips/YangCGCSJLGYC25","title":"ReSim: Reliable World Simulation for Autonomous Driving.","type":"Inproceedings","venue":"NeurIPS","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":null,"sourceUrl":"https://dblp.org/rec/conf/nips/YangCGCSJLGYC25","documentUrl":"http://papers.nips.cc/paper_files/paper/2025/hash/f502981cbe221d857ad409450a7917c3-Abstract-Conference.html","pages":null},{"key":"conf/siggraph/0001SSBLAPYNGLW25","title":"Relightable Full-Body Gaussian Codec Avatars.","type":"Inproceedings","venue":"SIGGRAPH (Conference Paper Track)","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1145/3721238.3730739","sourceUrl":"https://dblp.org/rec/conf/siggraph/0001SSBLAPYNGLW25","documentUrl":"https://doi.org/10.1145/3721238.3730739","pages":"146:1-146:12"},{"key":"journals/pami/FuZCLZGL25","title":"PanopticNeRF-360: Panoramic 3D-to-2D Label Transfer in Urban Scenes.","type":"Article","venue":"IEEE Trans. Pattern Anal. Mach. Intell.","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.1109/TPAMI.2025.3581608","sourceUrl":"https://dblp.org/rec/journals/pami/FuZCLZGL25","documentUrl":"https://doi.org/10.1109/TPAMI.2025.3581608","pages":"8804-8822"},{"key":"journals/ral/HanselmannDCLG25","title":"Emperror: A Flexible Generative Perception Error Model for Probing Self-Driving Planners.","type":"Article","venue":"IEEE Robotics Autom. Lett.","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.1109/LRA.2025.3562789","sourceUrl":"https://dblp.org/rec/journals/ral/HanselmannDCLG25","documentUrl":"https://doi.org/10.1109/LRA.2025.3562789","pages":"5807-5814"}],"preprints":[{"key":"journals/corr/abs-2501-14726","title":"Relightable Full-Body Gaussian Codec Avatars.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2501.14726","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2501-14726","documentUrl":"https://doi.org/10.48550/ARXIV.2501.14726","pages":null,"arxivId":"2501.14726","arxivUrl":"https://arxiv.org/abs/2501.14726"},{"key":"journals/corr/abs-2502-04318","title":"sshELF: Single-Shot Hierarchical Extrapolation of Latent Features for 3D Reconstruction from Sparse-Views.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2502.04318","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2502-04318","documentUrl":"https://doi.org/10.48550/ARXIV.2502.04318","pages":null,"arxivId":"2502.04318","arxivUrl":"https://arxiv.org/abs/2502.04318"},{"key":"journals/corr/abs-2502-05151","title":"Transforming Science with Large Language Models: A Survey on AI-assisted Scientific Discovery, Experimentation, Content Generation, and Evaluation.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2502.05151","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2502-05151","documentUrl":"https://doi.org/10.48550/ARXIV.2502.05151","pages":null,"arxivId":"2502.05151","arxivUrl":"https://arxiv.org/abs/2502.05151"},{"key":"journals/corr/abs-2503-11650","title":"Centaur: Robust End-to-End Autonomous Driving with Test-Time Training.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2503.11650","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-11650","documentUrl":"https://doi.org/10.48550/ARXIV.2503.11650","pages":null,"arxivId":"2503.11650","arxivUrl":"https://arxiv.org/abs/2503.11650"},{"key":"journals/corr/abs-2503-20168","title":"EVolSplat: Efficient Volume-based Gaussian Splatting for Urban View Synthesis.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2503.20168","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-20168","documentUrl":"https://doi.org/10.48550/ARXIV.2503.20168","pages":null,"arxivId":"2503.20168","arxivUrl":"https://arxiv.org/abs/2503.20168"},{"key":"journals/corr/abs-2503-21219","title":"GenFusion: Closing the Loop between Reconstruction and Generation via Videos.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2503.21219","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-21219","documentUrl":"https://doi.org/10.48550/ARXIV.2503.21219","pages":null,"arxivId":"2503.21219","arxivUrl":"https://arxiv.org/abs/2503.21219"},{"key":"journals/corr/abs-2503-24391","title":"Easi3R: Estimating Disentangled Motion from DUSt3R Without Training.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2503.24391","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-24391","documentUrl":"https://doi.org/10.48550/ARXIV.2503.24391","pages":null,"arxivId":"2503.24391","arxivUrl":"https://arxiv.org/abs/2503.24391"},{"key":"journals/corr/abs-2504-08385","title":"Scholar Inbox: Personalized Paper Recommendations for Scientists.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2504.08385","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2504-08385","documentUrl":"https://doi.org/10.48550/ARXIV.2504.08385","pages":null,"arxivId":"2504.08385","arxivUrl":"https://arxiv.org/abs/2504.08385"},{"key":"journals/corr/abs-2504-14032","title":"LoftUp: Learning a Coordinate-Based Feature Upsampler for Vision Foundation Models.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2504.14032","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2504-14032","documentUrl":"https://doi.org/10.48550/ARXIV.2504.14032","pages":null,"arxivId":"2504.14032","arxivUrl":"https://arxiv.org/abs/2504.14032"},{"key":"journals/corr/abs-2504-17838","title":"CaRL: Learning Scalable Planning Policies with Simple Rewards.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2504.17838","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2504-17838","documentUrl":"https://doi.org/10.48550/ARXIV.2504.17838","pages":null,"arxivId":"2504.17838","arxivUrl":"https://arxiv.org/abs/2504.17838"},{"key":"journals/corr/abs-2505-02075","title":"Benchmarking Feature Upsampling Methods for Vision Foundation Models using Interactive Segmentation.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2505.02075","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-02075","documentUrl":"https://doi.org/10.48550/ARXIV.2505.02075","pages":null,"arxivId":"2505.02075","arxivUrl":"https://arxiv.org/abs/2505.02075"},{"key":"journals/corr/abs-2506-04218","title":"Pseudo-Simulation for Autonomous Driving.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2506.04218","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-04218","documentUrl":"https://doi.org/10.48550/ARXIV.2506.04218","pages":null,"arxivId":"2506.04218","arxivUrl":"https://arxiv.org/abs/2506.04218"},{"key":"journals/corr/abs-2506-09981","title":"ReSim: Reliable World Simulation for Autonomous Driving.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2506.09981","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-09981","documentUrl":"https://doi.org/10.48550/ARXIV.2506.09981","pages":null,"arxivId":"2506.09981","arxivUrl":"https://arxiv.org/abs/2506.09981"},{"key":"journals/corr/abs-2506-19117","title":"PrITTI: Primitive-based Generation of Controllable and Editable 3D Semantic Scenes.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2506.19117","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-19117","documentUrl":"https://doi.org/10.48550/ARXIV.2506.19117","pages":null,"arxivId":"2506.19117","arxivUrl":"https://arxiv.org/abs/2506.19117"},{"key":"journals/corr/abs-2507-23597","title":"MoGA: 3D Generative Avatar Prior for Monocular Gaussian Avatar Reconstruction.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2507.23597","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2507-23597","documentUrl":"https://doi.org/10.48550/ARXIV.2507.23597","pages":null,"arxivId":"2507.23597","arxivUrl":"https://arxiv.org/abs/2507.23597"},{"key":"journals/corr/abs-2508-13148","title":"MDPO: Overcoming the Training-Inference Divide of Masked Diffusion Language Models.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2508.13148","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-13148","documentUrl":"https://doi.org/10.48550/ARXIV.2508.13148","pages":null,"arxivId":"2508.13148","arxivUrl":"https://arxiv.org/abs/2508.13148"},{"key":"journals/corr/abs-2509-00269","title":"3D-LATTE: Latent Space 3D Editing from Textual Instructions.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2509.00269","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-00269","documentUrl":"https://doi.org/10.48550/ARXIV.2509.00269","pages":null,"arxivId":"2509.00269","arxivUrl":"https://arxiv.org/abs/2509.00269"},{"key":"journals/corr/abs-2509-26645","title":"TTT3R: 3D Reconstruction as Test-Time Training.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2509.26645","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-26645","documentUrl":"https://doi.org/10.48550/ARXIV.2509.26645","pages":null,"arxivId":"2509.26645","arxivUrl":"https://arxiv.org/abs/2509.26645"},{"key":"journals/corr/abs-2510-08575","title":"ReSplat: Learning Recurrent Gaussian Splats.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2510.08575","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-08575","documentUrl":"https://doi.org/10.48550/ARXIV.2510.08575","pages":null,"arxivId":"2510.08575","arxivUrl":"https://arxiv.org/abs/2510.08575"},{"key":"journals/corr/abs-2511-06810","title":"ConeGS: Error-Guided Densification Using Pixel Cones for Improved Reconstruction with Fewer Primitives.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2511.06810","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2511-06810","documentUrl":"https://doi.org/10.48550/ARXIV.2511.06810","pages":null,"arxivId":"2511.06810","arxivUrl":"https://arxiv.org/abs/2511.06810"},{"key":"journals/corr/abs-2511-07292","title":"PlanT 2.0: Exposing Biases and Structural Flaws in Closed-Loop Driving.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2511.07292","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2511-07292","documentUrl":"https://doi.org/10.48550/ARXIV.2511.07292","pages":null,"arxivId":"2511.07292","arxivUrl":"https://arxiv.org/abs/2511.07292"},{"key":"journals/corr/abs-2512-10719","title":"SpaceDrive: Infusing Spatial Awareness into VLM-based Autonomous Driving.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2512.10719","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-10719","documentUrl":"https://doi.org/10.48550/ARXIV.2512.10719","pages":null,"arxivId":"2512.10719","arxivUrl":"https://arxiv.org/abs/2512.10719"},{"key":"journals/corr/abs-2512-20563","title":"LEAD: Minimizing Learner-Expert Asymmetry in End-to-End Driving.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2512.20563","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-20563","documentUrl":"https://doi.org/10.48550/ARXIV.2512.20563","pages":null,"arxivId":"2512.20563","arxivUrl":"https://arxiv.org/abs/2512.20563"}],"excludedFormal":[],"labName":"Autonomous Vision Group (AVG)","labUrl":"https://uni-tuebingen.de/en/fakultaeten/mathematisch-naturwissenschaftliche-fakultaet/fachbereiche/informatik/lehrstuehle/autonomous-vision/home/","labEvidence":"本人主页明确 heading the Autonomous Vision Group 并直接链接 Tübingen 官方组页；同页说明目前处于 leave of absence，另任 KE:SAI CEO。此为仍公开列出的团队关联。","labSourceUrl":"https://www.cvlibs.net/","affiliationZh":"University of Tübingen","sourceWarning":false,"excludedOther":[],"excludedHomonyms":[],"unassignedCandidates":[],"knownPreprintMinimum2025":null,"excludedMisattributed":[],"displayNotes":"身份已经机构或个人主页核对。2025 年正式记录 23 条（会议 21、期刊 2），所有作者位置均计入，不表示主导或贡献份额；预印本 23 条单列，不加总。","labDisplayNotes":"个人主页写明其领导图宾根大学 Autonomous Vision Group（AVG），并链接官方组页；同页也说明其目前离职休假、任 KE:SAI CEO。这里按仍在公开列出的关联归组，不推断其当前在组内的工作量。"},{"index":6,"name":"Jinjin Gu","nameZh":"Jinjin Gu","role":"Tenure-track Faculty Member","affiliation":"INSAIT","source":"DBLP official SPARQL","profileUrl":"https://dblp.org/pid/209/5709","identifier":"209/5709","identityEvidence":[{"url":"https://dblp.org/pid/209/5709","evidence":"DBLP 档案名 Jinjin Gu；机构/履历：Sofia University, Institute for Computer Science, Artificial Intelligence and Technology (INSAIT), Sofia, Bulgaria"}],"count2025":8,"conference2025":5,"journal2025":3,"preprint2025":11,"status":"verified","notes":"身份已通过机构/个人主页或 DBLP 机构信息核对；篇数为数据库记录统计，不表示每篇均由本人主导。","retrievedAt":"2026-10-19","yearPolicy":"DBLP yearOfPublication = 2025","queryUrl":"https://sparql.dblp.org/sparql?query=PREFIX%20dblp%3A%20%3Chttps%3A//dblp.org/rdf/schema%23%3E%20PREFIX%20xsd%3A%20%3Chttp%3A//www.w3.org/2001/XMLSchema%23%3E%20SELECT%20%3Fpub%20%3Ftitle%20%3Ftype%20%3Fvenue%20WHERE%20%7B%20%3Fpub%20dblp%3AauthoredBy%20%3Chttps%3A//dblp.org/pid/209/5709%3E%3B%20dblp%3AyearOfPublication%20%222025%22%5E%5Exsd%3AgYear%3B%20dblp%3Atitle%20%3Ftitle%3B%20a%20%3Ftype%20.%20OPTIONAL%20%7B%20%3Fpub%20dblp%3ApublishedIn%20%3Fvenue%20%7D%20%7D&format=json","papers":[{"key":"conf/cvpr/YouCGX025","title":"Teaching Large Language Models to Regress Accurate Image Quality Scores Using Score Distribution.","type":"Inproceedings","venue":"CVPR","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/CVPR52734.2025.01350","sourceUrl":"https://dblp.org/rec/conf/cvpr/YouCGX025","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/You_Teaching_Large_Language_Models_to_Regress_Accurate_Image_Quality_Scores_CVPR_2025_paper.html","pages":"14483-14494"},{"key":"conf/eccv/YouLGYXD24","title":"Depicting Beyond Scores: Advancing Image Quality Assessment Through Multi-modal Language Models.","type":"Inproceedings","venue":"ECCV (47)","year":2025,"yearOfPublication":2025,"yearOfEvent":2024,"doi":"https://doi.org/10.1007/978-3-031-72970-6_15","sourceUrl":"https://dblp.org/rec/conf/eccv/YouLGYXD24","documentUrl":"https://doi.org/10.1007/978-3-031-72970-6_15","pages":"259-276"},{"key":"conf/iclr/TaoG0WC25","title":"Overcoming False Illusions in Real-World Face Restoration with Multi-Modal Guided Diffusion Model.","type":"Inproceedings","venue":"ICLR","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":null,"sourceUrl":"https://dblp.org/rec/conf/iclr/TaoG0WC25","documentUrl":"https://openreview.net/forum?id=m9RNBZewW2","pages":null},{"key":"conf/iclr/YuGHL025","title":"UniCon: Unidirectional Information Flow for Effective Control of Large-Scale Diffusion Models.","type":"Inproceedings","venue":"ICLR","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":null,"sourceUrl":"https://dblp.org/rec/conf/iclr/YuGHL025","documentUrl":"https://openreview.net/forum?id=uJqKf24HGN","pages":null},{"key":"conf/iclr/ZhuGY0025","title":"An Intelligent Agentic System for Complex Image Restoration Problems.","type":"Inproceedings","venue":"ICLR","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":null,"sourceUrl":"https://dblp.org/rec/conf/iclr/ZhuGY0025","documentUrl":"https://openreview.net/forum?id=3RLxccFPHz","pages":null},{"key":"journals/pami/HuGYYLYLD25","title":"Interpreting Low-Level Vision Models With Causal Effect Maps.","type":"Article","venue":"IEEE Trans. Pattern Anal. Mach. Intell.","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.1109/TPAMI.2025.3557149","sourceUrl":"https://dblp.org/rec/journals/pami/HuGYYLYLD25","documentUrl":"https://doi.org/10.1109/TPAMI.2025.3557149","pages":"6396-6409"},{"key":"journals/tip/YouGCLZDX25","title":"Enhancing Descriptive Image Quality Assessment With a Large-Scale Multi-Modal Dataset.","type":"Article","venue":"IEEE Trans. Image Process.","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.1109/TIP.2025.3639998","sourceUrl":"https://dblp.org/rec/journals/tip/YouGCLZDX25","documentUrl":"https://doi.org/10.1109/TIP.2025.3639998","pages":"8201-8215"},{"key":"journals/tog/LinYHYSRGD25","title":"Harnessing Diffusion-Yielded Score Priors for Image Restoration.","type":"Article","venue":"ACM Trans. Graph.","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.1145/3763346","sourceUrl":"https://dblp.org/rec/journals/tog/LinYHYSRGD25","documentUrl":"https://doi.org/10.1145/3763346","pages":"208:1-208:21"}],"preprints":[{"key":"journals/corr/abs-2501-11561","title":"Teaching Large Language Models to Regress Accurate Image Quality Scores using Score Distribution.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2501.11561","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2501-11561","documentUrl":"https://doi.org/10.48550/ARXIV.2501.11561","pages":null,"arxivId":"2501.11561","arxivUrl":"https://arxiv.org/abs/2501.11561"},{"key":"journals/corr/abs-2502-12600","title":"Revisiting the Generalization Problem of Low-level Vision Models Through the Lens of Image Deraining.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2502.12600","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2502-12600","documentUrl":"https://doi.org/10.48550/ARXIV.2502.12600","pages":null,"arxivId":"2502.12600","arxivUrl":"https://arxiv.org/abs/2502.12600"},{"key":"journals/corr/abs-2503-17221","title":"UniCon: Unidirectional Information Flow for Effective Control of Large-Scale Diffusion Models.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2503.17221","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-17221","documentUrl":"https://doi.org/10.48550/ARXIV.2503.17221","pages":null,"arxivId":"2503.17221","arxivUrl":"https://arxiv.org/abs/2503.17221"},{"key":"journals/corr/abs-2505-16007","title":"Position: Agentic Systems Constitute a Key Component of Next-Generation Intelligent Image Processing.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2505.16007","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-16007","documentUrl":"https://doi.org/10.48550/ARXIV.2505.16007","pages":null,"arxivId":"2505.16007","arxivUrl":"https://arxiv.org/abs/2505.16007"},{"key":"journals/corr/abs-2505-23130","title":"PhotoArtAgent: Intelligent Photo Retouching with Language Model-Based Artist Agents.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2505.23130","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-23130","documentUrl":"https://doi.org/10.48550/ARXIV.2505.23130","pages":null,"arxivId":"2505.23130","arxivUrl":"https://arxiv.org/abs/2505.23130"},{"key":"journals/corr/abs-2507-20590","title":"Harnessing Diffusion-Yielded Score Priors for Image Restoration.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2507.20590","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2507-20590","documentUrl":"https://doi.org/10.48550/ARXIV.2507.20590","pages":null,"arxivId":"2507.20590","arxivUrl":"https://arxiv.org/abs/2507.20590"},{"key":"journals/corr/abs-2509-17677","title":"EngiBench: A Benchmark for Evaluating Large Language Models on Engineering Problem Solving.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2509.17677","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-17677","documentUrl":"https://doi.org/10.48550/ARXIV.2509.17677","pages":null,"arxivId":"2509.17677","arxivUrl":"https://arxiv.org/abs/2509.17677"},{"key":"journals/corr/abs-2510-06036","title":"Refusal Falls off a Cliff: How Safety Alignment Fails in Reasoning?","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2510.06036","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-06036","documentUrl":"https://doi.org/10.48550/ARXIV.2510.06036","pages":null,"arxivId":"2510.06036","arxivUrl":"https://arxiv.org/abs/2510.06036"},{"key":"journals/corr/abs-2510-13029","title":"Toward Reasoning-Centric Time-Series Analysis.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2510.13029","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-13029","documentUrl":"https://doi.org/10.48550/ARXIV.2510.13029","pages":null,"arxivId":"2510.13029","arxivUrl":"https://arxiv.org/abs/2510.13029"},{"key":"journals/corr/abs-2512-00993","title":"PhotoFramer: Multi-modal Image Composition Instruction.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2512.00993","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-00993","documentUrl":"https://doi.org/10.48550/ARXIV.2512.00993","pages":null,"arxivId":"2512.00993","arxivUrl":"https://arxiv.org/abs/2512.00993"},{"key":"journals/corr/abs-2512-23165","title":"Evaluating Parameter Efficient Methods for RLVR.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2512.23165","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-23165","documentUrl":"https://doi.org/10.48550/ARXIV.2512.23165","pages":null,"arxivId":"2512.23165","arxivUrl":"https://arxiv.org/abs/2512.23165"}],"excludedFormal":[],"labName":"Vision Group at INSAIT","labUrl":"https://vision.insait.ai/","labEvidence":"INSAIT 官方 Vision Group 网站将 Jinjin Gu 列为 Faculty，页尾明确 Vision Group at INSAIT。该项是共享研究组关联，不将其等同 Jinjin Gu 个人独占组。","labSourceUrl":"https://vision.insait.ai/people/jinjin-gu/","affiliationZh":"INSAIT","sourceWarning":false,"excludedOther":[],"excludedHomonyms":[],"unassignedCandidates":[],"knownPreprintMinimum2025":null,"excludedMisattributed":[],"displayNotes":"身份已经机构或个人主页核对。2025 年正式记录 8 条（会议 5、期刊 3），所有作者位置均计入，不表示主导或贡献份额；预印本 11 条单列，不加总。","labDisplayNotes":"INSAIT 官方 Vision Group 网站将其列为 Faculty，据此归组。这是多位教师共享的研究组，分组只含本人参与的记录。"},{"index":7,"name":"Qixing Huang","nameZh":"Qixing Huang","role":"Associate Professor","affiliation":"The University of Texas at Austin","source":"DBLP official SPARQL","profileUrl":"https://dblp.org/pid/82/241","identifier":"82/241","identityEvidence":[{"url":"https://dblp.org/pid/82/241","evidence":"DBLP 档案名 Qixing Huang；机构/履历：Stanford University, CA, USA；Toyota Technological Institute at Chicago, IL, USA；University of Texas at Austin, Department of Computer Science, TX, USA"},{"url":"https://s2025.conference-schedule.org/presentation/?id=gensub_146&sess=sess191","evidence":"SIGGRAPH course abstract, not a research paper; official program labels Event Type: Course and the authors maintain a course schedule.","matchedPaperKeys":["conf/siggraph/ChenGPLFHSM25"]}],"count2025":23,"conference2025":18,"journal2025":5,"preprint2025":15,"status":"verified_manual","notes":"身份已通过机构/个人主页或 DBLP 机构信息核对；篇数为数据库记录统计，不表示每篇均由本人主导。 已识别的课程摘要、受邀讲座摘要或学会人物公告不计为研究论文。不同 ORCID 本身不构成同名判定。","retrievedAt":"2026-10-19","yearPolicy":"DBLP yearOfPublication = 2025","queryUrl":"https://sparql.dblp.org/sparql?query=PREFIX%20dblp%3A%20%3Chttps%3A//dblp.org/rdf/schema%23%3E%20PREFIX%20xsd%3A%20%3Chttp%3A//www.w3.org/2001/XMLSchema%23%3E%20SELECT%20%3Fpub%20%3Ftitle%20%3Ftype%20%3Fvenue%20WHERE%20%7B%20%3Fpub%20dblp%3AauthoredBy%20%3Chttps%3A//dblp.org/pid/82/241%3E%3B%20dblp%3AyearOfPublication%20%222025%22%5E%5Exsd%3AgYear%3B%20dblp%3Atitle%20%3Ftitle%3B%20a%20%3Ftype%20.%20OPTIONAL%20%7B%20%3Fpub%20dblp%3ApublishedIn%20%3Fvenue%20%7D%20%7D&format=json","papers":[{"key":"conf/3dim/HeRH25","title":"A Robust Translation Synchronization Algorithm.","type":"Inproceedings","venue":"3DV","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/3DV66043.2025.00030","sourceUrl":"https://dblp.org/rec/conf/3dim/HeRH25","documentUrl":"https://doi.org/10.1109/3DV66043.2025.00030","pages":"276-285"},{"key":"conf/cvpr/ChenWC0YZYFLHL25","title":"CADCrafter: Generating Computer-Aided Design Models from Unconstrained Images.","type":"Inproceedings","venue":"CVPR","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/CVPR52734.2025.01034","sourceUrl":"https://dblp.org/rec/conf/cvpr/ChenWC0YZYFLHL25","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Chen_CADCrafter_Generating_Computer-Aided_Design_Models_from_Unconstrained_Images_CVPR_2025_paper.html","pages":"11073-11082"},{"key":"conf/cvpr/HadgiMSGHRMO25","title":"Escaping Plato's Cave: Towards the Alignment of 3D and Text Latent Spaces.","type":"Inproceedings","venue":"CVPR","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/CVPR52734.2025.01846","sourceUrl":"https://dblp.org/rec/conf/cvpr/HadgiMSGHRMO25","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Hadgi_Escaping_Platos_Cave_Towards_the_Alignment_of_3D_and_Text_CVPR_2025_paper.html","pages":"19825-19835"},{"key":"conf/cvpr/JiangXXCJLS0B0G25","title":"MegaSynth: Scaling Up 3D Scene Reconstruction with Synthesized Data.","type":"Inproceedings","venue":"CVPR","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/CVPR52734.2025.01533","sourceUrl":"https://dblp.org/rec/conf/cvpr/JiangXXCJLS0B0G25","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Jiang_MegaSynth_Scaling_Up_3D_Scene_Reconstruction_with_Synthesized_Data_CVPR_2025_paper.html","pages":"16441-16452"},{"key":"conf/cvpr/Xia0VHP25","title":"Reconstructing Humans with a Biomechanically Accurate Skeleton.","type":"Inproceedings","venue":"CVPR","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/CVPR52734.2025.00504","sourceUrl":"https://dblp.org/rec/conf/cvpr/Xia0VHP25","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Xia_Reconstructing_Humans_with_a_Biomechanically_Accurate_Skeleton_CVPR_2025_paper.html","pages":"5355-5365"},{"key":"conf/cvpr/YangCKCHC25","title":"GenVDM: Generating Vector Displacement Maps From a Single Image.","type":"Inproceedings","venue":"CVPR","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/CVPR52734.2025.02479","sourceUrl":"https://dblp.org/rec/conf/cvpr/YangCKCHC25","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Yang_GenVDM_Generating_Vector_Displacement_Maps_From_a_Single_Image_CVPR_2025_paper.html","pages":"26618-26629"},{"key":"conf/eccv/HeYZDBH24","title":"Freditor: High-Fidelity and Transferable NeRF Editing by Frequency Decomposition.","type":"Inproceedings","venue":"ECCV (41)","year":2025,"yearOfPublication":2025,"yearOfEvent":2024,"doi":"https://doi.org/10.1007/978-3-031-72940-9_5","sourceUrl":"https://dblp.org/rec/conf/eccv/HeYZDBH24","documentUrl":"https://doi.org/10.1007/978-3-031-72940-9_5","pages":"73-91"},{"key":"conf/eccv/LuKLLYHH24","title":"UGG: Unified Generative Grasping.","type":"Inproceedings","venue":"ECCV (67)","year":2025,"yearOfPublication":2025,"yearOfEvent":2024,"doi":"https://doi.org/10.1007/978-3-031-72855-6_24","sourceUrl":"https://dblp.org/rec/conf/eccv/LuKLLYHH24","documentUrl":"https://doi.org/10.1007/978-3-031-72855-6_24","pages":"414-433"},{"key":"conf/eccv/YanBCZHL24","title":"ViGoR: Improving Visual Grounding of Large Vision Language Models with Fine-Grained Reward Modeling.","type":"Inproceedings","venue":"ECCV (61)","year":2025,"yearOfPublication":2025,"yearOfEvent":2024,"doi":"https://doi.org/10.1007/978-3-031-73030-6_3","sourceUrl":"https://dblp.org/rec/conf/eccv/YanBCZHL24","documentUrl":"https://doi.org/10.1007/978-3-031-73030-6_3","pages":"37-53"},{"key":"conf/eccv/ZhaoSGDZYBDH24","title":"An Optimization Framework to Enforce Multi-view Consistency for Texturing 3D Meshes.","type":"Inproceedings","venue":"ECCV (36)","year":2025,"yearOfPublication":2025,"yearOfEvent":2024,"doi":"https://doi.org/10.1007/978-3-031-72764-1_9","sourceUrl":"https://dblp.org/rec/conf/eccv/ZhaoSGDZYBDH24","documentUrl":"https://doi.org/10.1007/978-3-031-72764-1_9","pages":"145-162"},{"key":"conf/iccv/BaiH25","title":"FiffDepth: Feed-Forward Transformation of Diffusion-Based Generators for Detailed Depth Estimation.","type":"Inproceedings","venue":"ICCV","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/ICCV51701.2025.00569","sourceUrl":"https://dblp.org/rec/conf/iccv/BaiH25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.00569","pages":"6023-6033"},{"key":"conf/iccv/JiangHP25","title":"Real3D: Towards Scaling Large Reconstruction Models with Real Images.","type":"Inproceedings","venue":"ICCV","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/ICCV51701.2025.00551","sourceUrl":"https://dblp.org/rec/conf/iccv/JiangHP25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.00551","pages":"5821-5833"},{"key":"conf/iccv/JiangTWJZBZLSHP25","title":"Rayzer: a Self-Supervised Large View Synthesis Model.","type":"Inproceedings","venue":"ICCV","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/ICCV51701.2025.00468","sourceUrl":"https://dblp.org/rec/conf/iccv/JiangTWJZBZLSHP25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.00468","pages":"4918-4929"},{"key":"conf/iccv/LeeJKHYK25","title":"PASTA: Part-Aware Sketch-to-3D Shape Generation with Text-Aligned Prior.","type":"Inproceedings","venue":"ICCV","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/ICCV51701.2025.01727","sourceUrl":"https://dblp.org/rec/conf/iccv/LeeJKHYK25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.01727","pages":"18585-18595"},{"key":"conf/iccv/LuHBHZ25","title":"Humoto: A 4D Dataset of Mocap Human Object Interactions.","type":"Inproceedings","venue":"ICCV","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/ICCV51701.2025.01013","sourceUrl":"https://dblp.org/rec/conf/iccv/LuHBHZ25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.01013","pages":"10886-10897"},{"key":"conf/iccv/LuHH25","title":"Jigsaw++: Imagining Complete Shape Priors for Object Reassembly.","type":"Inproceedings","venue":"ICCV","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/ICCV51701.2025.00631","sourceUrl":"https://dblp.org/rec/conf/iccv/LuHH25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.00631","pages":"6704-6714"},{"key":"conf/iclr/0005DJXPH25","title":"Atlas Gaussians Diffusion for 3D Generation.","type":"Inproceedings","venue":"ICLR","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":null,"sourceUrl":"https://dblp.org/rec/conf/iclr/0005DJXPH25","documentUrl":"https://openreview.net/forum?id=H2Gxil855b","pages":null},{"key":"conf/nips/BaiFYWH25","title":"GeoVideo: Introducing Geometric Regularization into Video Generation Model.","type":"Inproceedings","venue":"NeurIPS","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":null,"sourceUrl":"https://dblp.org/rec/conf/nips/BaiFYWH25","documentUrl":"http://papers.nips.cc/paper_files/paper/2025/hash/536d18fbb454f80221465f1a42c6f389-Abstract-Conference.html","pages":null},{"key":"journals/cgf/FangYMH25","title":"Text-Guided Interactive Scene Synthesis with Scene Prior Guidance.","type":"Article","venue":"Comput. Graph. Forum","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.1111/CGF.70039","sourceUrl":"https://dblp.org/rec/journals/cgf/FangYMH25","documentUrl":"https://doi.org/10.1111/CGF.70039","pages":null},{"key":"journals/cgf/HeYDLGH25","title":"An Efficient Global-to-Local Rotation Optimization Approach via Spherical Harmonics.","type":"Article","venue":"Comput. Graph. Forum","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.1111/CGF.70185","sourceUrl":"https://dblp.org/rec/journals/cgf/HeYDLGH25","documentUrl":"https://doi.org/10.1111/CGF.70185","pages":null},{"key":"journals/cgf/LuLHHJLH25","title":"A Survey on Computational Solutions for Reconstructing Complete Objects by Reassembling Their Fractured Parts.","type":"Article","venue":"Comput. Graph. Forum","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.1111/CGF.70081","sourceUrl":"https://dblp.org/rec/journals/cgf/LuLHHJLH25","documentUrl":"https://doi.org/10.1111/CGF.70081","pages":null},{"key":"journals/pami/ChiCHR25","title":"InfoGCN++: Learning Representation by Predicting the Future for Online Skeleton-Based Action Recognition.","type":"Article","venue":"IEEE Trans. Pattern Anal. Mach. Intell.","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.1109/TPAMI.2024.3466212","sourceUrl":"https://dblp.org/rec/journals/pami/ChiCHR25","documentUrl":"https://doi.org/10.1109/TPAMI.2024.3466212","pages":"514-528"},{"key":"journals/tog/YangYNHGH25","title":"GenAnalysis: Joint Shape Analysis by Learning Man-Made Shape Generators with Deformation Regularizations.","type":"Article","venue":"ACM Trans. Graph.","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.1145/3731164","sourceUrl":"https://dblp.org/rec/journals/tog/YangYNHGH25","documentUrl":"https://doi.org/10.1145/3731164","pages":"61:1-61:19"}],"preprints":[{"key":"journals/corr/abs-2503-00605","title":"GenVDM: Generating Vector Displacement Maps From a Single Image.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2503.00605","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-00605","documentUrl":"https://doi.org/10.48550/ARXIV.2503.00605","pages":null,"arxivId":"2503.00605","arxivUrl":"https://arxiv.org/abs/2503.00605"},{"key":"journals/corr/abs-2503-00807","title":"GenAnalysis: Joint Shape Analysis by Learning Man-Made Shape Generators with Deformation Regularizations.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2503.00807","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-00807","documentUrl":"https://doi.org/10.48550/ARXIV.2503.00807","pages":null,"arxivId":"2503.00807","arxivUrl":"https://arxiv.org/abs/2503.00807"},{"key":"journals/corr/abs-2503-05283","title":"Escaping Plato's Cave: Towards the Alignment of 3D and Text Latent Spaces.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2503.05283","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-05283","documentUrl":"https://doi.org/10.48550/ARXIV.2503.05283","pages":null,"arxivId":"2503.05283","arxivUrl":"https://arxiv.org/abs/2503.05283"},{"key":"journals/corr/abs-2503-12834","title":"PASTA: Part-Aware Sketch-to-3D Shape Generation with Text-Aligned Prior.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2503.12834","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-12834","documentUrl":"https://doi.org/10.48550/ARXIV.2503.12834","pages":null,"arxivId":"2503.12834","arxivUrl":"https://arxiv.org/abs/2503.12834"},{"key":"journals/corr/abs-2503-21751","title":"Reconstructing Humans with a Biomechanically Accurate Skeleton.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2503.21751","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-21751","documentUrl":"https://doi.org/10.48550/ARXIV.2503.21751","pages":null,"arxivId":"2503.21751","arxivUrl":"https://arxiv.org/abs/2503.21751"},{"key":"journals/corr/abs-2504-04753","title":"CADCrafter: Generating Computer-Aided Design Models from Unconstrained Images.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2504.04753","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2504-04753","documentUrl":"https://doi.org/10.48550/ARXIV.2504.04753","pages":null,"arxivId":"2504.04753","arxivUrl":"https://arxiv.org/abs/2504.04753"},{"key":"journals/corr/abs-2504-10414","title":"HUMOTO: A 4D Dataset of Mocap Human Object Interactions.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2504.10414","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2504-10414","documentUrl":"https://doi.org/10.48550/ARXIV.2504.10414","pages":null,"arxivId":"2504.10414","arxivUrl":"https://arxiv.org/abs/2504.10414"},{"key":"journals/corr/abs-2505-00702","title":"RayZer: A Self-supervised Large View Synthesis Model.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2505.00702","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-00702","documentUrl":"https://doi.org/10.48550/ARXIV.2505.00702","pages":null,"arxivId":"2505.00702","arxivUrl":"https://arxiv.org/abs/2505.00702"},{"key":"journals/corr/abs-2505-12734","title":"SounDiT: Geo-Contextual Soundscape-to-Landscape Generation.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2505.12734","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-12734","documentUrl":"https://doi.org/10.48550/ARXIV.2505.12734","pages":null,"arxivId":"2505.12734","arxivUrl":"https://arxiv.org/abs/2505.12734"},{"key":"journals/corr/abs-2510-20385","title":"Positional Encoding Field.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2510.20385","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-20385","documentUrl":"https://doi.org/10.48550/ARXIV.2510.20385","pages":null,"arxivId":"2510.20385","arxivUrl":"https://arxiv.org/abs/2510.20385"},{"key":"journals/corr/abs-2512-03453","title":"GeoVideo: Introducing Geometric Regularization into Video Generation Model.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2512.03453","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-03453","documentUrl":"https://doi.org/10.48550/ARXIV.2512.03453","pages":null,"arxivId":"2512.03453","arxivUrl":"https://arxiv.org/abs/2512.03453"},{"key":"journals/corr/abs-2512-04248","title":"MVRoom: Controllable 3D Indoor Scene Generation with Multi-View Diffusion Models.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2512.04248","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-04248","documentUrl":"https://doi.org/10.48550/ARXIV.2512.04248","pages":null,"arxivId":"2512.04248","arxivUrl":"https://arxiv.org/abs/2512.04248"},{"key":"journals/corr/abs-2512-07821","title":"WorldReel: 4D Video Generation with Consistent Geometry and Motion Modeling.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2512.07821","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-07821","documentUrl":"https://doi.org/10.48550/ARXIV.2512.07821","pages":null,"arxivId":"2512.07821","arxivUrl":"https://arxiv.org/abs/2512.07821"},{"key":"journals/corr/abs-2512-17781","title":"LiteGE: Lightweight Geodesic Embedding for Efficient Geodesics Computation and Non-Isometric Shape Correspondence.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2512.17781","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-17781","documentUrl":"https://doi.org/10.48550/ARXIV.2512.17781","pages":null,"arxivId":"2512.17781","arxivUrl":"https://arxiv.org/abs/2512.17781"},{"key":"journals/corr/abs-2512-19049","title":"Decoupled Generative Modeling for Human-Object Interaction Synthesis.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2512.19049","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-19049","documentUrl":"https://doi.org/10.48550/ARXIV.2512.19049","pages":null,"arxivId":"2512.19049","arxivUrl":"https://arxiv.org/abs/2512.19049"}],"excludedFormal":[{"key":"conf/siggraph/ChenGPLFHSM25","title":"Graphics4Science: Computer Graphics for Scientific Impacts.","type":"Inproceedings","venue":"SIGGRAPH Courses","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1145/3721241.3733986","sourceUrl":"https://dblp.org/rec/conf/siggraph/ChenGPLFHSM25","documentUrl":"https://doi.org/10.1145/3721241.3733986","pages":"21:1-21:3","exclusionReason":"SIGGRAPH course abstract, not a research paper; official program labels Event Type: Course and the authors maintain a course schedule.","exclusionSource":"https://s2025.conference-schedule.org/presentation/?id=gensub_146&sess=sess191"}],"excludedOther":[{"key":"journals/corr/abs-2506-15786","title":"Graphics4Science: Computer Graphics for Scientific Impacts.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2506.15786","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-15786","documentUrl":"https://doi.org/10.48550/ARXIV.2506.15786","pages":null,"exclusionReason":"CoRR version of the same explicitly identified SIGGRAPH course abstract.","exclusionSource":"https://graphics4science.github.io/"}],"labName":"Machine Learning Laboratory","labUrl":"https://ml.utexas.edu/","labEvidence":"UT Austin 官方 Machine Learning Laboratory 的 People 名单明确列 Qixing Huang，并链接本人主页；属于共享实验室成员关系，未宣称由他独自领导。","labSourceUrl":"https://ml.utexas.edu/people","affiliationZh":"The University of Texas at Austin","sourceWarning":true,"excludedHomonyms":[],"unassignedCandidates":[],"knownPreprintMinimum2025":null,"excludedMisattributed":[],"displayNotes":"身份已核对。另排除 1 条课程类条目，它不是研究论文；ORCID 不同本身不被当作同名证据。计入 23 条（会议 18、期刊 5）；预印本 15 条单列，不加总。","labDisplayNotes":"UT Austin Machine Learning Laboratory 官方名单列其为成员，并链接本人主页。这是共享实验室的成员关系，不表示由他领导；分组只含本人参与的记录。"},{"index":8,"name":"Phillip Isola","nameZh":"Phillip Isola","role":"Associate Professor","affiliation":"Massachusetts Institute of Technology","source":"DBLP official SPARQL","profileUrl":"https://dblp.org/pid/36/9988","identifier":"36/9988","identityEvidence":[{"url":"https://dblp.org/pid/36/9988","evidence":"DBLP 唯一同名作者档案；通过作者/机构主页与发表题名交叉核对。"},{"url":"https://web.mit.edu/phillipi/","evidence":"作者/机构页面与该 DBLP 档案交叉匹配的题名示例：Scalable Optimization in the Modular Norm.；The Platonic Representation Hypothesis.","matchedPaperKeys":["conf/nips/LargeLHBIB24","journals/corr/abs-2405-07987"]}],"count2025":7,"conference2025":7,"journal2025":0,"preprint2025":9,"status":"verified","notes":"身份已通过机构/个人主页或 DBLP 机构信息核对；篇数为数据库记录统计，不表示每篇均由本人主导。","retrievedAt":"2026-10-19","yearPolicy":"DBLP yearOfPublication = 2025","queryUrl":"https://sparql.dblp.org/sparql?query=PREFIX%20dblp%3A%20%3Chttps%3A//dblp.org/rdf/schema%23%3E%20PREFIX%20xsd%3A%20%3Chttp%3A//www.w3.org/2001/XMLSchema%23%3E%20SELECT%20%3Fpub%20%3Ftitle%20%3Ftype%20%3Fvenue%20WHERE%20%7B%20%3Fpub%20dblp%3AauthoredBy%20%3Chttps%3A//dblp.org/pid/36/9988%3E%3B%20dblp%3AyearOfPublication%20%222025%22%5E%5Exsd%3AgYear%3B%20dblp%3Atitle%20%3Ftitle%3B%20a%20%3Ftype%20.%20OPTIONAL%20%7B%20%3Fpub%20dblp%3ApublishedIn%20%3Fvenue%20%7D%20%7D&format=json","papers":[{"key":"conf/cvpr/TamirAIASFSID0F25","title":"What Makes for a Good Stereoscopic Image?","type":"Inproceedings","venue":"CVPR Workshops","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":null,"sourceUrl":"https://dblp.org/rec/conf/cvpr/TamirAIASFSID0F25","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025W/CV4Metaverse/html/Tamir_What_Makes_for_a_Good_Stereoscopic_Image_CVPRW_2025_paper.html","pages":"261-272"},{"key":"conf/iccv/BahngCDI25","title":"Cycle Consistency as Reward: Learning Image-Text Alignment Without Human Preferences.","type":"Inproceedings","venue":"ICCV","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/ICCV51701.2025.02129","sourceUrl":"https://dblp.org/rec/conf/iccv/BahngCDI25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.02129","pages":"22934-22946"},{"key":"conf/iclr/DuggalI0F25","title":"Adaptive Length Image Tokenization via Recurrent Allocation.","type":"Inproceedings","venue":"ICLR","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":null,"sourceUrl":"https://dblp.org/rec/conf/iclr/DuggalI0F25","documentUrl":"https://openreview.net/forum?id=mb2ryuZ3wz","pages":null},{"key":"conf/iclr/SundaramCTBI25","title":"Personalized Representation from Personalized Generation.","type":"Inproceedings","venue":"ICLR","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":null,"sourceUrl":"https://dblp.org/rec/conf/iclr/SundaramCTBI25","documentUrl":"https://openreview.net/forum?id=jw7P4MHLWw","pages":null},{"key":"conf/icml/Rodriguez-Munoz25","title":"Separating Knowledge and Perception with Procedural Data.","type":"Inproceedings","venue":"ICML","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":null,"sourceUrl":"https://dblp.org/rec/conf/icml/Rodriguez-Munoz25","documentUrl":"https://proceedings.mlr.press/v267/rodriguez-munoz25a.html","pages":null},{"key":"conf/iros/PfaffFBIT25","title":"Scalable Real2Sim: Physics-Aware Asset Generation Via Robotic Pick-and-Place Setups.","type":"Inproceedings","venue":"IROS","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/IROS60139.2025.11246653","sourceUrl":"https://dblp.org/rec/conf/iros/PfaffFBIT25","documentUrl":"https://doi.org/10.1109/IROS60139.2025.11246653","pages":"6296-6303"},{"key":"conf/nips/DuggalBFTI25","title":"Single-pass Adaptive Image Tokenization for Minimum Program Search.","type":"Inproceedings","venue":"NeurIPS","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":null,"sourceUrl":"https://dblp.org/rec/conf/nips/DuggalBFTI25","documentUrl":"http://papers.nips.cc/paper_files/paper/2025/hash/dc35c593e61f6df62db541b976d09dcf-Abstract-Conference.html","pages":null}],"preprints":[{"key":"journals/corr/abs-2503-00370","title":"Scalable Real2Sim: Physics-Aware Asset Generation Via Robotic Pick-and-Place Setups.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2503.00370","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-00370","documentUrl":"https://doi.org/10.48550/ARXIV.2503.00370","pages":null,"arxivId":"2503.00370","arxivUrl":"https://arxiv.org/abs/2503.00370"},{"key":"journals/corr/abs-2506-02095","title":"Cycle Consistency as Reward: Learning Image-Text Alignment without Human Preferences.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2506.02095","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-02095","documentUrl":"https://doi.org/10.48550/ARXIV.2506.02095","pages":null,"arxivId":"2506.02095","arxivUrl":"https://arxiv.org/abs/2506.02095"},{"key":"journals/corr/abs-2507-07995","title":"Single-pass Adaptive Image Tokenization for Minimum Program Search.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2507.07995","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2507-07995","documentUrl":"https://doi.org/10.48550/ARXIV.2507.07995","pages":null,"arxivId":"2507.07995","arxivUrl":"https://arxiv.org/abs/2507.07995"},{"key":"journals/corr/abs-2507-12821","title":"Assessing Adaptive World Models in Machines with Novel Games.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2507.12821","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2507-12821","documentUrl":"https://doi.org/10.48550/ARXIV.2507.12821","pages":null,"arxivId":"2507.12821","arxivUrl":"https://arxiv.org/abs/2507.12821"},{"key":"journals/corr/abs-2507-13338","title":"Training Transformers with Enforced Lipschitz Constants.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2507.13338","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2507-13338","documentUrl":"https://doi.org/10.48550/ARXIV.2507.13338","pages":null,"arxivId":"2507.13338","arxivUrl":"https://arxiv.org/abs/2507.13338"},{"key":"journals/corr/abs-2508-11697","title":"Separating Knowledge and Perception with Procedural Data.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2508.11697","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-11697","documentUrl":"https://doi.org/10.48550/ARXIV.2508.11697","pages":null,"arxivId":"2508.11697","arxivUrl":"https://arxiv.org/abs/2508.11697"},{"key":"journals/corr/abs-2508-12524","title":"Results of the NeurIPS 2023 Neural MMO Competition on Multi-task Reinforcement Learning.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2508.12524","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-12524","documentUrl":"https://doi.org/10.48550/ARXIV.2508.12524","pages":null,"arxivId":"2508.12524","arxivUrl":"https://arxiv.org/abs/2508.12524"},{"key":"journals/corr/abs-2510-02425","title":"Words That Make Language Models Perceive.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2510.02425","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-02425","documentUrl":"https://doi.org/10.48550/ARXIV.2510.02425","pages":null,"arxivId":"2510.02425","arxivUrl":"https://arxiv.org/abs/2510.02425"},{"key":"journals/corr/abs-2510-08492","title":"Better Together: Leveraging Unpaired Multimodal Data for Stronger Unimodal Models.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2510.08492","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-08492","documentUrl":"https://doi.org/10.48550/ARXIV.2510.08492","pages":null,"arxivId":"2510.08492","arxivUrl":"https://arxiv.org/abs/2510.08492"}],"excludedFormal":[],"labName":"Computer Science and Artificial Intelligence Laboratory (CSAIL)","labUrl":"https://www.csail.mit.edu/","labEvidence":"MIT 官方介绍将 Phillip Isola 列为 CSAIL principal investigator；CSAIL 官方本人页标为 PI。个人小组没有确认独立名称，此条仅表示共享实验室成员关系。","labSourceUrl":"https://sqi.mit.edu/about/people/phillip-isola","affiliationZh":"Massachusetts Institute of Technology","sourceWarning":false,"excludedOther":[],"excludedHomonyms":[],"unassignedCandidates":[],"knownPreprintMinimum2025":null,"excludedMisattributed":[],"displayNotes":"身份已经机构或个人主页核对。2025 年正式记录 7 条，均为会议论文，所有作者位置均计入；预印本 9 条单列，不加总。","labDisplayNotes":"MIT 官方介绍与 CSAIL 本人页均列其为 CSAIL 的 PI，据此归组。CSAIL 是 MIT 的大型共享实验室，本人小组的独立名称未能确认；分组只含本人参与的记录，远非 CSAIL 的产量。"},{"index":9,"name":"Chenfanfu Jiang","nameZh":"Chenfanfu Jiang","role":"Professor","affiliation":"University of California, Los Angeles","source":"DBLP official SPARQL","profileUrl":"https://dblp.org/pid/132/7630","identifier":"132/7630","identityEvidence":[{"url":"https://dblp.org/pid/132/7630","evidence":"DBLP 唯一同名作者档案；通过作者/机构主页与发表题名交叉核对。"},{"url":"https://math.ucla.edu/~cffjiang/","evidence":"作者本人主页确认姓名与声明中的任职机构；发表列表与 DBLP 档案交叉核对。"},{"url":"https://www.math.ucla.edu/aivc/publication/","evidence":"作者/机构页面与该 DBLP 档案交叉匹配的题名示例：GarmentDreamer: 3DGS Guided Garment Synthesis with Diverse Geometry and Texture Details.；PhysMotion: Physics-Grounded Dynamics From a Single Image.","matchedPaperKeys":["conf/3dim/LiLJXGWYJ25","conf/3dim/TanJLZXYJ26"]}],"count2025":20,"conference2025":16,"journal2025":4,"preprint2025":18,"status":"verified","notes":"身份已通过机构/个人主页或 DBLP 机构信息核对；篇数为数据库记录统计，不表示每篇均由本人主导。","retrievedAt":"2026-10-19","yearPolicy":"DBLP yearOfPublication = 2025","queryUrl":"https://sparql.dblp.org/sparql?query=PREFIX%20dblp%3A%20%3Chttps%3A//dblp.org/rdf/schema%23%3E%20PREFIX%20xsd%3A%20%3Chttp%3A//www.w3.org/2001/XMLSchema%23%3E%20SELECT%20%3Fpub%20%3Ftitle%20%3Ftype%20%3Fvenue%20WHERE%20%7B%20%3Fpub%20dblp%3AauthoredBy%20%3Chttps%3A//dblp.org/pid/132/7630%3E%3B%20dblp%3AyearOfPublication%20%222025%22%5E%5Exsd%3AgYear%3B%20dblp%3Atitle%20%3Ftitle%3B%20a%20%3Ftype%20.%20OPTIONAL%20%7B%20%3Fpub%20dblp%3ApublishedIn%20%3Fvenue%20%7D%20%7D&format=json","papers":[{"key":"conf/3dim/LiLJXGWYJ25","title":"GarmentDreamer: 3DGS Guided Garment Synthesis with Diverse Geometry and Texture Details.","type":"Inproceedings","venue":"3DV","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/3DV66043.2025.00134","sourceUrl":"https://dblp.org/rec/conf/3dim/LiLJXGWYJ25","documentUrl":"https://doi.org/10.1109/3DV66043.2025.00134","pages":"1416-1426"},{"key":"conf/cvpr/Feng0BS0W0J025","title":"ARM: Appearance Reconstruction Model for Relightable 3D Generation.","type":"Inproceedings","venue":"CVPR","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/CVPR52734.2025.01996","sourceUrl":"https://dblp.org/rec/conf/cvpr/Feng0BS0W0J025","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Feng_ARM_Appearance_Reconstruction_Model_for_Relightable_3D_Generation_CVPR_2025_paper.html","pages":"21425-21437"},{"key":"conf/cvpr/FengFSJ0ZSW0J025","title":"Gaussian Splashing: Unified Particles for Versatile Motion Synthesis and Rendering.","type":"Inproceedings","venue":"CVPR","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/CVPR52734.2025.00057","sourceUrl":"https://dblp.org/rec/conf/cvpr/FengFSJ0ZSW0J025","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Feng_Gaussian_Splashing_Unified_Particles_for_Versatile_Motion_Synthesis_and_Rendering_CVPR_2025_paper.html","pages":"518-529"},{"key":"conf/cvpr/LiMLCJ0X25","title":"Articulated Kinematics Distillation from Video Diffusion Models.","type":"Inproceedings","venue":"CVPR","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/CVPR52734.2025.01637","sourceUrl":"https://dblp.org/rec/conf/cvpr/LiMLCJ0X25","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Li_Articulated_Kinematics_Distillation_from_Video_Diffusion_Models_CVPR_2025_paper.html","pages":"17571-17581"},{"key":"conf/cvpr/ShenS0J025","title":"EnliveningGS: Active Locomotion of 3DGS.","type":"Inproceedings","venue":"CVPR","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/CVPR52734.2025.00092","sourceUrl":"https://dblp.org/rec/conf/cvpr/ShenS0J025","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Shen_EnliveningGS_Active_Locomotion_of_3DGS_CVPR_2025_paper.html","pages":"896-905"},{"key":"conf/cvpr/XieZJJ25","title":"PhysAnimator: Physics-Guided Generative Cartoon Animation.","type":"Inproceedings","venue":"CVPR","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/CVPR52734.2025.01008","sourceUrl":"https://dblp.org/rec/conf/cvpr/XieZJJ25","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Xie_PhysAnimator_Physics-Guided_Generative_Cartoon_Animation_CVPR_2025_paper.html","pages":"10793-10804"},{"key":"conf/icassp/GuoXHXJTJ025","title":"CFSum: A Transformer-Based Multi-Modal Video Summarization Framework With Coarse-Fine Fusion.","type":"Inproceedings","venue":"ICASSP","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/ICASSP49660.2025.10889812","sourceUrl":"https://dblp.org/rec/conf/icassp/GuoXHXJTJ025","documentUrl":"https://doi.org/10.1109/ICASSP49660.2025.10889812","pages":"1-5"},{"key":"conf/iclr/BansalLXZYBJSCG25","title":"VideoPhy: Evaluating Physical Commonsense for Video Generation.","type":"Inproceedings","venue":"ICLR","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":null,"sourceUrl":"https://dblp.org/rec/conf/iclr/BansalLXZYBJSCG25","documentUrl":"https://openreview.net/forum?id=9D2QvO1uWj","pages":null},{"key":"conf/iclr/CaoGWKHKJT025","title":"Lightweight Predictive 3D Gaussian Splats.","type":"Inproceedings","venue":"ICLR","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":null,"sourceUrl":"https://dblp.org/rec/conf/iclr/CaoGWKHKJT025","documentUrl":"https://openreview.net/forum?id=PbheqxnO1e","pages":null},{"key":"conf/icra/DuYMJZYMCHJ25","title":"Embedded IPC: Fast and Intersection-Free Simulation in Reduced Subspace for Robot Manipulation.","type":"Inproceedings","venue":"ICRA","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/ICRA55743.2025.11128485","sourceUrl":"https://dblp.org/rec/conf/icra/DuYMJZYMCHJ25","documentUrl":"https://doi.org/10.1109/ICRA55743.2025.11128485","pages":"6911-6918"},{"key":"conf/iros/MaDYJZXCYHJ25","title":"GRIP: A General Robotic Incremental Potential Contact Simulation Dataset for Unified Deformable-Rigid Coupled Grasping.","type":"Inproceedings","venue":"IROS","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/IROS60139.2025.11247903","sourceUrl":"https://dblp.org/rec/conf/iros/MaDYJZXCYHJ25","documentUrl":"https://doi.org/10.1109/IROS60139.2025.11247903","pages":"6312-6319"},{"key":"conf/iros/YuDZCJH25","title":"A Convex Formulation of Material Points and Rigid Bodies with GPU-Accelerated Async-Coupling for Interactive Simulation.","type":"Inproceedings","venue":"IROS","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/IROS60139.2025.11245821","sourceUrl":"https://dblp.org/rec/conf/iros/YuDZCJH25","documentUrl":"https://doi.org/10.1109/IROS60139.2025.11245821","pages":"6280-6287"},{"key":"conf/nips/ChenCGKJRTK25","title":"Towards Physical Understanding in Video Generation: A 3D Point Regularization Approach.","type":"Inproceedings","venue":"NeurIPS","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":null,"sourceUrl":"https://dblp.org/rec/conf/nips/ChenCGKJRTK25","documentUrl":"http://papers.nips.cc/paper_files/paper/2025/hash/94e845868a9ace4bc239d0c529d32f4c-Abstract-Conference.html","pages":null},{"key":"conf/nips/LiDYLZLJZH25","title":"Taccel: Scaling Up Vision-based Tactile Robotics via High-performance GPU Simulation.","type":"Inproceedings","venue":"NeurIPS","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":null,"sourceUrl":"https://dblp.org/rec/conf/nips/LiDYLZLJZH25","documentUrl":"http://papers.nips.cc/paper_files/paper/2025/hash/87d91d52272c3166315ca20b18519b9e-Abstract-Conference.html","pages":null},{"key":"conf/siggraph/LanSL0J025","title":"3DGS2: Near Second-order Converging 3D Gaussian Splatting.","type":"Inproceedings","venue":"SIGGRAPH (Conference Paper Track)","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1145/3721238.3730687","sourceUrl":"https://dblp.org/rec/conf/siggraph/LanSL0J025","documentUrl":"https://doi.org/10.1145/3721238.3730687","pages":"99:1-99:10"},{"key":"conf/siggraph/ShenS0JAZ025","title":"Elastic Locomotion with Mixed Second-order Differentiation.","type":"Inproceedings","venue":"SIGGRAPH (Conference Paper Track)","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1145/3721238.3730685","sourceUrl":"https://dblp.org/rec/conf/siggraph/ShenS0JAZ025","documentUrl":"https://doi.org/10.1145/3721238.3730685","pages":"148:1-148:11"},{"key":"journals/pacmcgit/LiuWJZ25","title":"An Incompressible Crack Model for Volume Preserving MPM Fracture.","type":"Article","venue":"Proc. ACM Comput. Graph. Interact. Tech.","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.1145/3728298","sourceUrl":"https://dblp.org/rec/journals/pacmcgit/LiuWJZ25","documentUrl":"https://doi.org/10.1145/3728298","pages":"6:1-6:18"},{"key":"journals/tog/LanLYXSWJY25","title":"JGS2: Near Second-order Converging Jacobi/Gauss-Seidel for GPU Elastodynamics.","type":"Article","venue":"ACM Trans. Graph.","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.1145/3731183","sourceUrl":"https://dblp.org/rec/journals/tog/LanLYXSWJY25","documentUrl":"https://doi.org/10.1145/3731183","pages":"44:1-44:15"},{"key":"journals/tog/LiYDJXCYJ25","title":"Dress-1-to-3: Single Image to Simulation-Ready 3D Outfit with Diffusion Prior and Differentiable Physics.","type":"Article","venue":"ACM Trans. Graph.","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.1145/3731177","sourceUrl":"https://dblp.org/rec/journals/tog/LiYDJXCYJ25","documentUrl":"https://doi.org/10.1145/3731177","pages":"71:1-71:16"},{"key":"journals/tog/LuLLWIJWY25","title":"High-performance CPU Cloth Simulation Using Domain-decomposed Projective Dynamics.","type":"Article","venue":"ACM Trans. Graph.","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.1145/3731182","sourceUrl":"https://dblp.org/rec/journals/tog/LuLLWIJWY25","documentUrl":"https://doi.org/10.1145/3731182","pages":"51:1-51:17"}],"preprints":[{"key":"journals/corr/abs-2501-13975","title":"3DGS2: Near Second-order Converging 3D Gaussian Splatting.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2501.13975","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2501-13975","documentUrl":"https://doi.org/10.48550/ARXIV.2501.13975","pages":null,"arxivId":"2501.13975","arxivUrl":"https://arxiv.org/abs/2501.13975"},{"key":"journals/corr/abs-2501-16550","title":"PhysAnimator: Physics-Guided Generative Cartoon Animation.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2501.16550","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2501-16550","documentUrl":"https://doi.org/10.48550/ARXIV.2501.16550","pages":null,"arxivId":"2501.16550","arxivUrl":"https://arxiv.org/abs/2501.16550"},{"key":"journals/corr/abs-2502-03449","title":"Dress-1-to-3: Single Image to Simulation-Ready 3D Outfit with Diffusion Prior and Differentiable Physics.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2502.03449","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2502-03449","documentUrl":"https://doi.org/10.48550/ARXIV.2502.03449","pages":null,"arxivId":"2502.03449","arxivUrl":"https://arxiv.org/abs/2502.03449"},{"key":"journals/corr/abs-2502-03639","title":"Towards Physical Understanding in Video Generation: A 3D Point Regularization Approach.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2502.03639","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2502-03639","documentUrl":"https://doi.org/10.48550/ARXIV.2502.03639","pages":null,"arxivId":"2502.03639","arxivUrl":"https://arxiv.org/abs/2502.03639"},{"key":"journals/corr/abs-2503-00364","title":"CFSum: A Transformer-Based Multi-Modal Video Summarization Framework With Coarse-Fine Fusion.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2503.00364","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-00364","documentUrl":"https://doi.org/10.48550/ARXIV.2503.00364","pages":null,"arxivId":"2503.00364","arxivUrl":"https://arxiv.org/abs/2503.00364"},{"key":"journals/corr/abs-2503-05020","title":"GRIP: A General Robotic Incremental Potential Contact Simulation Dataset for Unified Deformable-Rigid Coupled Grasping.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2503.05020","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-05020","documentUrl":"https://doi.org/10.48550/ARXIV.2503.05020","pages":null,"arxivId":"2503.05020","arxivUrl":"https://arxiv.org/abs/2503.05020"},{"key":"journals/corr/abs-2503-05046","title":"A Convex Formulation of Material Points and Rigid Bodies with GPU-Accelerated Async-Coupling for Interactive Simulation.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2503.05046","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-05046","documentUrl":"https://doi.org/10.48550/ARXIV.2503.05046","pages":null,"arxivId":"2503.05046","arxivUrl":"https://arxiv.org/abs/2503.05046"},{"key":"journals/corr/abs-2504-01204","title":"Articulated Kinematics Distillation from Video Diffusion Models.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2504.01204","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2504-01204","documentUrl":"https://doi.org/10.48550/ARXIV.2504.01204","pages":null,"arxivId":"2504.01204","arxivUrl":"https://arxiv.org/abs/2504.01204"},{"key":"journals/corr/abs-2504-12908","title":"Taccel: Scaling Up Vision-based Tactile Robotics via High-performance GPU Simulation.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2504.12908","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2504-12908","documentUrl":"https://doi.org/10.48550/ARXIV.2504.12908","pages":null,"arxivId":"2504.12908","arxivUrl":"https://arxiv.org/abs/2504.12908"},{"key":"journals/corr/abs-2505-12539","title":"Penetration-free Solid-Fluid Interaction on Shells and Rods.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2505.12539","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-12539","documentUrl":"https://doi.org/10.48550/ARXIV.2505.12539","pages":null,"arxivId":"2505.12539","arxivUrl":"https://arxiv.org/abs/2505.12539"},{"key":"journals/corr/abs-2506-06494","title":"JGS2: Near Second-order Converging Jacobi/Gauss-Seidel for GPU Elastodynamics.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2506.06494","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-06494","documentUrl":"https://doi.org/10.48550/ARXIV.2506.06494","pages":null,"arxivId":"2506.06494","arxivUrl":"https://arxiv.org/abs/2506.06494"},{"key":"journals/corr/abs-2507-09435","title":"GeoWarp: An automatically differentiable and GPU-accelerated implicit MPM framework for geomechanics based on NVIDIA Warp.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2507.09435","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2507-09435","documentUrl":"https://doi.org/10.48550/ARXIV.2507.09435","pages":null,"arxivId":"2507.09435","arxivUrl":"https://arxiv.org/abs/2507.09435"},{"key":"journals/corr/abs-2508-11722","title":"Substepping the Material Point Method.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2508.11722","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-11722","documentUrl":"https://doi.org/10.48550/ARXIV.2508.11722","pages":null,"arxivId":"2508.11722","arxivUrl":"https://arxiv.org/abs/2508.11722"},{"key":"journals/corr/abs-2509-15953","title":"Right-Side-Out: Learning Zero-Shot Sim-to-Real Garment Reversal.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2509.15953","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-15953","documentUrl":"https://doi.org/10.48550/ARXIV.2509.15953","pages":null,"arxivId":"2509.15953","arxivUrl":"https://arxiv.org/abs/2509.15953"},{"key":"journals/corr/abs-2511-13191","title":"Birth of a Painting: Differentiable Brushstroke Reconstruction.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2511.13191","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2511-13191","documentUrl":"https://doi.org/10.48550/ARXIV.2511.13191","pages":null,"arxivId":"2511.13191","arxivUrl":"https://arxiv.org/abs/2511.13191"},{"key":"journals/corr/abs-2512-01629","title":"SPARK: Sim-ready Part-level Articulated Reconstruction with VLM Knowledge.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2512.01629","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-01629","documentUrl":"https://doi.org/10.48550/ARXIV.2512.01629","pages":null,"arxivId":"2512.01629","arxivUrl":"https://arxiv.org/abs/2512.01629"},{"key":"journals/corr/abs-2512-12984","title":"VoroLight: Learning Quality Volumetric Voronoi Meshes from General Inputs.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2512.12984","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-12984","documentUrl":"https://doi.org/10.48550/ARXIV.2512.12984","pages":null,"arxivId":"2512.12984","arxivUrl":"https://arxiv.org/abs/2512.12984"},{"key":"journals/corr/abs-2512-14133","title":"AnimaMimic: Imitating 3D Animation from Video Priors.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2512.14133","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-14133","documentUrl":"https://doi.org/10.48550/ARXIV.2512.14133","pages":null,"arxivId":"2512.14133","arxivUrl":"https://arxiv.org/abs/2512.14133"}],"excludedFormal":[],"labName":"Artificial Intelligence & Visual Computing Laboratory (AIVC)","labUrl":"https://www.math.ucla.edu/aivc","labEvidence":"个人主页明确写其为 UCLA 的 AIVC Lab director，并直接链接实验室。","labSourceUrl":"https://math.ucla.edu/~cffjiang/","affiliationZh":"University of California, Los Angeles","sourceWarning":false,"excludedOther":[],"excludedHomonyms":[],"unassignedCandidates":[],"knownPreprintMinimum2025":null,"excludedMisattributed":[],"displayNotes":"身份已经机构或个人主页核对。2025 年正式记录 20 条（会议 16、期刊 4），所有作者位置均计入，不表示主导或贡献份额；预印本 18 条单列，不加总。","labDisplayNotes":"个人主页写明其为 UCLA AIVC Lab 主任，并直接链接实验室，据此归组。这反映检索时的公开关联，不代表 2025 全年的归属。"},{"index":10,"name":"Yueming Jin","nameZh":"Yueming Jin","role":"Assistant Professor","affiliation":"National University of Singapore","source":"DBLP official SPARQL","profileUrl":"https://dblp.org/pid/183/6320","identifier":"183/6320","identityEvidence":[{"url":"https://dblp.org/pid/183/6320","evidence":"DBLP 唯一同名作者档案；通过作者/机构主页与发表题名交叉核对。"},{"url":"https://yuemingjin.github.io/","evidence":"作者/机构页面与该 DBLP 档案交叉匹配的题名示例：Unleashing the Power of Image-Tabular Self-Supervised Learning via Breaking Cross-Tabular Barriers.；MedSegDiff-V2: Diffusion-Based Medical Image Segmentation with Transformer.","matchedPaperKeys":["conf/aaai/FuZZCJ26","conf/aaai/Wu0FXJ024"]}],"count2025":16,"conference2025":9,"journal2025":7,"preprint2025":22,"status":"verified","notes":"身份已通过机构/个人主页或 DBLP 机构信息核对；篇数为数据库记录统计，不表示每篇均由本人主导。","retrievedAt":"2026-10-19","yearPolicy":"DBLP yearOfPublication = 2025","queryUrl":"https://sparql.dblp.org/sparql?query=PREFIX%20dblp%3A%20%3Chttps%3A//dblp.org/rdf/schema%23%3E%20PREFIX%20xsd%3A%20%3Chttp%3A//www.w3.org/2001/XMLSchema%23%3E%20SELECT%20%3Fpub%20%3Ftitle%20%3Ftype%20%3Fvenue%20WHERE%20%7B%20%3Fpub%20dblp%3AauthoredBy%20%3Chttps%3A//dblp.org/pid/183/6320%3E%3B%20dblp%3AyearOfPublication%20%222025%22%5E%5Exsd%3AgYear%3B%20dblp%3Atitle%20%3Ftitle%3B%20a%20%3Ftype%20.%20OPTIONAL%20%7B%20%3Fpub%20dblp%3ApublishedIn%20%3Fvenue%20%7D%20%7D&format=json","papers":[{"key":"conf/aaai/ZhuXJNAPLW25","title":"AAAI Bridge Program 2025: AI for Medicine and Healthcare.","type":"Inproceedings","venue":"AAAI Bridge Program","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":null,"sourceUrl":"https://dblp.org/rec/conf/aaai/ZhuXJNAPLW25","documentUrl":"https://proceedings.mlr.press/v281/zhu25a.html","pages":"1-4"},{"key":"conf/acl/WuZLXJ25","title":"Agentic Reasoning: A Streamlined Framework for Enhancing LLM Reasoning with Agentic Tools.","type":"Inproceedings","venue":"ACL (1)","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.18653/V1/2025.ACL-LONG.1383","sourceUrl":"https://dblp.org/rec/conf/acl/WuZLXJ25","documentUrl":"https://doi.org/10.18653/V1/2025.ACL-LONG.1383","pages":"28489-28503"},{"key":"conf/acl/WuZQCXMJG25","title":"Medical Graph RAG: Evidence-based Medical Large Language Model via Graph Retrieval-Augmented Generation.","type":"Inproceedings","venue":"ACL (1)","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.18653/V1/2025.ACL-LONG.1381","sourceUrl":"https://dblp.org/rec/conf/acl/WuZQCXMJG25","documentUrl":"https://doi.org/10.18653/V1/2025.ACL-LONG.1381","pages":"28443-28467"},{"key":"conf/eccv/QiZWYJL24","title":"Energy-Induced Explicit Quantification for Multi-modality MRI Fusion.","type":"Inproceedings","venue":"ECCV (7)","year":2025,"yearOfPublication":2025,"yearOfEvent":2024,"doi":"https://doi.org/10.1007/978-3-031-72667-5_25","sourceUrl":"https://dblp.org/rec/conf/eccv/QiZWYJL24","documentUrl":"https://doi.org/10.1007/978-3-031-72667-5_25","pages":"439-455"},{"key":"conf/iccv/QinWSLZWHJ25","title":"Structure Matters: Revisiting Boundary Refinement in Video Object Segmentation.","type":"Inproceedings","venue":"ICCV","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/ICCV51701.2025.01339","sourceUrl":"https://dblp.org/rec/conf/iccv/QinWSLZWHJ25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.01339","pages":"14431-14442"},{"key":"conf/iccv/YangWJWLJLZH25","title":"Generalized Deep Multi-View Clustering Via Causal Learning With Partially Aligned Cross-View Correspondence.","type":"Inproceedings","venue":"ICCV","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/ICCV51701.2025.00193","sourceUrl":"https://dblp.org/rec/conf/iccv/YangWJWLJLZH25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.00193","pages":"1990-1999"},{"key":"conf/icml/Yang0WJL0Z0J25","title":"Automatically Identify and Rectify: Robust Deep Contrastive Multi-view Clustering in Noisy Scenarios.","type":"Inproceedings","venue":"ICML","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":null,"sourceUrl":"https://dblp.org/rec/conf/icml/Yang0WJL0Z0J25","documentUrl":"https://proceedings.mlr.press/v267/yang25am.html","pages":null},{"key":"conf/mm/NiuXW0JL25","title":"EIR-SDG: Explore Invariant Representation for Single-source Domain Generalization in Medical Image Segmentation.","type":"Inproceedings","venue":"ACM Multimedia","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1145/3746027.3755199","sourceUrl":"https://dblp.org/rec/conf/mm/NiuXW0JL25","documentUrl":"https://doi.org/10.1145/3746027.3755199","pages":"7931-7939"},{"key":"conf/nips/ZengYMWJJ25","title":"Multi-scale Temporal Prediction via Incremental Generation and Multi-agent Collaboration.","type":"Inproceedings","venue":"NeurIPS","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":null,"sourceUrl":"https://dblp.org/rec/conf/nips/ZengYMWJJ25","documentUrl":"http://papers.nips.cc/paper_files/paper/2025/hash/208b3bfaf8b6685e8d88fd7aaaaa1a9d-Abstract-Conference.html","pages":null},{"key":"journals/mia/AliEJLGZZDCXWYZSLPFMBB25","title":"An objective comparison of methods for augmented reality in laparoscopic liver resection by preoperative-to-intraoperative image fusion from the MICCAI2022 challenge.","type":"Article","venue":"Medical Image Anal.","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.1016/J.MEDIA.2024.103371","sourceUrl":"https://dblp.org/rec/journals/mia/AliEJLGZZDCXWYZSLPFMBB25","documentUrl":"https://doi.org/10.1016/J.MEDIA.2024.103371","pages":"103371"},{"key":"journals/pami/WuZXJ25","title":"Pro-NeXt: An All-in-One Unified Model for General Fine-Grained Visual Recognition.","type":"Article","venue":"IEEE Trans. Pattern Anal. Mach. Intell.","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.1109/TPAMI.2025.3584902","sourceUrl":"https://dblp.org/rec/journals/pami/WuZXJ25","documentUrl":"https://doi.org/10.1109/TPAMI.2025.3584902","pages":"9187-9200"},{"key":"journals/tbe/XuWYSJM25","title":"Personalizing Federated Instrument Segmentation With Visual Trait Priors in Robotic Surgery.","type":"Article","venue":"IEEE Trans. Biomed. Eng.","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.1109/TBME.2025.3526667","sourceUrl":"https://dblp.org/rec/journals/tbe/XuWYSJM25","documentUrl":"https://doi.org/10.1109/TBME.2025.3526667","pages":"1886-1896"},{"key":"journals/tmi/DuCZLIGJCH25","title":"LMT++: Adaptively Collaborating LLMs With Multi-Specialized Teachers for Continual VQA in Robotic Surgical Videos.","type":"Article","venue":"IEEE Trans. Medical Imaging","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.1109/TMI.2025.3581108","sourceUrl":"https://dblp.org/rec/journals/tmi/DuCZLIGJCH25","documentUrl":"https://doi.org/10.1109/TMI.2025.3581108","pages":"4678-4689"},{"key":"journals/tmi/PeiGZLJH25","title":"S²Former-OR: Single-Stage Bi-Modal Transformer for Scene Graph Generation in OR.","type":"Article","venue":"IEEE Trans. Medical Imaging","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.1109/TMI.2024.3444279","sourceUrl":"https://dblp.org/rec/journals/tmi/PeiGZLJH25","documentUrl":"https://doi.org/10.1109/TMI.2024.3444279","pages":"361-372"},{"key":"journals/tmi/PeiZQWJH25","title":"Instrument-Tissue-Guided Surgical Action Triplet Detection via Textual-Temporal Trail Exploration.","type":"Article","venue":"IEEE Trans. Medical Imaging","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.1109/TMI.2025.3590457","sourceUrl":"https://dblp.org/rec/journals/tmi/PeiZQWJH25","documentUrl":"https://doi.org/10.1109/TMI.2025.3590457","pages":"5278-5289"},{"key":"journals/tmi/ZhangPXJH25","title":"DC²T: Disentanglement-Guided Consolidation and Consistency Training for Semi-Supervised Cross-Site Continual Segmentation.","type":"Article","venue":"IEEE Trans. Medical Imaging","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.1109/TMI.2024.3469528","sourceUrl":"https://dblp.org/rec/journals/tmi/ZhangPXJH25","documentUrl":"https://doi.org/10.1109/TMI.2024.3469528","pages":"903-914"}],"preprints":[{"key":"journals/corr/abs-2503-04082","title":"Instrument-Splatting: Controllable Photorealistic Reconstruction of Surgical Instruments Using Gaussian Splatting.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2503.04082","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-04082","documentUrl":"https://doi.org/10.48550/ARXIV.2503.04082","pages":null,"arxivId":"2503.04082","arxivUrl":"https://arxiv.org/abs/2503.04082"},{"key":"journals/corr/abs-2503-10265","title":"SurgRAW: Multi-Agent Workflow with Chain-of-Thought Reasoning for Surgical Intelligence.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2503.10265","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-10265","documentUrl":"https://doi.org/10.48550/ARXIV.2503.10265","pages":null,"arxivId":"2503.10265","arxivUrl":"https://arxiv.org/abs/2503.10265"},{"key":"journals/corr/abs-2503-18064","title":"Dynamic Allocation Hypernetwork with Adaptive Model Recalibration for FCL.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2503.18064","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-18064","documentUrl":"https://doi.org/10.48550/ARXIV.2503.18064","pages":null,"arxivId":"2503.18064","arxivUrl":"https://arxiv.org/abs/2503.18064"},{"key":"journals/corr/abs-2503-18968","title":"MedAgent-Pro: Towards Multi-modal Evidence-based Medical Diagnosis via Reasoning Agentic Workflow.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2503.18968","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-18968","documentUrl":"https://doi.org/10.48550/ARXIV.2503.18968","pages":null,"arxivId":"2503.18968","arxivUrl":"https://arxiv.org/abs/2503.18968"},{"key":"journals/corr/abs-2503-20808","title":"Dynamic Allocation Hypernetwork with Adaptive Model Recalibration for Federated Continual Learning.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2503.20808","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-20808","documentUrl":"https://doi.org/10.48550/ARXIV.2503.20808","pages":null,"arxivId":"2503.20808","arxivUrl":"https://arxiv.org/abs/2503.20808"},{"key":"journals/corr/abs-2504-09700","title":"ToolTipNet: A Segmentation-Driven Deep Learning Baseline for Surgical Instrument Tip Detection.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2504.09700","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2504-09700","documentUrl":"https://doi.org/10.48550/ARXIV.2504.09700","pages":null,"arxivId":"2504.09700","arxivUrl":"https://arxiv.org/abs/2504.09700"},{"key":"journals/corr/abs-2505-08581","title":"ReSurgSAM2: Referring Segment Anything in Surgical Video via Credible Long-term Tracking.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2505.08581","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-08581","documentUrl":"https://doi.org/10.48550/ARXIV.2505.08581","pages":null,"arxivId":"2505.08581","arxivUrl":"https://arxiv.org/abs/2505.08581"},{"key":"journals/corr/abs-2505-21387","title":"Automatically Identify and Rectify: Robust Deep Contrastive Multi-view Clustering in Noisy Scenarios.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2505.21387","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-21387","documentUrl":"https://doi.org/10.48550/ARXIV.2505.21387","pages":null,"arxivId":"2505.21387","arxivUrl":"https://arxiv.org/abs/2505.21387"},{"key":"journals/corr/abs-2506-02555","title":"SurgVLM: A Large Vision-Language Model and Systematic Evaluation Benchmark for Surgical Intelligence.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2506.02555","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-02555","documentUrl":"https://doi.org/10.48550/ARXIV.2506.02555","pages":null,"arxivId":"2506.02555","arxivUrl":"https://arxiv.org/abs/2506.02555"},{"key":"journals/corr/abs-2506-02692","title":"Large-scale Self-supervised Video Foundation Model for Intelligent Surgery.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2506.02692","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-02692","documentUrl":"https://doi.org/10.48550/ARXIV.2506.02692","pages":null,"arxivId":"2506.02692","arxivUrl":"https://arxiv.org/abs/2506.02692"},{"key":"journals/corr/abs-2506-15279","title":"BCRNet: Enhancing Landmark Detection in Laparoscopic Liver Surgery via Bezier Curve Refinement.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2506.15279","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-15279","documentUrl":"https://doi.org/10.48550/ARXIV.2506.15279","pages":null,"arxivId":"2506.15279","arxivUrl":"https://arxiv.org/abs/2506.15279"},{"key":"journals/corr/abs-2506-23759","title":"Spatio-Temporal Representation Decoupling and Enhancement for Federated Instrument Segmentation in Surgical Videos.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2506.23759","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-23759","documentUrl":"https://doi.org/10.48550/ARXIV.2506.23759","pages":null,"arxivId":"2506.23759","arxivUrl":"https://arxiv.org/abs/2506.23759"},{"key":"journals/corr/abs-2507-18944","title":"Structure Matters: Revisiting Boundary Refinement in Video Object Segmentation.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2507.18944","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2507-18944","documentUrl":"https://doi.org/10.48550/ARXIV.2507.18944","pages":null,"arxivId":"2507.18944","arxivUrl":"https://arxiv.org/abs/2507.18944"},{"key":"journals/corr/abs-2508-08764","title":"CARES: Collaborative Agentic Reasoning for Error Detection in Surgery.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2508.08764","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-08764","documentUrl":"https://doi.org/10.48550/ARXIV.2508.08764","pages":null,"arxivId":"2508.08764","arxivUrl":"https://arxiv.org/abs/2508.08764"},{"key":"journals/corr/abs-2509-16022","title":"Generalized Deep Multi-view Clustering via Causal Learning with Partially Aligned Cross-view Correspondence.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2509.16022","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-16022","documentUrl":"https://doi.org/10.48550/ARXIV.2509.16022","pages":null,"arxivId":"2509.16022","arxivUrl":"https://arxiv.org/abs/2509.16022"},{"key":"journals/corr/abs-2509-17429","title":"Multi-scale Temporal Prediction via Incremental Generation and Multi-agent Collaboration.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2509.17429","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-17429","documentUrl":"https://doi.org/10.48550/ARXIV.2509.17429","pages":null,"arxivId":"2509.17429","arxivUrl":"https://arxiv.org/abs/2509.17429"},{"key":"journals/corr/abs-2509-21761","title":"Backdoor Attribution: Elucidating and Controlling Backdoor in Language Models.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2509.21761","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-21761","documentUrl":"https://doi.org/10.48550/ARXIV.2509.21761","pages":null,"arxivId":"2509.21761","arxivUrl":"https://arxiv.org/abs/2509.21761"},{"key":"journals/corr/abs-2510-18313","title":"OmniNWM: Omniscient Driving Navigation World Models.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2510.18313","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-18313","documentUrl":"https://doi.org/10.48550/ARXIV.2510.18313","pages":null,"arxivId":"2510.18313","arxivUrl":"https://arxiv.org/abs/2510.18313"},{"key":"journals/corr/abs-2510-22973","title":"Scaling Up Occupancy-centric Driving Scene Generation: Dataset and Method.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2510.22973","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-22973","documentUrl":"https://doi.org/10.48550/ARXIV.2510.22973","pages":null,"arxivId":"2510.22973","arxivUrl":"https://arxiv.org/abs/2510.22973"},{"key":"journals/corr/abs-2511-16618","title":"SAM2S: Segment Anything in Surgical Videos via Semantic Long-term Tracking.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2511.16618","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2511-16618","documentUrl":"https://doi.org/10.48550/ARXIV.2511.16618","pages":null,"arxivId":"2511.16618","arxivUrl":"https://arxiv.org/abs/2511.16618"},{"key":"journals/corr/abs-2512-14026","title":"Unleashing the Power of Image-Tabular Self-Supervised Learning via Breaking Cross-Tabular Barriers.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2512.14026","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-14026","documentUrl":"https://doi.org/10.48550/ARXIV.2512.14026","pages":null,"arxivId":"2512.14026","arxivUrl":"https://arxiv.org/abs/2512.14026"},{"key":"journals/corr/abs-2512-23162","title":"SurgWorld: Learning Surgical Robot Policies from Videos via World Modeling.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2512.23162","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-23162","documentUrl":"https://doi.org/10.48550/ARXIV.2512.23162","pages":null,"arxivId":"2512.23162","arxivUrl":"https://arxiv.org/abs/2512.23162"}],"excludedFormal":[],"labName":"Intelligent Medical Vision & Robotics Laboratory","labUrl":"https://yuemingjin.github.io/","labEvidence":"NUS Biomedical Engineering 官方实验室表于 2026-09-04 更新，逐行列 Dr Jin Yueming 为该实验室 Principal Investigator，并把实验室名称链接到其个人主页。","labSourceUrl":"https://cde.nus.edu.sg/bme/research/lab/","affiliationZh":"National University of Singapore","sourceWarning":false,"excludedOther":[],"excludedHomonyms":[],"unassignedCandidates":[],"knownPreprintMinimum2025":null,"excludedMisattributed":[],"displayNotes":"身份已经机构或个人主页核对。2025 年正式记录 16 条（会议 9、期刊 7），所有作者位置均计入，不表示主导或贡献份额；预印本 22 条单列，不加总。","labDisplayNotes":"NUS 生物医学工程系官方实验室表（2026-09-04 更新）列其为 Intelligent Medical Vision & Robotics Laboratory 的 PI，并链接本人主页，据此归组。"},{"index":11,"name":"Changjian Li","nameZh":"Changjian Li","role":"Assistant Professor","affiliation":"University of Edinburgh","source":"DBLP official SPARQL","profileUrl":"https://dblp.org/pid/121/6228-1","identifier":"121/6228-1","identityEvidence":[{"url":"https://dblp.org/pid/121/6228-1","evidence":"DBLP 档案名 Changjian Li 0001；机构/履历：University College London, UK；University of Edinburgh, UK；University of Hong Kong, SA, China"}],"count2025":11,"conference2025":8,"journal2025":3,"preprint2025":6,"status":"verified","notes":"身份已通过机构/个人主页或 DBLP 机构信息核对；篇数为数据库记录统计，不表示每篇均由本人主导。","retrievedAt":"2026-10-19","yearPolicy":"DBLP yearOfPublication = 2025","queryUrl":"https://sparql.dblp.org/sparql?query=PREFIX%20dblp%3A%20%3Chttps%3A//dblp.org/rdf/schema%23%3E%20PREFIX%20xsd%3A%20%3Chttp%3A//www.w3.org/2001/XMLSchema%23%3E%20SELECT%20%3Fpub%20%3Ftitle%20%3Ftype%20%3Fvenue%20WHERE%20%7B%20%3Fpub%20dblp%3AauthoredBy%20%3Chttps%3A//dblp.org/pid/121/6228-1%3E%3B%20dblp%3AyearOfPublication%20%222025%22%5E%5Exsd%3AgYear%3B%20dblp%3Atitle%20%3Ftitle%3B%20a%20%3Ftype%20.%20OPTIONAL%20%7B%20%3Fpub%20dblp%3ApublishedIn%20%3Fvenue%20%7D%20%7D&format=json","papers":[{"key":"conf/cvpr/BhuniaLB25","title":"Odd-One-Out: Anomaly Detection by Comparing with Neighbors.","type":"Inproceedings","venue":"CVPR","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/CVPR52734.2025.01899","sourceUrl":"https://dblp.org/rec/conf/cvpr/BhuniaLB25","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Bhunia_Odd-One-Out_Anomaly_Detection_by_Comparing_with_Neighbors_CVPR_2025_paper.html","pages":"20395-20404"},{"key":"conf/cvpr/DanierALBA25","title":"DepthCues: Evaluating Monocular Depth Perception in Large Vision Models.","type":"Inproceedings","venue":"CVPR","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/CVPR52734.2025.01867","sourceUrl":"https://dblp.org/rec/conf/cvpr/DanierALBA25","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Danier_DepthCues_Evaluating_Monocular_Depth_Perception_in_Large_Vision_Models_CVPR_2025_paper.html","pages":"20049-20059"},{"key":"conf/cvpr/JiZWL25","title":"PoseTraj: Pose-Aware Trajectory Control in Video Diffusion.","type":"Inproceedings","venue":"CVPR","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/CVPR52734.2025.02121","sourceUrl":"https://dblp.org/rec/conf/cvpr/JiZWL25","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Ji_PoseTraj_Pose-Aware_Trajectory_Control_in_Video_Diffusion_CVPR_2025_paper.html","pages":"22776-22785"},{"key":"conf/cvpr/WalkerERVOLA25","title":"CrossSDF: 3D Reconstruction of Thin Structures From Cross-Sections.","type":"Inproceedings","venue":"CVPR","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/CVPR52734.2025.02880","sourceUrl":"https://dblp.org/rec/conf/cvpr/WalkerERVOLA25","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Walker_CrossSDF_3D_Reconstruction_of_Thin_Structures_From_Cross-Sections_CVPR_2025_paper.html","pages":"30928-30937"},{"key":"conf/cvpr/WeiF00Z025","title":"PCDreamer: Point Cloud Completion Through Multi-view Diffusion Priors.","type":"Inproceedings","venue":"CVPR","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/CVPR52734.2025.02537","sourceUrl":"https://dblp.org/rec/conf/cvpr/WeiF00Z025","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Wei_PCDreamer_Point_Cloud_Completion_Through_Multi-view_Diffusion_Priors_CVPR_2025_paper.html","pages":"27243-27253"},{"key":"conf/iccv/WangCL25","title":"VQ-SGen: A Vector Quantized Stroke Representation for Creative Sketch Generation.","type":"Inproceedings","venue":"ICCV","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/ICCV51701.2025.01795","sourceUrl":"https://dblp.org/rec/conf/iccv/WangCL25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.01795","pages":"19311-19320"},{"key":"conf/iccv/WangLV25","title":"CanFields: Consolidating Diffeomorphic Flows for Non-Rigid 4D Interpolation From Arbitrary-Length Sequences.","type":"Inproceedings","venue":"ICCV","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/ICCV51701.2025.02655","sourceUrl":"https://dblp.org/rec/conf/iccv/WangLV25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.02655","pages":"28587-28598"},{"key":"conf/nips/BhuniaLB25","title":"Interactive Anomaly Detection for Articulated Objects via Motion Anticipation.","type":"Inproceedings","venue":"NeurIPS","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":null,"sourceUrl":"https://dblp.org/rec/conf/nips/BhuniaLB25","documentUrl":"http://papers.nips.cc/paper_files/paper/2025/hash/aa776a81c3ade66c689aaa9fd31d9670-Abstract-Conference.html","pages":null},{"key":"journals/mia/DouWLWYZSC25","title":"CLIK-Diffusion: Clinical Knowledge-informed Diffusion Model for Tooth Alignment.","type":"Article","venue":"Medical Image Anal.","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.1016/J.MEDIA.2025.103746","sourceUrl":"https://dblp.org/rec/journals/mia/DouWLWYZSC25","documentUrl":"https://doi.org/10.1016/J.MEDIA.2025.103746","pages":"103746"},{"key":"journals/tmi/LiuFLWLSC25","title":"Geometry-Aware Attenuation Learning for Sparse-View CBCT Reconstruction.","type":"Article","venue":"IEEE Trans. Medical Imaging","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.1109/TMI.2024.3473970","sourceUrl":"https://dblp.org/rec/journals/tmi/LiuFLWLSC25","documentUrl":"https://doi.org/10.1109/TMI.2024.3473970","pages":"1083-1097"},{"key":"journals/tog/ZhongGXWL25","title":"Sketch2Anim: Towards Transferring Sketch Storyboards into 3D Animation.","type":"Article","venue":"ACM Trans. Graph.","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.1145/3731167","sourceUrl":"https://dblp.org/rec/journals/tog/ZhongGXWL25","documentUrl":"https://doi.org/10.1145/3731167","pages":"74:1-74:15"}],"preprints":[{"key":"journals/corr/abs-2503-16068","title":"PoseTraj: Pose-Aware Trajectory Control in Video Diffusion.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2503.16068","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-16068","documentUrl":"https://doi.org/10.48550/ARXIV.2503.16068","pages":null,"arxivId":"2503.16068","arxivUrl":"https://arxiv.org/abs/2503.16068"},{"key":"journals/corr/abs-2504-19189","title":"Sketch2Anim: Towards Transferring Sketch Storyboards into 3D Animation.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2504.19189","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2504-19189","documentUrl":"https://doi.org/10.48550/ARXIV.2504.19189","pages":null,"arxivId":"2504.19189","arxivUrl":"https://arxiv.org/abs/2504.19189"},{"key":"journals/corr/abs-2506-16556","title":"VesselSDF: Distance Field Priors for Vascular Network Reconstruction.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2506.16556","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-16556","documentUrl":"https://doi.org/10.48550/ARXIV.2506.16556","pages":null,"arxivId":"2506.16556","arxivUrl":"https://arxiv.org/abs/2506.16556"},{"key":"journals/corr/abs-2508-10201","title":"B-repLer: Semantic B-rep Latent Editor using Large Language Models.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2508.10201","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-10201","documentUrl":"https://doi.org/10.48550/ARXIV.2508.10201","pages":null,"arxivId":"2508.10201","arxivUrl":"https://arxiv.org/abs/2508.10201"},{"key":"journals/corr/abs-2511-18991","title":"View-Consistent Diffusion Representations for 3D-Consistent Video Generation.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2511.18991","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2511-18991","documentUrl":"https://doi.org/10.48550/ARXIV.2511.18991","pages":null,"arxivId":"2511.18991","arxivUrl":"https://arxiv.org/abs/2511.18991"},{"key":"journals/corr/abs-2512-13392","title":"Beyond the Visible: Disocclusion-Aware Editing via Proxy Dynamic Graphs.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2512.13392","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-13392","documentUrl":"https://doi.org/10.48550/ARXIV.2512.13392","pages":null,"arxivId":"2512.13392","arxivUrl":"https://arxiv.org/abs/2512.13392"}],"excludedFormal":[],"labName":"GraphViX Group (Graphics, Vision and X)","labUrl":"https://enigma-li.github.io/","labEvidence":"本人主页简介明确表示在 Edinburgh 领导 GraphViX Group，并给出 Graphics, Vision and X 全称；该个人页包含当前成员。","labSourceUrl":"https://enigma-li.github.io/","affiliationZh":"University of Edinburgh","sourceWarning":false,"excludedOther":[],"excludedHomonyms":[],"unassignedCandidates":[],"knownPreprintMinimum2025":null,"excludedMisattributed":[],"displayNotes":"身份已经机构或个人主页核对。2025 年正式记录 11 条（会议 8、期刊 3），所有作者位置均计入，不表示主导或贡献份额；预印本 6 条单列，不加总。","labDisplayNotes":"个人主页写明其在爱丁堡大学领导 GraphViX Group（Graphics, Vision and X），据此归组。"},{"index":12,"name":"Fuxin Li","nameZh":"Fuxin Li","role":"Professor","affiliation":"Oregon State University","source":"DBLP official SPARQL","profileUrl":"https://dblp.org/pid/03/2783","identifier":"03/2783","identityEvidence":[{"url":"https://dblp.org/pid/03/2783","evidence":"DBLP 唯一同名作者档案；通过作者/机构主页与发表题名交叉核对。"},{"url":"https://web.engr.oregonstate.edu/~lif/","evidence":"作者/机构页面与该 DBLP 档案交叉匹配的题名示例：Data Augmentation Approaches for Satellite Imagery.；iGOS++: integrated gradient optimized saliency by bilateral perturbations.","matchedPaperKeys":["conf/aaai/HopkinsWKLH25","conf/chil/KhorramLL21"]}],"count2025":4,"conference2025":4,"journal2025":0,"preprint2025":4,"status":"verified","notes":"身份已通过机构/个人主页或 DBLP 机构信息核对；篇数为数据库记录统计，不表示每篇均由本人主导。","retrievedAt":"2026-10-19","yearPolicy":"DBLP yearOfPublication = 2025","queryUrl":"https://sparql.dblp.org/sparql?query=PREFIX%20dblp%3A%20%3Chttps%3A//dblp.org/rdf/schema%23%3E%20PREFIX%20xsd%3A%20%3Chttp%3A//www.w3.org/2001/XMLSchema%23%3E%20SELECT%20%3Fpub%20%3Ftitle%20%3Ftype%20%3Fvenue%20WHERE%20%7B%20%3Fpub%20dblp%3AauthoredBy%20%3Chttps%3A//dblp.org/pid/03/2783%3E%3B%20dblp%3AyearOfPublication%20%222025%22%5E%5Exsd%3AgYear%3B%20dblp%3Atitle%20%3Ftitle%3B%20a%20%3Ftype%20.%20OPTIONAL%20%7B%20%3Fpub%20dblp%3ApublishedIn%20%3Fvenue%20%7D%20%7D&format=json","papers":[{"key":"conf/aaai/HopkinsWKLH25","title":"Data Augmentation Approaches for Satellite Imagery.","type":"Inproceedings","venue":"AAAI","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1609/AAAI.V39I27.35028","sourceUrl":"https://dblp.org/rec/conf/aaai/HopkinsWKLH25","documentUrl":"https://doi.org/10.1609/AAAI.V39I27.35028","pages":"28097-28105"},{"key":"conf/iccv/ChenTZBLHLX25","title":"Long-LRM: Long-Sequence Large Reconstruction Model for Wide-Coverage Gaussian Splats.","type":"Inproceedings","venue":"ICCV","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/ICCV51701.2025.00414","sourceUrl":"https://dblp.org/rec/conf/iccv/ChenTZBLHLX25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.00414","pages":"4349-4359"},{"key":"conf/iclr/KhademiL25","title":"Point-based Instance Completion with Scene Constraints.","type":"Inproceedings","venue":"ICLR","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":null,"sourceUrl":"https://dblp.org/rec/conf/iclr/KhademiL25","documentUrl":"https://openreview.net/forum?id=llSiIJosDj","pages":null},{"key":"conf/nips/YangULLL25","title":"Convex Potential Mirror Langevin Algorithm for Efficient Sampling of Energy-Based Models.","type":"Inproceedings","venue":"NeurIPS","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":null,"sourceUrl":"https://dblp.org/rec/conf/nips/YangULLL25","documentUrl":"http://papers.nips.cc/paper_files/paper/2025/hash/7f64034009f4a5fa417a57e1a987c5cd-Abstract-Conference.html","pages":null}],"preprints":[{"key":"journals/corr/abs-2503-13891","title":"Where do Large Vision-Language Models Look at when Answering Questions?","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2503.13891","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-13891","documentUrl":"https://doi.org/10.48550/ARXIV.2503.13891","pages":null,"arxivId":"2503.13891","arxivUrl":"https://arxiv.org/abs/2503.13891"},{"key":"journals/corr/abs-2504-05698","title":"Point-based Instance Completion with Scene Constraints.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2504.05698","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2504-05698","documentUrl":"https://doi.org/10.48550/ARXIV.2504.05698","pages":null,"arxivId":"2504.05698","arxivUrl":"https://arxiv.org/abs/2504.05698"},{"key":"journals/corr/abs-2506-06517","title":"GS4: Generalizable Sparse Splatting Semantic SLAM.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2506.06517","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-06517","documentUrl":"https://doi.org/10.48550/ARXIV.2506.06517","pages":null,"arxivId":"2506.06517","arxivUrl":"https://arxiv.org/abs/2506.06517"},{"key":"journals/corr/abs-2512-10267","title":"Long-LRM++: Preserving Fine Details in Feed-Forward Wide-Coverage Reconstruction.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2512.10267","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-10267","documentUrl":"https://doi.org/10.48550/ARXIV.2512.10267","pages":null,"arxivId":"2512.10267","arxivUrl":"https://arxiv.org/abs/2512.10267"}],"excludedFormal":[],"labName":"Deep Machine Vision (DMV)","labUrl":"https://web.engr.oregonstate.edu/~lif/#research","labEvidence":"个人主页原文 My research group Deep Machine Vision (DMV)；另说明团队是 DRAIL Lab 的一部分。这里链接明确的本组介绍。","labSourceUrl":"https://web.engr.oregonstate.edu/~lif/","affiliationZh":"Oregon State University","sourceWarning":false,"excludedOther":[],"excludedHomonyms":[],"unassignedCandidates":[],"knownPreprintMinimum2025":null,"excludedMisattributed":[],"displayNotes":"身份已经机构或个人主页核对。2025 年正式记录 4 条，均为会议论文，所有作者位置均计入；预印本 4 条单列，不加总。","labDisplayNotes":"个人主页写明其研究组为 Deep Machine Vision（DMV），并说明该组属于 DRAIL Lab；这里按更明确的本组归组，不并入 DRAIL。"},{"index":13,"name":"Minchen Li","nameZh":"Minchen Li","role":"Assistant Professor","affiliation":"Carnegie Mellon University","source":"DBLP official SPARQL","profileUrl":"https://dblp.org/pid/175/5809","identifier":"175/5809","identityEvidence":[{"url":"https://dblp.org/pid/175/5809","evidence":"DBLP 唯一同名作者档案；通过作者/机构主页与发表题名交叉核对。"},{"url":"https://www.cs.cmu.edu/~minchenl/","evidence":"作者/机构页面与该 DBLP 档案交叉匹配的题名示例：Prototyping Decomposed Cloud Software: A Case Study on 3D Skeletal Game Engine.；PAT3D: Physics-Augmented Text-to-3D Scene Generation.","matchedPaperKeys":["conf/cloudcom/LiCWHL15","conf/iclr/LinHLGCCLKLZL26"]}],"count2025":3,"conference2025":0,"journal2025":3,"preprint2025":6,"status":"verified","notes":"身份已通过机构/个人主页或 DBLP 机构信息核对；篇数为数据库记录统计，不表示每篇均由本人主导。","retrievedAt":"2026-10-19","yearPolicy":"DBLP yearOfPublication = 2025","queryUrl":"https://sparql.dblp.org/sparql?query=PREFIX%20dblp%3A%20%3Chttps%3A//dblp.org/rdf/schema%23%3E%20PREFIX%20xsd%3A%20%3Chttp%3A//www.w3.org/2001/XMLSchema%23%3E%20SELECT%20%3Fpub%20%3Ftitle%20%3Ftype%20%3Fvenue%20WHERE%20%7B%20%3Fpub%20dblp%3AauthoredBy%20%3Chttps%3A//dblp.org/pid/175/5809%3E%3B%20dblp%3AyearOfPublication%20%222025%22%5E%5Exsd%3AgYear%3B%20dblp%3Atitle%20%3Ftitle%3B%20a%20%3Ftype%20.%20OPTIONAL%20%7B%20%3Fpub%20dblp%3ApublishedIn%20%3Fvenue%20%7D%20%7D&format=json","papers":[{"key":"journals/tog/HuangLLKL25","title":"StiffGIPC: Advancing GPU IPC for Stiff Affine-Deformable Simulation.","type":"Article","venue":"ACM Trans. Graph.","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.1145/3735126","sourceUrl":"https://dblp.org/rec/journals/tog/HuangLLKL25","documentUrl":"https://doi.org/10.1145/3735126","pages":"31:1-31:20"},{"key":"journals/tog/LiuWL25","title":"CK-MPM: A Compact-Kernel Material Point Method.","type":"Article","venue":"ACM Trans. Graph.","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.1145/3731155","sourceUrl":"https://dblp.org/rec/journals/tog/LiuWL25","documentUrl":"https://doi.org/10.1145/3731155","pages":"152:1-152:14"},{"key":"journals/tog/LuoCLCL25","title":"VR-Doh: Hands-on 3D Modeling in Virtual Reality.","type":"Article","venue":"ACM Trans. Graph.","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.1145/3731154","sourceUrl":"https://dblp.org/rec/journals/tog/LuoCLCL25","documentUrl":"https://doi.org/10.1145/3731154","pages":"66:1-66:12"}],"preprints":[{"key":"journals/corr/abs-2503-00868","title":"Vid2Fluid: 3D Dynamic Fluid Assets from Single-View Videos with Generative Gaussian Splatting.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2503.00868","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-00868","documentUrl":"https://doi.org/10.48550/ARXIV.2503.00868","pages":null,"arxivId":"2503.00868","arxivUrl":"https://arxiv.org/abs/2503.00868"},{"key":"journals/corr/abs-2505-12539","title":"Penetration-free Solid-Fluid Interaction on Shells and Rods.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2505.12539","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-12539","documentUrl":"https://doi.org/10.48550/ARXIV.2505.12539","pages":null,"arxivId":"2505.12539","arxivUrl":"https://arxiv.org/abs/2505.12539"},{"key":"journals/corr/abs-2506-18867","title":"A B-Spline Finite Element Method for Cloth Simulation.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2506.18867","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-18867","documentUrl":"https://doi.org/10.48550/ARXIV.2506.18867","pages":null,"arxivId":"2506.18867","arxivUrl":"https://arxiv.org/abs/2506.18867"},{"key":"journals/corr/abs-2510-23880","title":"TRELLISWorld: Training-Free World Generation from Object Generators.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2510.23880","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-23880","documentUrl":"https://doi.org/10.48550/ARXIV.2510.23880","pages":null,"arxivId":"2510.23880","arxivUrl":"https://arxiv.org/abs/2510.23880"},{"key":"journals/corr/abs-2511-21978","title":"PAT3D: Physics-Augmented Text-to-3D Scene Generation.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2511.21978","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2511-21978","documentUrl":"https://doi.org/10.48550/ARXIV.2511.21978","pages":null,"arxivId":"2511.21978","arxivUrl":"https://arxiv.org/abs/2511.21978"},{"key":"journals/corr/abs-2512-12151","title":"Robust and Efficient Penetration-Free Elastodynamics without Barriers.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2512.12151","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-12151","documentUrl":"https://doi.org/10.48550/ARXIV.2512.12151","pages":null,"arxivId":"2512.12151","arxivUrl":"https://arxiv.org/abs/2512.12151"}],"excludedFormal":[],"labName":"Simulation Intelligence Group (SIG)","labUrl":"https://www.cs.cmu.edu/~minchenl/#sec_group","labEvidence":"当前个人主页专节标题为 Simulation Intelligence Group (SIG)，成员列 Minchen Li (Principal Investigator)；不把过去 UCLA 的归属当成当前组。","labSourceUrl":"https://www.cs.cmu.edu/~minchenl/","affiliationZh":"Carnegie Mellon University","sourceWarning":false,"excludedOther":[],"excludedHomonyms":[],"unassignedCandidates":[],"knownPreprintMinimum2025":null,"excludedMisattributed":[],"displayNotes":"身份已经机构或个人主页核对。2025 年正式记录 3 条，均为期刊论文，所有作者位置均计入；预印本 6 条单列，不加总。","labDisplayNotes":"当前个人主页的组名为 Simulation Intelligence Group（SIG），并列其为 PI；不把此前在 UCLA 的经历当作当前团队。它与北大王鹏帅的 Spatial Intelligence Group 是不同团队。"},{"index":14,"name":"Minghan Li","nameZh":"Minghan Li","role":"Assistant Professor","affiliation":"Colorado School of Mines","source":"DBLP official SPARQL","profileUrl":"https://dblp.org/pid/214/2450-1","identifier":"214/2450-1","identityEvidence":[{"url":"https://dblp.org/pid/214/2450-1","evidence":"DBLP 档案名 Minghan Li 0001；机构/履历：Hong Kong Polytechnic University, Department of Computing, Hung Hom, Hong Kong；Xi'an JiaoTong University, Key Lab of Intelligent Networks and Network Security, Xi'an, China"},{"url":"https://sites.google.com/view/minghanli-homepage/academic","evidence":"作者主页说明任职 Colorado School of Mines，博士毕业于 Hong Kong Polytechnic University、硕士毕业于 Xi’an Jiaotong University，与 DBLP Minghan Li 0001 的履历和个人主页链接一致。"},{"url":"https://sites.google.com/view/minghanli-homepage/publications","evidence":"作者/机构页面与该 DBLP 档案交叉匹配的题名示例：MDQE: Mining Discriminative Query Embeddings to Segment Occluded Instances on Challenging Videos.；Spatial Feature Calibration and Temporal Fusion for Effective One-Stage Video Instance Segmentation.","matchedPaperKeys":["conf/cvpr/Li0X023","conf/cvpr/LiLL021"]}],"count2025":3,"conference2025":3,"journal2025":0,"preprint2025":3,"status":"verified","notes":"身份已通过机构/个人主页或 DBLP 机构信息核对；篇数为数据库记录统计，不表示每篇均由本人主导。","retrievedAt":"2026-10-19","yearPolicy":"DBLP yearOfPublication = 2025","queryUrl":"https://sparql.dblp.org/sparql?query=PREFIX%20dblp%3A%20%3Chttps%3A//dblp.org/rdf/schema%23%3E%20PREFIX%20xsd%3A%20%3Chttp%3A//www.w3.org/2001/XMLSchema%23%3E%20SELECT%20%3Fpub%20%3Ftitle%20%3Ftype%20%3Fvenue%20WHERE%20%7B%20%3Fpub%20dblp%3AauthoredBy%20%3Chttps%3A//dblp.org/pid/214/2450-1%3E%3B%20dblp%3AyearOfPublication%20%222025%22%5E%5Exsd%3AgYear%3B%20dblp%3Atitle%20%3Ftitle%3B%20a%20%3Ftype%20.%20OPTIONAL%20%7B%20%3Fpub%20dblp%3ApublishedIn%20%3Fvenue%20%7D%20%7D&format=json","papers":[{"key":"conf/iccv/LiXWZW25","title":"FiVE-Bench: A Fine-Grained Video Editing Benchmark for Evaluating Emerging Diffusion and Rectified Flow Models.","type":"Inproceedings","venue":"ICCV","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/ICCV51701.2025.01548","sourceUrl":"https://dblp.org/rec/conf/iccv/LiXWZW25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.01548","pages":"16672-16681"},{"key":"conf/iclr/Xiao0ZM025","title":"Spatial-Mamba: Effective Visual State Space Models via Structure-Aware State Fusion.","type":"Inproceedings","venue":"ICLR","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":null,"sourceUrl":"https://dblp.org/rec/conf/iclr/Xiao0ZM025","documentUrl":"https://openreview.net/forum?id=iDe1mtxqK5","pages":null},{"key":"conf/nips/XieLLWYZ25","title":"DNAEdit: Direct Noise Alignment for Text-Guided Rectified Flow Editing.","type":"Inproceedings","venue":"NeurIPS","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":null,"sourceUrl":"https://dblp.org/rec/conf/nips/XieLLWYZ25","documentUrl":"http://papers.nips.cc/paper_files/paper/2025/hash/b44ae90136013a8d0e2d24f6015b6097-Abstract-Conference.html","pages":null}],"preprints":[{"key":"journals/corr/abs-2506-01430","title":"DNAEdit: Direct Noise Alignment for Text-Guided Rectified Flow Editing.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2506.01430","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-01430","documentUrl":"https://doi.org/10.48550/ARXIV.2506.01430","pages":null,"arxivId":"2506.01430","arxivUrl":"https://arxiv.org/abs/2506.01430"},{"key":"journals/corr/abs-2507-13353","title":"VideoITG: Multimodal Video Understanding with Instructed Temporal Grounding.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2507.13353","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2507-13353","documentUrl":"https://doi.org/10.48550/ARXIV.2507.13353","pages":null,"arxivId":"2507.13353","arxivUrl":"https://arxiv.org/abs/2507.13353"},{"key":"journals/corr/abs-2508-00873","title":"FairFedMed: Benchmarking Group Fairness in Federated Medical Imaging with FairLoRA.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2508.00873","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-00873","documentUrl":"https://doi.org/10.48550/ARXIV.2508.00873","pages":null,"arxivId":"2508.00873","arxivUrl":"https://arxiv.org/abs/2508.00873"}],"excludedFormal":[],"labName":"MAI Lab","labUrl":"http://mai-lab-2026.com/","labEvidence":"当前个人主页写 My lab (MAI Lab) 并直接链接；同段说明即将加入 Colorado School of Mines。此链接是当前团队入口，不代表 2025 年团队归属。","labSourceUrl":"https://sites.google.com/view/minghanli-homepage/academic","affiliationZh":"Colorado School of Mines","sourceWarning":false,"excludedOther":[],"excludedHomonyms":[],"unassignedCandidates":[],"knownPreprintMinimum2025":null,"excludedMisattributed":[],"displayNotes":"身份已经机构或个人主页核对。2025 年正式记录 3 条，均为会议论文，所有作者位置均计入；预印本 3 条单列，不加总。","labDisplayNotes":"当前主页写有 My lab（MAI Lab），并说明即将加入 Colorado School of Mines。这是现在的团队入口，不代表 2025 年的归属。"},{"index":15,"name":"Ruoshi Liu","nameZh":"Ruoshi Liu","role":"Assistant Professor","affiliation":"University of Maryland","source":"DBLP official SPARQL","profileUrl":"https://dblp.org/pid/283/4797","identifier":"283/4797","identityEvidence":[{"url":"https://dblp.org/pid/283/4797","evidence":"DBLP 唯一同名作者档案；通过作者/机构主页与发表题名交叉核对。"},{"url":"https://ruoshiliu.github.io/","evidence":"作者/机构页面与该 DBLP 档案交叉匹配的题名示例：Dreamitate: Real-World Visuomotor Policy Learning via Video Generation.；Differentiable Robot Rendering.","matchedPaperKeys":["conf/corl/LiangLOSDTSV24","conf/corl/LiuCSV24"]}],"count2025":5,"conference2025":4,"journal2025":1,"preprint2025":2,"status":"verified","notes":"身份已通过机构/个人主页或 DBLP 机构信息核对；篇数为数据库记录统计，不表示每篇均由本人主导。","retrievedAt":"2026-10-19","yearPolicy":"DBLP yearOfPublication = 2025","queryUrl":"https://sparql.dblp.org/sparql?query=PREFIX%20dblp%3A%20%3Chttps%3A//dblp.org/rdf/schema%23%3E%20PREFIX%20xsd%3A%20%3Chttp%3A//www.w3.org/2001/XMLSchema%23%3E%20SELECT%20%3Fpub%20%3Ftitle%20%3Ftype%20%3Fvenue%20WHERE%20%7B%20%3Fpub%20dblp%3AauthoredBy%20%3Chttps%3A//dblp.org/pid/283/4797%3E%3B%20dblp%3AyearOfPublication%20%222025%22%5E%5Exsd%3AgYear%3B%20dblp%3Atitle%20%3Ftitle%3B%20a%20%3Ftype%20.%20OPTIONAL%20%7B%20%3Fpub%20dblp%3ApublishedIn%20%3Fvenue%20%7D%20%7D&format=json","papers":[{"key":"conf/eccv/CanberkBOLV24","title":"EraseDraw: Learning to Insert Objects by Erasing Them from Images.","type":"Inproceedings","venue":"ECCV (79)","year":2025,"yearOfPublication":2025,"yearOfEvent":2024,"doi":"https://doi.org/10.1007/978-3-031-72986-7_9","sourceUrl":"https://dblp.org/rec/conf/eccv/CanberkBOLV24","documentUrl":"https://doi.org/10.1007/978-3-031-72986-7_9","pages":"144-160"},{"key":"conf/eccv/HoorickWOSLTDZV24","title":"Generative Camera Dolly: Extreme Monocular Dynamic Novel View Synthesis.","type":"Inproceedings","venue":"ECCV (24)","year":2025,"yearOfPublication":2025,"yearOfEvent":2024,"doi":"https://doi.org/10.1007/978-3-031-72691-0_18","sourceUrl":"https://dblp.org/rec/conf/eccv/HoorickWOSLTDZV24","documentUrl":"https://doi.org/10.1007/978-3-031-72691-0_18","pages":"313-331"},{"key":"conf/eccv/SudhakarLHVZ24","title":"Controlling the World by Sleight of Hand.","type":"Inproceedings","venue":"ECCV (30)","year":2025,"yearOfPublication":2025,"yearOfEvent":2024,"doi":"https://doi.org/10.1007/978-3-031-73404-5_24","sourceUrl":"https://dblp.org/rec/conf/eccv/SudhakarLHVZ24","documentUrl":"https://doi.org/10.1007/978-3-031-73404-5_24","pages":"414-430"},{"key":"conf/icra/LiuHHSV25","title":"Self-Improving Autonomous Underwater Manipulation.","type":"Inproceedings","venue":"ICRA","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/ICRA55743.2025.11128759","sourceUrl":"https://dblp.org/rec/conf/icra/LiuHHSV25","documentUrl":"https://doi.org/10.1109/ICRA55743.2025.11128759","pages":"16915-16922"},{"key":"journals/iotj/LiuYHYGLYYZWRLLZ25","title":"DRBRN: A Deep Reconstruction Bottleneck Representation Network for CT-Image-Based Pancreatic Cancer Diagnosis in Internet of Medical Things.","type":"Article","venue":"IEEE Internet Things J.","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.1109/JIOT.2025.3603595","sourceUrl":"https://dblp.org/rec/journals/iotj/LiuYHYGLYYZWRLLZ25","documentUrl":"https://doi.org/10.1109/JIOT.2025.3603595","pages":"48060-48068"}],"preprints":[{"key":"journals/corr/abs-2508-00795","title":"Video Generators are Robot Policies.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2508.00795","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-00795","documentUrl":"https://doi.org/10.48550/ARXIV.2508.00795","pages":null,"arxivId":"2508.00795","arxivUrl":"https://arxiv.org/abs/2508.00795"},{"key":"journals/corr/abs-2511-20544","title":"New York Smells: A Large Multimodal Dataset for Olfaction.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2511.20544","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2511-20544","documentUrl":"https://doi.org/10.48550/ARXIV.2511.20544","pages":null,"arxivId":"2511.20544","arxivUrl":"https://arxiv.org/abs/2511.20544"}],"excludedFormal":[],"labName":null,"labUrl":null,"labEvidence":"本人及 UMD 官方主页确认有研究团队，个人页称 our lab，但本轮未确认具名 Lab；未把雇主或研究方向改写为团队名称。","labSourceUrl":"https://ruoshiliu.github.io/","affiliationZh":"University of Maryland","sourceWarning":false,"excludedOther":[],"excludedHomonyms":[],"unassignedCandidates":[],"knownPreprintMinimum2025":null,"excludedMisattributed":[],"displayNotes":"身份已经机构或个人主页核对。2025 年正式记录 5 条（会议 4、期刊 1），所有作者位置均计入；预印本 2 条单列，不加总。","labDisplayNotes":"本人主页与马里兰大学官方页可以确认其有研究组，但未见组名；图中以「姓名及合作者」单列。"},{"index":16,"name":"Xiaoming Liu","nameZh":"Xiaoming Liu","role":"Distinguished Professor","affiliation":"University of North Carolina at Chapel Hill","source":"DBLP official SPARQL","profileUrl":"https://dblp.org/pid/l/XiaomingLiu0002","identifier":"l/XiaomingLiu0002","identityEvidence":[{"url":"https://dblp.org/pid/l/XiaomingLiu0002","evidence":"DBLP 档案名 Xiaoming Liu 0002；机构/履历：GE Global Research；Michigan State University, MI, USA；University of North Carolina at Chapel Hill, NC, USA"}],"count2025":17,"conference2025":15,"journal2025":2,"preprint2025":17,"status":"verified","notes":"身份已通过机构/个人主页或 DBLP 机构信息核对；篇数为数据库记录统计，不表示每篇均由本人主导。","retrievedAt":"2026-10-19","yearPolicy":"DBLP yearOfPublication = 2025","queryUrl":"https://sparql.dblp.org/sparql?query=PREFIX%20dblp%3A%20%3Chttps%3A//dblp.org/rdf/schema%23%3E%20PREFIX%20xsd%3A%20%3Chttp%3A//www.w3.org/2001/XMLSchema%23%3E%20SELECT%20%3Fpub%20%3Ftitle%20%3Ftype%20%3Fvenue%20WHERE%20%7B%20%3Fpub%20dblp%3AauthoredBy%20%3Chttps%3A//dblp.org/pid/l/XiaomingLiu0002%3E%3B%20dblp%3AyearOfPublication%20%222025%22%5E%5Exsd%3AgYear%3B%20dblp%3Atitle%20%3Ftitle%3B%20a%20%3Ftype%20.%20OPTIONAL%20%7B%20%3Fpub%20dblp%3ApublishedIn%20%3Fvenue%20%7D%20%7D&format=json","papers":[{"key":"conf/cvpr/GuoSZLL25","title":"Rethinking Vision-Language Model in Face Forensics: Multi-Modal Interpretable Forged Face Detector.","type":"Inproceedings","venue":"CVPR","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/CVPR52734.2025.00019","sourceUrl":"https://dblp.org/rec/conf/cvpr/GuoSZLL25","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Guo_Rethinking_Vision-Language_Model_in_Face_Forensics_Multi-Modal_Interpretable_Forged_Face_CVPR_2025_paper.html","pages":"105-116"},{"key":"conf/cvpr/HuangLK25","title":"H-MoRe: Learning Human-centric Motion Representation for Action Analysis.","type":"Inproceedings","venue":"CVPR","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/CVPR52734.2025.02114","sourceUrl":"https://dblp.org/rec/conf/cvpr/HuangLK25","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Huang_H-MoRe_Learning_Human-centric_Motion_Representation_for_Action_Analysis_CVPR_2025_paper.html","pages":"22702-22713"},{"key":"conf/cvpr/KimYSLL25","title":"SapiensID: Foundation for Human Recognition.","type":"Inproceedings","venue":"CVPR","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/CVPR52734.2025.01301","sourceUrl":"https://dblp.org/rec/conf/cvpr/KimYSLL25","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Kim_SapiensID_Foundation_for_Human_Recognition_CVPR_2025_paper.html","pages":"13937-13947"},{"key":"conf/cvpr/Long00M25","title":"RICCARDO: Radar Hit Prediction and Convolution for Camera-Radar 3D Object Detection.","type":"Inproceedings","venue":"CVPR","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/CVPR52734.2025.02075","sourceUrl":"https://dblp.org/rec/conf/cvpr/Long00M25","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Long_RICCARDO_Radar_Hit_Prediction_and_Convolution_for_Camera-Radar_3D_Object_CVPR_2025_paper.html","pages":"22276-22285"},{"key":"conf/eccv/HouSZZHYL24","title":"COMPOSE: Comprehensive Portrait Shadow Editing.","type":"Inproceedings","venue":"ECCV (61)","year":2025,"yearOfPublication":2025,"yearOfEvent":2024,"doi":"https://doi.org/10.1007/978-3-031-73030-6_20","sourceUrl":"https://dblp.org/rec/conf/eccv/HouSZZHYL24","documentUrl":"https://doi.org/10.1007/978-3-031-73030-6_20","pages":"356-373"},{"key":"conf/eccv/SuKLJL24","title":"Open-Set Biometrics: Beyond Good Closed-Set Models.","type":"Inproceedings","venue":"ECCV (62)","year":2025,"yearOfPublication":2025,"yearOfEvent":2024,"doi":"https://doi.org/10.1007/978-3-031-73033-7_14","sourceUrl":"https://dblp.org/rec/conf/eccv/SuKLJL24","documentUrl":"https://doi.org/10.1007/978-3-031-73033-7_14","pages":"243-261"},{"key":"conf/eccv/ZhuGKL24","title":"RePLAy: Remove Projective LiDAR Depthmap Artifacts via Exploiting Epipolar Geometry.","type":"Inproceedings","venue":"ECCV (81)","year":2025,"yearOfPublication":2025,"yearOfEvent":2024,"doi":"https://doi.org/10.1007/978-3-031-73004-7_23","sourceUrl":"https://dblp.org/rec/conf/eccv/ZhuGKL24","documentUrl":"https://doi.org/10.1007/978-3-031-73004-7_23","pages":"393-411"},{"key":"conf/eccv/ZhuL24","title":"Revisit Self-supervised Depth Estimation with Local Structure-from-Motion.","type":"Inproceedings","venue":"ECCV (82)","year":2025,"yearOfPublication":2025,"yearOfEvent":2024,"doi":"https://doi.org/10.1007/978-3-031-73007-8_3","sourceUrl":"https://dblp.org/rec/conf/eccv/ZhuL24","documentUrl":"https://doi.org/10.1007/978-3-031-73007-8_3","pages":"38-56"},{"key":"conf/icb/NguyenFSNLLREDTVMFOGWLZ25","title":"AG-VPReID 2025: Aerial-Ground Video-based Person Re-identification Challenge Results.","type":"Inproceedings","venue":"IJCB","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/IJCB65343.2025.11410726","sourceUrl":"https://dblp.org/rec/conf/icb/NguyenFSNLLREDTVMFOGWLZ25","documentUrl":"https://doi.org/10.1109/IJCB65343.2025.11410726","pages":"1-10"},{"key":"conf/iccv/AsnaniCLA25","title":"CustomMark: Customization of Diffusion Models for Proactive Attribution.","type":"Inproceedings","venue":"ICCVW","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/ICCVW69036.2025.00162","sourceUrl":"https://dblp.org/rec/conf/iccv/AsnaniCLA25","documentUrl":"https://doi.org/10.1109/ICCVW69036.2025.00162","pages":"1523-1533"},{"key":"conf/iccv/KumarGZHRL25","title":"CHARM3R: Towards Unseen Camera Height Robust Monocular 3D Detector.","type":"Inproceedings","venue":"ICCV","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/ICCV51701.2025.00821","sourceUrl":"https://dblp.org/rec/conf/iccv/KumarGZHRL25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.00821","pages":"8777-8788"},{"key":"conf/iccv/MaLLSGMZZCHGDLWGCEELLGL25","title":"UniAttackData+: Unified Physical-Digital Attack Detection+ Challenge.","type":"Inproceedings","venue":"ICCVW","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/ICCVW69036.2025.00335","sourceUrl":"https://dblp.org/rec/conf/iccv/MaLLSGMZZCHGDLWGCEELLGL25","documentUrl":"https://doi.org/10.1109/ICCVW69036.2025.00335","pages":"3202-3211"},{"key":"conf/iccv/ZhuSKJL25","title":"A Quality-Guided Mixture of Score-Fusion Experts Framework for Human Recognition.","type":"Inproceedings","venue":"ICCV","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/ICCV51701.2025.01215","sourceUrl":"https://dblp.org/rec/conf/iccv/ZhuSKJL25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.01215","pages":"13076-13086"},{"key":"conf/nips/YeFHLLYL25","title":"BiggerGait: Unlocking Gait Recognition with Layer-wise Representations from Large Vision Models.","type":"Inproceedings","venue":"NeurIPS","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":null,"sourceUrl":"https://dblp.org/rec/conf/nips/YeFHLLYL25","documentUrl":"http://papers.nips.cc/paper_files/paper/2025/hash/6a5c23219f401f3efd322579002dbb80-Abstract-Conference.html","pages":null},{"key":"conf/wacv/YaoL00W0025","title":"Can Adversarial Examples be Parsed to Reveal Victim Model Information?","type":"Inproceedings","venue":"WACV","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/WACV61041.2025.00685","sourceUrl":"https://dblp.org/rec/conf/wacv/YaoL00W0025","documentUrl":"https://doi.org/10.1109/WACV61041.2025.00685","pages":"7049-7061"},{"key":"journals/ijcv/GuoLML25","title":"Language-Guided Hierarchical Fine-Grained Image Forgery Detection and Localization.","type":"Article","venue":"Int. J. Comput. Vis.","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.1007/S11263-024-02255-9","sourceUrl":"https://dblp.org/rec/journals/ijcv/GuoLML25","documentUrl":"https://doi.org/10.1007/S11263-024-02255-9","pages":"2670-2691"},{"key":"journals/inffus/DeAndresTameTMVKRLGMFOZ25","title":"Second FRCSyn-onGoing: Winning solutions and post-challenge analysis to improve face recognition with synthetic data.","type":"Article","venue":"Inf. Fusion","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.1016/J.INFFUS.2025.103099","sourceUrl":"https://dblp.org/rec/journals/inffus/DeAndresTameTMVKRLGMFOZ25","documentUrl":"https://doi.org/10.1016/J.INFFUS.2025.103099","pages":"103099"}],"preprints":[{"key":"journals/corr/abs-2503-20188","title":"Rethinking Vision-Language Model in Face Forensics: Multi-Modal Interpretable Forged Face Detector.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2503.20188","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-20188","documentUrl":"https://doi.org/10.48550/ARXIV.2503.20188","pages":null,"arxivId":"2503.20188","arxivUrl":"https://arxiv.org/abs/2503.20188"},{"key":"journals/corr/abs-2503-21886","title":"Refined Geometry-guided Head Avatar Reconstruction from Monocular RGB Video.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2503.21886","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-21886","documentUrl":"https://doi.org/10.48550/ARXIV.2503.21886","pages":null,"arxivId":"2503.21886","arxivUrl":"https://arxiv.org/abs/2503.21886"},{"key":"journals/corr/abs-2504-04708","title":"SapiensID: Foundation for Human Recognition.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2504.04708","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2504-04708","documentUrl":"https://doi.org/10.48550/ARXIV.2504.04708","pages":null,"arxivId":"2504.04708","arxivUrl":"https://arxiv.org/abs/2504.04708"},{"key":"journals/corr/abs-2504-09086","title":"RICCARDO: Radar Hit Prediction and Convolution for Camera-Radar 3D Object Detection.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2504.09086","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2504-09086","documentUrl":"https://doi.org/10.48550/ARXIV.2504.09086","pages":null,"arxivId":"2504.09086","arxivUrl":"https://arxiv.org/abs/2504.09086"},{"key":"journals/corr/abs-2504-10676","title":"H-MoRe: Learning Human-centric Motion Representation for Action Analysis.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2504.10676","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2504-10676","documentUrl":"https://doi.org/10.48550/ARXIV.2504.10676","pages":null,"arxivId":"2504.10676","arxivUrl":"https://arxiv.org/abs/2504.10676"},{"key":"journals/corr/abs-2505-04616","title":"Person Recognition at Altitude and Range: Fusion of Face, Body Shape and Gait.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2505.04616","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-04616","documentUrl":"https://doi.org/10.48550/ARXIV.2505.04616","pages":null,"arxivId":"2505.04616","arxivUrl":"https://arxiv.org/abs/2505.04616"},{"key":"journals/corr/abs-2505-13327","title":"Benchmarking Unified Face Attack Detection via Hierarchical Prompt Tuning.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2505.13327","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-13327","documentUrl":"https://doi.org/10.48550/ARXIV.2505.13327","pages":null,"arxivId":"2505.13327","arxivUrl":"https://arxiv.org/abs/2505.13327"},{"key":"journals/corr/abs-2505-18132","title":"BiggerGait: Unlocking Gait Recognition with Layer-wise Representations from Large Vision Models.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2505.18132","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-18132","documentUrl":"https://doi.org/10.48550/ARXIV.2505.18132","pages":null,"arxivId":"2505.18132","arxivUrl":"https://arxiv.org/abs/2505.18132"},{"key":"journals/corr/abs-2505-24247","title":"50 Years of Automated Face Recognition.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2505.24247","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-24247","documentUrl":"https://doi.org/10.48550/ARXIV.2505.24247","pages":null,"arxivId":"2505.24247","arxivUrl":"https://arxiv.org/abs/2505.24247"},{"key":"journals/corr/abs-2506-22843","title":"AG-VPReID 2025: Aerial-Ground Video-based Person Re-identification Challenge Results.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2506.22843","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-22843","documentUrl":"https://doi.org/10.48550/ARXIV.2506.22843","pages":null,"arxivId":"2506.22843","arxivUrl":"https://arxiv.org/abs/2506.22843"},{"key":"journals/corr/abs-2508-00053","title":"A Quality-Guided Mixture of Score-Fusion Experts Framework for Human Recognition.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2508.00053","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-00053","documentUrl":"https://doi.org/10.48550/ARXIV.2508.00053","pages":null,"arxivId":"2508.00053","arxivUrl":"https://arxiv.org/abs/2508.00053"},{"key":"journals/corr/abs-2508-05038","title":"HAMoBE: Hierarchical and Adaptive Mixture of Biometric Experts for Video-based Person ReID.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2508.05038","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-05038","documentUrl":"https://doi.org/10.48550/ARXIV.2508.05038","pages":null,"arxivId":"2508.05038","arxivUrl":"https://arxiv.org/abs/2508.05038"},{"key":"journals/corr/abs-2508-11185","title":"CHARM3R: Towards Unseen Camera Height Robust Monocular 3D Detector.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2508.11185","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-11185","documentUrl":"https://doi.org/10.48550/ARXIV.2508.11185","pages":null,"arxivId":"2508.11185","arxivUrl":"https://arxiv.org/abs/2508.11185"},{"key":"journals/corr/abs-2508-21222","title":"Generalizable Object Re-Identification via Visual In-Context Prompting.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2508.21222","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-21222","documentUrl":"https://doi.org/10.48550/ARXIV.2508.21222","pages":null,"arxivId":"2508.21222","arxivUrl":"https://arxiv.org/abs/2508.21222"},{"key":"journals/corr/abs-2511-16642","title":"TRIM: Scalable 3D Gaussian Diffusion Inference with Temporal and Spatial Trimming.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2511.16642","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2511-16642","documentUrl":"https://doi.org/10.48550/ARXIV.2511.16642","pages":null,"arxivId":"2511.16642","arxivUrl":"https://arxiv.org/abs/2511.16642"},{"key":"journals/corr/abs-2511-17674","title":"Person Recognition in Aerial Surveillance: A Decade Survey.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2511.17674","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2511-17674","documentUrl":"https://doi.org/10.48550/ARXIV.2511.17674","pages":null,"arxivId":"2511.17674","arxivUrl":"https://arxiv.org/abs/2511.17674"},{"key":"journals/corr/abs-2511-18104","title":"Consolidating Diffusion-Generated Video Detection with Unified Multimodal Forgery Learning.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2511.18104","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2511-18104","documentUrl":"https://doi.org/10.48550/ARXIV.2511.18104","pages":null,"arxivId":"2511.18104","arxivUrl":"https://arxiv.org/abs/2511.18104"}],"excludedFormal":[],"labName":"Computer Vision Lab","labUrl":"https://www.cs.unc.edu/~liuxm/","labEvidence":"UNC 当前官方教师页在其联系方式及 Personal Website 后明确列 Computer Vision Lab，并链接此 UNC 个人主页；使用当前 UNC 入口，不将先前 MSU 团队所在地套用为当前地址。","labSourceUrl":"https://cs.unc.edu/person/xiaoming-liu/","affiliationZh":"University of North Carolina at Chapel Hill","sourceWarning":false,"excludedOther":[],"excludedHomonyms":[],"unassignedCandidates":[],"knownPreprintMinimum2025":null,"excludedMisattributed":[],"displayNotes":"身份已经机构或个人主页核对。2025 年正式记录 17 条（会议 15、期刊 2），所有作者位置均计入，不表示主导或贡献份额；预印本 17 条单列，不加总。","labDisplayNotes":"UNC 当前官方教师页写明其 Computer Vision Lab，并链接本人 UNC 主页，据此归组；不沿用此前在 MSU 时期的地点。"},{"index":17,"name":"Ziwei Liu","nameZh":"Ziwei Liu","role":"Associate Professor","affiliation":"Nanyang Technological University","source":"DBLP official SPARQL","profileUrl":"https://dblp.org/pid/05/6300-2","identifier":"05/6300-2","identityEvidence":[{"url":"https://dblp.org/pid/05/6300-2","evidence":"DBLP 档案名 Ziwei Liu 0002；机构/履历：Chinese University of Hong Kong, Department of Information Engineering, Hong Kong；Nanyang Technological University, S-Lab, Singapore"},{"url":"https://api.crossref.org/works/10.1109/TMC.2025.3545340","evidence":"Publisher-deposited Crossref metadata assigns Ziwei Liu to Sichuan University with ORCID 0000-0001-6206-637X, not NTU Ziwei Liu (0000-0002-4220-5958).","matchedPaperKeys":["journals/tmc/LiuZYSYL25"]},{"url":"https://www.sciencedirect.com/science/article/pii/S1566253525002325","evidence":"DBLP paper signature uses the same Sichuan University Ziwei Liu ORCID 0000-0001-6206-637X as ReflexGest; publisher author list and Sichuan author profile confirm this separate visible-light sensing group.","matchedPaperKeys":["journals/inffus/YangLCYSF25"]},{"url":"https://liuziwei7.github.io/publications.html","evidence":"Author or laboratory publication page: counted formal-paper titles matched after punctuation/case normalization. Additional title variants and missing entries were checked separately below.","matchedPaperKeys":["conf/acl/DingJ0JGWZW000T25","conf/acl/MiyaiYZMYILLLA25","conf/acl/TianZ0025","conf/acl/ZhangTH0025","conf/cvpr/0001HW0Z0L025","conf/cvpr/0009KSP0025","conf/cvpr/0009TDCHL0XWSPL25","conf/cvpr/ChengMZCPZWF00P25","conf/cvpr/DongLSYHRL25","conf/cvpr/GuanWXYSHLCLFD025","conf/cvpr/HeW0P025","conf/cvpr/HongGKYNLM25","conf/cvpr/HuangWLW25","conf/cvpr/JiangXLZRGLCY025","conf/cvpr/KumbongLLLLLFRR25","conf/cvpr/PangLC0Z025","conf/cvpr/Xie0H025","conf/cvpr/YangLGDZZWZXWOL25","conf/eccv/BahmaniLYSRLLPTWTL24","conf/eccv/ChenWWPJL24","conf/eccv/GuanXZWHZLFDLWZL24","conf/eccv/HuHL24","conf/eccv/JiangZLSYLL24","conf/eccv/LiuDZLZZYWHLCL24","conf/eccv/LiuWHSYZCLL24","conf/eccv/MaYHGJPPGBKBFLLENN24","conf/eccv/TangCCWZL24","conf/eccv/WuSJHL24","conf/eccv/XieZZLZHYL24","conf/eccv/XuKSZPCLL24","conf/eccv/YangDLLWTJKZZL24","conf/eccv/YangLY24","conf/eccv/YinCWWWMXYSYLY24","conf/eccv/ZhangJGHCHZGYHL24","conf/eccv/ZhangWWWLL24","conf/iccv/CaoSWL25","conf/iccv/LiuHCWHSCLL25","conf/iccv/LuLDZDLCYZWL25","conf/iccv/LvPSCZLW25","conf/iccv/LvSPCWQL25","conf/iccv/QiuZWCYWZL25","conf/iccv/RenZXPLWZL25","conf/iccv/WangLLWDY25","conf/iccv/XieKDSZCLP25","conf/iccv/ZhangSLL25","conf/iccv/ZhangWTLWL25","conf/iclr/00030HH0L25","conf/iclr/BianKXP0025","conf/iclr/CaoP0W025","conf/iclr/LiuD0HLR25","conf/iclr/LvSSY00W25","conf/icml/WuL025","conf/mm/LiHSLLMGL025","conf/naacl/ZhangLZPCHLZYLL25","conf/nips/CaoCPL25","conf/nips/GaoLLLGYXWSLS25","conf/nips/LiangRMTLGFOLGH25","conf/nips/LiDHLLLPKLL25","conf/nips/LiuHJZDZHHCQOZL25","conf/nips/TanYWHGLL25","conf/nips/WangYHYZWLP25","conf/nips/WuYPXLLW25","conf/nips/ZhangZCWLPLL25","conf/nips/ZuoDKYJZSPLG25","conf/siggraph/GuYLLDS0L000025","conf/siggraph/Yang00WW0L25","conf/siggrapha/HeLLH0OL25","conf/wacv/Kong0CZPC025","journals/ijcv/ShaoWL25","journals/ijcv/ShaoWNL25","journals/ijcv/TangWZCHHLLZW25","journals/ijcv/WangCMZHWYHYYGWSJCLDLQL25","journals/ijcv/XieLLLOL25","journals/ijcv/ZhangSZHYWSQSL25","journals/ijcv/ZhouCYZL25","journals/pami/CaoHWPL25","journals/pami/KongXRZPCOL25","journals/pami/LiLCLLL25","journals/pami/LiZCWPCYLL25","journals/pami/XieKZRPCL25","journals/pami/ZhangZL25","journals/pami/ZhouZWNYZL25","journals/pr/ZhangWYSL25","journals/tmlr/0080ZGZ00ZZL0L25","journals/tmlr/Ma0CJ0LC025","journals/tmlr/MiyaiYZMLYIJ0L025","journals/tmlr/ZhangWLLMLL25","journals/tmlr/ZhangZLZYZWTLL25"]},{"url":"https://dblp.org/rec/conf/accv/HuangCWL24","evidence":"The original DBLP author signature carries target ORCID 0000-0002-4220-5958; venue event year 2024 is retained separately from publication year 2025.","matchedPaperKeys":["conf/accv/HuangCWL24"]},{"url":"https://gordonchen19.github.io/STENCIL.github.io/static/pdfs/chen.pdf","evidence":"Original first page assigns Ziwei Liu to Nanyang Technological University.","matchedPaperKeys":["conf/icip/ChenHTL25"]},{"url":"https://liuziwei7.github.io/publications.html","evidence":"Author personally lists HumanLiff: Layer-wise 3D Human Generation with Diffusion Model, IJCV 2025, with the same eight authors as the DBLP HumanLiff record. This is a title variant, not an unmatched paper.","matchedPaperKeys":["journals/ijcv/HuHHPMXYL25"]},{"url":"https://www.researchgate.net/profile/Ziwei_Liu45","evidence":"The separately self-presented Sichuan University researcher lists the visible-light recognition work; used with the publisher author list and paper-level ORCID, not as sole profile-matching evidence."}],"count2025":91,"conference2025":70,"journal2025":21,"preprint2025":null,"status":"verified_manual","notes":"身份已通过机构/个人主页或 DBLP 机构信息核对；篇数为数据库记录统计，不表示每篇均由本人主导。 发现同名误归后，全部正式候选用本人论文列表、论文原文或正确 ORCID 重新核对。预印本候选保留于 unassignedCandidates；null 不表示零篇。","retrievedAt":"2026-10-19","yearPolicy":"DBLP yearOfPublication = 2025","queryUrl":"https://sparql.dblp.org/sparql?query=PREFIX%20dblp%3A%20%3Chttps%3A//dblp.org/rdf/schema%23%3E%20PREFIX%20xsd%3A%20%3Chttp%3A//www.w3.org/2001/XMLSchema%23%3E%20SELECT%20%3Fpub%20%3Ftitle%20%3Ftype%20%3Fvenue%20WHERE%20%7B%20%3Fpub%20dblp%3AauthoredBy%20%3Chttps%3A//dblp.org/pid/05/6300-2%3E%3B%20dblp%3AyearOfPublication%20%222025%22%5E%5Exsd%3AgYear%3B%20dblp%3Atitle%20%3Ftitle%3B%20a%20%3Ftype%20.%20OPTIONAL%20%7B%20%3Fpub%20dblp%3ApublishedIn%20%3Fvenue%20%7D%20%7D&format=json","papers":[{"key":"conf/accv/HuangCWL24","title":"Towards Robust Video Frame Interpolation with Long-Term Propagation.","type":"Inproceedings","venue":"ACCV Workshops (2)","year":2025,"yearOfPublication":2025,"yearOfEvent":2024,"doi":"https://doi.org/10.1007/978-981-96-2644-1_19","sourceUrl":"https://dblp.org/rec/conf/accv/HuangCWL24","documentUrl":"https://doi.org/10.1007/978-981-96-2644-1_19","pages":"276-291"},{"key":"conf/acl/DingJ0JGWZW000T25","title":"Dynamic Parallel Tree Search for Efficient LLM Reasoning.","type":"Inproceedings","venue":"ACL (1)","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.18653/V1/2025.ACL-LONG.550","sourceUrl":"https://dblp.org/rec/conf/acl/DingJ0JGWZW000T25","documentUrl":"https://doi.org/10.18653/V1/2025.ACL-LONG.550","pages":"11233-11252"},{"key":"conf/acl/MiyaiYZMYILLLA25","title":"Unsolvable Problem Detection: Robust Understanding Evaluation for Large Multimodal Models.","type":"Inproceedings","venue":"ACL (1)","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.18653/V1/2025.ACL-LONG.326","sourceUrl":"https://dblp.org/rec/conf/acl/MiyaiYZMYILLLA25","documentUrl":"https://doi.org/10.18653/V1/2025.ACL-LONG.326","pages":"6497-6540"},{"key":"conf/acl/TianZ0025","title":"MMInA: Benchmarking Multihop Multimodal Internet Agents.","type":"Inproceedings","venue":"ACL (Findings)","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.18653/V1/2025.FINDINGS-ACL.703","sourceUrl":"https://dblp.org/rec/conf/acl/TianZ0025","documentUrl":"https://doi.org/10.18653/V1/2025.FINDINGS-ACL.703","pages":"13682-13697"},{"key":"conf/acl/ZhangTH0025","title":"Evaluation Agent: Efficient and Promptable Evaluation Framework for Visual Generative Models.","type":"Inproceedings","venue":"ACL (1)","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.18653/V1/2025.ACL-LONG.374","sourceUrl":"https://dblp.org/rec/conf/acl/ZhangTH0025","documentUrl":"https://doi.org/10.18653/V1/2025.ACL-LONG.374","pages":"7561-7582"},{"key":"conf/cvpr/0001HW0Z0L025","title":"WildAvatar: Learning In-the-wild 3D Avatars from the Web.","type":"Inproceedings","venue":"CVPR","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/CVPR52734.2025.01488","sourceUrl":"https://dblp.org/rec/conf/cvpr/0001HW0Z0L025","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Huang_WildAvatar_Learning_In-the-wild_3D_Avatars_from_the_Web_CVPR_2025_paper.html","pages":"15963-15975"},{"key":"conf/cvpr/0009KSP0025","title":"LiMoE: Mixture of LiDAR Representation Learners from Automotive Scenes.","type":"Inproceedings","venue":"CVPR","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/CVPR52734.2025.02549","sourceUrl":"https://dblp.org/rec/conf/cvpr/0009KSP0025","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Xu_LiMoE_Mixture_of_LiDAR_Representation_Learners_from_Automotive_Scenes_CVPR_2025_paper.html","pages":"27368-27379"},{"key":"conf/cvpr/0009TDCHL0XWSPL25","title":"3DTopia-XL: Scaling High-quality 3D Asset Generation via Primitive Diffusion.","type":"Inproceedings","venue":"CVPR","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/CVPR52734.2025.02475","sourceUrl":"https://dblp.org/rec/conf/cvpr/0009TDCHL0XWSPL25","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Chen_3DTopia-XL_Scaling_High-quality_3D_Asset_Generation_via_Primitive_Diffusion_CVPR_2025_paper.html","pages":"26576-26586"},{"key":"conf/cvpr/ChengMZCPZWF00P25","title":"MVPaint: Synchronized Multi-View Diffusion for Painting Anything 3D.","type":"Inproceedings","venue":"CVPR","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/CVPR52734.2025.00063","sourceUrl":"https://dblp.org/rec/conf/cvpr/ChengMZCPZWF00P25","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Cheng_MVPaint_Synchronized_Multi-View_Diffusion_for_Painting_Anything_3D_CVPR_2025_paper.html","pages":"585-594"},{"key":"conf/cvpr/DongLSYHRL25","title":"Insight-V: Exploring Long-Chain Visual Reasoning with Multimodal Large Language Models.","type":"Inproceedings","venue":"CVPR","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/CVPR52734.2025.00847","sourceUrl":"https://dblp.org/rec/conf/cvpr/DongLSYHRL25","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Dong_Insight-V_Exploring_Long-Chain_Visual_Reasoning_with_Multimodal_Large_Language_Models_CVPR_2025_paper.html","pages":"9062-9072"},{"key":"conf/cvpr/GuanWXYSHLCLFD025","title":"AudCast: Audio-Driven Human Video Generation by Cascaded Diffusion Transformers.","type":"Inproceedings","venue":"CVPR","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/CVPR52734.2025.00998","sourceUrl":"https://dblp.org/rec/conf/cvpr/GuanWXYSHLCLFD025","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Guan_AudCast_Audio-Driven_Human_Video_Generation_by_Cascaded_Diffusion_Transformers_CVPR_2025_paper.html","pages":"10678-10689"},{"key":"conf/cvpr/HeW0P025","title":"Neural LightRig: Unlocking Accurate Object Normal and Material Estimation with Multi-Light Diffusion.","type":"Inproceedings","venue":"CVPR","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/CVPR52734.2025.02469","sourceUrl":"https://dblp.org/rec/conf/cvpr/HeW0P025","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/He_Neural_LightRig_Unlocking_Accurate_Object_Normal_and_Material_Estimation_with_CVPR_2025_paper.html","pages":"26514-26524"},{"key":"conf/cvpr/HongGKYNLM25","title":"EgoLM: Multi-Modal Language Model of Egocentric Motions.","type":"Inproceedings","venue":"CVPR","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/CVPR52734.2025.00503","sourceUrl":"https://dblp.org/rec/conf/cvpr/HongGKYNLM25","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Hong_EgoLM_Multi-Modal_Language_Model_of_Egocentric_Motions_CVPR_2025_paper.html","pages":"5344-5354"},{"key":"conf/cvpr/HuangWLW25","title":"Material Anything: Generating Materials for Any 3D Object via Diffusion.","type":"Inproceedings","venue":"CVPR","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/CVPR52734.2025.02473","sourceUrl":"https://dblp.org/rec/conf/cvpr/HuangWLW25","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Huang_Material_Anything_Generating_Materials_for_Any_3D_Object_via_Diffusion_CVPR_2025_paper.html","pages":"26556-26565"},{"key":"conf/cvpr/JiangXLZRGLCY025","title":"SOLAMI: Social Vision-Language-Action Modeling for Immersive Interaction with 3D Autonomous Characters.","type":"Inproceedings","venue":"CVPR","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/CVPR52734.2025.02504","sourceUrl":"https://dblp.org/rec/conf/cvpr/JiangXLZRGLCY025","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Jiang_SOLAMI_Social_Vision-Language-Action_Modeling_for_Immersive_Interaction_with_3D_Autonomous_CVPR_2025_paper.html","pages":"26887-26898"},{"key":"conf/cvpr/KumbongLLLLLFRR25","title":"HMAR: Efficient Hierarchical Masked Auto-Regressive Image Generation.","type":"Inproceedings","venue":"CVPR","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/CVPR52734.2025.00242","sourceUrl":"https://dblp.org/rec/conf/cvpr/KumbongLLLLLFRR25","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Kumbong_HMAR_Efficient_Hierarchical_Masked_Auto-Regressive_Image_Generation_CVPR_2025_paper.html","pages":"2535-2544"},{"key":"conf/cvpr/PangLC0Z025","title":"Disco4D: Disentangled 4D Human Generation and Animation from a Single Image.","type":"Inproceedings","venue":"CVPR","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/CVPR52734.2025.02452","sourceUrl":"https://dblp.org/rec/conf/cvpr/PangLC0Z025","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Pang_Disco4D_Disentangled_4D_Human_Generation_and_Animation_from_a_Single_CVPR_2025_paper.html","pages":"26331-26344"},{"key":"conf/cvpr/Xie0H025","title":"Generative Gaussian Splatting for Unbounded 3D City Generation.","type":"Inproceedings","venue":"CVPR","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/CVPR52734.2025.00573","sourceUrl":"https://dblp.org/rec/conf/cvpr/Xie0H025","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Xie_Generative_Gaussian_Splatting_for_Unbounded_3D_City_Generation_CVPR_2025_paper.html","pages":"6111-6120"},{"key":"conf/cvpr/YangLGDZZWZXWOL25","title":"EgoLife: Towards Egocentric Life Assistant.","type":"Inproceedings","venue":"CVPR","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/CVPR52734.2025.02690","sourceUrl":"https://dblp.org/rec/conf/cvpr/YangLGDZZWZXWOL25","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Yang_EgoLife_Towards_Egocentric_Life_Assistant_CVPR_2025_paper.html","pages":"28885-28900"},{"key":"conf/eccv/BahmaniLYSRLLPTWTL24","title":"TC4D: Trajectory-Conditioned Text-to-4D Generation.","type":"Inproceedings","venue":"ECCV (46)","year":2025,"yearOfPublication":2025,"yearOfEvent":2024,"doi":"https://doi.org/10.1007/978-3-031-72952-2_4","sourceUrl":"https://dblp.org/rec/conf/eccv/BahmaniLYSRLLPTWTL24","documentUrl":"https://doi.org/10.1007/978-3-031-72952-2_4","pages":"53-72"},{"key":"conf/eccv/ChenWWPJL24","title":"ComboVerse: Compositional 3D Assets Creation Using Spatially-Aware Diffusion Guidance.","type":"Inproceedings","venue":"ECCV (24)","year":2025,"yearOfPublication":2025,"yearOfEvent":2024,"doi":"https://doi.org/10.1007/978-3-031-72691-0_8","sourceUrl":"https://dblp.org/rec/conf/eccv/ChenWWPJL24","documentUrl":"https://doi.org/10.1007/978-3-031-72691-0_8","pages":"128-146"},{"key":"conf/eccv/GuanXZWHZLFDLWZL24","title":"ReSyncer: Rewiring Style-Based Generator for Unified Audio-Visually Synced Facial Performer.","type":"Inproceedings","venue":"ECCV (41)","year":2025,"yearOfPublication":2025,"yearOfEvent":2024,"doi":"https://doi.org/10.1007/978-3-031-72940-9_20","sourceUrl":"https://dblp.org/rec/conf/eccv/GuanXZWHZLFDLWZL24","documentUrl":"https://doi.org/10.1007/978-3-031-72940-9_20","pages":"348-367"},{"key":"conf/eccv/HuHL24","title":"StructLDM: Structured Latent Diffusion for 3D Human Generation.","type":"Inproceedings","venue":"ECCV (51)","year":2025,"yearOfPublication":2025,"yearOfEvent":2024,"doi":"https://doi.org/10.1007/978-3-031-72983-6_21","sourceUrl":"https://dblp.org/rec/conf/eccv/HuHL24","documentUrl":"https://doi.org/10.1007/978-3-031-72983-6_21","pages":"363-381"},{"key":"conf/eccv/JiangZLSYLL24","title":"GroupDiff: Diffusion-Based Group Portrait Editing.","type":"Inproceedings","venue":"ECCV (34)","year":2025,"yearOfPublication":2025,"yearOfEvent":2024,"doi":"https://doi.org/10.1007/978-3-031-72754-2_13","sourceUrl":"https://dblp.org/rec/conf/eccv/JiangZLSYLL24","documentUrl":"https://doi.org/10.1007/978-3-031-72754-2_13","pages":"221-239"},{"key":"conf/eccv/LiuDZLZZYWHLCL24","title":"MMBench: Is Your Multi-modal Model an All-Around Player?","type":"Inproceedings","venue":"ECCV (6)","year":2025,"yearOfPublication":2025,"yearOfEvent":2024,"doi":"https://doi.org/10.1007/978-3-031-72658-3_13","sourceUrl":"https://dblp.org/rec/conf/eccv/LiuDZLZZYWHLCL24","documentUrl":"https://doi.org/10.1007/978-3-031-72658-3_13","pages":"216-233"},{"key":"conf/eccv/LiuWHSYZCLL24","title":"MVSGaussian: Fast Generalizable Gaussian Splatting Reconstruction from Multi-View Stereo.","type":"Inproceedings","venue":"ECCV (18)","year":2025,"yearOfPublication":2025,"yearOfEvent":2024,"doi":"https://doi.org/10.1007/978-3-031-72649-1_3","sourceUrl":"https://dblp.org/rec/conf/eccv/LiuWHSYZCLL24","documentUrl":"https://doi.org/10.1007/978-3-031-72649-1_3","pages":"37-53"},{"key":"conf/eccv/MaYHGJPPGBKBFLLENN24","title":"Nymeria: A Massive Collection of Multimodal Egocentric Daily Motion in the Wild.","type":"Inproceedings","venue":"ECCV (24)","year":2025,"yearOfPublication":2025,"yearOfEvent":2024,"doi":"https://doi.org/10.1007/978-3-031-72691-0_25","sourceUrl":"https://dblp.org/rec/conf/eccv/MaYHGJPPGBKBFLLENN24","documentUrl":"https://doi.org/10.1007/978-3-031-72691-0_25","pages":"445-465"},{"key":"conf/eccv/TangCCWZL24","title":"LGM: Large Multi-view Gaussian Model for High-Resolution 3D Content Creation.","type":"Inproceedings","venue":"ECCV (4)","year":2025,"yearOfPublication":2025,"yearOfEvent":2024,"doi":"https://doi.org/10.1007/978-3-031-73235-5_1","sourceUrl":"https://dblp.org/rec/conf/eccv/TangCCWZL24","documentUrl":"https://doi.org/10.1007/978-3-031-73235-5_1","pages":"1-18"},{"key":"conf/eccv/WuSJHL24","title":"FreeInit: Bridging Initialization Gap in Video Diffusion Models.","type":"Inproceedings","venue":"ECCV (3)","year":2025,"yearOfPublication":2025,"yearOfEvent":2024,"doi":"https://doi.org/10.1007/978-3-031-72646-0_22","sourceUrl":"https://dblp.org/rec/conf/eccv/WuSJHL24","documentUrl":"https://doi.org/10.1007/978-3-031-72646-0_22","pages":"378-394"},{"key":"conf/eccv/XieZZLZHYL24","title":"🐱 FunQA: Towards Surprising Video Comprehension.","type":"Inproceedings","venue":"ECCV (1)","year":2025,"yearOfPublication":2025,"yearOfEvent":2024,"doi":"https://doi.org/10.1007/978-3-031-73232-4_3","sourceUrl":"https://dblp.org/rec/conf/eccv/XieZZLZHYL24","documentUrl":"https://doi.org/10.1007/978-3-031-73232-4_3","pages":"39-57"},{"key":"conf/eccv/XuKSZPCLL24","title":"4D Contrastive Superflows are Dense 3D Representation Learners.","type":"Inproceedings","venue":"ECCV (1)","year":2025,"yearOfPublication":2025,"yearOfEvent":2024,"doi":"https://doi.org/10.1007/978-3-031-73232-4_4","sourceUrl":"https://dblp.org/rec/conf/eccv/XuKSZPCLL24","documentUrl":"https://doi.org/10.1007/978-3-031-73232-4_4","pages":"58-80"},{"key":"conf/eccv/YangDLLWTJKZZL24","title":"Octopus: Embodied Vision-Language Programmer from Environmental Feedback.","type":"Inproceedings","venue":"ECCV (1)","year":2025,"yearOfPublication":2025,"yearOfEvent":2024,"doi":"https://doi.org/10.1007/978-3-031-73232-4_2","sourceUrl":"https://dblp.org/rec/conf/eccv/YangDLLWTJKZZL24","documentUrl":"https://doi.org/10.1007/978-3-031-73232-4_2","pages":"20-38"},{"key":"conf/eccv/YangLY24","title":"Deep Nets with Subsampling Layers Unwittingly Discard Useful Activations at Test-Time.","type":"Inproceedings","venue":"ECCV (21)","year":2025,"yearOfPublication":2025,"yearOfEvent":2024,"doi":"https://doi.org/10.1007/978-3-031-72664-4_13","sourceUrl":"https://dblp.org/rec/conf/eccv/YangLY24","documentUrl":"https://doi.org/10.1007/978-3-031-72664-4_13","pages":"223-241"},{"key":"conf/eccv/YinCWWWMXYSYLY24","title":"WHAC: World-Grounded Humans and Cameras.","type":"Inproceedings","venue":"ECCV (34)","year":2025,"yearOfPublication":2025,"yearOfEvent":2024,"doi":"https://doi.org/10.1007/978-3-031-72754-2_2","sourceUrl":"https://dblp.org/rec/conf/eccv/YinCWWWMXYSYLY24","documentUrl":"https://doi.org/10.1007/978-3-031-72754-2_2","pages":"20-37"},{"key":"conf/eccv/ZhangJGHCHZGYHL24","title":"Large Motion Model for Unified Multi-modal Motion Generation.","type":"Inproceedings","venue":"ECCV (13)","year":2025,"yearOfPublication":2025,"yearOfEvent":2024,"doi":"https://doi.org/10.1007/978-3-031-72624-8_23","sourceUrl":"https://dblp.org/rec/conf/eccv/ZhangJGHCHZGYHL24","documentUrl":"https://doi.org/10.1007/978-3-031-72624-8_23","pages":"397-421"},{"key":"conf/eccv/ZhangWWWLL24","title":"Omni6D: Large-Vocabulary 3D Object Dataset for Category-Level 6D Object Pose Estimation.","type":"Inproceedings","venue":"ECCV (25)","year":2025,"yearOfPublication":2025,"yearOfEvent":2024,"doi":"https://doi.org/10.1007/978-3-031-72698-9_13","sourceUrl":"https://dblp.org/rec/conf/eccv/ZhangWWWLL24","documentUrl":"https://doi.org/10.1007/978-3-031-72698-9_13","pages":"216-232"},{"key":"conf/iccv/CaoSWL25","title":"FreeMorph: Tuning-Free Generalized Image Morphing with Diffusion Model.","type":"Inproceedings","venue":"ICCV","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/ICCV51701.2025.01683","sourceUrl":"https://dblp.org/rec/conf/iccv/CaoSWL25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.01683","pages":"18111-18120"},{"key":"conf/iccv/LiuHCWHSCLL25","title":"Free4D: Tuning-Free 4D Scene Generation with Spatial-Temporal Consistency.","type":"Inproceedings","venue":"ICCV","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/ICCV51701.2025.02372","sourceUrl":"https://dblp.org/rec/conf/iccv/LiuHCWHSCLL25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.02372","pages":"25571-25582"},{"key":"conf/iccv/LuLDZDLCYZWL25","title":"DPoser-X: Diffusion Model as Robust 3D Whole-Body Human Pose Prior.","type":"Inproceedings","venue":"ICCV","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/ICCV51701.2025.00931","sourceUrl":"https://dblp.org/rec/conf/iccv/LuLDZDLCYZWL25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.00931","pages":"9988-9997"},{"key":"conf/iccv/LvPSCZLW25","title":"Rethinking Cross-Modal Interaction in Multimodal Diffusion Transformers.","type":"Inproceedings","venue":"ICCV","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/ICCV51701.2025.00561","sourceUrl":"https://dblp.org/rec/conf/iccv/LvPSCZLW25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.00561","pages":"5934-5943"},{"key":"conf/iccv/LvSPCWQL25","title":"Dual-Expert Consistency Model for Efficient and High-Quality Video Generation.","type":"Inproceedings","venue":"ICCV","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/ICCV51701.2025.01390","sourceUrl":"https://dblp.org/rec/conf/iccv/LvSPCWQL25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.01390","pages":"14983-14993"},{"key":"conf/iccv/QiuZWCYWZL25","title":"FreeScale: Unleashing the Resolution of Diffusion Models via Tuning-Free Scale Fusion.","type":"Inproceedings","venue":"ICCV","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/ICCV51701.2025.01569","sourceUrl":"https://dblp.org/rec/conf/iccv/QiuZWCYWZL25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.01569","pages":"16893-16903"},{"key":"conf/iccv/RenZXPLWZL25","title":"GauUpdate: New Object Insertion in 3D Gaussian Fields with Consistent Global Illumination.","type":"Inproceedings","venue":"ICCV","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/ICCV51701.2025.02661","sourceUrl":"https://dblp.org/rec/conf/iccv/RenZXPLWZL25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.02661","pages":"28653-28663"},{"key":"conf/iccv/WangLLWDY25","title":"Vistadream: Sampling Multiview Consistent Images for Single-View Scene Reconstruction.","type":"Inproceedings","venue":"ICCV","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/ICCV51701.2025.02485","sourceUrl":"https://dblp.org/rec/conf/iccv/WangLLWDY25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.02485","pages":"26772-26782"},{"key":"conf/iccv/XieKDSZCLP25","title":"Are VLMs Ready for Autonomous Driving? An Empirical Study from the Reliability, Data, and Metric Perspectives.","type":"Inproceedings","venue":"ICCV","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/ICCV51701.2025.00621","sourceUrl":"https://dblp.org/rec/conf/iccv/XieKDSZCLP25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.00621","pages":"6285-6297"},{"key":"conf/iccv/ZhangSLL25","title":"Large Multi-modal Models Can Interpret Features in Large Multi-modal Models.","type":"Inproceedings","venue":"ICCV","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/ICCV51701.2025.00348","sourceUrl":"https://dblp.org/rec/conf/iccv/ZhangSLL25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.00348","pages":"3650-3661"},{"key":"conf/iccv/ZhangWTLWL25","title":"GenDoP: Auto-regressive Camera Trajectory Generation as a Director of Photography.","type":"Inproceedings","venue":"ICCV","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/ICCV51701.2025.01694","sourceUrl":"https://dblp.org/rec/conf/iccv/ZhangWTLWL25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.01694","pages":"18229-18239"},{"key":"conf/icip/ChenHTL25","title":"Stencil: Subject-Driven Generation with Context Guidance.","type":"Inproceedings","venue":"ICIP","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/ICIP55913.2025.11084422","sourceUrl":"https://dblp.org/rec/conf/icip/ChenHTL25","documentUrl":"https://doi.org/10.1109/ICIP55913.2025.11084422","pages":"719-724"},{"key":"conf/iclr/00030HH0L25","title":"Phidias: A Generative Model for Creating 3D Content from Text, Image, and 3D Conditions with Reference-Augmented Diffusion.","type":"Inproceedings","venue":"ICLR","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":null,"sourceUrl":"https://dblp.org/rec/conf/iclr/00030HH0L25","documentUrl":"https://openreview.net/forum?id=TEkoMEjf7E","pages":null},{"key":"conf/iclr/BianKXP0025","title":"DynamicCity: Large-Scale 4D Occupancy Generation from Dynamic Scenes.","type":"Inproceedings","venue":"ICLR","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":null,"sourceUrl":"https://dblp.org/rec/conf/iclr/BianKXP0025","documentUrl":"https://openreview.net/forum?id=M7KyLjuN0A","pages":null},{"key":"conf/iclr/CaoP0W025","title":"AvatarGO: Zero-shot 4D Human-Object Interaction Generation and Animation.","type":"Inproceedings","venue":"ICLR","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":null,"sourceUrl":"https://dblp.org/rec/conf/iclr/CaoP0W025","documentUrl":"https://openreview.net/forum?id=Trf0R8eoGF","pages":null},{"key":"conf/iclr/LiuD0HLR25","title":"Oryx MLLM: On-Demand Spatial-Temporal Understanding at Arbitrary Resolution.","type":"Inproceedings","venue":"ICLR","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":null,"sourceUrl":"https://dblp.org/rec/conf/iclr/LiuD0HLR25","documentUrl":"https://openreview.net/forum?id=ODiY6pbHZQ","pages":null},{"key":"conf/iclr/LvSSY00W25","title":"FasterCache: Training-Free Video Diffusion Model Acceleration with High Quality.","type":"Inproceedings","venue":"ICLR","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":null,"sourceUrl":"https://dblp.org/rec/conf/iclr/LvSSY00W25","documentUrl":"https://openreview.net/forum?id=W49UjcpGxx","pages":null},{"key":"conf/icml/WuL025","title":"Streamline Without Sacrifice - Squeeze out Computation Redundancy in LMM.","type":"Inproceedings","venue":"ICML","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":null,"sourceUrl":"https://dblp.org/rec/conf/icml/WuL025","documentUrl":"https://proceedings.mlr.press/v267/wu25s.html","pages":null},{"key":"conf/mm/LiHSLLMGL025","title":"A Motion is Worth a Hybrid Sentence: Taming Language Model for Unified Motion Generation by Fine-grained Planning.","type":"Inproceedings","venue":"ACM Multimedia","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1145/3746027.3755164","sourceUrl":"https://dblp.org/rec/conf/mm/LiHSLLMGL025","documentUrl":"https://doi.org/10.1145/3746027.3755164","pages":"1404-1413"},{"key":"conf/naacl/ZhangLZPCHLZYLL25","title":"LMMs-Eval: Reality Check on the Evaluation of Large Multimodal Models.","type":"Inproceedings","venue":"NAACL (Findings)","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.18653/V1/2025.FINDINGS-NAACL.51","sourceUrl":"https://dblp.org/rec/conf/naacl/ZhangLZPCHLZYLL25","documentUrl":"https://doi.org/10.18653/V1/2025.FINDINGS-NAACL.51","pages":"881-916"},{"key":"conf/nips/CaoCPL25","title":"PhysX-3D: Physical-Grounded 3D Asset Generation.","type":"Inproceedings","venue":"NeurIPS","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":null,"sourceUrl":"https://dblp.org/rec/conf/nips/CaoCPL25","documentUrl":"http://papers.nips.cc/paper_files/paper/2025/hash/86beeac1799c083e4597d4aa17385a25-Abstract-Conference.html","pages":null},{"key":"conf/nips/GaoLLLGYXWSLS25","title":"GOOD: Training-Free Guided Diffusion Sampling for Out-of-Distribution Detection.","type":"Inproceedings","venue":"NeurIPS","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":null,"sourceUrl":"https://dblp.org/rec/conf/nips/GaoLLLGYXWSLS25","documentUrl":"http://papers.nips.cc/paper_files/paper/2025/hash/123fd8a56501194823c8e0dca00733df-Abstract-Conference.html","pages":null},{"key":"conf/nips/LiangRMTLGFOLGH25","title":"Feed-Forward Bullet-Time Reconstruction of Dynamic Scenes from Monocular Videos.","type":"Inproceedings","venue":"NeurIPS","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":null,"sourceUrl":"https://dblp.org/rec/conf/nips/LiangRMTLGFOLGH25","documentUrl":"http://papers.nips.cc/paper_files/paper/2025/hash/dee4c334b00c6f34061eb71d3a9df79b-Abstract-Conference.html","pages":null},{"key":"conf/nips/LiDHLLLPKLL25","title":"3EED: Ground Everything Everywhere in 3D.","type":"Inproceedings","venue":"NeurIPS","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":null,"sourceUrl":"https://dblp.org/rec/conf/nips/LiDHLLLPKLL25","documentUrl":"http://papers.nips.cc/paper_files/paper/2025/hash/e45be391e19850e39621a8579bb29ada-Abstract-Datasets_and_Benchmarks_Track.html","pages":null},{"key":"conf/nips/LiuHJZDZHHCQOZL25","title":"ShotBench: Expert-Level Cinematic Understanding in Vision-Language Models.","type":"Inproceedings","venue":"NeurIPS","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":null,"sourceUrl":"https://dblp.org/rec/conf/nips/LiuHJZDZHHCQOZL25","documentUrl":"http://papers.nips.cc/paper_files/paper/2025/hash/bc94f2e93a8b05573e8e787d35665ca6-Abstract-Conference.html","pages":null},{"key":"conf/nips/TanYWHGLL25","title":"Imagine360: Immersive 360 Video Generation from Perspective Anchor.","type":"Inproceedings","venue":"NeurIPS","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":null,"sourceUrl":"https://dblp.org/rec/conf/nips/TanYWHGLL25","documentUrl":"http://papers.nips.cc/paper_files/paper/2025/hash/cc83e97320000f4e08cb9e293b12cf7e-Abstract-Conference.html","pages":null},{"key":"conf/nips/WangYHYZWLP25","title":"GeneMAN: Generalizable Single-Image 3D Human Reconstruction from Multi-Source Human Data.","type":"Inproceedings","venue":"NeurIPS","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":null,"sourceUrl":"https://dblp.org/rec/conf/nips/WangYHYZWLP25","documentUrl":"http://papers.nips.cc/paper_files/paper/2025/hash/768c19273e20fa09147885d03da7550f-Abstract-Conference.html","pages":null},{"key":"conf/nips/WuYPXLLW25","title":"Video World Models with Long-term Spatial Memory.","type":"Inproceedings","venue":"NeurIPS","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":null,"sourceUrl":"https://dblp.org/rec/conf/nips/WuYPXLLW25","documentUrl":"http://papers.nips.cc/paper_files/paper/2025/hash/467655d26fcc207bca08915dc91964c6-Abstract-Conference.html","pages":null},{"key":"conf/nips/ZhangZCWLPLL25","title":"Hi3DEval: Advancing 3D Generation Evaluation with Hierarchical Validity.","type":"Inproceedings","venue":"NeurIPS","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":null,"sourceUrl":"https://dblp.org/rec/conf/nips/ZhangZCWLPLL25","documentUrl":"http://papers.nips.cc/paper_files/paper/2025/hash/42ffaddcc6edc9fb05ff9f9b49fca700-Abstract-Datasets_and_Benchmarks_Track.html","pages":null},{"key":"conf/nips/ZuoDKYJZSPLG25","title":"VideoLucy: Deep Memory Backtracking for Long Video Understanding.","type":"Inproceedings","venue":"NeurIPS","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":null,"sourceUrl":"https://dblp.org/rec/conf/nips/ZuoDKYJZSPLG25","documentUrl":"http://papers.nips.cc/paper_files/paper/2025/hash/24a2b1e2d4c3b20f09eb006d3d610777-Abstract-Conference.html","pages":null},{"key":"conf/siggraph/GuYLLDS0L000025","title":"Diffusion as Shader: 3D-aware Video Diffusion for Versatile Video Generation Control.","type":"Inproceedings","venue":"SIGGRAPH (Conference Paper Track)","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1145/3721238.3730607","sourceUrl":"https://dblp.org/rec/conf/siggraph/GuYLLDS0L000025","documentUrl":"https://doi.org/10.1145/3721238.3730607","pages":"62:1-62:12"},{"key":"conf/siggraph/Yang00WW0L25","title":"LayerPano3D: Layered 3D Panorama for Hyper-Immersive Scene Generation.","type":"Inproceedings","venue":"SIGGRAPH (Conference Paper Track)","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1145/3721238.3730643","sourceUrl":"https://dblp.org/rec/conf/siggraph/Yang00WW0L25","documentUrl":"https://doi.org/10.1145/3721238.3730643","pages":"109:1-109:10"},{"key":"conf/siggrapha/HeLLH0OL25","title":"Cut2Next: Generating Next Shot via In-Context Tuning.","type":"Inproceedings","venue":"SIGGRAPH Asia","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1145/3757377.3763896","sourceUrl":"https://dblp.org/rec/conf/siggrapha/HeLLH0OL25","documentUrl":"https://doi.org/10.1145/3757377.3763896","pages":"22:1-22:11"},{"key":"conf/wacv/Kong0CZPC025","title":"Calib3D: Calibrating Model Preferences for Reliable 3D Scene Understanding.","type":"Inproceedings","venue":"WACV","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/WACV61041.2025.00198","sourceUrl":"https://dblp.org/rec/conf/wacv/Kong0CZPC025","documentUrl":"https://doi.org/10.1109/WACV61041.2025.00198","pages":"1965-1978"},{"key":"journals/ijcv/HuHHPMXYL25","title":"HumanLiff: Layer-wise 3D Human Diffusion Model.","type":"Article","venue":"Int. J. Comput. Vis.","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.1007/S11263-025-02477-5","sourceUrl":"https://dblp.org/rec/journals/ijcv/HuHHPMXYL25","documentUrl":"https://doi.org/10.1007/S11263-025-02477-5","pages":"5938-5957"},{"key":"journals/ijcv/ShaoWL25","title":"Robust Sequential DeepFake Detection.","type":"Article","venue":"Int. J. Comput. Vis.","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.1007/S11263-024-02339-6","sourceUrl":"https://dblp.org/rec/journals/ijcv/ShaoWL25","documentUrl":"https://doi.org/10.1007/S11263-024-02339-6","pages":"3278-3295"},{"key":"journals/ijcv/ShaoWNL25","title":"DeepFake-Adapter: Dual-Level Adapter for DeepFake Detection.","type":"Article","venue":"Int. J. Comput. Vis.","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.1007/S11263-024-02274-6","sourceUrl":"https://dblp.org/rec/journals/ijcv/ShaoWNL25","documentUrl":"https://doi.org/10.1007/S11263-024-02274-6","pages":"3613-3628"},{"key":"journals/ijcv/TangWZCHHLLZW25","title":"Real-Time Neural Radiance Talking Portrait Synthesis via Audio-Spatial Decomposition.","type":"Article","venue":"Int. J. Comput. Vis.","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.1007/S11263-025-02481-9","sourceUrl":"https://dblp.org/rec/journals/ijcv/TangWZCHHLLZW25","documentUrl":"https://doi.org/10.1007/S11263-025-02481-9","pages":"6362-6373"},{"key":"journals/ijcv/WangCMZHWYHYYGWSJCLDLQL25","title":"LaVie: High-Quality Video Generation with Cascaded Latent Diffusion Models.","type":"Article","venue":"Int. J. Comput. Vis.","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.1007/S11263-024-02295-1","sourceUrl":"https://dblp.org/rec/journals/ijcv/WangCMZHWYHYYGWSJCLDLQL25","documentUrl":"https://doi.org/10.1007/S11263-024-02295-1","pages":"3059-3078"},{"key":"journals/ijcv/XieLLLOL25","title":"MosaicFusion: Diffusion Models as Data Augmenters for Large Vocabulary Instance Segmentation.","type":"Article","venue":"Int. J. Comput. Vis.","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.1007/S11263-024-02223-3","sourceUrl":"https://dblp.org/rec/journals/ijcv/XieLLLOL25","documentUrl":"https://doi.org/10.1007/S11263-024-02223-3","pages":"1456-1475"},{"key":"journals/ijcv/ZhangSZHYWSQSL25","title":"Bamboo: Building Mega-Scale Vision Dataset Continually with Human-Machine Synergy.","type":"Article","venue":"Int. J. Comput. Vis.","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.1007/S11263-025-02450-2","sourceUrl":"https://dblp.org/rec/journals/ijcv/ZhangSZHYWSQSL25","documentUrl":"https://doi.org/10.1007/S11263-025-02450-2","pages":"5806-5821"},{"key":"journals/ijcv/ZhouCYZL25","title":"Revisiting Class-Incremental Learning with Pre-Trained Models: Generalizability and Adaptivity are All You Need.","type":"Article","venue":"Int. J. Comput. Vis.","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.1007/S11263-024-02218-0","sourceUrl":"https://dblp.org/rec/journals/ijcv/ZhouCYZL25","documentUrl":"https://doi.org/10.1007/S11263-024-02218-0","pages":"1012-1032"},{"key":"journals/pami/CaoHWPL25","title":"DiffTF++: 3D-Aware Diffusion Transformer for Large-Vocabulary 3D Generation.","type":"Article","venue":"IEEE Trans. Pattern Anal. Mach. Intell.","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.1109/TPAMI.2025.3528247","sourceUrl":"https://dblp.org/rec/journals/pami/CaoHWPL25","documentUrl":"https://doi.org/10.1109/TPAMI.2025.3528247","pages":"3018-3030"},{"key":"journals/pami/KongXRZPCOL25","title":"Multi-Modal Data-Efficient 3D Scene Understanding for Autonomous Driving.","type":"Article","venue":"IEEE Trans. Pattern Anal. Mach. Intell.","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.1109/TPAMI.2025.3535625","sourceUrl":"https://dblp.org/rec/journals/pami/KongXRZPCOL25","documentUrl":"https://doi.org/10.1109/TPAMI.2025.3535625","pages":"3748-3765"},{"key":"journals/pami/LiLCLLL25","title":"Benchmarking and Analyzing Generative Data for Visual Recognition.","type":"Article","venue":"IEEE Trans. Pattern Anal. Mach. Intell.","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.1109/TPAMI.2025.3572476","sourceUrl":"https://dblp.org/rec/journals/pami/LiLCLLL25","documentUrl":"https://doi.org/10.1109/TPAMI.2025.3572476","pages":"7675-7688"},{"key":"journals/pami/LiZCWPCYLL25","title":"Otter: A Multi-Modal Model With In-Context Instruction Tuning.","type":"Article","venue":"IEEE Trans. Pattern Anal. Mach. Intell.","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.1109/TPAMI.2025.3571946","sourceUrl":"https://dblp.org/rec/journals/pami/LiZCWPCYLL25","documentUrl":"https://doi.org/10.1109/TPAMI.2025.3571946","pages":"7543-7557"},{"key":"journals/pami/XieKZRPCL25","title":"Benchmarking and Improving Bird's Eye View Perception Robustness in Autonomous Driving.","type":"Article","venue":"IEEE Trans. Pattern Anal. Mach. Intell.","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.1109/TPAMI.2025.3535960","sourceUrl":"https://dblp.org/rec/journals/pami/XieKZRPCL25","documentUrl":"https://doi.org/10.1109/TPAMI.2025.3535960","pages":"3878-3894"},{"key":"journals/pami/ZhangZL25","title":"Neural Prompt Search.","type":"Article","venue":"IEEE Trans. Pattern Anal. Mach. Intell.","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.1109/TPAMI.2024.3435939","sourceUrl":"https://dblp.org/rec/journals/pami/ZhangZL25","documentUrl":"https://doi.org/10.1109/TPAMI.2024.3435939","pages":"5268-5280"},{"key":"journals/pami/ZhouZWNYZL25","title":"Learning Without Forgetting for Vision-Language Models.","type":"Article","venue":"IEEE Trans. Pattern Anal. Mach. Intell.","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.1109/TPAMI.2025.3540889","sourceUrl":"https://dblp.org/rec/journals/pami/ZhouZWNYZL25","documentUrl":"https://doi.org/10.1109/TPAMI.2025.3540889","pages":"4489-4504"},{"key":"journals/pr/ZhangWYSL25","title":"Robust face anti-spoofing with Dual Probabilistic Modeling.","type":"Article","venue":"Pattern Recognit.","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.1016/J.PATCOG.2025.111700","sourceUrl":"https://dblp.org/rec/journals/pr/ZhangWYSL25","documentUrl":"https://doi.org/10.1016/J.PATCOG.2025.111700","pages":"111700"},{"key":"journals/tmlr/0080ZGZ00ZZL0L25","title":"LLaVA-OneVision: Easy Visual Task Transfer.","type":"Article","venue":"Trans. Mach. Learn. Res.","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":null,"sourceUrl":"https://dblp.org/rec/journals/tmlr/0080ZGZ00ZZL0L25","documentUrl":"https://openreview.net/forum?id=zKv8qULV6n","pages":null},{"key":"journals/tmlr/Ma0CJ0LC025","title":"Latte: Latent Diffusion Transformer for Video Generation.","type":"Article","venue":"Trans. Mach. Learn. Res.","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":null,"sourceUrl":"https://dblp.org/rec/journals/tmlr/Ma0CJ0LC025","documentUrl":"https://openreview.net/forum?id=ntGPYNUF3t","pages":null},{"key":"journals/tmlr/MiyaiYZMLYIJ0L025","title":"Generalized Out-of-Distribution Detection and Beyond in Vision Language Model Era: A Survey.","type":"Article","venue":"Trans. Mach. Learn. Res.","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":null,"sourceUrl":"https://dblp.org/rec/journals/tmlr/MiyaiYZMLYIJ0L025","documentUrl":"https://openreview.net/forum?id=FO3IA4lUEY","pages":null},{"key":"journals/tmlr/ZhangWLLMLL25","title":"LLaVA-Video: Video Instruction Tuning With Synthetic Data.","type":"Article","venue":"Trans. Mach. Learn. Res.","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":null,"sourceUrl":"https://dblp.org/rec/journals/tmlr/ZhangWLLMLL25","documentUrl":"https://openreview.net/forum?id=EElFGvt39K","pages":null},{"key":"journals/tmlr/ZhangZLZYZWTLL25","title":"Long Context Transfer from Language to Vision.","type":"Article","venue":"Trans. Mach. Learn. Res.","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":null,"sourceUrl":"https://dblp.org/rec/journals/tmlr/ZhangZLZYZWTLL25","documentUrl":"https://openreview.net/forum?id=30RAWQVGlx","pages":null}],"preprints":[],"excludedFormal":[],"excludedHomonyms":[{"key":"journals/tmc/LiuZYSYL25","title":"ReflexGest: Recognizing Hand Gestures Under VLC-Capable Lamps.","type":"Article","venue":"IEEE Trans. Mob. Comput.","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.1109/TMC.2025.3545340","sourceUrl":"https://dblp.org/rec/journals/tmc/LiuZYSYL25","documentUrl":"https://doi.org/10.1109/TMC.2025.3545340","pages":"6583-6594","exclusionReason":"Publisher-deposited Crossref metadata assigns Ziwei Liu to Sichuan University with ORCID 0000-0001-6206-637X, not NTU Ziwei Liu (0000-0002-4220-5958).","exclusionSource":"https://api.crossref.org/works/10.1109/TMC.2025.3545340"},{"key":"journals/inffus/YangLCYSF25","title":"Visible light human activity recognition driven by generative language model.","type":"Article","venue":"Inf. Fusion","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.1016/J.INFFUS.2025.103159","sourceUrl":"https://dblp.org/rec/journals/inffus/YangLCYSF25","documentUrl":"https://doi.org/10.1016/J.INFFUS.2025.103159","pages":"103159","exclusionReason":"DBLP paper signature uses the same Sichuan University Ziwei Liu ORCID 0000-0001-6206-637X as ReflexGest; publisher author list and Sichuan author profile confirm this separate visible-light sensing group.","exclusionSource":"https://www.sciencedirect.com/science/article/pii/S1566253525002325"}],"sourceWarning":true,"preprintStatus":"partial_identity_review","unassignedCandidates":[{"key":"journals/corr/abs-2501-03847","title":"Diffusion as Shader: 3D-aware Video Diffusion for Versatile Video Generation Control.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2501.03847","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2501-03847","documentUrl":"https://doi.org/10.48550/ARXIV.2501.03847","pages":null,"reviewStatus":"Preprint identity not separately audited after mixed-profile contamination was detected; excluded from reported totals."},{"key":"journals/corr/abs-2501-04003","title":"Are VLMs Ready for Autonomous Driving? An Empirical Study from the Reliability, Data, and Metric Perspectives.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2501.04003","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2501-04003","documentUrl":"https://doi.org/10.48550/ARXIV.2501.04003","pages":null,"reviewStatus":"Preprint identity not separately audited after mixed-profile contamination was detected; excluded from reported totals."},{"key":"journals/corr/abs-2501-04004","title":"LiMoE: Mixture of LiDAR Representation Learners from Automotive Scenes.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2501.04004","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2501-04004","documentUrl":"https://doi.org/10.48550/ARXIV.2501.04004","pages":null,"reviewStatus":"Preprint identity not separately audited after mixed-profile contamination was detected; excluded from reported totals."},{"key":"journals/corr/abs-2501-04005","title":"LargeAD: Large-Scale Cross-Sensor Data Pretraining for Autonomous Driving.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2501.04005","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2501-04005","documentUrl":"https://doi.org/10.48550/ARXIV.2501.04005","pages":null,"reviewStatus":"Preprint identity not separately audited after mixed-profile contamination was detected; excluded from reported totals."},{"key":"journals/corr/abs-2501-08453","title":"Vchitect-2.0: Parallel Transformer for Scaling Up Video Diffusion Models.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2501.08453","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2501-08453","documentUrl":"https://doi.org/10.48550/ARXIV.2501.08453","pages":null,"reviewStatus":"Preprint identity not separately audited after mixed-profile contamination was detected; excluded from reported totals."},{"key":"journals/corr/abs-2501-08983","title":"CityDreamer4D: Compositional Generative Model of Unbounded 4D Cities.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2501.08983","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2501-08983","documentUrl":"https://doi.org/10.48550/ARXIV.2501.08983","pages":null,"reviewStatus":"Preprint identity not separately audited after mixed-profile contamination was detected; excluded from reported totals."},{"key":"journals/corr/abs-2501-08994","title":"RepVideo: Rethinking Cross-Layer Representation for Video Generation.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2501.08994","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2501-08994","documentUrl":"https://doi.org/10.48550/ARXIV.2501.08994","pages":null,"reviewStatus":"Preprint identity not separately audited after mixed-profile contamination was detected; excluded from reported totals."},{"key":"journals/corr/abs-2501-09782","title":"SMPLest-X: Ultimate Scaling for Expressive Human Pose and Shape Estimation.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2501.09782","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2501-09782","documentUrl":"https://doi.org/10.48550/ARXIV.2501.09782","pages":null,"reviewStatus":"Preprint identity not separately audited after mixed-profile contamination was detected; excluded from reported totals."},{"key":"journals/corr/abs-2501-13826","title":"Video-MMMU: Evaluating Knowledge Acquisition from Multi-Discipline Professional Videos.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2501.13826","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2501-13826","documentUrl":"https://doi.org/10.48550/ARXIV.2501.13826","pages":null,"reviewStatus":"Preprint identity not separately audited after mixed-profile contamination was detected; excluded from reported totals."},{"key":"journals/corr/abs-2502-04328","title":"Ola: Pushing the Frontiers of Omni-Modal Language Model with Progressive Modality Alignment.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2502.04328","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2502-04328","documentUrl":"https://doi.org/10.48550/ARXIV.2502.04328","pages":null,"reviewStatus":"Preprint identity not separately audited after mixed-profile contamination was detected; excluded from reported totals."},{"key":"journals/corr/abs-2502-06782","title":"Lumina-Video: Efficient and Flexible Video Generation with Multi-scale Next-DiT.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2502.06782","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2502-06782","documentUrl":"https://doi.org/10.48550/ARXIV.2502.06782","pages":null,"reviewStatus":"Preprint identity not separately audited after mixed-profile contamination was detected; excluded from reported totals."},{"key":"journals/corr/abs-2502-16235","title":"Dynamic Parallel Tree Search for Efficient LLM Reasoning.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2502.16235","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2502-16235","documentUrl":"https://doi.org/10.48550/ARXIV.2502.16235","pages":null,"reviewStatus":"Preprint identity not separately audited after mixed-profile contamination was detected; excluded from reported totals."},{"key":"journals/corr/abs-2503-03803","title":"EgoLife: Towards Egocentric Life Assistant.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2503.03803","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-03803","documentUrl":"https://doi.org/10.48550/ARXIV.2503.03803","pages":null,"reviewStatus":"Preprint identity not separately audited after mixed-profile contamination was detected; excluded from reported totals."},{"key":"journals/corr/abs-2503-09942","title":"Cosh-DiT: Co-Speech Gesture Video Synthesis via Hybrid Audio-Visual Diffusion Transformers.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2503.09942","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-09942","documentUrl":"https://doi.org/10.48550/ARXIV.2503.09942","pages":null,"reviewStatus":"Preprint identity not separately audited after mixed-profile contamination was detected; excluded from reported totals."},{"key":"journals/corr/abs-2503-12605","title":"Multimodal Chain-of-Thought Reasoning: A Comprehensive Survey.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2503.12605","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-12605","documentUrl":"https://doi.org/10.48550/ARXIV.2503.12605","pages":null,"reviewStatus":"Preprint identity not separately audited after mixed-profile contamination was detected; excluded from reported totals."},{"key":"journals/corr/abs-2503-18886","title":"CFG-Zero*: Improved Classifier-Free Guidance for Flow Matching Models.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2503.18886","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-18886","documentUrl":"https://doi.org/10.48550/ARXIV.2503.18886","pages":null,"reviewStatus":"Preprint identity not separately audited after mixed-profile contamination was detected; excluded from reported totals."},{"key":"journals/corr/abs-2503-19824","title":"AudCast: Audio-Driven Human Video Generation by Cascaded Diffusion Transformers.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2503.19824","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-19824","documentUrl":"https://doi.org/10.48550/ARXIV.2503.19824","pages":null,"reviewStatus":"Preprint identity not separately audited after mixed-profile contamination was detected; excluded from reported totals."},{"key":"journals/corr/abs-2503-19912","title":"SuperFlow++: Enhanced Spatiotemporal Consistency for Cross-Modal Data Pretraining.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2503.19912","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-19912","documentUrl":"https://doi.org/10.48550/ARXIV.2503.19912","pages":null,"reviewStatus":"Preprint identity not separately audited after mixed-profile contamination was detected; excluded from reported totals."},{"key":"journals/corr/abs-2503-20785","title":"Free4D: Tuning-free 4D Scene Generation with Spatial-Temporal Consistency.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2503.20785","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-20785","documentUrl":"https://doi.org/10.48550/ARXIV.2503.20785","pages":null,"reviewStatus":"Preprint identity not separately audited after mixed-profile contamination was detected; excluded from reported totals."},{"key":"journals/corr/abs-2503-21745","title":"3DGen-Bench: Comprehensive Benchmark Suite for 3D Generative Models.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2503.21745","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-21745","documentUrl":"https://doi.org/10.48550/ARXIV.2503.21745","pages":null,"reviewStatus":"Preprint identity not separately audited after mixed-profile contamination was detected; excluded from reported totals."},{"key":"journals/corr/abs-2503-21755","title":"VBench-2.0: Advancing Video Generation Benchmark Suite for Intrinsic Faithfulness.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2503.21755","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-21755","documentUrl":"https://doi.org/10.48550/ARXIV.2503.21755","pages":null,"reviewStatus":"Preprint identity not separately audited after mixed-profile contamination was detected; excluded from reported totals."},{"key":"journals/corr/abs-2504-07083","title":"GenDoP: Auto-regressive Camera Trajectory Generation as a Director of Photography.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2504.07083","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2504-07083","documentUrl":"https://doi.org/10.48550/ARXIV.2504.07083","pages":null,"reviewStatus":"Preprint identity not separately audited after mixed-profile contamination was detected; excluded from reported totals."},{"key":"journals/corr/abs-2505-05474","title":"3D Scene Generation: A Survey.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2505.05474","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-05474","documentUrl":"https://doi.org/10.48550/ARXIV.2505.05474","pages":null,"reviewStatus":"Preprint identity not separately audited after mixed-profile contamination was detected; excluded from reported totals."},{"key":"journals/corr/abs-2505-15816","title":"Streamline Without Sacrifice - Squeeze out Computation Redundancy in LMM.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2505.15816","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-15816","documentUrl":"https://doi.org/10.48550/ARXIV.2505.15816","pages":null,"reviewStatus":"Preprint identity not separately audited after mixed-profile contamination was detected; excluded from reported totals."},{"key":"journals/corr/abs-2506-03123","title":"DCM: Dual-Expert Consistency Model for Efficient and High-Quality Video Generation.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2506.03123","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-03123","documentUrl":"https://doi.org/10.48550/ARXIV.2506.03123","pages":null,"reviewStatus":"Preprint identity not separately audited after mixed-profile contamination was detected; excluded from reported totals."},{"key":"journals/corr/abs-2506-04421","title":"HMAR: Efficient Hierarchical Masked Auto-Regressive Image Generation.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2506.04421","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-04421","documentUrl":"https://doi.org/10.48550/ARXIV.2506.04421","pages":null,"reviewStatus":"Preprint identity not separately audited after mixed-profile contamination was detected; excluded from reported totals."},{"key":"journals/corr/abs-2506-05284","title":"Video World Models with Long-term Spatial Memory.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2506.05284","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-05284","documentUrl":"https://doi.org/10.48550/ARXIV.2506.05284","pages":null,"reviewStatus":"Preprint identity not separately audited after mixed-profile contamination was detected; excluded from reported totals."},{"key":"journals/corr/abs-2506-07986","title":"Rethinking Cross-Modal Interaction in Multimodal Diffusion Transformers.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2506.07986","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-07986","documentUrl":"https://doi.org/10.48550/ARXIV.2506.07986","pages":null,"reviewStatus":"Preprint identity not separately audited after mixed-profile contamination was detected; excluded from reported totals."},{"key":"journals/corr/abs-2506-12409","title":"Branch, or Layer? Zeroth-Order Optimization for Continual Learning of Vision-Language Models.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2506.12409","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-12409","documentUrl":"https://doi.org/10.48550/ARXIV.2506.12409","pages":null,"reviewStatus":"Preprint identity not separately audited after mixed-profile contamination was detected; excluded from reported totals."},{"key":"journals/corr/abs-2506-13654","title":"Ego-R1: Chain-of-Tool-Thought for Ultra-Long Egocentric Video Reasoning.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2506.13654","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-13654","documentUrl":"https://doi.org/10.48550/ARXIV.2506.13654","pages":null,"reviewStatus":"Preprint identity not separately audited after mixed-profile contamination was detected; excluded from reported totals."},{"key":"journals/corr/abs-2506-20670","title":"MMSearch-R1: Incentivizing LMMs to Search.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2506.20670","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-20670","documentUrl":"https://doi.org/10.48550/ARXIV.2506.20670","pages":null,"reviewStatus":"Preprint identity not separately audited after mixed-profile contamination was detected; excluded from reported totals."},{"key":"journals/corr/abs-2506-21356","title":"ShotBench: Expert-Level Cinematic Understanding in Vision-Language Models.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2506.21356","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-21356","documentUrl":"https://doi.org/10.48550/ARXIV.2506.21356","pages":null,"reviewStatus":"Preprint identity not separately audited after mixed-profile contamination was detected; excluded from reported totals."},{"key":"journals/corr/abs-2507-01953","title":"FreeMorph: Tuning-Free Generalized Image Morphing with Diffusion Model.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2507.01953","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2507-01953","documentUrl":"https://doi.org/10.48550/ARXIV.2507.01953","pages":null,"reviewStatus":"Preprint identity not separately audited after mixed-profile contamination was detected; excluded from reported totals."},{"key":"journals/corr/abs-2507-12465","title":"PhysX-3D: Physical-Grounded 3D Asset Generation.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2507.12465","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2507-12465","documentUrl":"https://doi.org/10.48550/ARXIV.2507.12465","pages":null,"reviewStatus":"Preprint identity not separately audited after mixed-profile contamination was detected; excluded from reported totals."},{"key":"journals/corr/abs-2507-21045","title":"Reconstructing 4D Spatial Intelligence: A Survey.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2507.21045","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2507-21045","documentUrl":"https://doi.org/10.48550/ARXIV.2507.21045","pages":null,"reviewStatus":"Preprint identity not separately audited after mixed-profile contamination was detected; excluded from reported totals."},{"key":"journals/corr/abs-2508-00599","title":"DPoser-X: Diffusion Model as Robust 3D Whole-body Human Pose Prior.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2508.00599","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-00599","documentUrl":"https://doi.org/10.48550/ARXIV.2508.00599","pages":null,"reviewStatus":"Preprint identity not separately audited after mixed-profile contamination was detected; excluded from reported totals."},{"key":"journals/corr/abs-2508-03694","title":"LongVie: Multimodal-Guided Controllable Ultra-Long Video Generation.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2508.03694","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-03694","documentUrl":"https://doi.org/10.48550/ARXIV.2508.03694","pages":null,"reviewStatus":"Preprint identity not separately audited after mixed-profile contamination was detected; excluded from reported totals."},{"key":"journals/corr/abs-2508-05609","title":"Hi3DEval: Advancing 3D Generation Evaluation with Hierarchical Validity.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2508.05609","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-05609","documentUrl":"https://doi.org/10.48550/ARXIV.2508.05609","pages":null,"reviewStatus":"Preprint identity not separately audited after mixed-profile contamination was detected; excluded from reported totals."},{"key":"journals/corr/abs-2508-08244","title":"Cut2Next: Generating Next Shot via In-Context Tuning.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2508.08244","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-08244","documentUrl":"https://doi.org/10.48550/ARXIV.2508.08244","pages":null,"reviewStatus":"Preprint identity not separately audited after mixed-profile contamination was detected; excluded from reported totals."},{"key":"journals/corr/abs-2508-13013","title":"EgoTwin: Dreaming Body and View in First Person.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2508.13013","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-13013","documentUrl":"https://doi.org/10.48550/ARXIV.2508.13013","pages":null,"reviewStatus":"Preprint identity not separately audited after mixed-profile contamination was detected; excluded from reported totals."},{"key":"journals/corr/abs-2508-13142","title":"Has GPT-5 Achieved Spatial Intelligence? An Empirical Study.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2508.13142","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-13142","documentUrl":"https://doi.org/10.48550/ARXIV.2508.13142","pages":null,"reviewStatus":"Preprint identity not separately audited after mixed-profile contamination was detected; excluded from reported totals."},{"key":"journals/corr/abs-2508-13154","title":"4DNeX: Feed-Forward 4D Generative Modeling Made Easy.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2508.13154","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-13154","documentUrl":"https://doi.org/10.48550/ARXIV.2508.13154","pages":null,"reviewStatus":"Preprint identity not separately audited after mixed-profile contamination was detected; excluded from reported totals."},{"key":"journals/corr/abs-2508-15228","title":"Collaborative Multi-Modal Coding for High-Quality 3D Generation.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2508.15228","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-15228","documentUrl":"https://doi.org/10.48550/ARXIV.2508.15228","pages":null,"reviewStatus":"Preprint identity not separately audited after mixed-profile contamination was detected; excluded from reported totals."},{"key":"journals/corr/abs-2508-15774","title":"CineScale: Free Lunch in High-Resolution Cinematic Visual Generation.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2508.15774","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-15774","documentUrl":"https://doi.org/10.48550/ARXIV.2508.15774","pages":null,"reviewStatus":"Preprint identity not separately audited after mixed-profile contamination was detected; excluded from reported totals."},{"key":"journals/corr/abs-2509-17120","title":"Stencil: Subject-Driven Generation with Context Guidance.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2509.17120","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-17120","documentUrl":"https://doi.org/10.48550/ARXIV.2509.17120","pages":null,"reviewStatus":"Preprint identity not separately audited after mixed-profile contamination was detected; excluded from reported totals."},{"key":"journals/corr/abs-2509-20146","title":"EchoBench: Benchmarking Sycophancy in Medical Large Vision-Language Models.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2509.20146","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-20146","documentUrl":"https://doi.org/10.48550/ARXIV.2509.20146","pages":null,"reviewStatus":"Preprint identity not separately audited after mixed-profile contamination was detected; excluded from reported totals."},{"key":"journals/corr/abs-2509-23661","title":"LLaVA-OneVision-1.5: Fully Open Framework for Democratized Multimodal Training.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2509.23661","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-23661","documentUrl":"https://doi.org/10.48550/ARXIV.2509.23661","pages":null,"reviewStatus":"Preprint identity not separately audited after mixed-profile contamination was detected; excluded from reported totals."},{"key":"journals/corr/abs-2509-24897","title":"RealUnify: Do Unified Models Truly Benefit from Unification? A Comprehensive Benchmark.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2509.24897","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-24897","documentUrl":"https://doi.org/10.48550/ARXIV.2509.24897","pages":null,"reviewStatus":"Preprint identity not separately audited after mixed-profile contamination was detected; excluded from reported totals."},{"key":"journals/corr/abs-2509-25190","title":"Visual Jigsaw Post-Training Improves MLLMs.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2509.25190","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-25190","documentUrl":"https://doi.org/10.48550/ARXIV.2509.25190","pages":null,"reviewStatus":"Preprint identity not separately audited after mixed-profile contamination was detected; excluded from reported totals."},{"key":"journals/corr/abs-2510-05094","title":"VChain: Chain-of-Visual-Thought for Reasoning in Video Generation.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2510.05094","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-05094","documentUrl":"https://doi.org/10.48550/ARXIV.2510.05094","pages":null,"reviewStatus":"Preprint identity not separately audited after mixed-profile contamination was detected; excluded from reported totals."},{"key":"journals/corr/abs-2510-12422","title":"VideoLucy: Deep Memory Backtracking for Long Video Understanding.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2510.12422","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-12422","documentUrl":"https://doi.org/10.48550/ARXIV.2510.12422","pages":null,"reviewStatus":"Preprint identity not separately audited after mixed-profile contamination was detected; excluded from reported totals."},{"key":"journals/corr/abs-2510-13759","title":"Uni-MMMU: A Massive Multi-discipline Multimodal Unified Benchmark.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2510.13759","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-13759","documentUrl":"https://doi.org/10.48550/ARXIV.2510.13759","pages":null,"reviewStatus":"Preprint identity not separately audited after mixed-profile contamination was detected; excluded from reported totals."},{"key":"journals/corr/abs-2510-14955","title":"RealDPO: Real or Not Real, that is the Preference.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2510.14955","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-14955","documentUrl":"https://doi.org/10.48550/ARXIV.2510.14955","pages":null,"reviewStatus":"Preprint identity not separately audited after mixed-profile contamination was detected; excluded from reported totals."},{"key":"journals/corr/abs-2510-14979","title":"From Pixels to Words - Towards Native Vision-Language Primitives at Scale.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2510.14979","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-14979","documentUrl":"https://doi.org/10.48550/ARXIV.2510.14979","pages":null,"reviewStatus":"Preprint identity not separately audited after mixed-profile contamination was detected; excluded from reported totals."},{"key":"journals/corr/abs-2510-17131","title":"GOOD: Training-Free Guided Diffusion Sampling for Out-of-Distribution Detection.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2510.17131","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-17131","documentUrl":"https://doi.org/10.48550/ARXIV.2510.17131","pages":null,"reviewStatus":"Preprint identity not separately audited after mixed-profile contamination was detected; excluded from reported totals."},{"key":"journals/corr/abs-2510-18212","title":"A Definition of AGI.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2510.18212","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-18212","documentUrl":"https://doi.org/10.48550/ARXIV.2510.18212","pages":null,"reviewStatus":"Preprint identity not separately audited after mixed-profile contamination was detected; excluded from reported totals."},{"key":"journals/corr/abs-2510-22706","title":"IGGT: Instance-Grounded Geometry Transformer for Semantic 3D Reconstruction.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2510.22706","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-22706","documentUrl":"https://doi.org/10.48550/ARXIV.2510.22706","pages":null,"reviewStatus":"Preprint identity not separately audited after mixed-profile contamination was detected; excluded from reported totals."},{"key":"journals/corr/abs-2510-26794","title":"The Quest for Generalizable Motion Generation: Data, Model, and Evaluation.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2510.26794","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-26794","documentUrl":"https://doi.org/10.48550/ARXIV.2510.26794","pages":null,"reviewStatus":"Preprint identity not separately audited after mixed-profile contamination was detected; excluded from reported totals."},{"key":"journals/corr/abs-2510-26796","title":"SEE4D: Pose-Free 4D Generation via Auto-Regressive Video Inpainting.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2510.26796","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-26796","documentUrl":"https://doi.org/10.48550/ARXIV.2510.26796","pages":null,"reviewStatus":"Preprint identity not separately audited after mixed-profile contamination was detected; excluded from reported totals."},{"key":"journals/corr/abs-2511-01755","title":"3EED: Ground Everything Everywhere in 3D.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2511.01755","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2511-01755","documentUrl":"https://doi.org/10.48550/ARXIV.2511.01755","pages":null,"reviewStatus":"Preprint identity not separately audited after mixed-profile contamination was detected; excluded from reported totals."},{"key":"journals/corr/abs-2511-08585","title":"Simulating the Visual World with Artificial Intelligence: A Roadmap.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2511.08585","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2511-08585","documentUrl":"https://doi.org/10.48550/ARXIV.2511.08585","pages":null,"reviewStatus":"Preprint identity not separately audited after mixed-profile contamination was detected; excluded from reported totals."},{"key":"journals/corr/abs-2511-10560","title":"OmniVGGT: Omni-Modality Driven Visual Geometry Grounded Transformer.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2511.10560","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2511-10560","documentUrl":"https://doi.org/10.48550/ARXIV.2511.10560","pages":null,"reviewStatus":"Preprint identity not separately audited after mixed-profile contamination was detected; excluded from reported totals."},{"key":"journals/corr/abs-2511-13648","title":"PhysX-Anything: Simulation-Ready Physical 3D Assets from Single Image.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2511.13648","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2511-13648","documentUrl":"https://doi.org/10.48550/ARXIV.2511.13648","pages":null,"reviewStatus":"Preprint identity not separately audited after mixed-profile contamination was detected; excluded from reported totals."},{"key":"journals/corr/abs-2511-13719","title":"Scaling Spatial Intelligence with Multimodal Foundation Models.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2511.13719","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2511-13719","documentUrl":"https://doi.org/10.48550/ARXIV.2511.13719","pages":null,"reviewStatus":"Preprint identity not separately audited after mixed-profile contamination was detected; excluded from reported totals."},{"key":"journals/corr/abs-2511-15169","title":"SafeRBench: A Comprehensive Benchmark for Safety Assessment in Large Reasoning Models.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2511.15169","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2511-15169","documentUrl":"https://doi.org/10.48550/ARXIV.2511.15169","pages":null,"reviewStatus":"Preprint identity not separately audited after mixed-profile contamination was detected; excluded from reported totals."},{"key":"journals/corr/abs-2511-16334","title":"OpenMMReasoner: Pushing the Frontiers for Multimodal Reasoning with an Open and General Recipe.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2511.16334","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2511-16334","documentUrl":"https://doi.org/10.48550/ARXIV.2511.16334","pages":null,"reviewStatus":"Preprint identity not separately audited after mixed-profile contamination was detected; excluded from reported totals."},{"key":"journals/corr/abs-2512-02982","title":"U4D: Uncertainty-Aware 4D World Modeling from LiDAR Sequences.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2512.02982","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-02982","documentUrl":"https://doi.org/10.48550/ARXIV.2512.02982","pages":null,"reviewStatus":"Preprint identity not separately audited after mixed-profile contamination was detected; excluded from reported totals."},{"key":"journals/corr/abs-2512-03905","title":"Zero-Shot Video Translation and Editing with Frame Spatial-Temporal Correspondence.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2512.03905","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-03905","documentUrl":"https://doi.org/10.48550/ARXIV.2512.03905","pages":null,"reviewStatus":"Preprint identity not separately audited after mixed-profile contamination was detected; excluded from reported totals."},{"key":"journals/corr/abs-2512-05115","title":"Light-X: Generative 4D Video Rendering with Camera and Illumination Control.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2512.05115","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-05115","documentUrl":"https://doi.org/10.48550/ARXIV.2512.05115","pages":null,"reviewStatus":"Preprint identity not separately audited after mixed-profile contamination was detected; excluded from reported totals."},{"key":"journals/corr/abs-2512-10958","title":"WorldLens: Full-Spectrum Evaluations of Driving World Models in Real World.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2512.10958","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-10958","documentUrl":"https://doi.org/10.48550/ARXIV.2512.10958","pages":null,"reviewStatus":"Preprint identity not separately audited after mixed-profile contamination was detected; excluded from reported totals."},{"key":"journals/corr/abs-2512-13604","title":"LongVie 2: Multimodal Controllable Ultra-Long Video World Model.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2512.13604","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-13604","documentUrl":"https://doi.org/10.48550/ARXIV.2512.13604","pages":null,"reviewStatus":"Preprint identity not separately audited after mixed-profile contamination was detected; excluded from reported totals."},{"key":"journals/corr/abs-2512-16760","title":"Vision-Language-Action Models for Autonomous Driving: Past, Present, and Future.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2512.16760","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-16760","documentUrl":"https://doi.org/10.48550/ARXIV.2512.16760","pages":null,"reviewStatus":"Preprint identity not separately audited after mixed-profile contamination was detected; excluded from reported totals."},{"key":"journals/corr/abs-2512-19693","title":"The Prism Hypothesis: Harmonizing Semantic and Pixel Representations via Unified Autoencoding.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2512.19693","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-19693","documentUrl":"https://doi.org/10.48550/ARXIV.2512.19693","pages":null,"reviewStatus":"Preprint identity not separately audited after mixed-profile contamination was detected; excluded from reported totals."},{"key":"journals/corr/abs-2512-21338","title":"HiStream: Efficient High-Resolution Video Generation via Redundancy-Eliminated Streaming.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2512.21338","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-21338","documentUrl":"https://doi.org/10.48550/ARXIV.2512.21338","pages":null,"reviewStatus":"Preprint identity not separately audited after mixed-profile contamination was detected; excluded from reported totals."}],"labName":"MMLab@NTU","labUrl":"https://www.mmlab-ntu.com/","labEvidence":"本人简介明确 Associate Professor in MMLab@NTU 并直接链接。此为共享实验室，不代表个人独占的 Lab 论文总量。","labSourceUrl":"https://liuziwei7.github.io/","affiliationZh":"Nanyang Technological University","excludedOther":[],"knownPreprintMinimum2025":null,"excludedMisattributed":[{"key":"journals/tmc/LiuZYSYL25","title":"ReflexGest: Recognizing Hand Gestures Under VLC-Capable Lamps.","type":"Article","venue":"IEEE Trans. Mob. Comput.","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.1109/TMC.2025.3545340","sourceUrl":"https://dblp.org/rec/journals/tmc/LiuZYSYL25","documentUrl":"https://doi.org/10.1109/TMC.2025.3545340","pages":"6583-6594","exclusionReason":"Publisher-deposited Crossref metadata assigns Ziwei Liu to Sichuan University with ORCID 0000-0001-6206-637X, not NTU Ziwei Liu (0000-0002-4220-5958).","exclusionSource":"https://api.crossref.org/works/10.1109/TMC.2025.3545340"},{"key":"journals/inffus/YangLCYSF25","title":"Visible light human activity recognition driven by generative language model.","type":"Article","venue":"Inf. Fusion","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.1016/J.INFFUS.2025.103159","sourceUrl":"https://dblp.org/rec/journals/inffus/YangLCYSF25","documentUrl":"https://doi.org/10.1016/J.INFFUS.2025.103159","pages":"103159","exclusionReason":"DBLP paper signature uses the same Sichuan University Ziwei Liu ORCID 0000-0001-6206-637X as ReflexGest; publisher author list and Sichuan author profile confirm this separate visible-light sensing group.","exclusionSource":"https://www.sciencedirect.com/science/article/pii/S1566253525002325"}],"displayNotes":"曾发现同名误归，已用本人论文列表、论文原文或正确的 ORCID 逐条重核全部正式候选。计入 91 条（会议 70、期刊 21），所有作者位置均计入，不表示主导。预印本候选尚未完成归属，暂不给出总数，这不是零。","labDisplayNotes":"本人简介写明任职于 MMLab@NTU。该 Lab 与 Xingang Pan 共享，组内按 DBLP key 去重后为 105 条；这不是 Lab 全体成员的产量。"},{"index":18,"name":"Jiebo Luo","nameZh":"Jiebo Luo","role":"Professor","affiliation":"University of Rochester","source":"DBLP official SPARQL","profileUrl":"https://dblp.org/pid/25/5545","identifier":"25/5545","identityEvidence":[{"url":"https://dblp.org/pid/25/5545","evidence":"DBLP 档案名 Jiebo Luo 0001；机构/履历：Eastman Kodak Company, R&D Labs, Rochester, NY, USA；University of Rochester, Department of Computer Science, NY, USA"}],"count2025":47,"conference2025":34,"journal2025":13,"preprint2025":50,"status":"verified","notes":"身份已通过机构/个人主页或 DBLP 机构信息核对；篇数为数据库记录统计，不表示每篇均由本人主导。","retrievedAt":"2026-10-19","yearPolicy":"DBLP yearOfPublication = 2025","queryUrl":"https://sparql.dblp.org/sparql?query=PREFIX%20dblp%3A%20%3Chttps%3A//dblp.org/rdf/schema%23%3E%20PREFIX%20xsd%3A%20%3Chttp%3A//www.w3.org/2001/XMLSchema%23%3E%20SELECT%20%3Fpub%20%3Ftitle%20%3Ftype%20%3Fvenue%20WHERE%20%7B%20%3Fpub%20dblp%3AauthoredBy%20%3Chttps%3A//dblp.org/pid/25/5545%3E%3B%20dblp%3AyearOfPublication%20%222025%22%5E%5Exsd%3AgYear%3B%20dblp%3Atitle%20%3Ftitle%3B%20a%20%3Ftype%20.%20OPTIONAL%20%7B%20%3Fpub%20dblp%3ApublishedIn%20%3Fvenue%20%7D%20%7D&format=json","papers":[{"key":"conf/3dim/LiuSZTHTLX25","title":"GaussianStyle: Gaussian Head Avatar via StyleGAN.","type":"Inproceedings","venue":"3DV","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/3DV66043.2025.00103","sourceUrl":"https://dblp.org/rec/conf/3dim/LiuSZTHTLX25","documentUrl":"https://doi.org/10.1109/3DV66043.2025.00103","pages":"1064-1079"},{"key":"conf/aaai/ChenL0QY0025","title":"Ouroboros-Diffusion: Exploring Consistent Content Generation in Tuning-free Long Video Diffusion.","type":"Inproceedings","venue":"AAAI","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1609/AAAI.V39I2.32205","sourceUrl":"https://dblp.org/rec/conf/aaai/ChenL0QY0025","documentUrl":"https://doi.org/10.1609/AAAI.V39I2.32205","pages":"2079-2087"},{"key":"conf/aaai/Hua0X025","title":"V2Xum-LLM: Cross-Modal Video Summarization with Temporal Prompt Instruction Tuning.","type":"Inproceedings","venue":"AAAI","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1609/AAAI.V39I4.32374","sourceUrl":"https://dblp.org/rec/conf/aaai/Hua0X025","documentUrl":"https://doi.org/10.1609/AAAI.V39I4.32374","pages":"3599-3607"},{"key":"conf/acl/XiaMXW0ALBCDKY025","title":"From Selection to Generation: A Survey of LLM-based Active Learning.","type":"Inproceedings","venue":"ACL (1)","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.18653/V1/2025.ACL-LONG.708","sourceUrl":"https://dblp.org/rec/conf/acl/XiaMXW0ALBCDKY025","documentUrl":"https://doi.org/10.18653/V1/2025.ACL-LONG.708","pages":"14552-14569"},{"key":"conf/aied/ZhouLSLSLDB25","title":"Empower Secondary School Teachers to Create ML-Supported Inquiry-Based Learning Activities.","type":"Inproceedings","venue":"AIED (1)","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1007/978-3-031-98414-3_11","sourceUrl":"https://dblp.org/rec/conf/aied/ZhouLSLSLDB25","documentUrl":"https://doi.org/10.1007/978-3-031-98414-3_11","pages":"150-164"},{"key":"conf/bigdataconf/ChatterjeeTNKHA25","title":"Assessing Historical Structural Oppression Worldwide via Rule-Guided Prompting of Large Language Models.","type":"Inproceedings","venue":"IEEE Big Data","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/BIGDATA66926.2025.11401510","sourceUrl":"https://dblp.org/rec/conf/bigdataconf/ChatterjeeTNKHA25","documentUrl":"https://doi.org/10.1109/BIGDATA66926.2025.11401510","pages":"2783-2792"},{"key":"conf/bigdataconf/ZhengL025","title":"Irony in Emojis: A Comparative Study of Human and LLM Interpretation.","type":"Inproceedings","venue":"IEEE Big Data","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/BIGDATA66926.2025.11401988","sourceUrl":"https://dblp.org/rec/conf/bigdataconf/ZhengL025","documentUrl":"https://doi.org/10.1109/BIGDATA66926.2025.11401988","pages":"3171-3175"},{"key":"conf/coling/HuangPWL025","title":"Evolver: Chain-of-Evolution Prompting to Boost Large Multimodal Models for Hateful Meme Detection.","type":"Inproceedings","venue":"COLING","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":null,"sourceUrl":"https://dblp.org/rec/conf/coling/HuangPWL025","documentUrl":"https://aclanthology.org/2025.coling-main.489/","pages":"7321-7330"},{"key":"conf/cvpr/0016LLL00HL25","title":"HOIGen-1M: A Large-scale Dataset for Human-Object Interaction Video Generation.","type":"Inproceedings","venue":"CVPR","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/CVPR52734.2025.02235","sourceUrl":"https://dblp.org/rec/conf/cvpr/0016LLL00HL25","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Liu_HOIGen-1M_A_Large-scale_Dataset_for_Human-Object_Interaction_Video_Generation_CVPR_2025_paper.html","pages":"24001-24010"},{"key":"conf/cvpr/HuaLZSKZ00L025","title":"FINECAPTION: Compositional Image Captioning Focusing on Wherever You Want at Any Granularity.","type":"Inproceedings","venue":"CVPR","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/CVPR52734.2025.02306","sourceUrl":"https://dblp.org/rec/conf/cvpr/HuaLZSKZ00L025","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Hua_FINECAPTION_Compositional_Image_Captioning_Focusing_on_Wherever_You_Want_at_CVPR_2025_paper.html","pages":"24763-24773"},{"key":"conf/cvpr/YuanHHGSC0025","title":"Identity-Preserving Text-to-Video Generation by Frequency Decomposition.","type":"Inproceedings","venue":"CVPR","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/CVPR52734.2025.01211","sourceUrl":"https://dblp.org/rec/conf/cvpr/YuanHHGSC0025","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Yuan_Identity-Preserving_Text-to-Video_Generation_by_Frequency_Decomposition_CVPR_2025_paper.html","pages":"12978-12988"},{"key":"conf/eccv/HuaSKJZCCL24","title":"FineMatch: Aspect-Based Fine-Grained Image and Text Mismatch Detection and Correction.","type":"Inproceedings","venue":"ECCV (9)","year":2025,"yearOfPublication":2025,"yearOfEvent":2024,"doi":"https://doi.org/10.1007/978-3-031-72673-6_26","sourceUrl":"https://dblp.org/rec/conf/eccv/HuaSKJZCCL24","documentUrl":"https://doi.org/10.1007/978-3-031-72673-6_26","pages":"474-491"},{"key":"conf/emnlp/LinWXHWHL25","title":"Facilitating Long Context Understanding via Supervised Chain-of-Thought Reasoning.","type":"Inproceedings","venue":"EMNLP","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.18653/V1/2025.EMNLP-MAIN.615","sourceUrl":"https://dblp.org/rec/conf/emnlp/LinWXHWHL25","documentUrl":"https://doi.org/10.18653/V1/2025.EMNLP-MAIN.615","pages":"12232-12248"},{"key":"conf/emnlp/YangLZSLCTQYLM25","title":"Code to Think, Think to Code: A Survey on Code-Enhanced Reasoning and Reasoning-Driven Code Intelligence in LLMs.","type":"Inproceedings","venue":"EMNLP","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.18653/V1/2025.EMNLP-MAIN.130","sourceUrl":"https://dblp.org/rec/conf/emnlp/YangLZSLCTQYLM25","documentUrl":"https://doi.org/10.18653/V1/2025.EMNLP-MAIN.130","pages":"2586-2616"},{"key":"conf/fat/Lyu0KK25","title":"Characterizing Bias: Benchmarking Large Language Models in Simplified versus Traditional Chinese.","type":"Inproceedings","venue":"FAccT","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1145/3715275.3732182","sourceUrl":"https://dblp.org/rec/conf/fat/Lyu0KK25","documentUrl":"https://doi.org/10.1145/3715275.3732182","pages":"2815-2846"},{"key":"conf/iccv/ChenLQYZLM25","title":"Aligning Global Semantics and Local Textures in Generative Video Enhancement.","type":"Inproceedings","venue":"ICCV","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/ICCV51701.2025.01587","sourceUrl":"https://dblp.org/rec/conf/iccv/ChenLQYZLM25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.01587","pages":"17087-17096"},{"key":"conf/iccv/LinLXL25","title":"INS-MMBench: A Comprehensive Benchmark for Evaluating LVLMs' Performance in Insurance.","type":"Inproceedings","venue":"ICCV","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/ICCV51701.2025.00845","sourceUrl":"https://dblp.org/rec/conf/iccv/LinLXL25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.00845","pages":"9036-9047"},{"key":"conf/iccv/WangHLYLZWLT25","title":"Exploring the Adversarial Vulnerabilities of Vision-Language-Action Models in Robotics.","type":"Inproceedings","venue":"ICCV","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/ICCV51701.2025.00653","sourceUrl":"https://dblp.org/rec/conf/iccv/WangHLYLZWLT25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.00653","pages":"6948-6958"},{"key":"conf/iccv/YuZZL25","title":"Omnipaint: Mastering Object-Oriented Editing Via Disentangled Insertion-Removal Inpainting.","type":"Inproceedings","venue":"ICCV","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/ICCV51701.2025.01609","sourceUrl":"https://dblp.org/rec/conf/iccv/YuZZL25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.01609","pages":"17324-17334"},{"key":"conf/iccv/ZhouAL25","title":"Latent-Reframe: Enabling Camera Control for Video Diffusion Models Without Training.","type":"Inproceedings","venue":"ICCV","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/ICCV51701.2025.01187","sourceUrl":"https://dblp.org/rec/conf/iccv/ZhouAL25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.01187","pages":"12779-12789"},{"key":"conf/icml/000100L0LWWZMSZ25","title":"On Path to Multimodal Generalist: General-Level and General-Bench.","type":"Inproceedings","venue":"ICML","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":null,"sourceUrl":"https://dblp.org/rec/conf/icml/000100L0LWWZMSZ25","documentUrl":"https://proceedings.mlr.press/v267/fei25a.html","pages":null},{"key":"conf/icpr/HaoFLL24","title":"Rare Fungi Image Classification Based on Few-Shot Learning and Data Augmentation.","type":"Inproceedings","venue":"ICPR (16)","year":2025,"yearOfPublication":2025,"yearOfEvent":2024,"doi":"https://doi.org/10.1007/978-3-031-78444-6_4","sourceUrl":"https://dblp.org/rec/conf/icpr/HaoFLL24","documentUrl":"https://doi.org/10.1007/978-3-031-78444-6_4","pages":"50-62"},{"key":"conf/icpr/ZhangYLJYCL24","title":"A Benchmark and Chain-of-Thought Prompting Strategy for Large Multimodal Models with Multiple Image Inputs.","type":"Inproceedings","venue":"ICPR (18)","year":2025,"yearOfPublication":2025,"yearOfEvent":2024,"doi":"https://doi.org/10.1007/978-3-031-78456-9_15","sourceUrl":"https://dblp.org/rec/conf/icpr/ZhangYLJYCL24","documentUrl":"https://doi.org/10.1007/978-3-031-78456-9_15","pages":"226-241"},{"key":"conf/mm/0018LHZW00C25","title":"SMPV: Social Media Prediction for Videos.","type":"Inproceedings","venue":"ACM Multimedia","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1145/3746027.3763757","sourceUrl":"https://dblp.org/rec/conf/mm/0018LHZW00C25","documentUrl":"https://doi.org/10.1145/3746027.3763757","pages":"14055-14057"},{"key":"conf/mm/Pan0GZH025","title":"SafeCFG: Controlling Harmful Features with Dynamic Safe Guidance for Safe Generation.","type":"Inproceedings","venue":"ACM Multimedia","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1145/3746027.3754717","sourceUrl":"https://dblp.org/rec/conf/mm/Pan0GZH025","documentUrl":"https://doi.org/10.1145/3746027.3754717","pages":"11219-11228"},{"key":"conf/mm/ZhaoWL0Z00X25","title":"PP-Motion: Physical-Perceptual Fidelity Evaluation for Human Motion Generation.","type":"Inproceedings","venue":"ACM Multimedia","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1145/3746027.3754940","sourceUrl":"https://dblp.org/rec/conf/mm/ZhaoWL0Z00X25","documentUrl":"https://doi.org/10.1145/3746027.3754940","pages":"6840-6849"},{"key":"conf/nips/AnWGLS25","title":"On Inductive Biases That Enable Generalization in Diffusion Transformers.","type":"Inproceedings","venue":"NeurIPS","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":null,"sourceUrl":"https://dblp.org/rec/conf/nips/AnWGLS25","documentUrl":"http://papers.nips.cc/paper_files/paper/2025/hash/2dc52e27a26afabb0bf2123bceaf9208-Abstract-Conference.html","pages":null},{"key":"conf/nips/HuaZSTHAXL25","title":"MMIG-Bench: Towards Comprehensive and Explainable Evaluation of Multi-Modal Image Generation Models.","type":"Inproceedings","venue":"NeurIPS","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":null,"sourceUrl":"https://dblp.org/rec/conf/nips/HuaZSTHAXL25","documentUrl":"http://papers.nips.cc/paper_files/paper/2025/hash/d3f8714b9f9727b43d64019f2f4043d2-Abstract-Datasets_and_Benchmarks_Track.html","pages":null},{"key":"conf/nips/LinWSWLSYCLLB25","title":"Unleashing Hour-Scale Video Training for Long Video-Language Understanding.","type":"Inproceedings","venue":"NeurIPS","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":null,"sourceUrl":"https://dblp.org/rec/conf/nips/LinWSWLSYCLLB25","documentUrl":"http://papers.nips.cc/paper_files/paper/2025/hash/19741c617c87a25627682e5714af1501-Abstract-Conference.html","pages":null},{"key":"conf/nips/LuoZLYLFHJCLJ25","title":"Video-RAG: Visually-aligned Retrieval-Augmented Long Video Comprehension.","type":"Inproceedings","venue":"NeurIPS","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":null,"sourceUrl":"https://dblp.org/rec/conf/nips/LuoZLYLFHJCLJ25","documentUrl":"http://papers.nips.cc/paper_files/paper/2025/hash/f593c9c251d4d7cf14d4ab9861dfb7eb-Abstract-Conference.html","pages":null},{"key":"conf/nips/SunHWLDRRT25","title":"Latent Chain-of-Thought for Visual Reasoning.","type":"Inproceedings","venue":"NeurIPS","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":null,"sourceUrl":"https://dblp.org/rec/conf/nips/SunHWLDRRT25","documentUrl":"http://papers.nips.cc/paper_files/paper/2025/hash/95c6ae3f3393786203a4b6dcb9df1036-Abstract-Conference.html","pages":null},{"key":"conf/nips/YuanHDYHLMLY25","title":"OpenS2V-Nexus: A Detailed Benchmark and Million-Scale Dataset for Subject-to-Video Generation.","type":"Inproceedings","venue":"NeurIPS","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":null,"sourceUrl":"https://dblp.org/rec/conf/nips/YuanHDYHLMLY25","documentUrl":"http://papers.nips.cc/paper_files/paper/2025/hash/dae77d03bd51a5acfe8519848a3af6c9-Abstract-Datasets_and_Benchmarks_Track.html","pages":null},{"key":"conf/nips/ZhengYYZLL25","title":"PixPerfect: Seamless Latent Diffusion Local Editing with Discriminative Pixel-Space Refinement.","type":"Inproceedings","venue":"NeurIPS","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":null,"sourceUrl":"https://dblp.org/rec/conf/nips/ZhengYYZLL25","documentUrl":"http://papers.nips.cc/paper_files/paper/2025/hash/ba3354bcfeae4f166a8bfe75443ac8f7-Abstract-Conference.html","pages":null},{"key":"conf/www/QiL025","title":"Representation Bias in Political Sample Simulations with Large Language Models.","type":"Inproceedings","venue":"WWW (Companion Volume)","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1145/3701716.3715591","sourceUrl":"https://dblp.org/rec/conf/www/QiL025","documentUrl":"https://doi.org/10.1145/3701716.3715591","pages":"1264-1267"},{"key":"journals/ipm/ZhangJZZL25","title":"Exploring online communication in Asperger's syndrome: A combined approach with large language models and time series analysis.","type":"Article","venue":"Inf. Process. Manag.","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.1016/J.IPM.2025.104204","sourceUrl":"https://dblp.org/rec/journals/ipm/ZhangJZZL25","documentUrl":"https://doi.org/10.1016/J.IPM.2025.104204","pages":"104204"},{"key":"journals/npjdm/LiuLYHLTBSYWZC25","title":"A multimodal multidomain multilingual medical foundation model for zero shot clinical diagnosis.","type":"Article","venue":"npj Digit. Medicine","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.1038/S41746-024-01339-7","sourceUrl":"https://dblp.org/rec/journals/npjdm/LiuLYHLTBSYWZC25","documentUrl":"https://doi.org/10.1038/S41746-024-01339-7","pages":null},{"key":"journals/pami/LiuWHYBSCZLZC25","title":"Aligning, Autoencoding and Prompting Large Language Models for Novel Disease Reporting.","type":"Article","venue":"IEEE Trans. Pattern Anal. Mach. Intell.","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.1109/TPAMI.2025.3534586","sourceUrl":"https://dblp.org/rec/journals/pami/LiuWHYBSCZLZC25","documentUrl":"https://doi.org/10.1109/TPAMI.2025.3534586","pages":"3332-3343"},{"key":"journals/pami/WangWYL25","title":"End-to-End Open-Vocabulary Video Visual Relationship Detection Using Multi-Modal Prompting.","type":"Article","venue":"IEEE Trans. Pattern Anal. Mach. Intell.","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.1109/TPAMI.2025.3561366","sourceUrl":"https://dblp.org/rec/journals/pami/WangWYL25","documentUrl":"https://doi.org/10.1109/TPAMI.2025.3561366","pages":"6599-6615"},{"key":"journals/pami/YuanHSXZLCYL25","title":"MagicTime: Time-Lapse Video Generation Models as Metamorphic Simulators.","type":"Article","venue":"IEEE Trans. Pattern Anal. Mach. Intell.","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.1109/TPAMI.2025.3558507","sourceUrl":"https://dblp.org/rec/journals/pami/YuanHSXZLCYL25","documentUrl":"https://doi.org/10.1109/TPAMI.2025.3558507","pages":"7340-7351"},{"key":"journals/pr/FengCSWJLLJL25","title":"Learning multi-granularity representation with transformer for visible-infrared person re-identification.","type":"Article","venue":"Pattern Recognit.","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.1016/J.PATCOG.2025.111510","sourceUrl":"https://dblp.org/rec/journals/pr/FengCSWJLLJL25","documentUrl":"https://doi.org/10.1016/J.PATCOG.2025.111510","pages":"111510"},{"key":"journals/spic/QiSHCSDLL25","title":"AMFMER: A multimodal full transformer for unifying aesthetic assessment tasks.","type":"Article","venue":"Signal Process. Image Commun.","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.1016/J.IMAGE.2025.117320","sourceUrl":"https://dblp.org/rec/journals/spic/QiSHCSDLL25","documentUrl":"https://doi.org/10.1016/J.IMAGE.2025.117320","pages":"117320"},{"key":"journals/tcsv/BaoDHLLLGL25","title":"3D Gaussian Splatting: Survey, Technologies, Challenges, and Opportunities.","type":"Article","venue":"IEEE Trans. Circuits Syst. Video Technol.","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.1109/TCSVT.2025.3538684","sourceUrl":"https://dblp.org/rec/journals/tcsv/BaoDHLLLGL25","documentUrl":"https://doi.org/10.1109/TCSVT.2025.3538684","pages":"6832-6852"},{"key":"journals/tcsv/LiWQDWCLLL25","title":"DRC: Discrete Representation Classifier With Salient Features via Fixed-Prototype.","type":"Article","venue":"IEEE Trans. Circuits Syst. Video Technol.","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.1109/TCSVT.2024.3453052","sourceUrl":"https://dblp.org/rec/journals/tcsv/LiWQDWCLLL25","documentUrl":"https://doi.org/10.1109/TCSVT.2024.3453052","pages":"118-133"},{"key":"journals/tist/LyuHZYMPYWL25","title":"GPT-4V(ision) as A Social Media Analysis Engine.","type":"Article","venue":"ACM Trans. Intell. Syst. Technol.","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.1145/3709005","sourceUrl":"https://dblp.org/rec/journals/tist/LyuHZYMPYWL25","documentUrl":"https://doi.org/10.1145/3709005","pages":"50:1-50:54"},{"key":"journals/tmlr/XiongLHWW0YSWHT25","title":"Autoregressive Models in Vision: A Survey.","type":"Article","venue":"Trans. Mach. Learn. Res.","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":null,"sourceUrl":"https://dblp.org/rec/journals/tmlr/XiongLHWW0YSWHT25","documentUrl":"https://openreview.net/forum?id=1BqXkjNEGP","pages":null},{"key":"journals/tmlr/ZangDLWLYLLL25","title":"MDTree: A Masked Dynamic Autoregressive Model for Phylogenetic Inference.","type":"Article","venue":"Trans. Mach. Learn. Res.","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":null,"sourceUrl":"https://dblp.org/rec/journals/tmlr/ZangDLWLYLLL25","documentUrl":"https://openreview.net/forum?id=dTSptQNygv","pages":null},{"key":"journals/tnn/HuaLDXL25","title":"Improving Pretrained Language Model Fine-Tuning With Noise Stability Regularization.","type":"Article","venue":"IEEE Trans. Neural Networks Learn. Syst.","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.1109/TNNLS.2023.3330926","sourceUrl":"https://dblp.org/rec/journals/tnn/HuaLDXL25","documentUrl":"https://doi.org/10.1109/TNNLS.2023.3330926","pages":"1898-1910"}],"preprints":[{"key":"journals/corr/abs-2501-09019","title":"Ouroboros-Diffusion: Exploring Consistent Content Generation in Tuning-free Long Video Diffusion.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2501.09019","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2501-09019","documentUrl":"https://doi.org/10.48550/ARXIV.2501.09019","pages":null,"arxivId":"2501.09019","arxivUrl":"https://arxiv.org/abs/2501.09019"},{"key":"journals/corr/abs-2501-11241","title":"Irony in Emojis: A Comparative Study of Human and LLM Interpretation.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2501.11241","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2501-11241","documentUrl":"https://doi.org/10.48550/ARXIV.2501.11241","pages":null,"arxivId":"2501.11241","arxivUrl":"https://arxiv.org/abs/2501.11241"},{"key":"journals/corr/abs-2501-16329","title":"sDREAMER: Self-distilled Mixture-of-Modality-Experts Transformer for Automatic Sleep Staging.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2501.16329","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2501-16329","documentUrl":"https://doi.org/10.48550/ARXIV.2501.16329","pages":null,"arxivId":"2501.16329","arxivUrl":"https://arxiv.org/abs/2501.16329"},{"key":"journals/corr/abs-2502-11767","title":"From Selection to Generation: A Survey of LLM-based Active Learning.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2502.11767","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2502-11767","documentUrl":"https://doi.org/10.48550/ARXIV.2502.11767","pages":null,"arxivId":"2502.11767","arxivUrl":"https://arxiv.org/abs/2502.11767"},{"key":"journals/corr/abs-2502-12073","title":"Can LLMs Simulate Social Media Engagement? A Study on Action-Guided Response Generation.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2502.12073","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2502-12073","documentUrl":"https://doi.org/10.48550/ARXIV.2502.12073","pages":null,"arxivId":"2502.12073","arxivUrl":"https://arxiv.org/abs/2502.12073"},{"key":"journals/corr/abs-2502-13127","title":"Facilitating Long Context Understanding via Supervised Chain-of-Thought Reasoning.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2502.13127","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2502-13127","documentUrl":"https://doi.org/10.48550/ARXIV.2502.13127","pages":null,"arxivId":"2502.13127","arxivUrl":"https://arxiv.org/abs/2502.13127"},{"key":"journals/corr/abs-2502-19411","title":"Code to Think, Think to Code: A Survey on Code-Enhanced Reasoning and Reasoning-Driven Code Intelligence in LLMs.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2502.19411","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2502-19411","documentUrl":"https://doi.org/10.48550/ARXIV.2502.19411","pages":null,"arxivId":"2502.19411","arxivUrl":"https://arxiv.org/abs/2502.19411"},{"key":"journals/corr/abs-2503-08677","title":"OmniPaint: Mastering Object-Oriented Editing via Disentangled Insertion-Removal Inpainting.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2503.08677","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-08677","documentUrl":"https://doi.org/10.48550/ARXIV.2503.08677","pages":null,"arxivId":"2503.08677","arxivUrl":"https://arxiv.org/abs/2503.08677"},{"key":"journals/corr/abs-2503-08689","title":"QuoTA: Query-oriented Token Assignment via CoT Query Decouple for Long Video Comprehension.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2503.08689","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-08689","documentUrl":"https://doi.org/10.48550/ARXIV.2503.08689","pages":null,"arxivId":"2503.08689","arxivUrl":"https://arxiv.org/abs/2503.08689"},{"key":"journals/corr/abs-2503-12605","title":"Multimodal Chain-of-Thought Reasoning: A Comprehensive Survey.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2503.12605","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-12605","documentUrl":"https://doi.org/10.48550/ARXIV.2503.12605","pages":null,"arxivId":"2503.12605","arxivUrl":"https://arxiv.org/abs/2503.12605"},{"key":"journals/corr/abs-2503-23377","title":"JavisDiT: Joint Audio-Video Diffusion Transformer with Hierarchical Spatio-Temporal Prior Synchronization.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2503.23377","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-23377","documentUrl":"https://doi.org/10.48550/ARXIV.2503.23377","pages":null,"arxivId":"2503.23377","arxivUrl":"https://arxiv.org/abs/2503.23377"},{"key":"journals/corr/abs-2503-23715","title":"HOIGen-1M: A Large-scale Dataset for Human-Object Interaction Video Generation.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2503.23715","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-23715","documentUrl":"https://doi.org/10.48550/ARXIV.2503.23715","pages":null,"arxivId":"2503.23715","arxivUrl":"https://arxiv.org/abs/2503.23715"},{"key":"journals/corr/abs-2504-03151","title":"Why Reasoning Matters? A Survey of Advancements in Multimodal Reasoning (v1).","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2504.03151","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2504-03151","documentUrl":"https://doi.org/10.48550/ARXIV.2504.03151","pages":null,"arxivId":"2504.03151","arxivUrl":"https://arxiv.org/abs/2504.03151"},{"key":"journals/corr/abs-2504-05541","title":"Caption Anything in Video: Fine-grained Object-centric Captioning via Spatiotemporal Multimodal Prompting.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2504.05541","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2504-05541","documentUrl":"https://doi.org/10.48550/ARXIV.2504.05541","pages":null,"arxivId":"2504.05541","arxivUrl":"https://arxiv.org/abs/2504.05541"},{"key":"journals/corr/abs-2504-08591","title":"ZipIR: Latent Pyramid Diffusion Transformer for High-Resolution Image Restoration.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2504.08591","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2504-08591","documentUrl":"https://doi.org/10.48550/ARXIV.2504.08591","pages":null,"arxivId":"2504.08591","arxivUrl":"https://arxiv.org/abs/2504.08591"},{"key":"journals/corr/abs-2504-10157","title":"SocioVerse: A World Model for Social Simulation Powered by LLM Agents and A Pool of 10 Million Real-World Users.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2504.10157","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2504-10157","documentUrl":"https://doi.org/10.48550/ARXIV.2504.10157","pages":null,"arxivId":"2504.10157","arxivUrl":"https://arxiv.org/abs/2504.10157"},{"key":"journals/corr/abs-2505-01490","title":"WorldGenBench: A World-Knowledge-Integrated Benchmark for Reasoning-Driven Text-to-Image Generation.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2505.01490","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-01490","documentUrl":"https://doi.org/10.48550/ARXIV.2505.01490","pages":null,"arxivId":"2505.01490","arxivUrl":"https://arxiv.org/abs/2505.01490"},{"key":"journals/corr/abs-2505-04620","title":"On Path to Multimodal Generalist: General-Level and General-Bench.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2505.04620","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-04620","documentUrl":"https://doi.org/10.48550/ARXIV.2505.04620","pages":null,"arxivId":"2505.04620","arxivUrl":"https://arxiv.org/abs/2505.04620"},{"key":"journals/corr/abs-2505-19415","title":"MMIG-Bench: Towards Comprehensive and Explainable Evaluation of Multi-Modal Image Generation Models.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2505.19415","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-19415","documentUrl":"https://doi.org/10.48550/ARXIV.2505.19415","pages":null,"arxivId":"2505.19415","arxivUrl":"https://arxiv.org/abs/2505.19415"},{"key":"journals/corr/abs-2505-20292","title":"OpenS2V-Nexus: A Detailed Benchmark and Million-Scale Dataset for Subject-to-Video Generation.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2505.20292","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-20292","documentUrl":"https://doi.org/10.48550/ARXIV.2505.20292","pages":null,"arxivId":"2505.20292","arxivUrl":"https://arxiv.org/abs/2505.20292"},{"key":"journals/corr/abs-2505-22645","title":"Characterizing Bias: Benchmarking Large Language Models in Simplified versus Traditional Chinese.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2505.22645","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-22645","documentUrl":"https://doi.org/10.48550/ARXIV.2505.22645","pages":null,"arxivId":"2505.22645","arxivUrl":"https://arxiv.org/abs/2505.22645"},{"key":"journals/corr/abs-2506-01327","title":"STSA: Federated Class-Incremental Learning via Spatial-Temporal Statistics Aggregation.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2506.01327","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-01327","documentUrl":"https://doi.org/10.48550/ARXIV.2506.01327","pages":null,"arxivId":"2506.01327","arxivUrl":"https://arxiv.org/abs/2506.01327"},{"key":"journals/corr/abs-2506-05332","title":"Unleashing Hour-Scale Video Training for Long Video-Language Understanding.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2506.05332","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-05332","documentUrl":"https://doi.org/10.48550/ARXIV.2506.05332","pages":null,"arxivId":"2506.05332","arxivUrl":"https://arxiv.org/abs/2506.05332"},{"key":"journals/corr/abs-2506-18999","title":"Diffusion Transformer-to-Mamba Distillation for High-Resolution Image Generation.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2506.18999","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-18999","documentUrl":"https://doi.org/10.48550/ARXIV.2506.18999","pages":null,"arxivId":"2506.18999","arxivUrl":"https://arxiv.org/abs/2506.18999"},{"key":"journals/corr/abs-2507-09961","title":"Text-Driven Causal Representation Learning for Source-Free Domain Generalization.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2507.09961","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2507-09961","documentUrl":"https://doi.org/10.48550/ARXIV.2507.09961","pages":null,"arxivId":"2507.09961","arxivUrl":"https://arxiv.org/abs/2507.09961"},{"key":"journals/corr/abs-2507-12851","title":"Simulate, Refocus and Ensemble: An Attention-Refocusing Scheme for Domain Generalization.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2507.12851","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2507-12851","documentUrl":"https://doi.org/10.48550/ARXIV.2507.12851","pages":null,"arxivId":"2507.12851","arxivUrl":"https://arxiv.org/abs/2507.12851"},{"key":"journals/corr/abs-2507-19929","title":"DynamiX: Large-Scale Dynamic Social Network Simulator.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2507.19929","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2507-19929","documentUrl":"https://doi.org/10.48550/ARXIV.2507.19929","pages":null,"arxivId":"2507.19929","arxivUrl":"https://arxiv.org/abs/2507.19929"},{"key":"journals/corr/abs-2508-05006","title":"The Docking Game: Loop Self-Play for Fast, Dynamic, and Accurate Prediction of Flexible Protein-Ligand Binding.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2508.05006","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-05006","documentUrl":"https://doi.org/10.48550/ARXIV.2508.05006","pages":null,"arxivId":"2508.05006","arxivUrl":"https://arxiv.org/abs/2508.05006"},{"key":"journals/corr/abs-2508-05008","title":"Multimodal Causal-Driven Representation Learning for Generalizable Medical Image Segmentation.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2508.05008","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-05008","documentUrl":"https://doi.org/10.48550/ARXIV.2508.05008","pages":null,"arxivId":"2508.05008","arxivUrl":"https://arxiv.org/abs/2508.05008"},{"key":"journals/corr/abs-2508-05205","title":"EndoMatcher: Generalizable Endoscopic Image Matcher via Multi-Domain Pre-training for Robot-Assisted Surgery.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2508.05205","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-05205","documentUrl":"https://doi.org/10.48550/ARXIV.2508.05205","pages":null,"arxivId":"2508.05205","arxivUrl":"https://arxiv.org/abs/2508.05205"},{"key":"journals/corr/abs-2508-08179","title":"PP-Motion: Physical-Perceptual Fidelity Evaluation for Human Motion Generation.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2508.08179","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-08179","documentUrl":"https://doi.org/10.48550/ARXIV.2508.08179","pages":null,"arxivId":"2508.08179","arxivUrl":"https://arxiv.org/abs/2508.08179"},{"key":"journals/corr/abs-2509-00357","title":"SurgLLM: A Versatile Large Multimodal Model with Spatial Focus and Temporal Awareness for Surgical Video Understanding.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2509.00357","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-00357","documentUrl":"https://doi.org/10.48550/ARXIV.2509.00357","pages":null,"arxivId":"2509.00357","arxivUrl":"https://arxiv.org/abs/2509.00357"},{"key":"journals/corr/abs-2509-02172","title":"RumorSphere: A Framework for Million-scale Agent-based Dynamic Simulation of Rumor Propagation.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2509.02172","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-02172","documentUrl":"https://doi.org/10.48550/ARXIV.2509.02172","pages":null,"arxivId":"2509.02172","arxivUrl":"https://arxiv.org/abs/2509.02172"},{"key":"journals/corr/abs-2509-11752","title":"A Fully Open and Generalizable Foundation Model for Ultrasound Clinical Applications.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2509.11752","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-11752","documentUrl":"https://doi.org/10.48550/ARXIV.2509.11752","pages":null,"arxivId":"2509.11752","arxivUrl":"https://arxiv.org/abs/2509.11752"},{"key":"journals/corr/abs-2509-11866","title":"Dr.V: A Hierarchical Perception-Temporal-Cognition Framework to Diagnose Video Hallucination by Fine-grained Spatial-Temporal Grounding.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2509.11866","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-11866","documentUrl":"https://doi.org/10.48550/ARXIV.2509.11866","pages":null,"arxivId":"2509.11866","arxivUrl":"https://arxiv.org/abs/2509.11866"},{"key":"journals/corr/abs-2509-15216","title":"Assessing Historical Structural Oppression Worldwide via Rule-Guided Prompting of Large Language Models.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2509.15216","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-15216","documentUrl":"https://doi.org/10.48550/ARXIV.2509.15216","pages":null,"arxivId":"2509.15216","arxivUrl":"https://arxiv.org/abs/2509.15216"},{"key":"journals/corr/abs-2510-02750","title":"Bayesian Test-time Adaptation for Object Recognition and Detection with Vision-language Models.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2510.02750","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-02750","documentUrl":"https://doi.org/10.48550/ARXIV.2510.02750","pages":null,"arxivId":"2510.02750","arxivUrl":"https://arxiv.org/abs/2510.02750"},{"key":"journals/corr/abs-2510-05034","title":"Video-LMM Post-Training: A Deep Dive into Video Reasoning with Large Multimodal Models.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2510.05034","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-05034","documentUrl":"https://doi.org/10.48550/ARXIV.2510.05034","pages":null,"arxivId":"2510.05034","arxivUrl":"https://arxiv.org/abs/2510.05034"},{"key":"journals/corr/abs-2510-23925","title":"Latent Chain-of-Thought for Visual Reasoning.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2510.23925","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-23925","documentUrl":"https://doi.org/10.48550/ARXIV.2510.23925","pages":null,"arxivId":"2510.23925","arxivUrl":"https://arxiv.org/abs/2510.23925"},{"key":"journals/corr/abs-2511-01775","title":"How Far Are Surgeons from Surgical World Models? A Pilot Study on Zero-shot Surgical Video Generation with Expert Assessment.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2511.01775","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2511-01775","documentUrl":"https://doi.org/10.48550/ARXIV.2511.01775","pages":null,"arxivId":"2511.01775","arxivUrl":"https://arxiv.org/abs/2511.01775"},{"key":"journals/corr/abs-2511-08521","title":"UniVA: Universal Video Agent towards Open-Source Next-Generation Video Generalist.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2511.08521","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2511-08521","documentUrl":"https://doi.org/10.48550/ARXIV.2511.08521","pages":null,"arxivId":"2511.08521","arxivUrl":"https://arxiv.org/abs/2511.08521"},{"key":"journals/corr/abs-2511-19261","title":"LAST: LeArning to Think in Space and Time for Generalist Vision-Language Models.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2511.19261","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2511-19261","documentUrl":"https://doi.org/10.48550/ARXIV.2511.19261","pages":null,"arxivId":"2511.19261","arxivUrl":"https://arxiv.org/abs/2511.19261"},{"key":"journals/corr/abs-2511-21087","title":"MIRA: Multimodal Iterative Reasoning Agent for Image Editing.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2511.21087","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2511-21087","documentUrl":"https://doi.org/10.48550/ARXIV.2511.21087","pages":null,"arxivId":"2511.21087","arxivUrl":"https://arxiv.org/abs/2511.21087"},{"key":"journals/corr/abs-2511-21120","title":"Learning Cell-Aware Hierarchical Multi-Modal Representations for Robust Molecular Modeling.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2511.21120","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2511-21120","documentUrl":"https://doi.org/10.48550/ARXIV.2511.21120","pages":null,"arxivId":"2511.21120","arxivUrl":"https://arxiv.org/abs/2511.21120"},{"key":"journals/corr/abs-2512-03247","title":"PixPerfect: Seamless Latent Diffusion Local Editing with Discriminative Pixel-Space Refinement.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2512.03247","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-03247","documentUrl":"https://doi.org/10.48550/ARXIV.2512.03247","pages":null,"arxivId":"2512.03247","arxivUrl":"https://arxiv.org/abs/2512.03247"},{"key":"journals/corr/abs-2512-03804","title":"EfficientECG: Cross-Attention with Feature Fusion for Efficient Electrocardiogram Classification.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2512.03804","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-03804","documentUrl":"https://doi.org/10.48550/ARXIV.2512.03804","pages":null,"arxivId":"2512.03804","arxivUrl":"https://arxiv.org/abs/2512.03804"},{"key":"journals/corr/abs-2512-06921","title":"NeuroABench: A Multimodal Evaluation Benchmark for Neurosurgical Anatomy Identification.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2512.06921","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-06921","documentUrl":"https://doi.org/10.48550/ARXIV.2512.06921","pages":null,"arxivId":"2512.06921","arxivUrl":"https://arxiv.org/abs/2512.06921"},{"key":"journals/corr/abs-2512-09907","title":"VisualActBench: Can VLMs See and Act like a Human?","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2512.09907","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-09907","documentUrl":"https://doi.org/10.48550/ARXIV.2512.09907","pages":null,"arxivId":"2512.09907","arxivUrl":"https://arxiv.org/abs/2512.09907"},{"key":"journals/corr/abs-2512-19512","title":"Anatomy-R1: Enhancing Anatomy Reasoning in Multimodal Large Language Models via Anatomical Similarity Curriculum and Group Diversity Augmentation.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2512.19512","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-19512","documentUrl":"https://doi.org/10.48550/ARXIV.2512.19512","pages":null,"arxivId":"2512.19512","arxivUrl":"https://arxiv.org/abs/2512.19512"},{"key":"journals/corr/abs-2512-22029","title":"LibContinual: A Comprehensive Library towards Realistic Continual Learning.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2512.22029","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-22029","documentUrl":"https://doi.org/10.48550/ARXIV.2512.22029","pages":null,"arxivId":"2512.22029","arxivUrl":"https://arxiv.org/abs/2512.22029"}],"excludedFormal":[],"labName":"Visual Intelligence & Social Multimedia Analytics (VIStA) Research Group","labUrl":"https://www.cs.rochester.edu/u/jluo/#People","labEvidence":"本人当前主页有 VIStA Research Group Members 专节，并给出全称；2025 年 Rochester 官方周年活动名单也将 Jiebo Luo 学生团队列为 VIStA，支持名称仍在使用。","labSourceUrl":"https://www.cs.rochester.edu/u/jluo/","affiliationZh":"University of Rochester","sourceWarning":false,"excludedOther":[],"excludedHomonyms":[],"unassignedCandidates":[],"knownPreprintMinimum2025":null,"excludedMisattributed":[],"displayNotes":"身份已经机构或个人主页核对。2025 年正式记录 47 条（会议 34、期刊 13），所有作者位置均计入，不表示主导或贡献份额；预印本 50 条单列，不加总。","labDisplayNotes":"本人主页设有 VIStA Research Group 成员专节并写出全称；罗切斯特大学 2025 年活动名单也将其学生列为 VIStA，据此归组。"},{"index":19,"name":"Xingang Pan","nameZh":"Xingang Pan","role":"Assistant Professor","affiliation":"Nanyang Technological University","source":"DBLP official SPARQL","profileUrl":"https://dblp.org/pid/211/7940","identifier":"211/7940","identityEvidence":[{"url":"https://dblp.org/pid/211/7940","evidence":"DBLP 唯一同名作者档案；通过作者/机构主页与发表题名交叉核对。"},{"url":"https://xingangpan.github.io/","evidence":"作者/机构页面与该 DBLP 档案交叉匹配的题名示例：GAN2X: Non-Lambertian Inverse Rendering of Image GANs.；Spatial as Deep: Spatial CNN for Traffic Scene Understanding.","matchedPaperKeys":["conf/3dim/PanTLT22","conf/aaai/PanSLWT18"]}],"count2025":16,"conference2025":16,"journal2025":0,"preprint2025":15,"status":"verified","notes":"身份已通过机构/个人主页或 DBLP 机构信息核对；篇数为数据库记录统计，不表示每篇均由本人主导。","retrievedAt":"2026-10-19","yearPolicy":"DBLP yearOfPublication = 2025","queryUrl":"https://sparql.dblp.org/sparql?query=PREFIX%20dblp%3A%20%3Chttps%3A//dblp.org/rdf/schema%23%3E%20PREFIX%20xsd%3A%20%3Chttp%3A//www.w3.org/2001/XMLSchema%23%3E%20SELECT%20%3Fpub%20%3Ftitle%20%3Ftype%20%3Fvenue%20WHERE%20%7B%20%3Fpub%20dblp%3AauthoredBy%20%3Chttps%3A//dblp.org/pid/211/7940%3E%3B%20dblp%3AyearOfPublication%20%222025%22%5E%5Exsd%3AgYear%3B%20dblp%3Atitle%20%3Ftitle%3B%20a%20%3Ftype%20.%20OPTIONAL%20%7B%20%3Fpub%20dblp%3ApublishedIn%20%3Fvenue%20%7D%20%7D&format=json","papers":[{"key":"conf/3dim/RPET25","title":"GVP: Generative Volumetric Primitives.","type":"Inproceedings","venue":"3DV","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/3DV66043.2025.00040","sourceUrl":"https://dblp.org/rec/conf/3dim/RPET25","documentUrl":"https://doi.org/10.1109/3DV66043.2025.00040","pages":"379-388"},{"key":"conf/cvpr/0001X0P25","title":"Alias-Free Latent Diffusion Models: Improving Fractional Shift Equivariance of Diffusion Latent Space.","type":"Inproceedings","venue":"CVPR","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/CVPR52734.2025.00013","sourceUrl":"https://dblp.org/rec/conf/cvpr/0001X0P25","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Zhou_Alias-Free_Latent_Diffusion_Models_Improving_Fractional_Shift_Equivariance_of_Diffusion_CVPR_2025_paper.html","pages":"34-44"},{"key":"conf/cvpr/ChenLZ0P25","title":"SAR3D: Autoregressive 3D Object Generation and Understanding via Multi-scale 3D VQVAE.","type":"Inproceedings","venue":"CVPR","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/CVPR52734.2025.02642","sourceUrl":"https://dblp.org/rec/conf/cvpr/ChenLZ0P25","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Chen_SAR3D_Autoregressive_3D_Object_Generation_and_Understanding_via_Multi-scale_3D_CVPR_2025_paper.html","pages":"28371-28382"},{"key":"conf/cvpr/HeW0P025","title":"Neural LightRig: Unlocking Accurate Object Normal and Material Estimation with Multi-Light Diffusion.","type":"Inproceedings","venue":"CVPR","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/CVPR52734.2025.02469","sourceUrl":"https://dblp.org/rec/conf/cvpr/HeW0P025","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/He_Neural_LightRig_Unlocking_Accurate_Object_Normal_and_Material_Estimation_with_CVPR_2025_paper.html","pages":"26514-26524"},{"key":"conf/cvpr/LuoZLPL25","title":"3DEnhancer: Consistent Multi-View Diffusion for 3D Enhancement.","type":"Inproceedings","venue":"CVPR","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/CVPR52734.2025.01532","sourceUrl":"https://dblp.org/rec/conf/cvpr/LuoZLPL25","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Luo_3DEnhancer_Consistent_Multi-View_Diffusion_for_3D_Enhancement_CVPR_2025_paper.html","pages":"16430-16440"},{"key":"conf/eccv/ChenWWPJL24","title":"ComboVerse: Compositional 3D Assets Creation Using Spatially-Aware Diffusion Guidance.","type":"Inproceedings","venue":"ECCV (24)","year":2025,"yearOfPublication":2025,"yearOfEvent":2024,"doi":"https://doi.org/10.1007/978-3-031-72691-0_8","sourceUrl":"https://dblp.org/rec/conf/eccv/ChenWWPJL24","documentUrl":"https://doi.org/10.1007/978-3-031-72691-0_8","pages":"128-146"},{"key":"conf/eccv/LanHYZMDPL24","title":"LN3Diff: Scalable Latent Neural Fields Diffusion for Speedy 3D Generation.","type":"Inproceedings","venue":"ECCV (4)","year":2025,"yearOfPublication":2025,"yearOfEvent":2024,"doi":"https://doi.org/10.1007/978-3-031-73235-5_7","sourceUrl":"https://dblp.org/rec/conf/eccv/LanHYZMDPL24","documentUrl":"https://doi.org/10.1007/978-3-031-73235-5_7","pages":"112-130"},{"key":"conf/iccv/OuyangXYZYYSP25","title":"TokensGen: Harnessing Condensed Tokens for Long Video Generation.","type":"Inproceedings","venue":"ICCV","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/ICCV51701.2025.01691","sourceUrl":"https://dblp.org/rec/conf/iccv/OuyangXYZYYSP25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.01691","pages":"18197-18206"},{"key":"conf/iccv/WeiZCP25","title":"FreeFlux: Understanding and Exploiting Layer-Specific Roles in RoPE-Based MMDiT for Versatile Image Editing.","type":"Inproceedings","venue":"ICCV","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/ICCV51701.2025.01555","sourceUrl":"https://dblp.org/rec/conf/iccv/WeiZCP25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.01555","pages":"16745-16754"},{"key":"conf/iccv/YangLCP25","title":"Textured 3D Regenerative Morphing with 3D Diffusion Prior.","type":"Inproceedings","venue":"ICCV","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/ICCV51701.2025.01407","sourceUrl":"https://dblp.org/rec/conf/iccv/YangLCP25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.01407","pages":"15159-15170"},{"key":"conf/iccv/ZhangTHPGLHYZLCY25","title":"Epona: Autoregressive Diffusion World Model for Autonomous Driving.","type":"Inproceedings","venue":"ICCV","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/ICCV51701.2025.02527","sourceUrl":"https://dblp.org/rec/conf/iccv/ZhangTHPGLHYZLCY25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.02527","pages":"27220-27230"},{"key":"conf/iclr/LanZLH00PL25","title":"GaussianAnything: Interactive Point Cloud Flow Matching for 3D Generation.","type":"Inproceedings","venue":"ICLR","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":null,"sourceUrl":"https://dblp.org/rec/conf/iclr/LanZLH00PL25","documentUrl":"https://openreview.net/forum?id=P4DbTSDQFu","pages":null},{"key":"conf/iclr/XiaoO000SP25","title":"Trajectory attention for fine-grained video motion control.","type":"Inproceedings","venue":"ICLR","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":null,"sourceUrl":"https://dblp.org/rec/conf/iclr/XiaoO000SP25","documentUrl":"https://openreview.net/forum?id=2z1HT5lw5M","pages":null},{"key":"conf/nips/XiaoLZOYZP25","title":"WorldMem: Long-term Consistent World Simulation with Memory.","type":"Inproceedings","venue":"NeurIPS","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":null,"sourceUrl":"https://dblp.org/rec/conf/nips/XiaoLZOYZP25","documentUrl":"http://papers.nips.cc/paper_files/paper/2025/hash/470629a47e2d65ce0606c40055df5d26-Abstract-Conference.html","pages":null},{"key":"conf/siggrapha/ChenLCP25","title":"ArtiLatent: Realistic Articulated 3D Object Generation via Structured Latents.","type":"Inproceedings","venue":"SIGGRAPH Asia","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1145/3757377.3763922","sourceUrl":"https://dblp.org/rec/conf/siggrapha/ChenLCP25","documentUrl":"https://doi.org/10.1145/3757377.3763922","pages":"157:1-157:11"},{"key":"conf/siggrapha/FortesWZP25","title":"Bokeh Diffusion: Defocus Blur Control in Text-to-Image Diffusion Models.","type":"Inproceedings","venue":"SIGGRAPH Asia","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1145/3757377.3763906","sourceUrl":"https://dblp.org/rec/conf/siggrapha/FortesWZP25","documentUrl":"https://doi.org/10.1145/3757377.3763906","pages":"160:1-160:11"}],"preprints":[{"key":"journals/corr/abs-2502-14316","title":"Textured 3D Regenerative Morphing with 3D Diffusion Prior.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2502.14316","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2502-14316","documentUrl":"https://doi.org/10.48550/ARXIV.2502.14316","pages":null,"arxivId":"2502.14316","arxivUrl":"https://arxiv.org/abs/2502.14316"},{"key":"journals/corr/abs-2503-08434","title":"Bokeh Diffusion: Defocus Blur Control in Text-to-Image Diffusion Models.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2503.08434","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-08434","documentUrl":"https://doi.org/10.48550/ARXIV.2503.08434","pages":null,"arxivId":"2503.08434","arxivUrl":"https://arxiv.org/abs/2503.08434"},{"key":"journals/corr/abs-2503-09419","title":"Alias-Free Latent Diffusion Models:Improving Fractional Shift Equivariance of Diffusion Latent Space.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2503.09419","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-09419","documentUrl":"https://doi.org/10.48550/ARXIV.2503.09419","pages":null,"arxivId":"2503.09419","arxivUrl":"https://arxiv.org/abs/2503.09419"},{"key":"journals/corr/abs-2503-16153","title":"FreeFlux: Understanding and Exploiting Layer-Specific Roles in RoPE-Based MMDiT for Versatile Image Editing.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2503.16153","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-16153","documentUrl":"https://doi.org/10.48550/ARXIV.2503.16153","pages":null,"arxivId":"2503.16153","arxivUrl":"https://arxiv.org/abs/2503.16153"},{"key":"journals/corr/abs-2504-12369","title":"WORLDMEM: Long-term Consistent World Simulation with Memory.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2504.12369","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2504-12369","documentUrl":"https://doi.org/10.48550/ARXIV.2504.12369","pages":null,"arxivId":"2504.12369","arxivUrl":"https://arxiv.org/abs/2504.12369"},{"key":"journals/corr/abs-2506-24113","title":"Epona: Autoregressive Diffusion World Model for Autonomous Driving.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2506.24113","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-24113","documentUrl":"https://doi.org/10.48550/ARXIV.2506.24113","pages":null,"arxivId":"2506.24113","arxivUrl":"https://arxiv.org/abs/2506.24113"},{"key":"journals/corr/abs-2507-15728","title":"TokensGen: Harnessing Condensed Tokens for Long Video Generation.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2507.15728","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2507-15728","documentUrl":"https://doi.org/10.48550/ARXIV.2507.15728","pages":null,"arxivId":"2507.15728","arxivUrl":"https://arxiv.org/abs/2507.15728"},{"key":"journals/corr/abs-2508-10893","title":"STream3R: Scalable Sequential 3D Reconstruction with Causal Transformer.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2508.10893","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-10893","documentUrl":"https://doi.org/10.48550/ARXIV.2508.10893","pages":null,"arxivId":"2508.10893","arxivUrl":"https://arxiv.org/abs/2508.10893"},{"key":"journals/corr/abs-2508-19188","title":"FastMesh: Efficient Artistic Mesh Generation via Component Decoupling.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2508.19188","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-19188","documentUrl":"https://doi.org/10.48550/ARXIV.2508.19188","pages":null,"arxivId":"2508.19188","arxivUrl":"https://arxiv.org/abs/2508.19188"},{"key":"journals/corr/abs-2509-21263","title":"Dense Semantic Matching with VGGT Prior.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2509.21263","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-21263","documentUrl":"https://doi.org/10.48550/ARXIV.2509.21263","pages":null,"arxivId":"2509.21263","arxivUrl":"https://arxiv.org/abs/2509.21263"},{"key":"journals/corr/abs-2510-21432","title":"ArtiLatent: Realistic Articulated 3D Object Generation via Structured Latents.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2510.21432","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-21432","documentUrl":"https://doi.org/10.48550/ARXIV.2510.21432","pages":null,"arxivId":"2510.21432","arxivUrl":"https://arxiv.org/abs/2510.21432"},{"key":"journals/corr/abs-2512-03040","title":"Video4Spatial: Towards Visuospatial Intelligence with Context-Guided Video Generation.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2512.03040","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-03040","documentUrl":"https://doi.org/10.48550/ARXIV.2512.03040","pages":null,"arxivId":"2512.03040","arxivUrl":"https://arxiv.org/abs/2512.03040"},{"key":"journals/corr/abs-2512-12425","title":"BokehDepth: Enhancing Monocular Depth Estimation through Bokeh Generation.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2512.12425","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-12425","documentUrl":"https://doi.org/10.48550/ARXIV.2512.12425","pages":null,"arxivId":"2512.12425","arxivUrl":"https://arxiv.org/abs/2512.12425"},{"key":"journals/corr/abs-2512-16615","title":"Trainable Log-linear Sparse Attention for Efficient Diffusion Transformers.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2512.16615","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-16615","documentUrl":"https://doi.org/10.48550/ARXIV.2512.16615","pages":null,"arxivId":"2512.16615","arxivUrl":"https://arxiv.org/abs/2512.16615"},{"key":"journals/corr/abs-2512-19539","title":"StoryMem: Multi-shot Long Video Storytelling with Memory.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2512.19539","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-19539","documentUrl":"https://doi.org/10.48550/ARXIV.2512.19539","pages":null,"arxivId":"2512.19539","arxivUrl":"https://arxiv.org/abs/2512.19539"}],"excludedFormal":[],"labName":"MMLab@NTU","labUrl":"https://www.mmlab-ntu.com/index.html","labEvidence":"本人主页招聘段写 joining our group at MMLab@NTU 并链接。与其他签署人共享 Lab，不能据此把个人署名数直接相加当 Lab 去重产量。","labSourceUrl":"https://xingangpan.github.io/","affiliationZh":"Nanyang Technological University","sourceWarning":false,"excludedOther":[],"excludedHomonyms":[],"unassignedCandidates":[],"knownPreprintMinimum2025":null,"excludedMisattributed":[],"displayNotes":"身份已经机构或个人主页核对。2025 年正式记录 16 条，均为会议论文，所有作者位置均计入；预印本 15 条单列，不加总。","labDisplayNotes":"个人主页的招聘段写明欢迎加入其在 MMLab@NTU 的组。与 Ziwei Liu 同组，去重合计 105 条，两人的数字不能直接相加。"},{"index":20,"name":"Yi-Zhe Song","nameZh":"Yi-Zhe Song","role":"Professor","affiliation":"University of Surrey","source":"DBLP official SPARQL","profileUrl":"https://dblp.org/pid/98/1684","identifier":"98/1684","identityEvidence":[{"url":"https://dblp.org/pid/98/1684","evidence":"DBLP 唯一同名作者档案；通过作者/机构主页与发表题名交叉核对。"},{"url":"https://www.surrey.ac.uk/people/yi-zhe-song","evidence":"作者/机构页面与该 DBLP 档案交叉匹配的题名示例：Garment Ideation: Iterative View-Aware Sketch-Based Garment Modeling.；Structure-Aware 3D VR Sketch to 3D Shape Retrieval.","matchedPaperKeys":["conf/3dim/ChowdhuryWCSG22","conf/3dim/LuoGXS22"]}],"count2025":17,"conference2025":13,"journal2025":4,"preprint2025":13,"status":"verified","notes":"身份已通过机构/个人主页或 DBLP 机构信息核对；篇数为数据库记录统计，不表示每篇均由本人主导。","retrievedAt":"2026-10-19","yearPolicy":"DBLP yearOfPublication = 2025","queryUrl":"https://sparql.dblp.org/sparql?query=PREFIX%20dblp%3A%20%3Chttps%3A//dblp.org/rdf/schema%23%3E%20PREFIX%20xsd%3A%20%3Chttp%3A//www.w3.org/2001/XMLSchema%23%3E%20SELECT%20%3Fpub%20%3Ftitle%20%3Ftype%20%3Fvenue%20WHERE%20%7B%20%3Fpub%20dblp%3AauthoredBy%20%3Chttps%3A//dblp.org/pid/98/1684%3E%3B%20dblp%3AyearOfPublication%20%222025%22%5E%5Exsd%3AgYear%3B%20dblp%3Atitle%20%3Ftitle%3B%20a%20%3Ftype%20.%20OPTIONAL%20%7B%20%3Fpub%20dblp%3ApublishedIn%20%3Fvenue%20%7D%20%7D&format=json","papers":[{"key":"conf/aaai/Chen0Q0P0S25","title":"VersaGen: Unleashing Versatile Visual Control for Text-to-Image Synthesis.","type":"Inproceedings","venue":"AAAI","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1609/AAAI.V39I3.32240","sourceUrl":"https://dblp.org/rec/conf/aaai/Chen0Q0P0S25","documentUrl":"https://doi.org/10.1609/AAAI.V39I3.32240","pages":"2394-2402"},{"key":"conf/cvpr/BandyopadhyayS25","title":"FlipSketch: Flipping Static Drawings to Text-Guided Sketch Animations.","type":"Inproceedings","venue":"CVPR","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/CVPR52734.2025.02644","sourceUrl":"https://dblp.org/rec/conf/cvpr/BandyopadhyayS25","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Bandyopadhyay_FlipSketch_Flipping_Static_Drawings_to_Text-Guided_Sketch_Animations_CVPR_2025_paper.html","pages":"28394-28404"},{"key":"conf/cvpr/ChenBZS25","title":"NitroFusion: High-Fidelity Single-Step Diffusion through Dynamic Adversarial Training.","type":"Inproceedings","venue":"CVPR","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/CVPR52734.2025.00717","sourceUrl":"https://dblp.org/rec/conf/cvpr/ChenBZS25","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Chen_NitroFusion_High-Fidelity_Single-Step_Diffusion_through_Dynamic_Adversarial_Training_CVPR_2025_paper.html","pages":"7654-7663"},{"key":"conf/cvpr/KoleyDSCBS25","title":"SketchFusion: Learning Universal Sketch Features through Fusing Foundation Models.","type":"Inproceedings","venue":"CVPR","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/CVPR52734.2025.00244","sourceUrl":"https://dblp.org/rec/conf/cvpr/KoleyDSCBS25","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Koley_SketchFusion_Learning_Universal_Sketch_Features_through_Fusing_Foundation_Models_CVPR_2025_paper.html","pages":"2556-2567"},{"key":"conf/cvpr/QuMZSDS25","title":"CaricatureBooth: Data-Free Interactive Caricature Generation in a Photo Booth.","type":"Inproceedings","venue":"CVPR","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/CVPR52734.2025.01010","sourceUrl":"https://dblp.org/rec/conf/cvpr/QuMZSDS25","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Qu_CaricatureBooth_Data-Free_Interactive_Caricature_Generation_in_a_Photo_Booth_CVPR_2025_paper.html","pages":"10815-10824"},{"key":"conf/cvpr/SainMCKBS25","title":"Sketch Down the FLOPs: Towards Efficient Networks for Human Sketch.","type":"Inproceedings","venue":"CVPR","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/CVPR52734.2025.02643","sourceUrl":"https://dblp.org/rec/conf/cvpr/SainMCKBS25","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Sain_Sketch_Down_the_FLOPs_Towards_Efficient_Networks_for_Human_Sketch_CVPR_2025_paper.html","pages":"28383-28393"},{"key":"conf/eccv/BandyopadhyayCSKXBS24","title":"Do Generalised Classifiers Really Work on Human Drawn Sketches?","type":"Inproceedings","venue":"ECCV (56)","year":2025,"yearOfPublication":2025,"yearOfEvent":2024,"doi":"https://doi.org/10.1007/978-3-031-72992-8_13","sourceUrl":"https://dblp.org/rec/conf/eccv/BandyopadhyayCSKXBS24","documentUrl":"https://doi.org/10.1007/978-3-031-72992-8_13","pages":"217-235"},{"key":"conf/eccv/NgZSX24","title":"PartCraft: Crafting Creative Objects by Parts.","type":"Inproceedings","venue":"ECCV (9)","year":2025,"yearOfPublication":2025,"yearOfEvent":2024,"doi":"https://doi.org/10.1007/978-3-031-72673-6_23","sourceUrl":"https://dblp.org/rec/conf/eccv/NgZSX24","documentUrl":"https://doi.org/10.1007/978-3-031-72673-6_23","pages":"420-437"},{"key":"conf/eccv/SainCKBS24","title":"Freeview Sketching: View-Aware Fine-Grained Sketch-Based Image Retrieval.","type":"Inproceedings","venue":"ECCV (57)","year":2025,"yearOfPublication":2025,"yearOfEvent":2024,"doi":"https://doi.org/10.1007/978-3-031-72998-0_9","sourceUrl":"https://dblp.org/rec/conf/eccv/SainCKBS24","documentUrl":"https://doi.org/10.1007/978-3-031-72998-0_9","pages":"145-162"},{"key":"conf/iccv/MaityBKCSS25","title":"Doodle Your Keypoints: Sketch-Based Few-Shot Keypoint Detection.","type":"Inproceedings","venue":"ICCV","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/ICCV51701.2025.00034","sourceUrl":"https://dblp.org/rec/conf/iccv/MaityBKCSS25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.00034","pages":"284-296"},{"key":"conf/nips/ChenBZS25","title":"Normalized Attention Guidance: Universal Negative Guidance for Diffusion Models.","type":"Inproceedings","venue":"NeurIPS","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":null,"sourceUrl":"https://dblp.org/rec/conf/nips/ChenBZS25","documentUrl":"http://papers.nips.cc/paper_files/paper/2025/hash/c8aefe45deba3639af7120b141b87b50-Abstract-Conference.html","pages":null},{"key":"conf/nips/ZuoWQS25","title":"Fuse2Match: Training-Free Fusion of Flow, Diffusion, and Contrastive Models for Zero-Shot Semantic Matching.","type":"Inproceedings","venue":"NeurIPS","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":null,"sourceUrl":"https://dblp.org/rec/conf/nips/ZuoWQS25","documentUrl":"http://papers.nips.cc/paper_files/paper/2025/hash/159511050630689045bf5593e74b13cc-Abstract-Conference.html","pages":null},{"key":"conf/vcip/ZhangYPZS25","title":"Parameter-Efficient Adaptation of Vision-Language Models for Free-Hand Sketch Recognition.","type":"Inproceedings","venue":"VCIP","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/VCIP67698.2025.11396849","sourceUrl":"https://dblp.org/rec/conf/vcip/ZhangYPZS25","documentUrl":"https://doi.org/10.1109/VCIP67698.2025.11396849","pages":"1-5"},{"key":"journals/pami/GuoDSLDSM25","title":"Understanding Episode Hardness in Few-Shot Learning.","type":"Article","venue":"IEEE Trans. Pattern Anal. Mach. Intell.","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.1109/TPAMI.2024.3476075","sourceUrl":"https://dblp.org/rec/journals/pami/GuoDSLDSM25","documentUrl":"https://doi.org/10.1109/TPAMI.2024.3476075","pages":"616-633"},{"key":"journals/pr/LiLCSLMXS25","title":"Self-randomized focuses effectively boost metric-based few-shot classifiers.","type":"Article","venue":"Pattern Recognit.","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.1016/J.PATCOG.2025.111538","sourceUrl":"https://dblp.org/rec/journals/pr/LiLCSLMXS25","documentUrl":"https://doi.org/10.1016/J.PATCOG.2025.111538","pages":"111538"},{"key":"journals/tcsv/YangCDSM25","title":"Adaptive Multi-Resolution Feature Fusion for Fine-Grained Visual Classification.","type":"Article","venue":"IEEE Trans. Circuits Syst. Video Technol.","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.1109/TCSVT.2025.3546951","sourceUrl":"https://dblp.org/rec/journals/tcsv/YangCDSM25","documentUrl":"https://doi.org/10.1109/TCSVT.2025.3546951","pages":"8252-8264"},{"key":"journals/tip/TongCLWLHSM25","title":"Reserve to Adapt: Mining Inter-Class Relations for Open-Set Domain Adaptation.","type":"Article","venue":"IEEE Trans. Image Process.","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.1109/TIP.2025.3534023","sourceUrl":"https://dblp.org/rec/journals/tip/TongCLWLHSM25","documentUrl":"https://doi.org/10.1109/TIP.2025.3534023","pages":"1382-1397"}],"preprints":[{"key":"journals/corr/abs-2501-04144","title":"Chirpy3D: Continuous Part Latents for Creative 3D Bird Generation.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2501.04144","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2501-04144","documentUrl":"https://doi.org/10.48550/ARXIV.2501.04144","pages":null,"arxivId":"2501.04144","arxivUrl":"https://arxiv.org/abs/2501.04144"},{"key":"journals/corr/abs-2501-16022","title":"Freestyle Sketch-in-the-Loop Image Segmentation.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2501.16022","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2501-16022","documentUrl":"https://doi.org/10.48550/ARXIV.2501.16022","pages":null,"arxivId":"2501.16022","arxivUrl":"https://arxiv.org/abs/2501.16022"},{"key":"journals/corr/abs-2503-14129","title":"SketchFusion: Learning Universal Sketch Features through Fusing Foundation Models.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2503.14129","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-14129","documentUrl":"https://doi.org/10.48550/ARXIV.2503.14129","pages":null,"arxivId":"2503.14129","arxivUrl":"https://arxiv.org/abs/2503.14129"},{"key":"journals/corr/abs-2505-21179","title":"Normalized Attention Guidance: Universal Negative Guidance for Diffusion Model.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2505.21179","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-21179","documentUrl":"https://doi.org/10.48550/ARXIV.2505.21179","pages":null,"arxivId":"2505.21179","arxivUrl":"https://arxiv.org/abs/2505.21179"},{"key":"journals/corr/abs-2505-23763","title":"Sketch Down the FLOPs: Towards Efficient Networks for Human Sketch.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2505.23763","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-23763","documentUrl":"https://doi.org/10.48550/ARXIV.2505.23763","pages":null,"arxivId":"2505.23763","arxivUrl":"https://arxiv.org/abs/2505.23763"},{"key":"journals/corr/abs-2507-07994","title":"Doodle Your Keypoints: Sketch-Based Few-Shot Keypoint Detection.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2507.07994","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2507-07994","documentUrl":"https://doi.org/10.48550/ARXIV.2507.07994","pages":null,"arxivId":"2507.07994","arxivUrl":"https://arxiv.org/abs/2507.07994"},{"key":"journals/corr/abs-2507-20548","title":"Annotation-Free Human Sketch Quality Assessment.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2507.20548","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2507-20548","documentUrl":"https://doi.org/10.48550/ARXIV.2507.20548","pages":null,"arxivId":"2507.20548","arxivUrl":"https://arxiv.org/abs/2507.20548"},{"key":"journals/corr/abs-2508-07149","title":"SketchAnimator: Animate Sketch via Motion Customization of Text-to-Video Diffusion Models.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2508.07149","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-07149","documentUrl":"https://doi.org/10.48550/ARXIV.2508.07149","pages":null,"arxivId":"2508.07149","arxivUrl":"https://arxiv.org/abs/2508.07149"},{"key":"journals/corr/abs-2508-20665","title":"Amadeus: Autoregressive Model with Bidirectional Attribute Modelling for Symbolic Music.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2508.20665","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-20665","documentUrl":"https://doi.org/10.48550/ARXIV.2508.20665","pages":null,"arxivId":"2508.20665","arxivUrl":"https://arxiv.org/abs/2508.20665"},{"key":"journals/corr/abs-2509-13756","title":"Controllable-Continuous Color Editing in Diffusion Model via Color Mapping.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2509.13756","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-13756","documentUrl":"https://doi.org/10.48550/ARXIV.2509.13756","pages":null,"arxivId":"2509.13756","arxivUrl":"https://arxiv.org/abs/2509.13756"},{"key":"journals/corr/abs-2509-21318","title":"SD3.5-Flash: Distribution-Guided Distillation of Generative Flows.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2509.21318","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-21318","documentUrl":"https://doi.org/10.48550/ARXIV.2509.21318","pages":null,"arxivId":"2509.21318","arxivUrl":"https://arxiv.org/abs/2509.21318"},{"key":"journals/corr/abs-2510-25319","title":"4-Doodle: Text to 3D Sketches that Move!","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2510.25319","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-25319","documentUrl":"https://doi.org/10.48550/ARXIV.2510.25319","pages":null,"arxivId":"2510.25319","arxivUrl":"https://arxiv.org/abs/2510.25319"},{"key":"journals/corr/abs-2511-20426","title":"Block Cascading: Training Free Acceleration of Block-Causal Video Models.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2511.20426","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2511-20426","documentUrl":"https://doi.org/10.48550/ARXIV.2511.20426","pages":null,"arxivId":"2511.20426","arxivUrl":"https://arxiv.org/abs/2511.20426"}],"excludedFormal":[],"labName":"SketchX Lab","labUrl":null,"labEvidence":"Surrey 官方个人页明确写 leads the SketchX Lab within CVSSP；缓存未提供可确认的当前专属实验室主页，故 labUrl 留空。","labSourceUrl":"https://www.surrey.ac.uk/people/yi-zhe-song","affiliationZh":"University of Surrey","sourceWarning":false,"excludedOther":[],"excludedHomonyms":[],"unassignedCandidates":[],"knownPreprintMinimum2025":null,"excludedMisattributed":[],"displayNotes":"身份已经机构或个人主页核对。2025 年正式记录 17 条（会议 13、期刊 4），所有作者位置均计入，不表示主导或贡献份额；预印本 13 条单列，不加总。","labDisplayNotes":"Surrey 官方页面写明其领导 CVSSP 内的 SketchX Lab，据此归组；未找到可确认的实验室专属主页，故不附链接。"},{"index":21,"name":"Qianqian Wang","nameZh":"Qianqian Wang","role":"Assistant Professor","affiliation":"Harvard University","source":"DBLP official SPARQL","profileUrl":"https://dblp.org/pid/118/6735-2","identifier":"118/6735-2","identityEvidence":[{"url":"https://dblp.org/pid/118/6735-2","evidence":"DBLP 档案名 Qianqian Wang 0002；机构/履历：Cornell University, Cornell Tech, New York, NY, USa；University of California, Berkeley, CA, USA；Zhejiang University, State Key Lab of CAD&CG, Hangzhou, China"},{"url":"https://qianqianwang68.github.io/","evidence":"作者/机构页面与该 DBLP 档案交叉匹配的题名示例：Robot See Robot Do: Imitating Articulated Object Manipulation with Monocular 4D Reconstruction.；Neural 3D Scene Reconstruction with the Manhattan-world Assumption.","matchedPaperKeys":["conf/corl/KerrKWYWGK24","conf/cvpr/GuoPLW0BZ22"]},{"url":"https://seas.harvard.edu/person/qianqian-wang","evidence":"Harvard SEAS 官方档案 https://seas.harvard.edu/person/qianqian-wang 指向 qianqianwang68.github.io，与 DBLP Qianqian Wang 0002 的个人主页一致。"}],"count2025":6,"conference2025":6,"journal2025":0,"preprint2025":4,"status":"verified","notes":"身份已通过机构/个人主页或 DBLP 机构信息核对；篇数为数据库记录统计，不表示每篇均由本人主导。","retrievedAt":"2026-10-19","yearPolicy":"DBLP yearOfPublication = 2025","queryUrl":"https://sparql.dblp.org/sparql?query=PREFIX%20dblp%3A%20%3Chttps%3A//dblp.org/rdf/schema%23%3E%20PREFIX%20xsd%3A%20%3Chttp%3A//www.w3.org/2001/XMLSchema%23%3E%20SELECT%20%3Fpub%20%3Ftitle%20%3Ftype%20%3Fvenue%20WHERE%20%7B%20%3Fpub%20dblp%3AauthoredBy%20%3Chttps%3A//dblp.org/pid/118/6735-2%3E%3B%20dblp%3AyearOfPublication%20%222025%22%5E%5Exsd%3AgYear%3B%20dblp%3Atitle%20%3Ftitle%3B%20a%20%3Ftype%20.%20OPTIONAL%20%7B%20%3Fpub%20dblp%3ApublishedIn%20%3Fvenue%20%7D%20%7D&format=json","papers":[{"key":"conf/cvpr/HuangZXKZKW25","title":"Segment Any Motion in Videos.","type":"Inproceedings","venue":"CVPR","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/CVPR52734.2025.00323","sourceUrl":"https://dblp.org/rec/conf/cvpr/HuangZXKZKW25","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Huang_Segment_Any_Motion_in_Videos_CVPR_2025_paper.html","pages":"3406-3416"},{"key":"conf/cvpr/Li0C0JYKHS25","title":"MegaSaM: Accurate, Fast and Robust Structure and Motion from Casual Dynamic Videos.","type":"Inproceedings","venue":"CVPR","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/CVPR52734.2025.00981","sourceUrl":"https://dblp.org/rec/conf/cvpr/Li0C0JYKHS25","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Li_MegaSaM_Accurate_Fast_and_Robust_Structure_and_Motion_from_Casual_CVPR_2025_paper.html","pages":"10486-10496"},{"key":"conf/cvpr/Qian0TKWX25","title":"Bridging Viewpoint Gaps: Geometric Reasoning Boosts Semantic Correspondence.","type":"Inproceedings","venue":"CVPR","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/CVPR52734.2025.01081","sourceUrl":"https://dblp.org/rec/conf/cvpr/Qian0TKWX25","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Qian_Bridging_Viewpoint_Gaps_Geometric_Reasoning_Boosts_Semantic_Correspondence_CVPR_2025_paper.html","pages":"11579-11589"},{"key":"conf/cvpr/WangZHEK25","title":"Continuous 3D Perception Model with Persistent State.","type":"Inproceedings","venue":"CVPR","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/CVPR52734.2025.00983","sourceUrl":"https://dblp.org/rec/conf/cvpr/WangZHEK25","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Wang_Continuous_3D_Perception_Model_with_Persistent_State_CVPR_2025_paper.html","pages":"10510-10522"},{"key":"conf/iccv/FengZWYYBDK25","title":"ST4RTrack: Simultaneous 4D Reconstruction and Tracking in the World.","type":"Inproceedings","venue":"ICCV","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/ICCV51701.2025.00796","sourceUrl":"https://dblp.org/rec/conf/iccv/FengZWYYBDK25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.00796","pages":"8503-8513"},{"key":"conf/iccv/WangYGZALK25","title":"Shape of Motion: 4D Reconstruction From a Single Video.","type":"Inproceedings","venue":"ICCV","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/ICCV51701.2025.00901","sourceUrl":"https://dblp.org/rec/conf/iccv/WangYGZALK25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.00901","pages":"9660-9672"}],"preprints":[{"key":"journals/corr/abs-2501-12387","title":"Continuous 3D Perception Model with Persistent State.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2501.12387","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2501-12387","documentUrl":"https://doi.org/10.48550/ARXIV.2501.12387","pages":null,"arxivId":"2501.12387","arxivUrl":"https://arxiv.org/abs/2501.12387"},{"key":"journals/corr/abs-2503-22268","title":"Segment Any Motion in Videos.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2503.22268","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-22268","documentUrl":"https://doi.org/10.48550/ARXIV.2503.22268","pages":null,"arxivId":"2503.22268","arxivUrl":"https://arxiv.org/abs/2503.22268"},{"key":"journals/corr/abs-2504-13152","title":"St4RTrack: Simultaneous 4D Reconstruction and Tracking in the World.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2504.13152","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2504-13152","documentUrl":"https://doi.org/10.48550/ARXIV.2504.13152","pages":null,"arxivId":"2504.13152","arxivUrl":"https://arxiv.org/abs/2504.13152"},{"key":"journals/corr/abs-2512-10950","title":"E-RayZer: Self-supervised 3D Reconstruction as Spatial Visual Pre-training.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2512.10950","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-10950","documentUrl":"https://doi.org/10.48550/ARXIV.2512.10950","pages":null,"arxivId":"2512.10950","arxivUrl":"https://arxiv.org/abs/2512.10950"}],"excludedFormal":[],"labName":null,"labUrl":null,"labEvidence":"本人和 Harvard 官方简介确认正在建立研究组及招生，但本轮未发现其组的明确名称；Kempner Institute 任职未被改写为个人 Lab 名称。","labSourceUrl":"https://seas.harvard.edu/person/qianqian-wang","affiliationZh":"Harvard University","sourceWarning":false,"excludedOther":[],"excludedHomonyms":[],"unassignedCandidates":[],"knownPreprintMinimum2025":null,"excludedMisattributed":[],"displayNotes":"身份已经机构或个人主页核对。2025 年正式记录 6 条，均为会议论文，所有作者位置均计入；预印本 4 条单列，不加总。","labDisplayNotes":"哈佛官方简介与本人主页显示其正在组建团队、招收学生，但未见组名；不以 Kempner Institute 代替个人团队，图中以「姓名及合作者」单列。"},{"index":22,"name":"Yue Wang","nameZh":"Yue Wang","role":"Assistant Professor","affiliation":"University of Southern California","source":"DBLP official SPARQL","profileUrl":"https://dblp.org/pid/33/4822-41","identifier":"33/4822-41","identityEvidence":[{"url":"https://dblp.org/pid/33/4822-41","evidence":"DBLP 档案名 Yue Wang 0041；机构/履历：Massachusetts Institute of Technology, Cambridge, MA, USA；NVIDIA；University of Southern California, Los Angeles, CA, USA"}],"count2025":15,"conference2025":14,"journal2025":1,"preprint2025":20,"status":"verified","notes":"身份已通过机构/个人主页或 DBLP 机构信息核对；篇数为数据库记录统计，不表示每篇均由本人主导。","retrievedAt":"2026-10-19","yearPolicy":"DBLP yearOfPublication = 2025","queryUrl":"https://sparql.dblp.org/sparql?query=PREFIX%20dblp%3A%20%3Chttps%3A//dblp.org/rdf/schema%23%3E%20PREFIX%20xsd%3A%20%3Chttp%3A//www.w3.org/2001/XMLSchema%23%3E%20SELECT%20%3Fpub%20%3Ftitle%20%3Ftype%20%3Fvenue%20WHERE%20%7B%20%3Fpub%20dblp%3AauthoredBy%20%3Chttps%3A//dblp.org/pid/33/4822-41%3E%3B%20dblp%3AyearOfPublication%20%222025%22%5E%5Exsd%3AgYear%3B%20dblp%3Atitle%20%3Ftitle%3B%20a%20%3Ftype%20.%20OPTIONAL%20%7B%20%3Fpub%20dblp%3ApublishedIn%20%3Fvenue%20%7D%20%7D&format=json","papers":[{"key":"conf/cvpr/ShaoYZ0SGWPL25","title":"Learning Temporally Consistent Video Depth from Video Diffusion Priors.","type":"Inproceedings","venue":"CVPR","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/CVPR52734.2025.02127","sourceUrl":"https://dblp.org/rec/conf/cvpr/ShaoYZ0SGWPL25","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Shao_Learning_Temporally_Consistent_Video_Depth_from_Video_Diffusion_Priors_CVPR_2025_paper.html","pages":"22841-22852"},{"key":"conf/eccv/YangLLDGKWTW24","title":"Denoising Vision Transformers.","type":"Inproceedings","venue":"ECCV (85)","year":2025,"yearOfPublication":2025,"yearOfEvent":2024,"doi":"https://doi.org/10.1007/978-3-031-73013-9_26","sourceUrl":"https://dblp.org/rec/conf/eccv/YangLLDGKWTW24","documentUrl":"https://doi.org/10.1007/978-3-031-73013-9_26","pages":"453-469"},{"key":"conf/humanoids/MaoZSHSYZGMGW25","title":"Universal Humanoid Robot Pose Learning from Internet Human Videos.","type":"Inproceedings","venue":"Humanoids","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/HUMANOIDS65713.2025.11203143","sourceUrl":"https://dblp.org/rec/conf/humanoids/MaoZSHSYZGMGW25","documentUrl":"https://doi.org/10.1109/HUMANOIDS65713.2025.11203143","pages":"1-8"},{"key":"conf/iccv/HanJLWIYLWPFL25","title":"Extrapolated Urban View Synthesis Benchmark.","type":"Inproceedings","venue":"ICCV","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/ICCV51701.2025.02667","sourceUrl":"https://dblp.org/rec/conf/iccv/HanJLWIYLWPFL25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.02667","pages":"28718-28728"},{"key":"conf/iccv/LuRYSWGWCCFH25","title":"InfiniCube: Unbounded and Controllable Dynamic 3D Driving Scene Generation with World-Guided Video Models.","type":"Inproceedings","venue":"ICCV","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/ICCV51701.2025.02532","sourceUrl":"https://dblp.org/rec/conf/iccv/LuRYSWGWCCFH25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.02532","pages":"27272-27283"},{"key":"conf/iclr/0002HI00LYSIKX025","title":"STORM: Spatio-TempOral Reconstruction Model For Large-Scale Outdoor Scenes.","type":"Inproceedings","venue":"ICLR","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":null,"sourceUrl":"https://dblp.org/rec/conf/iclr/0002HI00LYSIKX025","documentUrl":"https://openreview.net/forum?id=M2NFWRPMUd","pages":null},{"key":"conf/iclr/0004LD0G25","title":"Multiview Equivariance Improves 3D Correspondence Understanding with Minimal Feature Finetuning.","type":"Inproceedings","venue":"ICLR","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":null,"sourceUrl":"https://dblp.org/rec/conf/iclr/0004LD0G25","documentUrl":"https://openreview.net/forum?id=CNO4rbSV6v","pages":null},{"key":"conf/iclr/ChenYHLEILGF0SW25","title":"OmniRe: Omni Urban Scene Reconstruction.","type":"Inproceedings","venue":"ICLR","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":null,"sourceUrl":"https://dblp.org/rec/conf/iclr/ChenYHLEILGF0SW25","documentUrl":"https://openreview.net/forum?id=11xgiMEI5o","pages":null},{"key":"conf/iclr/ChoICS0WLYK0025","title":"Language-Image Models with 3D Understanding.","type":"Inproceedings","venue":"ICLR","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":null,"sourceUrl":"https://dblp.org/rec/conf/iclr/ChoICS0WLYK0025","documentUrl":"https://openreview.net/forum?id=yaQbTAD2JJ","pages":null},{"key":"conf/iclr/ChowMLSG025","title":"PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding.","type":"Inproceedings","venue":"ICLR","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":null,"sourceUrl":"https://dblp.org/rec/conf/iclr/ChowMLSG025","documentUrl":"https://openreview.net/forum?id=Q6a9W6kzv5","pages":null},{"key":"conf/iclr/LuYXLI0025","title":"LoRA3D: Low-Rank Self-Calibration of 3D Geometric Foundation models.","type":"Inproceedings","venue":"ICLR","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":null,"sourceUrl":"https://dblp.org/rec/conf/iclr/LuYXLI0025","documentUrl":"https://openreview.net/forum?id=LSp4KBhAom","pages":null},{"key":"conf/icra/MaoLICWYXXPW25","title":"DreamDrive: Generative 4D Scene Modeling from Street View Images.","type":"Inproceedings","venue":"ICRA","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/ICRA55743.2025.11127463","sourceUrl":"https://dblp.org/rec/conf/icra/MaoLICWYXXPW25","documentUrl":"https://doi.org/10.1109/ICRA55743.2025.11127463","pages":"367-374"},{"key":"conf/icra/YePZGHCWR25","title":"SMART: Advancing Scalable Map Priors for Driving Topology Reasoning.","type":"Inproceedings","venue":"ICRA","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/ICRA55743.2025.11127994","sourceUrl":"https://dblp.org/rec/conf/icra/YePZGHCWR25","documentUrl":"https://doi.org/10.1109/ICRA55743.2025.11127994","pages":"3298-3304"},{"key":"conf/nips/LiFCLYFPYWWZPW25","title":"Martian World Model: Controllable Video Synthesis with Physically Accurate 3D Reconstructions.","type":"Inproceedings","venue":"NeurIPS","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":null,"sourceUrl":"https://dblp.org/rec/conf/nips/LiFCLYFPYWWZPW25","documentUrl":"http://papers.nips.cc/paper_files/paper/2025/hash/ddb6b9fea6a366579e38bdbf2e5591a8-Abstract-Datasets_and_Benchmarks_Track.html","pages":null},{"key":"journals/tmlr/SmithHSSGW25","title":"SIRE: SE(3) Intrinsic Rigidity Embeddings.","type":"Article","venue":"Trans. Mach. Learn. Res.","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":null,"sourceUrl":"https://dblp.org/rec/journals/tmlr/SmithHSSGW25","documentUrl":"https://openreview.net/forum?id=OZ9H0TOYMt","pages":null}],"preprints":[{"key":"journals/corr/abs-2501-00601","title":"DreamDrive: Generative 4D Scene Modeling from Street View Images.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2501.00601","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2501-00601","documentUrl":"https://doi.org/10.48550/ARXIV.2501.00601","pages":null,"arxivId":"2501.00601","arxivUrl":"https://arxiv.org/abs/2501.00601"},{"key":"journals/corr/abs-2501-00602","title":"STORM: Spatio-Temporal Reconstruction Model for Large-Scale Outdoor Scenes.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2501.00602","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2501-00602","documentUrl":"https://doi.org/10.48550/ARXIV.2501.00602","pages":null,"arxivId":"2501.00602","arxivUrl":"https://arxiv.org/abs/2501.00602"},{"key":"journals/corr/abs-2501-16411","title":"PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2501.16411","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2501-16411","documentUrl":"https://doi.org/10.48550/ARXIV.2501.16411","pages":null,"arxivId":"2501.16411","arxivUrl":"https://arxiv.org/abs/2501.16411"},{"key":"journals/corr/abs-2502-04329","title":"SMART: Advancing Scalable Map Priors for Driving Topology Reasoning.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2502.04329","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2502-04329","documentUrl":"https://doi.org/10.48550/ARXIV.2502.04329","pages":null,"arxivId":"2502.04329","arxivUrl":"https://arxiv.org/abs/2502.04329"},{"key":"journals/corr/abs-2503-07739","title":"SIRE: SE(3) Intrinsic Rigidity Embeddings.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2503.07739","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-07739","documentUrl":"https://doi.org/10.48550/ARXIV.2503.07739","pages":null,"arxivId":"2503.07739","arxivUrl":"https://arxiv.org/abs/2503.07739"},{"key":"journals/corr/abs-2504-18904","title":"RoboVerse: Towards a Unified Platform, Dataset and Benchmark for Scalable and Generalizable Robot Learning.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2504.18904","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2504-18904","documentUrl":"https://doi.org/10.48550/ARXIV.2504.18904","pages":null,"arxivId":"2504.18904","arxivUrl":"https://arxiv.org/abs/2504.18904"},{"key":"journals/corr/abs-2505-09698","title":"ManipBench: Benchmarking Vision-Language Models for Low-Level Robot Manipulation.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2505.09698","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-09698","documentUrl":"https://doi.org/10.48550/ARXIV.2505.09698","pages":null,"arxivId":"2505.09698","arxivUrl":"https://arxiv.org/abs/2505.09698"},{"key":"journals/corr/abs-2506-09366","title":"SkillBlender: Towards Versatile Humanoid Whole-Body Loco-Manipulation via Skill Blending.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2506.09366","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-09366","documentUrl":"https://doi.org/10.48550/ARXIV.2506.09366","pages":null,"arxivId":"2506.09366","arxivUrl":"https://arxiv.org/abs/2506.09366"},{"key":"journals/corr/abs-2506-19201","title":"The MOTIF Hand: A Robotic Hand for Multimodal Observations with Thermal, Inertial, and Force Sensors.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2506.19201","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-19201","documentUrl":"https://doi.org/10.48550/ARXIV.2506.19201","pages":null,"arxivId":"2506.19201","arxivUrl":"https://arxiv.org/abs/2506.19201"},{"key":"journals/corr/abs-2507-07978","title":"Martian World Models: Controllable Video Synthesis with Physically Accurate 3D Reconstructions.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2507.07978","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2507-07978","documentUrl":"https://doi.org/10.48550/ARXIV.2507.07978","pages":null,"arxivId":"2507.07978","arxivUrl":"https://arxiv.org/abs/2507.07978"},{"key":"journals/corr/abs-2508-08254","title":"Learning an Implicit Physics Model for Image-based Fluid Simulation.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2508.08254","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-08254","documentUrl":"https://doi.org/10.48550/ARXIV.2508.08254","pages":null,"arxivId":"2508.08254","arxivUrl":"https://arxiv.org/abs/2508.08254"},{"key":"journals/corr/abs-2509-22970","title":"Robot Learning from Any Images.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2509.22970","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-22970","documentUrl":"https://doi.org/10.48550/ARXIV.2509.22970","pages":null,"arxivId":"2509.22970","arxivUrl":"https://arxiv.org/abs/2509.22970"},{"key":"journals/corr/abs-2510-05070","title":"ResMimic: From General Motion Tracking to Humanoid Whole-body Loco-Manipulation via Residual Learning.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2510.05070","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-05070","documentUrl":"https://doi.org/10.48550/ARXIV.2510.05070","pages":null,"arxivId":"2510.05070","arxivUrl":"https://arxiv.org/abs/2510.05070"},{"key":"journals/corr/abs-2510-08807","title":"Humanoid Everyday: A Comprehensive Robotic Dataset for Open-World Humanoid Manipulation.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2510.08807","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-08807","documentUrl":"https://doi.org/10.48550/ARXIV.2510.08807","pages":null,"arxivId":"2510.08807","arxivUrl":"https://arxiv.org/abs/2510.08807"},{"key":"journals/corr/abs-2511-01163","title":"ROVER: Benchmarking Reciprocal Cross-Modal Reasoning for Omnimodal Generation.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2511.01163","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2511-01163","documentUrl":"https://doi.org/10.48550/ARXIV.2511.01163","pages":null,"arxivId":"2511.01163","arxivUrl":"https://arxiv.org/abs/2511.01163"},{"key":"journals/corr/abs-2511-07416","title":"Robot Learning from a Physical World Model.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2511.07416","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2511-07416","documentUrl":"https://doi.org/10.48550/ARXIV.2511.07416","pages":null,"arxivId":"2511.07416","arxivUrl":"https://arxiv.org/abs/2511.07416"},{"key":"journals/corr/abs-2511-17441","title":"RoboCOIN: An Open-Sourced Bimanual Robotic Data COllection for INtegrated Manipulation.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2511.17441","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2511-17441","documentUrl":"https://doi.org/10.48550/ARXIV.2511.17441","pages":null,"arxivId":"2511.17441","arxivUrl":"https://arxiv.org/abs/2511.17441"},{"key":"journals/corr/abs-2512-10947","title":"Towards Efficient and Effective Multi-Camera Encoding for End-to-End Driving.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2512.10947","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-10947","documentUrl":"https://doi.org/10.48550/ARXIV.2512.10947","pages":null,"arxivId":"2512.10947","arxivUrl":"https://arxiv.org/abs/2512.10947"},{"key":"journals/corr/abs-2512-11797","title":"AnchorDream: Repurposing Video Diffusion for Embodiment-Aware Robot Data Synthesis.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2512.11797","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-11797","documentUrl":"https://doi.org/10.48550/ARXIV.2512.11797","pages":null,"arxivId":"2512.11797","arxivUrl":"https://arxiv.org/abs/2512.11797"},{"key":"journals/corr/abs-2512-16881","title":"PolaRiS: Scalable Real-to-Sim Evaluations for Generalist Robot Policies.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2512.16881","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-16881","documentUrl":"https://doi.org/10.48550/ARXIV.2512.16881","pages":null,"arxivId":"2512.16881","arxivUrl":"https://arxiv.org/abs/2512.16881"}],"excludedFormal":[],"labName":"Physical Superintelligence Lab","labUrl":"https://psi-lab.ai","labEvidence":"本人当前主页明确 leading the Physical Superintelligence Lab 并直接链接；旧导航仍出现 usc-gvl 地址，因此采用正文当前名称，不沿用旧域名推断。","labSourceUrl":"https://yuewang.xyz/","affiliationZh":"University of Southern California","sourceWarning":false,"excludedOther":[],"excludedHomonyms":[],"unassignedCandidates":[],"knownPreprintMinimum2025":null,"excludedMisattributed":[],"displayNotes":"身份已经机构或个人主页核对。2025 年正式记录 15 条（会议 14、期刊 1），所有作者位置均计入，不表示主导或贡献份额；预印本 20 条单列，不加总。","labDisplayNotes":"本人主页正文写明其领导 Physical Superintelligence Lab，并链接 psi-lab.ai；导航仍有旧的 USC-GVL 地址，这里采用正文中的当前名称。"},{"index":23,"name":"Qi Wu","nameZh":"Qi Wu","role":"Associate Professor","affiliation":"Adelaide University","source":"DBLP official SPARQL","profileUrl":"https://dblp.org/pid/96/3446-1","identifier":"96/3446-1","identityEvidence":[{"url":"https://dblp.org/pid/96/3446-1","evidence":"DBLP 档案名 Qi Wu 0001；机构/履历：University of Adelaide, School of Computer Science, Australian Centre for Robotic Vision, Adelaide, Australia；University of Bath, UK"}],"count2025":30,"conference2025":24,"journal2025":6,"preprint2025":28,"status":"verified","notes":"身份已通过机构/个人主页或 DBLP 机构信息核对；篇数为数据库记录统计，不表示每篇均由本人主导。","retrievedAt":"2026-10-19","yearPolicy":"DBLP yearOfPublication = 2025","queryUrl":"https://sparql.dblp.org/sparql?query=PREFIX%20dblp%3A%20%3Chttps%3A//dblp.org/rdf/schema%23%3E%20PREFIX%20xsd%3A%20%3Chttp%3A//www.w3.org/2001/XMLSchema%23%3E%20SELECT%20%3Fpub%20%3Ftitle%20%3Ftype%20%3Fvenue%20WHERE%20%7B%20%3Fpub%20dblp%3AauthoredBy%20%3Chttps%3A//dblp.org/pid/96/3446-1%3E%3B%20dblp%3AyearOfPublication%20%222025%22%5E%5Exsd%3AgYear%3B%20dblp%3Atitle%20%3Ftitle%3B%20a%20%3Ftype%20.%20OPTIONAL%20%7B%20%3Fpub%20dblp%3ApublishedIn%20%3Fvenue%20%7D%20%7D&format=json","papers":[{"key":"conf/aaai/GaiW0WZ025","title":"MFL-Owner: Ownership Protection for Multi-modal Federated Learning via Orthogonal Transform Watermark.","type":"Inproceedings","venue":"AAAI","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1609/AAAI.V39I3.32313","sourceUrl":"https://dblp.org/rec/conf/aaai/GaiW0WZ025","documentUrl":"https://doi.org/10.1609/AAAI.V39I3.32313","pages":"3049-3058"},{"key":"conf/accv/ChenXWCATCW24","title":"Act Like a Radiologist: Radiology Report Generation Across Anatomical Regions.","type":"Inproceedings","venue":"ACCV (6)","year":2025,"yearOfPublication":2025,"yearOfEvent":2024,"doi":"https://doi.org/10.1007/978-981-96-0960-4_3","sourceUrl":"https://dblp.org/rec/conf/accv/ChenXWCATCW24","documentUrl":"https://doi.org/10.1007/978-981-96-0960-4_3","pages":"36-52"},{"key":"conf/cvpr/TangYGZ0G025","title":"Missing Target-Relevant Information Prediction with World Model for Accurate Zero-Shot Composed Image Retrieval.","type":"Inproceedings","venue":"CVPR","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/CVPR52734.2025.02308","sourceUrl":"https://dblp.org/rec/conf/cvpr/TangYGZ0G025","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Tang_Missing_Target-Relevant_Information_Prediction_with_World_Model_for_Accurate_Zero-Shot_CVPR_2025_paper.html","pages":"24785-24795"},{"key":"conf/cvpr/TangZQYG0LR0025","title":"Reason-before-Retrieve: One-Stage Reflective Chain-of-Thoughts for Training-Free Zero-Shot Composed Image Retrieval.","type":"Inproceedings","venue":"CVPR","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/CVPR52734.2025.01343","sourceUrl":"https://dblp.org/rec/conf/cvpr/TangZQYG0LR0025","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Tang_Reason-before-Retrieve_One-Stage_Reflective_Chain-of-Thoughts_for_Training-Free_Zero-Shot_Composed_Image_Retrieval_CVPR_2025_paper.html","pages":"14400-14410"},{"key":"conf/dicta/ChenWX25","title":"MoE-Enhanced-TTT: Advancing Medical Image Segmentation.","type":"Inproceedings","venue":"DICTA","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/DICTA68720.2025.11302485","sourceUrl":"https://dblp.org/rec/conf/dicta/ChenWX25","documentUrl":"https://doi.org/10.1109/DICTA68720.2025.11302485","pages":"1-8"},{"key":"conf/dicta/ChenZW25","title":"Streaming Video Diffusion: Online Video Editing with Diffusion Models.","type":"Inproceedings","venue":"DICTA","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/DICTA68720.2025.11302466","sourceUrl":"https://dblp.org/rec/conf/dicta/ChenZW25","documentUrl":"https://doi.org/10.1109/DICTA68720.2025.11302466","pages":"1-9"},{"key":"conf/dicta/WangCTKYXW25","title":"X-Gen: Enhancing Radiology Report Generation via LLM-Driven Data Augmentation and Decoupled Training.","type":"Inproceedings","venue":"DICTA","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/DICTA68720.2025.11302459","sourceUrl":"https://dblp.org/rec/conf/dicta/WangCTKYXW25","documentUrl":"https://doi.org/10.1109/DICTA68720.2025.11302459","pages":"1-8"},{"key":"conf/dicta/WangCXW25","title":"Filling in the Missing Piece: Advancing Automated Radiology Report Generation with Clinical Insights.","type":"Inproceedings","venue":"DICTA","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/DICTA68720.2025.11302443","sourceUrl":"https://dblp.org/rec/conf/dicta/WangCXW25","documentUrl":"https://doi.org/10.1109/DICTA68720.2025.11302443","pages":"1-8"},{"key":"conf/eccv/QiaoLLLW24","title":"LLM as Copilot for Coarse-Grained Vision-and-Language Navigation.","type":"Inproceedings","venue":"ECCV (5)","year":2025,"yearOfPublication":2025,"yearOfEvent":2024,"doi":"https://doi.org/10.1007/978-3-031-72652-1_27","sourceUrl":"https://dblp.org/rec/conf/eccv/QiaoLLLW24","documentUrl":"https://doi.org/10.1007/978-3-031-72652-1_27","pages":"459-476"},{"key":"conf/eccv/ShiQWLD24","title":"Improving Online Source-Free Domain Adaptation for Object Detection by Unsupervised Data Acquisition.","type":"Inproceedings","venue":"ECCV Workshops (7)","year":2025,"yearOfPublication":2025,"yearOfEvent":2024,"doi":"https://doi.org/10.1007/978-3-031-91767-7_14","sourceUrl":"https://dblp.org/rec/conf/eccv/ShiQWLD24","documentUrl":"https://doi.org/10.1007/978-3-031-91767-7_14","pages":"195-205"},{"key":"conf/eccv/ZhouHWWW24","title":"NavGPT-2: Unleashing Navigational Reasoning Capability for Large Vision-Language Models.","type":"Inproceedings","venue":"ECCV (7)","year":2025,"yearOfPublication":2025,"yearOfEvent":2024,"doi":"https://doi.org/10.1007/978-3-031-72667-5_15","sourceUrl":"https://dblp.org/rec/conf/eccv/ZhouHWWW24","documentUrl":"https://doi.org/10.1007/978-3-031-72667-5_15","pages":"260-278"},{"key":"conf/iccv/ZhangQWYWWL25","title":"COSMO: Combination of Selective Memorization for Low-Cost Vision-and-Language Navigation.","type":"Inproceedings","venue":"ICCV","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/ICCV51701.2025.00523","sourceUrl":"https://dblp.org/rec/conf/iccv/ZhangQWYWWL25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.00523","pages":"5511-5522"},{"key":"conf/iccv/ZhouHWZBW25","title":"SAME: Learning Generic Language-Guided Visual Navigation with State-Adaptive Mixture of Experts.","type":"Inproceedings","venue":"ICCV","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/ICCV51701.2025.00731","sourceUrl":"https://dblp.org/rec/conf/iccv/ZhouHWZBW25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.00731","pages":"7794-7807"},{"key":"conf/iclr/0010Z025","title":"Are Large Vision Language Models Good Game Players?","type":"Inproceedings","venue":"ICLR","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":null,"sourceUrl":"https://dblp.org/rec/conf/iclr/0010Z025","documentUrl":"https://openreview.net/forum?id=c4OGMNyzPT","pages":null},{"key":"conf/iclr/HongQWLW25","title":"General Scene Adaptation for Vision-and-Language Navigation.","type":"Inproceedings","venue":"ICLR","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":null,"sourceUrl":"https://dblp.org/rec/conf/iclr/HongQWLW25","documentUrl":"https://openreview.net/forum?id=2oKkQTyfz7","pages":null},{"key":"conf/icra/LiZHSLQW25","title":"Ground-Level Viewpoint Vision-and-Language Navigation in Continuous Environments.","type":"Inproceedings","venue":"ICRA","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/ICRA55743.2025.11127275","sourceUrl":"https://dblp.org/rec/conf/icra/LiZHSLQW25","documentUrl":"https://doi.org/10.1109/ICRA55743.2025.11127275","pages":"5266-5273"},{"key":"conf/icra/QiaoLWWLZTW25","title":"Open-Nav: Exploring Zero-Shot Vision-and-Language Navigation in Continuous Environment with Open-Source LLMs.","type":"Inproceedings","venue":"ICRA","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/ICRA55743.2025.11127584","sourceUrl":"https://dblp.org/rec/conf/icra/QiaoLWWLZTW25","documentUrl":"https://doi.org/10.1109/ICRA55743.2025.11127584","pages":"6710-6717"},{"key":"conf/icra/ZhuQZHWL25","title":"MiniVLN: Efficient Vision-and-Language Navigation by Progressive Knowledge Distillation.","type":"Inproceedings","venue":"ICRA","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/ICRA55743.2025.11127306","sourceUrl":"https://dblp.org/rec/conf/icra/ZhuQZHWL25","documentUrl":"https://doi.org/10.1109/ICRA55743.2025.11127306","pages":"97-103"},{"key":"conf/ijcai/LeiG0Z025","title":"Secure and Efficient Watermarking for Latent Diffusion Models in Model Distribution Scenarios.","type":"Inproceedings","venue":"IJCAI","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.24963/IJCAI.2025/831","sourceUrl":"https://dblp.org/rec/conf/ijcai/LeiG0Z025","documentUrl":"https://doi.org/10.24963/IJCAI.2025/831","pages":"7473-7481"},{"key":"conf/iros/ShiLLXDQW25","title":"SmartWay: Enhanced Waypoint Prediction and Backtracking for Zero-Shot Vision-and-Language Navigation.","type":"Inproceedings","venue":"IROS","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/IROS60139.2025.11246147","sourceUrl":"https://dblp.org/rec/conf/iros/ShiLLXDQW25","documentUrl":"https://doi.org/10.1109/IROS60139.2025.11246147","pages":"16923-16930"},{"key":"conf/mm/LiuZQ0025","title":"VLN-ChEnv: Vision-language Navigation in Changeable Environments.","type":"Inproceedings","venue":"ACM Multimedia","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1145/3746027.3755202","sourceUrl":"https://dblp.org/rec/conf/mm/LiuZQ0025","documentUrl":"https://doi.org/10.1145/3746027.3755202","pages":"3798-3807"},{"key":"conf/nips/QiaoHLAZXWW25","title":"NavBench: Probing Multimodal Large Language Models for Embodied Navigation.","type":"Inproceedings","venue":"NeurIPS","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":null,"sourceUrl":"https://dblp.org/rec/conf/nips/QiaoHLAZXWW25","documentUrl":"http://papers.nips.cc/paper_files/paper/2025/hash/8932bbe603280f51d425e2781cd6ea6e-Abstract-Conference.html","pages":null},{"key":"conf/wacv/LiuZQZLGWHWL25","title":"GroundingMate: Aiding Object Grounding for Goal-Oriented Vision-and-Language Navigation.","type":"Inproceedings","venue":"WACV","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/WACV61041.2025.00180","sourceUrl":"https://dblp.org/rec/conf/wacv/LiuZQZLGWHWL25","documentUrl":"https://doi.org/10.1109/WACV61041.2025.00180","pages":"1775-1784"},{"key":"conf/wasa/ZhuangYQTGXW25","title":"Soft Multi-view Representation Learning for Disambiguating Text-Based Person Retrieval.","type":"Inproceedings","venue":"WASA (1)","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1007/978-981-96-8725-1_12","sourceUrl":"https://dblp.org/rec/conf/wasa/ZhuangYQTGXW25","documentUrl":"https://doi.org/10.1007/978-981-96-8725-1_12","pages":"143-156"},{"key":"journals/csr/ZhangCYGCCWXX25","title":"Advances in attention mechanisms for medical image segmentation.","type":"Article","venue":"Comput. Sci. Rev.","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.1016/J.COSREV.2024.100721","sourceUrl":"https://dblp.org/rec/journals/csr/ZhangCYGCCWXX25","documentUrl":"https://doi.org/10.1016/J.COSREV.2024.100721","pages":"100721"},{"key":"journals/cvm/TianYW25","title":"Script-to-Storyboard: A New Contextual Retrieval Dataset and Benchmark.","type":"Article","venue":"Comput. Vis. Media","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.26599/CVM.2025.9450322","sourceUrl":"https://dblp.org/rec/journals/cvm/TianYW25","documentUrl":"https://doi.org/10.26599/CVM.2025.9450322","pages":"103-122"},{"key":"journals/ijautcomp/Tan0H0LZ25","title":"Auto-3D-house Design from Structured User Requirements.","type":"Article","venue":"Int. J. Autom. Comput.","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.1007/S11633-024-1498-0","sourceUrl":"https://dblp.org/rec/journals/ijautcomp/Tan0H0LZ25","documentUrl":"https://doi.org/10.1007/S11633-024-1498-0","pages":"368-385"},{"key":"journals/pami/LiCQZWSHY25","title":"Dubbing Movies via Hierarchical Phoneme Modeling and Acoustic Diffusion Denoising.","type":"Article","venue":"IEEE Trans. Pattern Anal. Mach. Intell.","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.1109/TPAMI.2025.3597267","sourceUrl":"https://dblp.org/rec/journals/pami/LiCQZWSHY25","documentUrl":"https://doi.org/10.1109/TPAMI.2025.3597267","pages":"10361-10377"},{"key":"journals/tjs/LiangYDWG25","title":"Cs-pbft: a comprehensive scoring-based Practical Byzantine Fault Tolerance consensus algorithm.","type":"Article","venue":"J. Supercomput.","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.1007/S11227-025-07342-3","sourceUrl":"https://dblp.org/rec/journals/tjs/LiangYDWG25","documentUrl":"https://doi.org/10.1007/S11227-025-07342-3","pages":"859"},{"key":"journals/tmm/WenTWWW25","title":"Enhanced Reasoning via Multimodal LLMs and Collaborative Inference.","type":"Article","venue":"IEEE Trans. Multim.","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.1109/TMM.2025.3590940","sourceUrl":"https://dblp.org/rec/journals/tmm/WenTWWW25","documentUrl":"https://doi.org/10.1109/TMM.2025.3590940","pages":"7166-7178"}],"preprints":[{"key":"journals/corr/abs-2501-17403","title":"General Scene Adaptation for Vision-and-Language Navigation.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2501.17403","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2501-17403","documentUrl":"https://doi.org/10.48550/ARXIV.2501.17403","pages":null,"arxivId":"2501.17403","arxivUrl":"https://arxiv.org/abs/2501.17403"},{"key":"journals/corr/abs-2502-02024","title":"UD-Mamba: A pixel-level uncertainty-driven Mamba model for medical image segmentation.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2502.02024","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2502-02024","documentUrl":"https://doi.org/10.48550/ARXIV.2502.02024","pages":null,"arxivId":"2502.02024","arxivUrl":"https://arxiv.org/abs/2502.02024"},{"key":"journals/corr/abs-2502-04400","title":"Adaptive Prototype Knowledge Transfer for Federated Learning with Mixed Modalities and Heterogeneous Tasks.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2502.04400","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2502-04400","documentUrl":"https://doi.org/10.48550/ARXIV.2502.04400","pages":null,"arxivId":"2502.04400","arxivUrl":"https://arxiv.org/abs/2502.04400"},{"key":"journals/corr/abs-2502-09152","title":"Vertical Federated Continual Learning via Evolving Prototype Knowledge.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2502.09152","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2502-09152","documentUrl":"https://doi.org/10.48550/ARXIV.2502.09152","pages":null,"arxivId":"2502.09152","arxivUrl":"https://arxiv.org/abs/2502.09152"},{"key":"journals/corr/abs-2502-13345","title":"Secure and Efficient Watermarking for Latent Diffusion Models in Model Distribution Scenarios.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2502.13345","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2502-13345","documentUrl":"https://doi.org/10.48550/ARXIV.2502.13345","pages":null,"arxivId":"2502.13345","arxivUrl":"https://arxiv.org/abs/2502.13345"},{"key":"journals/corr/abs-2502-19024","title":"Ground-level Viewpoint Vision-and-Language Navigation in Continuous Environments.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2502.19024","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2502-19024","documentUrl":"https://doi.org/10.48550/ARXIV.2502.19024","pages":null,"arxivId":"2502.19024","arxivUrl":"https://arxiv.org/abs/2502.19024"},{"key":"journals/corr/abs-2503-02358","title":"Are Large Vision Language Models Good Game Players?","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2503.02358","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-02358","documentUrl":"https://doi.org/10.48550/ARXIV.2503.02358","pages":null,"arxivId":"2503.02358","arxivUrl":"https://arxiv.org/abs/2503.02358"},{"key":"journals/corr/abs-2503-06847","title":"MADS: Multi-Attribute Document Supervision for Zero-Shot Image Classification.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2503.06847","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-06847","documentUrl":"https://doi.org/10.48550/ARXIV.2503.06847","pages":null,"arxivId":"2503.06847","arxivUrl":"https://arxiv.org/abs/2503.06847"},{"key":"journals/corr/abs-2503-10069","title":"SmartWay: Enhanced Waypoint Prediction and Backtracking for Zero-Shot Vision-and-Language Navigation.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2503.10069","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-10069","documentUrl":"https://doi.org/10.48550/ARXIV.2503.10069","pages":null,"arxivId":"2503.10069","arxivUrl":"https://arxiv.org/abs/2503.10069"},{"key":"journals/corr/abs-2503-17109","title":"Missing Target-Relevant Information Prediction with World Model for Accurate Zero-Shot Composed Image Retrieval.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2503.17109","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-17109","documentUrl":"https://doi.org/10.48550/ARXIV.2503.17109","pages":null,"arxivId":"2503.17109","arxivUrl":"https://arxiv.org/abs/2503.17109"},{"key":"journals/corr/abs-2503-19308","title":"A Comprehensive Analysis of Mamba for 3D Volumetric Medical Image Segmentation.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2503.19308","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-19308","documentUrl":"https://doi.org/10.48550/ARXIV.2503.19308","pages":null,"arxivId":"2503.19308","arxivUrl":"https://arxiv.org/abs/2503.19308"},{"key":"journals/corr/abs-2503-24065","title":"COSMO: Combination of Selective Memorization for Low-cost Vision-and-Language Navigation.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2503.24065","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-24065","documentUrl":"https://doi.org/10.48550/ARXIV.2503.24065","pages":null,"arxivId":"2503.24065","arxivUrl":"https://arxiv.org/abs/2503.24065"},{"key":"journals/corr/abs-2504-11774","title":"PCDiff: Proactive Control for Ownership Protection in Diffusion Models with Watermark Compatibility.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2504.11774","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2504-11774","documentUrl":"https://doi.org/10.48550/ARXIV.2504.11774","pages":null,"arxivId":"2504.11774","arxivUrl":"https://arxiv.org/abs/2504.11774"},{"key":"journals/corr/abs-2504-18579","title":"ZipR1: Reinforcing Token Sparsity in MLLMs.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2504.18579","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2504-18579","documentUrl":"https://doi.org/10.48550/ARXIV.2504.18579","pages":null,"arxivId":"2504.18579","arxivUrl":"https://arxiv.org/abs/2504.18579"},{"key":"journals/corr/abs-2504-21044","title":"AGATE: Stealthy Black-box Watermarking for Multimodal Model Copyright Protection.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2504.21044","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2504-21044","documentUrl":"https://doi.org/10.48550/ARXIV.2504.21044","pages":null,"arxivId":"2504.21044","arxivUrl":"https://arxiv.org/abs/2504.21044"},{"key":"journals/corr/abs-2505-07500","title":"Learning to Reason and Navigate: Parameter Efficient Action Planning with Large Language Models.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2505.07500","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-07500","documentUrl":"https://doi.org/10.48550/ARXIV.2505.07500","pages":null,"arxivId":"2505.07500","arxivUrl":"https://arxiv.org/abs/2505.07500"},{"key":"journals/corr/abs-2505-12443","title":"BadNAVer: Exploring Jailbreak Attacks On Vision-and-Language Navigation.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2505.12443","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-12443","documentUrl":"https://doi.org/10.48550/ARXIV.2505.12443","pages":null,"arxivId":"2505.12443","arxivUrl":"https://arxiv.org/abs/2505.12443"},{"key":"journals/corr/abs-2506-01031","title":"NavBench: Probing Multimodal Large Language Models for Embodied Navigation.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2506.01031","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-01031","documentUrl":"https://doi.org/10.48550/ARXIV.2506.01031","pages":null,"arxivId":"2506.01031","arxivUrl":"https://arxiv.org/abs/2506.01031"},{"key":"journals/corr/abs-2508-10315","title":"A Vision-Language Pre-training Model-Guided Approach for Mitigating Backdoor Attacks in Federated Learning.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2508.10315","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-10315","documentUrl":"https://doi.org/10.48550/ARXIV.2508.10315","pages":null,"arxivId":"2508.10315","arxivUrl":"https://arxiv.org/abs/2508.10315"},{"key":"journals/corr/abs-2509-12129","title":"Embodied Navigation Foundation Model.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2509.12129","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-12129","documentUrl":"https://doi.org/10.48550/ARXIV.2509.12129","pages":null,"arxivId":"2509.12129","arxivUrl":"https://arxiv.org/abs/2509.12129"},{"key":"journals/corr/abs-2509-16673","title":"MedCutMix: A Data-Centric Approach to Improve Radiology Vision-Language Pre-training with Disease Awareness.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2509.16673","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-16673","documentUrl":"https://doi.org/10.48550/ARXIV.2509.16673","pages":null,"arxivId":"2509.16673","arxivUrl":"https://arxiv.org/abs/2509.16673"},{"key":"journals/corr/abs-2509-24910","title":"Learning Goal-Oriented Language-Guided Navigation with Self-Improving Demonstrations at Scale.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2509.24910","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-24910","documentUrl":"https://doi.org/10.48550/ARXIV.2509.24910","pages":null,"arxivId":"2509.24910","arxivUrl":"https://arxiv.org/abs/2509.24910"},{"key":"journals/corr/abs-2510-13080","title":"Counting Hallucinations in Diffusion Models.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2510.13080","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-13080","documentUrl":"https://doi.org/10.48550/ARXIV.2510.13080","pages":null,"arxivId":"2510.13080","arxivUrl":"https://arxiv.org/abs/2510.13080"},{"key":"journals/corr/abs-2511-00933","title":"Fast-SmartWay: Panoramic-Free End-to-End Zero-Shot Vision-and-Language Navigation.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2511.00933","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2511-00933","documentUrl":"https://doi.org/10.48550/ARXIV.2511.00933","pages":null,"arxivId":"2511.00933","arxivUrl":"https://arxiv.org/abs/2511.00933"},{"key":"journals/corr/abs-2511-12201","title":"OmniSparse: Training-Aware Fine-Grained Sparse Attention for Long-Video MLLMs.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2511.12201","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2511-12201","documentUrl":"https://doi.org/10.48550/ARXIV.2511.12201","pages":null,"arxivId":"2511.12201","arxivUrl":"https://arxiv.org/abs/2511.12201"},{"key":"journals/corr/abs-2512-10322","title":"User-Feedback-Driven Continual Adaptation for Vision-and-Language Navigation.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2512.10322","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-10322","documentUrl":"https://doi.org/10.48550/ARXIV.2512.10322","pages":null,"arxivId":"2512.10322","arxivUrl":"https://arxiv.org/abs/2512.10322"},{"key":"journals/corr/abs-2512-19021","title":"VLNVerse: A Benchmark for Vision-Language Navigation with Versatile, Embodied, Realistic Simulation and Evaluation.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2512.19021","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-19021","documentUrl":"https://doi.org/10.48550/ARXIV.2512.19021","pages":null,"arxivId":"2512.19021","arxivUrl":"https://arxiv.org/abs/2512.19021"},{"key":"journals/corr/abs-2512-24851","title":"VLN-MME: Diagnosing MLLMs as Language-guided Visual Navigation agents.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2512.24851","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-24851","documentUrl":"https://doi.org/10.48550/ARXIV.2512.24851","pages":null,"arxivId":"2512.24851","arxivUrl":"https://arxiv.org/abs/2512.24851"}],"excludedFormal":[],"labName":"Vision, Ask, Answer and Act (V3A) Laboratory","labUrl":null,"labEvidence":"Adelaide AIML 官方 Our people 名单明确将 Qi Wu 列为该实验室 Lead；本轮未核得独立实验室网址，保留机构证据链接。","labSourceUrl":"https://adelaide.edu.au/research/australian-institute-for-machine-learning/our-people/","affiliationZh":"Adelaide University","sourceWarning":false,"excludedOther":[],"excludedHomonyms":[],"unassignedCandidates":[],"knownPreprintMinimum2025":null,"excludedMisattributed":[],"displayNotes":"身份已经机构或个人主页核对。2025 年正式记录 30 条（会议 24、期刊 6），所有作者位置均计入，不表示主导或贡献份额；预印本 28 条单列，不加总。","labDisplayNotes":"阿德莱德大学 AIML 官方人员名单列其为 V3A Laboratory 负责人，据此归组；未确认独立的实验室网址。"},{"index":24,"name":"Shangzhe Wu","nameZh":"Shangzhe Wu","role":"Assistant Professor","affiliation":"University of Cambridge","source":"DBLP official SPARQL","profileUrl":"https://dblp.org/pid/164/9884","identifier":"164/9884","identityEvidence":[{"url":"https://dblp.org/pid/164/9884","evidence":"DBLP 唯一同名作者档案；通过作者/机构主页与发表题名交叉核对。"},{"url":"https://elliottwu.com/","evidence":"作者/机构页面与该 DBLP 档案交叉匹配的题名示例：Farm3D: Learning Articulated 3D Animals by Distilling 2D Diffusion.；NeuROK: Generative 4D Neural Object Kinematics.","matchedPaperKeys":["conf/3dim/JakabLWRV24","conf/cvpr/GengHGZWW26"]},{"url":"https://www.sciencedirect.com/science/article/pii/S0925231225011476","evidence":"The original publisher biography explicitly describes Shangzhe Wu as a BUCT bachelor and current BUCT masters student; the signatory is a Cambridge faculty member, Oxford PhD and former Stanford postdoc. Crossref also provides a distinct ORCID 0009-0000-1848-8524.","matchedPaperKeys":["journals/ijon/WangWLM25"]},{"url":"https://elliottwu.com/","evidence":"Author or laboratory publication page: counted formal-paper titles matched after punctuation/case normalization. Additional title variants and missing entries were checked separately below.","matchedPaperKeys":["conf/cvpr/0001ZW025","conf/cvpr/He0W025","conf/cvpr/KayeJWRV25","conf/cvpr/ZhangLZW025","conf/eccv/SunLZLWW24","conf/nips/ZhaoWW25","conf/siggraph/DengZ0W025"]}],"count2025":7,"conference2025":7,"journal2025":0,"preprint2025":null,"status":"verified_manual","notes":"身份已通过机构/个人主页或 DBLP 机构信息核对；篇数为数据库记录统计，不表示每篇均由本人主导。 发现同名误归后，全部正式候选用本人论文列表、论文原文或正确 ORCID 重新核对。预印本候选保留于 unassignedCandidates；null 不表示零篇。","retrievedAt":"2026-10-19","yearPolicy":"DBLP yearOfPublication = 2025","queryUrl":"https://sparql.dblp.org/sparql?query=PREFIX%20dblp%3A%20%3Chttps%3A//dblp.org/rdf/schema%23%3E%20PREFIX%20xsd%3A%20%3Chttp%3A//www.w3.org/2001/XMLSchema%23%3E%20SELECT%20%3Fpub%20%3Ftitle%20%3Ftype%20%3Fvenue%20WHERE%20%7B%20%3Fpub%20dblp%3AauthoredBy%20%3Chttps%3A//dblp.org/pid/164/9884%3E%3B%20dblp%3AyearOfPublication%20%222025%22%5E%5Exsd%3AgYear%3B%20dblp%3Atitle%20%3Ftitle%3B%20a%20%3Ftype%20.%20OPTIONAL%20%7B%20%3Fpub%20dblp%3ApublishedIn%20%3Fvenue%20%7D%20%7D&format=json","papers":[{"key":"conf/cvpr/0001ZW025","title":"Birth and Death of a Rose.","type":"Inproceedings","venue":"CVPR","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/CVPR52734.2025.02431","sourceUrl":"https://dblp.org/rec/conf/cvpr/0001ZW025","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Geng_Birth_and_Death_of_a_Rose_CVPR_2025_paper.html","pages":"26102-26113"},{"key":"conf/cvpr/He0W025","title":"Category-Agnostic Neural Object Rigging.","type":"Inproceedings","venue":"CVPR","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/CVPR52734.2025.02056","sourceUrl":"https://dblp.org/rec/conf/cvpr/He0W025","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/He_Category-Agnostic_Neural_Object_Rigging_CVPR_2025_paper.html","pages":"22078-22088"},{"key":"conf/cvpr/KayeJWRV25","title":"DualPM: Dual Posed-Canonical Point Maps for 3D Shape and Pose Reconstruction.","type":"Inproceedings","venue":"CVPR","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/CVPR52734.2025.00602","sourceUrl":"https://dblp.org/rec/conf/cvpr/KayeJWRV25","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Kaye_DualPM_Dual_Posed-Canonical_Point_Maps_for_3D_Shape_and_Pose_CVPR_2025_paper.html","pages":"6425-6435"},{"key":"conf/cvpr/ZhangLZW025","title":"The Scene Language: Representing Scenes with Programs, Words, and Embeddings.","type":"Inproceedings","venue":"CVPR","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/CVPR52734.2025.02293","sourceUrl":"https://dblp.org/rec/conf/cvpr/ZhangLZW025","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Zhang_The_Scene_Language_Representing_Scenes_with_Programs_Words_and_Embeddings_CVPR_2025_paper.html","pages":"24625-24634"},{"key":"conf/eccv/SunLZLWW24","title":"Ponymation: Learning Articulated 3D Animal Motions from Unlabeled Online Videos.","type":"Inproceedings","venue":"ECCV (1)","year":2025,"yearOfPublication":2025,"yearOfEvent":2024,"doi":"https://doi.org/10.1007/978-3-031-73232-4_6","sourceUrl":"https://dblp.org/rec/conf/eccv/SunLZLWW24","documentUrl":"https://doi.org/10.1007/978-3-031-73232-4_6","pages":"100-119"},{"key":"conf/nips/ZhaoWW25","title":"Web-Scale Collection of Video Data for 4D Animal Reconstruction.","type":"Inproceedings","venue":"NeurIPS","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":null,"sourceUrl":"https://dblp.org/rec/conf/nips/ZhaoWW25","documentUrl":"http://papers.nips.cc/paper_files/paper/2025/hash/1eb2045ddad699579c01e7133d097ee4-Abstract-Datasets_and_Benchmarks_Track.html","pages":null},{"key":"conf/siggraph/DengZ0W025","title":"Anymate: A Dataset and Baselines for Learning 3D Object Rigging.","type":"Inproceedings","venue":"SIGGRAPH (Conference Paper Track)","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1145/3721238.3730743","sourceUrl":"https://dblp.org/rec/conf/siggraph/DengZ0W025","documentUrl":"https://doi.org/10.1145/3721238.3730743","pages":"112:1-112:10"}],"preprints":[],"excludedFormal":[],"excludedHomonyms":[{"key":"journals/ijon/WangWLM25","title":"Talent3D: Optimizing geometry and enhancing appearance for high-quality Text-to-3D shape generation.","type":"Article","venue":"Neurocomputing","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.1016/J.NEUCOM.2025.130475","sourceUrl":"https://dblp.org/rec/journals/ijon/WangWLM25","documentUrl":"https://doi.org/10.1016/J.NEUCOM.2025.130475","pages":"130475","exclusionReason":"The original publisher biography explicitly describes Shangzhe Wu as a BUCT bachelor and current BUCT masters student; the signatory is a Cambridge faculty member, Oxford PhD and former Stanford postdoc. Crossref also provides a distinct ORCID 0009-0000-1848-8524.","exclusionSource":"https://www.sciencedirect.com/science/article/pii/S0925231225011476"}],"sourceWarning":true,"preprintStatus":"partial_identity_review","unassignedCandidates":[{"key":"journals/corr/abs-2505-06227","title":"Anymate: A Dataset and Baselines for Learning 3D Object Rigging.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2505.06227","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-06227","documentUrl":"https://doi.org/10.48550/ARXIV.2505.06227","pages":null,"reviewStatus":"Preprint identity not separately audited after mixed-profile contamination was detected; excluded from reported totals."},{"key":"journals/corr/abs-2505-20283","title":"Category-Agnostic Neural Object Rigging.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2505.20283","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-20283","documentUrl":"https://doi.org/10.48550/ARXIV.2505.20283","pages":null,"reviewStatus":"Preprint identity not separately audited after mixed-profile contamination was detected; excluded from reported totals."},{"key":"journals/corr/abs-2511-01169","title":"Web-Scale Collection of Video Data for 4D Animal Reconstruction.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2511.01169","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2511-01169","documentUrl":"https://doi.org/10.48550/ARXIV.2511.01169","pages":null,"reviewStatus":"Preprint identity not separately audited after mixed-profile contamination was detected; excluded from reported totals."},{"key":"journals/corr/abs-2512-11798","title":"Particulate: Feed-Forward 3D Object Articulation.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2512.11798","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-11798","documentUrl":"https://doi.org/10.48550/ARXIV.2512.11798","pages":null,"reviewStatus":"Preprint identity not separately audited after mixed-profile contamination was detected; excluded from reported totals."}],"labName":"Machine Intelligence","labUrl":null,"labEvidence":"Cambridge 官方个人页明确 Research group: Machine Intelligence。这是共享研究组关联，不是给其个人新团队虚构名称，也不使用其过去 Oxford VGG 或 Stanford 组作为当前关联。","labSourceUrl":"https://www.eng.cam.ac.uk/profiles/sw2181","affiliationZh":"University of Cambridge","excludedOther":[],"knownPreprintMinimum2025":null,"excludedMisattributed":[{"key":"journals/ijon/WangWLM25","title":"Talent3D: Optimizing geometry and enhancing appearance for high-quality Text-to-3D shape generation.","type":"Article","venue":"Neurocomputing","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.1016/J.NEUCOM.2025.130475","sourceUrl":"https://dblp.org/rec/journals/ijon/WangWLM25","documentUrl":"https://doi.org/10.1016/J.NEUCOM.2025.130475","pages":"130475","exclusionReason":"The original publisher biography explicitly describes Shangzhe Wu as a BUCT bachelor and current BUCT masters student; the signatory is a Cambridge faculty member, Oxford PhD and former Stanford postdoc. Crossref also provides a distinct ORCID 0009-0000-1848-8524.","exclusionSource":"https://www.sciencedirect.com/science/article/pii/S0925231225011476"}],"displayNotes":"曾发现同名误归，已用本人论文列表、论文原文或正确的 ORCID 逐条重核全部正式候选。计入 7 条，均为会议论文。预印本候选尚未完成归属，暂不给出总数，这不是零。","labDisplayNotes":"剑桥大学官方个人页写明其研究组为 Machine Intelligence，据此归组。这是工程系的共享研究组，不是个人实验室；不采用其过去在牛津或斯坦福的团队。"},{"index":25,"name":"Cihang Xie","nameZh":"Cihang Xie","role":"Assistant Professor","affiliation":"University of California, Santa Cruz","source":"DBLP official SPARQL","profileUrl":"https://dblp.org/pid/175/3366","identifier":"175/3366","identityEvidence":[{"url":"https://dblp.org/pid/175/3366","evidence":"DBLP 唯一同名作者档案；通过作者/机构主页与发表题名交叉核对。"},{"url":"https://cihangxie.github.io/","evidence":"作者/机构页面与该 DBLP 档案交叉匹配的题名示例：Learning Transferable Adversarial Examples via Ghost Networks.；Practical Disruption of Image Translation Deepfake Networks.","matchedPaperKeys":["conf/aaai/LiBZXZY20","conf/aaai/RuizBXS23"]}],"count2025":24,"conference2025":17,"journal2025":7,"preprint2025":23,"status":"verified","notes":"身份已通过机构/个人主页或 DBLP 机构信息核对；篇数为数据库记录统计，不表示每篇均由本人主导。","retrievedAt":"2026-10-19","yearPolicy":"DBLP yearOfPublication = 2025","queryUrl":"https://sparql.dblp.org/sparql?query=PREFIX%20dblp%3A%20%3Chttps%3A//dblp.org/rdf/schema%23%3E%20PREFIX%20xsd%3A%20%3Chttp%3A//www.w3.org/2001/XMLSchema%23%3E%20SELECT%20%3Fpub%20%3Ftitle%20%3Ftype%20%3Fvenue%20WHERE%20%7B%20%3Fpub%20dblp%3AauthoredBy%20%3Chttps%3A//dblp.org/pid/175/3366%3E%3B%20dblp%3AyearOfPublication%20%222025%22%5E%5Exsd%3AgYear%3B%20dblp%3Atitle%20%3Ftitle%3B%20a%20%3Ftype%20.%20OPTIONAL%20%7B%20%3Fpub%20dblp%3ApublishedIn%20%3Fvenue%20%7D%20%7D&format=json","papers":[{"key":"conf/cvpr/LiWLWZX25","title":"Efficient VideoMAE via Temporal Progressive Training.","type":"Inproceedings","venue":"CVPR Workshops","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":null,"sourceUrl":"https://dblp.org/rec/conf/cvpr/LiWLWZX25","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025W/PVUW/html/Li_Efficient_VideoMAE_via_Temporal_Progressive_Training_CVPRW_2025_paper.html","pages":"2659-2668"},{"key":"conf/cvpr/Wang0RWM0ZYX25","title":"Mamba-Reg: Vision Mamba Also Needs Registers.","type":"Inproceedings","venue":"CVPR","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/CVPR52734.2025.01392","sourceUrl":"https://dblp.org/rec/conf/cvpr/Wang0RWM0ZYX25","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Wang_Mamba-Reg_Vision_Mamba_Also_Needs_Registers_CVPR_2025_paper.html","pages":"14944-14953"},{"key":"conf/cvpr/WangYYRWW0ZYX25","title":"Adventurer: Optimizing Vision Mamba Architecture Designs for Efficiency.","type":"Inproceedings","venue":"CVPR","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/CVPR52734.2025.02807","sourceUrl":"https://dblp.org/rec/conf/cvpr/WangYYRWW0ZYX25","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Wang_Adventurer_Optimizing_Vision_Mamba_Architecture_Designs_for_Efficiency_CVPR_2025_paper.html","pages":"30157-30166"},{"key":"conf/cvpr/Yang0LKPRZLXZ25","title":"Generative Image Layer Decomposition with Visual Effects.","type":"Inproceedings","venue":"CVPR","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/CVPR52734.2025.00716","sourceUrl":"https://dblp.org/rec/conf/cvpr/Yang0LKPRZLXZ25","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Yang_Generative_Image_Layer_Decomposition_with_Visual_Effects_CVPR_2025_paper.html","pages":"7643-7653"},{"key":"conf/cvpr/YangWBBKCX25","title":"Probing Vulnerabilities of Vision-LiDAR Based Autonomous Driving Systems.","type":"Inproceedings","venue":"CVPR Workshops","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":null,"sourceUrl":"https://dblp.org/rec/conf/cvpr/YangWBBKCX25","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025W/AdvML/html/Yang_Probing_Vulnerabilities_of_Vision-LiDAR_Based_Autonomous_Driving_Systems_CVPRW_2025_paper.html","pages":"3561-3569"},{"key":"conf/eccv/TuCWZZHZYX24","title":"How Many Are in This Image A Safety Evaluation Benchmark for Vision LLMs.","type":"Inproceedings","venue":"ECCV (51)","year":2025,"yearOfPublication":2025,"yearOfEvent":2024,"doi":"https://doi.org/10.1007/978-3-031-72983-6_3","sourceUrl":"https://dblp.org/rec/conf/eccv/TuCWZZHZYX24","documentUrl":"https://doi.org/10.1007/978-3-031-72983-6_3","pages":"37-55"},{"key":"conf/eccv/XiaoZLLMYZYZX24","title":"A Semantic Space is Worth 256 Language Descriptions: Make Stronger Segmentation Models with Descriptive Properties.","type":"Inproceedings","venue":"ECCV (38)","year":2025,"yearOfPublication":2025,"yearOfEvent":2024,"doi":"https://doi.org/10.1007/978-3-031-72920-1_14","sourceUrl":"https://dblp.org/rec/conf/eccv/XiaoZLLMYZYZX24","documentUrl":"https://doi.org/10.1007/978-3-031-72920-1_14","pages":"239-258"},{"key":"conf/eccv/XieXYM24","title":"From Pixels to Objects: A Hierarchical Approach for Part and Object Segmentation Using Local and Global Aggregation.","type":"Inproceedings","venue":"ECCV (66)","year":2025,"yearOfPublication":2025,"yearOfEvent":2024,"doi":"https://doi.org/10.1007/978-3-031-72848-8_20","sourceUrl":"https://dblp.org/rec/conf/eccv/XieXYM24","documentUrl":"https://doi.org/10.1007/978-3-031-72848-8_20","pages":"341-356"},{"key":"conf/emnlp/TuFCLTX25","title":"ViLBench: A Suite for Vision-Language Process Reward Modeling.","type":"Inproceedings","venue":"EMNLP","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.18653/V1/2025.EMNLP-MAIN.344","sourceUrl":"https://dblp.org/rec/conf/emnlp/TuFCLTX25","documentUrl":"https://doi.org/10.18653/V1/2025.EMNLP-MAIN.344","pages":"6764-6779"},{"key":"conf/iccv/LiLTX25","title":"OpenVision: A Fully-Open, Cost-Effective Family of Advanced Vision Encoders for Multimodal Learning.","type":"Inproceedings","venue":"ICCV","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/ICCV51701.2025.00379","sourceUrl":"https://dblp.org/rec/conf/iccv/LiLTX25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.00379","pages":"3977-3987"},{"key":"conf/iccv/ShuZJX25","title":"Audio-Visual LLM for Video Understanding.","type":"Inproceedings","venue":"ICCVW","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/ICCVW69036.2025.00447","sourceUrl":"https://dblp.org/rec/conf/iccv/ShuZJX25","documentUrl":"https://doi.org/10.1109/ICCVW69036.2025.00447","pages":"4305-4314"},{"key":"conf/iccv/WangSXLZ25","title":"VideoLLaMB: Long Streaming Video Understanding with Recurrent Memory Bridges.","type":"Inproceedings","venue":"ICCV","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/ICCV51701.2025.02240","sourceUrl":"https://dblp.org/rec/conf/iccv/WangSXLZ25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.02240","pages":"24170-24181"},{"key":"conf/iclr/HuiYZSWWXZ25","title":"HQ-Edit: A High-Quality Dataset for Instruction-based Image Editing.","type":"Inproceedings","venue":"ICLR","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":null,"sourceUrl":"https://dblp.org/rec/conf/iclr/HuiYZSWWXZ25","documentUrl":"https://openreview.net/forum?id=mZptYYttFj","pages":null},{"key":"conf/iclr/RenLTWSZMYWWYX25","title":"Autoregressive Pretraining with Mamba in Vision.","type":"Inproceedings","venue":"ICLR","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":null,"sourceUrl":"https://dblp.org/rec/conf/iclr/RenLTWSZMYWWYX25","documentUrl":"https://openreview.net/forum?id=PQpvhUrA1C","pages":null},{"key":"conf/iclr/XieZGWLZL00XZ25","title":"MedTrinity-25M: A Large-scale Multimodal Dataset with Multigranular Annotations for Medicine.","type":"Inproceedings","venue":"ICLR","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":null,"sourceUrl":"https://dblp.org/rec/conf/iclr/XieZGWLZL00XZ25","documentUrl":"https://openreview.net/forum?id=IwgmgidYPS","pages":null},{"key":"conf/icml/0047Y0ZYX25","title":"Scaling Laws in Patchification: An Image Is Worth 50, 176 Tokens And More.","type":"Inproceedings","venue":"ICML","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":null,"sourceUrl":"https://dblp.org/rec/conf/icml/0047Y0ZYX25","documentUrl":"https://proceedings.mlr.press/v267/wang25ed.html","pages":null},{"key":"conf/icml/LiTH0ZXRM0ZZX25","title":"What If We Recaption Billions of Web Images with LLaMA-3?","type":"Inproceedings","venue":"ICML","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":null,"sourceUrl":"https://dblp.org/rec/conf/icml/LiTH0ZXRM0ZZX25","documentUrl":"https://proceedings.mlr.press/v267/li25ch.html","pages":null},{"key":"journals/ftsec/MaGWWWSDXCZHLWZZBLWQZHL25","title":"Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety.","type":"Article","venue":"Found. Trends Priv. Secur.","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.1561/3300000051","sourceUrl":"https://dblp.org/rec/journals/ftsec/MaGWWWSDXCZHLWZZBLWQZHL25","documentUrl":"https://doi.org/10.1561/3300000051","pages":"254-469"},{"key":"journals/tmlr/ChenTWLTDZX25","title":"SFT or RL? An Early Investigation into Training R1-Like Reasoning Large Vision-Language Models.","type":"Article","venue":"Trans. Mach. Learn. Res.","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":null,"sourceUrl":"https://dblp.org/rec/journals/tmlr/ChenTWLTDZX25","documentUrl":"https://openreview.net/forum?id=wZI5qkQeDF","pages":null},{"key":"journals/tmlr/MeiCYX25","title":"SPFormer: Enhancing Vision Transformer with Superpixel Representation.","type":"Article","venue":"Trans. Mach. Learn. Res.","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":null,"sourceUrl":"https://dblp.org/rec/journals/tmlr/MeiCYX25","documentUrl":"https://openreview.net/forum?id=nu1SjVgSuy","pages":null},{"key":"journals/tmlr/RenZ0LYX25","title":"ARVideo: Autoregressive Pretraining for Self-Supervised Video Representation Learning.","type":"Article","venue":"Trans. Mach. Learn. Res.","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":null,"sourceUrl":"https://dblp.org/rec/journals/tmlr/RenZ0LYX25","documentUrl":"https://openreview.net/forum?id=TRKwzPnXWQ","pages":null},{"key":"journals/tmlr/WangTMZ0X25","title":"AttnGCG: Enhancing Jailbreaking Attacks on LLMs with Attention Manipulation.","type":"Article","venue":"Trans. Mach. Learn. Res.","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":null,"sourceUrl":"https://dblp.org/rec/journals/tmlr/WangTMZ0X25","documentUrl":"https://openreview.net/forum?id=prVLANCshF","pages":null},{"key":"journals/tmlr/YangHBLQZBWYSTSRLWZCWZZ25","title":"Reliable and Responsible Foundation Models.","type":"Article","venue":"Trans. Mach. Learn. Res.","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":null,"sourceUrl":"https://dblp.org/rec/journals/tmlr/YangHBLQZBWYSTSRLWZCWZZ25","documentUrl":"https://openreview.net/forum?id=nLJZh4M6S5","pages":null},{"key":"journals/tmlr/YangZX25","title":"AQA-Bench: An Interactive Benchmark for Evaluating LLMs' Sequential Reasoning Ability in Algorithmic Environments.","type":"Article","venue":"Trans. Mach. Learn. Res.","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":null,"sourceUrl":"https://dblp.org/rec/journals/tmlr/YangZX25","documentUrl":"https://openreview.net/forum?id=W22g6Ksmbi","pages":null}],"preprints":[{"key":"journals/corr/abs-2501-09446","title":"Double Visual Defense: Adversarial Pre-training and Instruction Tuning for Improving Vision-Language Model Robustness.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2501.09446","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2501-09446","documentUrl":"https://doi.org/10.48550/ARXIV.2501.09446","pages":null,"arxivId":"2501.09446","arxivUrl":"https://arxiv.org/abs/2501.09446"},{"key":"journals/corr/abs-2501-16085","title":"ARFlow: Autogressive Flow with Hybrid Linear Attention.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2501.16085","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2501-16085","documentUrl":"https://doi.org/10.48550/ARXIV.2501.16085","pages":null,"arxivId":"2501.16085","arxivUrl":"https://arxiv.org/abs/2501.16085"},{"key":"journals/corr/abs-2502-03738","title":"Scaling Laws in Patchification: An Image Is Worth 50,176 Tokens And More.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2502.03738","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2502-03738","documentUrl":"https://doi.org/10.48550/ARXIV.2502.03738","pages":null,"arxivId":"2502.03738","arxivUrl":"https://arxiv.org/abs/2502.03738"},{"key":"journals/corr/abs-2502-05206","title":"Safety at Scale: A Comprehensive Survey of Large Model Safety.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2502.05206","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2502-05206","documentUrl":"https://doi.org/10.48550/ARXIV.2502.05206","pages":null,"arxivId":"2502.05206","arxivUrl":"https://arxiv.org/abs/2502.05206"},{"key":"journals/corr/abs-2503-20271","title":"ViLBench: A Suite for Vision-Language Process Reward Modeling.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2503.20271","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-20271","documentUrl":"https://doi.org/10.48550/ARXIV.2503.20271","pages":null,"arxivId":"2503.20271","arxivUrl":"https://arxiv.org/abs/2503.20271"},{"key":"journals/corr/abs-2504-01903","title":"STAR-1: Safer Alignment of Reasoning LLMs with 1K Data.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2504.01903","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2504-01903","documentUrl":"https://doi.org/10.48550/ARXIV.2504.01903","pages":null,"arxivId":"2504.01903","arxivUrl":"https://arxiv.org/abs/2504.01903"},{"key":"journals/corr/abs-2504-11468","title":"SFT or RL? An Early Investigation into Training R1-Like Reasoning Large Vision-Language Models.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2504.11468","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2504-11468","documentUrl":"https://doi.org/10.48550/ARXIV.2504.11468","pages":null,"arxivId":"2504.11468","arxivUrl":"https://arxiv.org/abs/2504.11468"},{"key":"journals/corr/abs-2504-13143","title":"Complex-Edit: CoT-Like Instruction Generation for Complexity-Controllable Image Editing Benchmark.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2504.13143","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2504-13143","documentUrl":"https://doi.org/10.48550/ARXIV.2504.13143","pages":null,"arxivId":"2504.13143","arxivUrl":"https://arxiv.org/abs/2504.13143"},{"key":"journals/corr/abs-2505-04601","title":"OpenVision: A Fully-Open, Cost-Effective Family of Advanced Vision Encoders for Multimodal Learning.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2505.04601","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-04601","documentUrl":"https://doi.org/10.48550/ARXIV.2505.04601","pages":null,"arxivId":"2505.04601","arxivUrl":"https://arxiv.org/abs/2505.04601"},{"key":"journals/corr/abs-2505-14835","title":"Robust and Efficient AI-Based Attack Recovery in Autonomous Drones.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2505.14835","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-14835","documentUrl":"https://doi.org/10.48550/ARXIV.2505.14835","pages":null,"arxivId":"2505.14835","arxivUrl":"https://arxiv.org/abs/2505.14835"},{"key":"journals/corr/abs-2505-16964","title":"MedFrameQA: A Multi-Image Medical VQA Benchmark for Clinical Reasoning.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2505.16964","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-16964","documentUrl":"https://doi.org/10.48550/ARXIV.2505.16964","pages":null,"arxivId":"2505.16964","arxivUrl":"https://arxiv.org/abs/2505.16964"},{"key":"journals/corr/abs-2506-02126","title":"Knowledge or Reasoning? A Close Look at How LLMs Think Across Domains.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2506.02126","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-02126","documentUrl":"https://doi.org/10.48550/ARXIV.2506.02126","pages":null,"arxivId":"2506.02126","arxivUrl":"https://arxiv.org/abs/2506.02126"},{"key":"journals/corr/abs-2507-21033","title":"GPT-IMAGE-EDIT-1.5M: A Million-Scale, GPT-Generated Image Dataset.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2507.21033","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2507-21033","documentUrl":"https://doi.org/10.48550/ARXIV.2507.21033","pages":null,"arxivId":"2507.21033","arxivUrl":"https://arxiv.org/abs/2507.21033"},{"key":"journals/corr/abs-2508-21376","title":"AHELM: A Holistic Evaluation of Audio-Language Models.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2508.21376","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-21376","documentUrl":"https://doi.org/10.48550/ARXIV.2508.21376","pages":null,"arxivId":"2508.21376","arxivUrl":"https://arxiv.org/abs/2508.21376"},{"key":"journals/corr/abs-2509-01644","title":"OpenVision 2: A Family of Generative Pretrained Visual Encoders for Multimodal Learning.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2509.01644","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-01644","documentUrl":"https://doi.org/10.48550/ARXIV.2509.01644","pages":null,"arxivId":"2509.01644","arxivUrl":"https://arxiv.org/abs/2509.01644"},{"key":"journals/corr/abs-2510-00181","title":"CHAI: Command Hijacking against embodied AI.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2510.00181","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-00181","documentUrl":"https://doi.org/10.48550/ARXIV.2510.00181","pages":null,"arxivId":"2510.00181","arxivUrl":"https://arxiv.org/abs/2510.00181"},{"key":"journals/corr/abs-2510-04860","title":"Alignment Tipping Process: How Self-Evolution Pushes LLM Agents Off the Rails.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2510.04860","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-04860","documentUrl":"https://doi.org/10.48550/ARXIV.2510.04860","pages":null,"arxivId":"2510.04860","arxivUrl":"https://arxiv.org/abs/2510.04860"},{"key":"journals/corr/abs-2510-10880","title":"Where on Earth? A Vision-Language Benchmark for Probing Model Geolocation Skills Across Scales.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2510.10880","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-10880","documentUrl":"https://doi.org/10.48550/ARXIV.2510.10880","pages":null,"arxivId":"2510.10880","arxivUrl":"https://arxiv.org/abs/2510.10880"},{"key":"journals/corr/abs-2510-18212","title":"A Definition of AGI.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2510.18212","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-18212","documentUrl":"https://doi.org/10.48550/ARXIV.2510.18212","pages":null,"arxivId":"2510.18212","arxivUrl":"https://arxiv.org/abs/2510.18212"},{"key":"journals/corr/abs-2511-02779","title":"When Visualizing is the First Step to Reasoning: MIRA, a Benchmark for Visual Chain-of-Thought.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2511.02779","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2511-02779","documentUrl":"https://doi.org/10.48550/ARXIV.2511.02779","pages":null,"arxivId":"2511.02779","arxivUrl":"https://arxiv.org/abs/2511.02779"},{"key":"journals/corr/abs-2511-07403","title":"SpatialThinker: Reinforcing 3D Reasoning in Multimodal LLMs via Spatial Rewards.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2511.07403","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2511-07403","documentUrl":"https://doi.org/10.48550/ARXIV.2511.07403","pages":null,"arxivId":"2511.07403","arxivUrl":"https://arxiv.org/abs/2511.07403"},{"key":"journals/corr/abs-2511-20573","title":"VQ-VA World: Towards High-Quality Visual Question-Visual Answering.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2511.20573","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2511-20573","documentUrl":"https://doi.org/10.48550/ARXIV.2511.20573","pages":null,"arxivId":"2511.20573","arxivUrl":"https://arxiv.org/abs/2511.20573"},{"key":"journals/corr/abs-2511-22815","title":"Captain Safari: A World Engine.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2511.22815","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2511-22815","documentUrl":"https://doi.org/10.48550/ARXIV.2511.22815","pages":null,"arxivId":"2511.22815","arxivUrl":"https://arxiv.org/abs/2511.22815"}],"excludedFormal":[],"labName":"Vision · Learning · Assured Autonomy (VLAA) Lab","labUrl":"https://ucsc-vlaa.github.io/","labEvidence":"本人主页明确写与 Yuyin Zhou 共同领导 VLAA Lab，并直接链接。","labSourceUrl":"https://cihangxie.github.io/","affiliationZh":"University of California, Santa Cruz","sourceWarning":false,"excludedOther":[],"excludedHomonyms":[],"unassignedCandidates":[],"knownPreprintMinimum2025":null,"excludedMisattributed":[],"displayNotes":"身份已经机构或个人主页核对。2025 年正式记录 24 条（会议 17、期刊 7），所有作者位置均计入，不表示主导或贡献份额；预印本 23 条单列，不加总。","labDisplayNotes":"个人主页写明与 Yuyin Zhou 共同领导 VLAA Lab。Yuyin Zhou 不在联署名单上，因此分组只含 Cihang Xie 参与的记录。"},{"index":26,"name":"Junsong Yuan","nameZh":"Junsong Yuan","role":"Professor","affiliation":"University at Buffalo, State University of New York","source":"DBLP official SPARQL","profileUrl":"https://dblp.org/pid/42/3332","identifier":"42/3332","identityEvidence":[{"url":"https://dblp.org/pid/42/3332","evidence":"DBLP 档案名 Junsong Yuan 0001；机构/履历：Nanyang Technological University, School of Electrical and Electronics Engineering, Singapore；Northwestern University, Evanston, IL, USA；State University of New York at Buffalo, Department of Computer Science and Engineering, NY, USA"},{"url":"https://richmediagai.github.io/richmediagai2025/program.html","evidence":"Single-page invited keynote abstract (page 40). The original 2025 workshop program explicitly labels the same talk by Junsong Yuan as Keynote.","matchedPaperKeys":["conf/richmediagai/Yuan25"]},{"url":"https://ieeexplore.ieee.org/abstract/document/11364187","evidence":"IEEE society contributor/lecturer announcement, not a research paper. Publisher abstract identifies it as society information.","matchedPaperKeys":["journals/spm/AlRegibCCFLMRWYY25"]}],"count2025":30,"conference2025":15,"journal2025":15,"preprint2025":22,"status":"verified_manual","notes":"身份已通过机构/个人主页或 DBLP 机构信息核对；篇数为数据库记录统计，不表示每篇均由本人主导。 已识别的课程摘要、受邀讲座摘要或学会人物公告不计为研究论文。不同 ORCID 本身不构成同名判定。","retrievedAt":"2026-10-19","yearPolicy":"DBLP yearOfPublication = 2025","queryUrl":"https://sparql.dblp.org/sparql?query=PREFIX%20dblp%3A%20%3Chttps%3A//dblp.org/rdf/schema%23%3E%20PREFIX%20xsd%3A%20%3Chttp%3A//www.w3.org/2001/XMLSchema%23%3E%20SELECT%20%3Fpub%20%3Ftitle%20%3Ftype%20%3Fvenue%20WHERE%20%7B%20%3Fpub%20dblp%3AauthoredBy%20%3Chttps%3A//dblp.org/pid/42/3332%3E%3B%20dblp%3AyearOfPublication%20%222025%22%5E%5Exsd%3AgYear%3B%20dblp%3Atitle%20%3Ftitle%3B%20a%20%3Ftype%20.%20OPTIONAL%20%7B%20%3Fpub%20dblp%3ApublishedIn%20%3Fvenue%20%7D%20%7D&format=json","papers":[{"key":"conf/cvpr/XieLCYCXFSW025","title":"dFLMoE: Decentralized Federated Learning via Mixture of Experts for Medical Data Analysis.","type":"Inproceedings","venue":"CVPR","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/CVPR52734.2025.00954","sourceUrl":"https://dblp.org/rec/conf/cvpr/XieLCYCXFSW025","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Xie_dFLMoE_Decentralized_Federated_Learning_via_Mixture_of_Experts_for_Medical_CVPR_2025_paper.html","pages":"10203-10213"},{"key":"conf/eccv/LuanGXSDPZLCYW24","title":"Divide and Fuse: Body Part Mesh Recovery from Partially Visible Human Images.","type":"Inproceedings","venue":"ECCV (24)","year":2025,"yearOfPublication":2025,"yearOfEvent":2024,"doi":"https://doi.org/10.1007/978-3-031-72691-0_20","sourceUrl":"https://dblp.org/rec/conf/eccv/LuanGXSDPZLCYW24","documentUrl":"https://doi.org/10.1007/978-3-031-72691-0_20","pages":"350-367"},{"key":"conf/eccv/WangXMY24","title":"Interaction-Centric Spatio-Temporal Context Reasoning for Multi-person Video HOI Recognition.","type":"Inproceedings","venue":"ECCV (32)","year":2025,"yearOfPublication":2025,"yearOfEvent":2024,"doi":"https://doi.org/10.1007/978-3-031-73411-3_24","sourceUrl":"https://dblp.org/rec/conf/eccv/WangXMY24","documentUrl":"https://doi.org/10.1007/978-3-031-73411-3_24","pages":"419-435"},{"key":"conf/eccv/WuWYGLYW24","title":"GRiT: A Generative Region-to-Text Transformer for Object Understanding.","type":"Inproceedings","venue":"ECCV (80)","year":2025,"yearOfPublication":2025,"yearOfEvent":2024,"doi":"https://doi.org/10.1007/978-3-031-72989-8_12","sourceUrl":"https://dblp.org/rec/conf/eccv/WuWYGLYW24","documentUrl":"https://doi.org/10.1007/978-3-031-72989-8_12","pages":"207-224"},{"key":"conf/eccv/ZhaiLLLWYDYLW24","title":"IDOL: Unified Dual-Modal Latent Diffusion for Human-Centric Joint Video-Depth Generation.","type":"Inproceedings","venue":"ECCV (15)","year":2025,"yearOfPublication":2025,"yearOfEvent":2024,"doi":"https://doi.org/10.1007/978-3-031-72633-0_8","sourceUrl":"https://dblp.org/rec/conf/eccv/ZhaiLLLWYDYLW24","documentUrl":"https://doi.org/10.1007/978-3-031-72633-0_8","pages":"134-152"},{"key":"conf/eccv/ZhuFCYQH24","title":"Exploring Pre-trained Text-to-Video Diffusion Models for Referring Video Object Segmentation.","type":"Inproceedings","venue":"ECCV (12)","year":2025,"yearOfPublication":2025,"yearOfEvent":2024,"doi":"https://doi.org/10.1007/978-3-031-73254-6_26","sourceUrl":"https://dblp.org/rec/conf/eccv/ZhuFCYQH24","documentUrl":"https://doi.org/10.1007/978-3-031-73254-6_26","pages":"452-469"},{"key":"conf/iccv/BhosaleWZTBXSYDG25","title":"PathDiff: Histopathology Image Synthesis with Unpaired Text and Mask Conditions.","type":"Inproceedings","venue":"ICCV","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/ICCV51701.2025.02081","sourceUrl":"https://dblp.org/rec/conf/iccv/BhosaleWZTBXSYDG25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.02081","pages":"22415-22424"},{"key":"conf/iccv/LiWYLMYL25","title":"UST-SSM: Unified Spatio-Temporal State Space Models for Point Cloud Video Modeling.","type":"Inproceedings","venue":"ICCV","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/ICCV51701.2025.00634","sourceUrl":"https://dblp.org/rec/conf/iccv/LiWYLMYL25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.00634","pages":"6738-6747"},{"key":"conf/iccv/WangLLDWLYL25","title":"Recognizing Actions From Robotic View for Natural Human-Robot Interaction.","type":"Inproceedings","venue":"ICCV","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/ICCV51701.2025.01319","sourceUrl":"https://dblp.org/rec/conf/iccv/WangLLDWLYL25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.01319","pages":"14218-14227"},{"key":"conf/iccv/ZhaiLPDCYD25","title":"Text2Outfit: Controllable Outfit Generation With Multimodal Language Models.","type":"Inproceedings","venue":"ICCV","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/ICCV51701.2025.01500","sourceUrl":"https://dblp.org/rec/conf/iccv/ZhaiLPDCYD25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.01500","pages":"16165-16174"},{"key":"conf/iccv/ZhuDRXKY25","title":"CompSlider: Compositional Slider for Disentangled Multiple-Attribute Image Generation.","type":"Inproceedings","venue":"ICCV","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/ICCV51701.2025.01549","sourceUrl":"https://dblp.org/rec/conf/iccv/ZhuDRXKY25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.01549","pages":"16682-16691"},{"key":"conf/icmcs/AnandYBY25","title":"Multimodal Conversatioal Emotion Analysis with Robustness to Incomplete Modality Details.","type":"Inproceedings","venue":"ICME","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/ICME59968.2025.11210029","sourceUrl":"https://dblp.org/rec/conf/icmcs/AnandYBY25","documentUrl":"https://doi.org/10.1109/ICME59968.2025.11210029","pages":"1-6"},{"key":"conf/mm/ZhaoWL0Z00X25","title":"PP-Motion: Physical-Perceptual Fidelity Evaluation for Human Motion Generation.","type":"Inproceedings","venue":"ACM Multimedia","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1145/3746027.3754940","sourceUrl":"https://dblp.org/rec/conf/mm/ZhaoWL0Z00X25","documentUrl":"https://doi.org/10.1145/3746027.3754940","pages":"6840-6849"},{"key":"conf/nips/ZhuLFWQY25","title":"GeoRemover: Removing Objects and Their Causal Visual Artifacts.","type":"Inproceedings","venue":"NeurIPS","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":null,"sourceUrl":"https://dblp.org/rec/conf/nips/ZhuLFWQY25","documentUrl":"http://papers.nips.cc/paper_files/paper/2025/hash/be41269a9fe258f1ecba663b0b402322-Abstract-Conference.html","pages":null},{"key":"conf/www/XiMCDGS025","title":"Generative Prompting for Complex Product Retrieval.","type":"Inproceedings","venue":"WWW (Companion Volume)","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1145/3701716.3715546","sourceUrl":"https://dblp.org/rec/conf/www/XiMCDGS025","documentUrl":"https://doi.org/10.1145/3701716.3715546","pages":"1412-1416"},{"key":"journals/air/ZhuZZDDXY25","title":"Scene reconstruction techniques for autonomous driving: a review of 3D Gaussian splatting.","type":"Article","venue":"Artif. Intell. Rev.","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.1007/S10462-024-10955-4","sourceUrl":"https://dblp.org/rec/journals/air/ZhuZZDDXY25","documentUrl":"https://doi.org/10.1007/S10462-024-10955-4","pages":"30"},{"key":"journals/comsis/ZhangCLLCY25","title":"PFLIC: A novel personalized federated learning-based iterative clustering.","type":"Article","venue":"Comput. Sci. Inf. Syst.","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.2298/CSIS250131052Z","sourceUrl":"https://dblp.org/rec/journals/comsis/ZhangCLLCY25","documentUrl":"https://doi.org/10.2298/CSIS250131052Z","pages":"945-970"},{"key":"journals/ijcv/LiLLZLY25","title":"Deep Hierarchical Learning for 3D Semantic Segmentation.","type":"Article","venue":"Int. J. Comput. Vis.","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.1007/S11263-025-02387-6","sourceUrl":"https://dblp.org/rec/journals/ijcv/LiLLZLY25","documentUrl":"https://doi.org/10.1007/S11263-025-02387-6","pages":"4420-4441"},{"key":"journals/mva/FengLCGLYQ25","title":"Benchmarking large and small MLLMs.","type":"Article","venue":"Mach. Vis. Appl.","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.1007/S00138-025-01762-0","sourceUrl":"https://dblp.org/rec/journals/mva/FengLCGLYQ25","documentUrl":"https://doi.org/10.1007/S00138-025-01762-0","pages":"137"},{"key":"journals/pami/LuanZMLCXY25","title":"Scalable High-Fidelity 3D Hand Shape Reconstruction via Graph-Image Frequency Mapping and Graph Frequency Decomposition.","type":"Article","venue":"IEEE Trans. Pattern Anal. Mach. Intell.","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.1109/TPAMI.2025.3554516","sourceUrl":"https://dblp.org/rec/journals/pami/LuanZMLCXY25","documentUrl":"https://doi.org/10.1109/TPAMI.2025.3554516","pages":"5832-5846"},{"key":"journals/tce/TangZLY25","title":"Uncovering Malicious Accounts in Online Social Networks Using XGBoost and Graph Convolution Networks.","type":"Article","venue":"IEEE Trans. Consumer Electron.","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.1109/TCE.2024.3406194","sourceUrl":"https://dblp.org/rec/journals/tce/TangZLY25","documentUrl":"https://doi.org/10.1109/TCE.2024.3406194","pages":"6489-6498"},{"key":"journals/tifs/TuZGZYD25","title":"FADE: A Dataset for Detecting Falling Objects Around Buildings in Video.","type":"Article","venue":"IEEE Trans. Inf. Forensics Secur.","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.1109/TIFS.2025.3607254","sourceUrl":"https://dblp.org/rec/journals/tifs/TuZGZYD25","documentUrl":"https://doi.org/10.1109/TIFS.2025.3607254","pages":"9746-9759"},{"key":"journals/tip/FengLCQYYH25","title":"Pluralistic Salient Object Detection.","type":"Article","venue":"IEEE Trans. Image Process.","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.1109/TIP.2025.3557563","sourceUrl":"https://dblp.org/rec/journals/tip/FengLCQYYH25","documentUrl":"https://doi.org/10.1109/TIP.2025.3557563","pages":"2325-2337"},{"key":"journals/tip/LiaoYZLY25","title":"FocalTransNet: A Hybrid Focal-Enhanced Transformer Network for Medical Image Segmentation.","type":"Article","venue":"IEEE Trans. Image Process.","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.1109/TIP.2025.3602739","sourceUrl":"https://dblp.org/rec/journals/tip/LiaoYZLY25","documentUrl":"https://doi.org/10.1109/TIP.2025.3602739","pages":"5614-5627"},{"key":"journals/tip/LiuLZLY25","title":"PoseMoE: Mixture-of-Experts Network for Monocular 3D Human Pose Estimation.","type":"Article","venue":"IEEE Trans. Image Process.","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.1109/TIP.2025.3644785","sourceUrl":"https://dblp.org/rec/journals/tip/LiuLZLY25","documentUrl":"https://doi.org/10.1109/TIP.2025.3644785","pages":"8537-8551"},{"key":"journals/tip/TuZGYD25","title":"Informative Sample Selection Model for Skeleton-Based Action Recognition With Limited Training Samples.","type":"Article","venue":"IEEE Trans. Image Process.","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.1109/TIP.2025.3627418","sourceUrl":"https://dblp.org/rec/journals/tip/TuZGYD25","documentUrl":"https://doi.org/10.1109/TIP.2025.3627418","pages":"7335-7346"},{"key":"journals/tip/WenCSJYGYZ25","title":"HOVER: Hyperbolic Video-Text Retrieval.","type":"Article","venue":"IEEE Trans. Image Process.","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.1109/TIP.2025.3611174","sourceUrl":"https://dblp.org/rec/journals/tip/WenCSJYGYZ25","documentUrl":"https://doi.org/10.1109/TIP.2025.3611174","pages":"6192-6203"},{"key":"journals/titb/LaiLLLY25","title":"Bilateral Proxy Federated Domain Generalization for Privacy-Preserving Medical Image Diagnosis.","type":"Article","venue":"IEEE J. Biomed. Health Informatics","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.1109/JBHI.2024.3456440","sourceUrl":"https://dblp.org/rec/journals/titb/LaiLLLY25","documentUrl":"https://doi.org/10.1109/JBHI.2024.3456440","pages":"2784-2797"},{"key":"journals/tmm/DingZYCXHY25","title":"SLCGC: A lightweight Self-supervised Low-Pass Contrastive Graph Clustering Network for Hyperspectral Images.","type":"Article","venue":"IEEE Trans. Multim.","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.1109/TMM.2025.3604954","sourceUrl":"https://dblp.org/rec/journals/tmm/DingZYCXHY25","documentUrl":"https://doi.org/10.1109/TMM.2025.3604954","pages":"8251-8262"},{"key":"journals/tvcg/LiWTOY25","title":"Aligning Instance-Semantic Sparse Representation Towards Unsupervised Object Segmentation and Shape Abstraction With Repeatable Primitives.","type":"Article","venue":"IEEE Trans. Vis. Comput. Graph.","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.1109/TVCG.2025.3532081","sourceUrl":"https://dblp.org/rec/journals/tvcg/LiWTOY25","documentUrl":"https://doi.org/10.1109/TVCG.2025.3532081","pages":"6884-6898"}],"preprints":[{"key":"journals/corr/abs-2501-04150","title":"Benchmarking Large and Small MLLMs.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2501.04150","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2501-04150","documentUrl":"https://doi.org/10.48550/ARXIV.2501.04150","pages":null,"arxivId":"2501.04150","arxivUrl":"https://arxiv.org/abs/2501.04150"},{"key":"journals/corr/abs-2502-04364","title":"Lost in Edits? A λ-Compass for AIGC Provenance.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2502.04364","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2502-04364","documentUrl":"https://doi.org/10.48550/ARXIV.2502.04364","pages":null,"arxivId":"2502.04364","arxivUrl":"https://arxiv.org/abs/2502.04364"},{"key":"journals/corr/abs-2503-06947","title":"Aligning Instance-Semantic Sparse Representation towards Unsupervised Object Segmentation and Shape Abstraction with Repeatable Primitives.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2503.06947","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-06947","documentUrl":"https://doi.org/10.48550/ARXIV.2503.06947","pages":null,"arxivId":"2503.06947","arxivUrl":"https://arxiv.org/abs/2503.06947"},{"key":"journals/corr/abs-2503-23768","title":"Texture or Semantics? Vision-Language Models Get Lost in Font Recognition.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2503.23768","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-23768","documentUrl":"https://doi.org/10.48550/ARXIV.2503.23768","pages":null,"arxivId":"2503.23768","arxivUrl":"https://arxiv.org/abs/2503.23768"},{"key":"journals/corr/abs-2506-00915","title":"3D Skeleton-Based Action Recognition: A Review.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2506.00915","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-00915","documentUrl":"https://doi.org/10.48550/ARXIV.2506.00915","pages":null,"arxivId":"2506.00915","arxivUrl":"https://arxiv.org/abs/2506.00915"},{"key":"journals/corr/abs-2506-09368","title":"Anomaly Detection and Generation with Diffusion Models: A Survey.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2506.09368","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-09368","documentUrl":"https://doi.org/10.48550/ARXIV.2506.09368","pages":null,"arxivId":"2506.09368","arxivUrl":"https://arxiv.org/abs/2506.09368"},{"key":"journals/corr/abs-2506-23440","title":"PathDiff: Histopathology Image Synthesis with Unpaired Text and Mask Conditions.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2506.23440","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-23440","documentUrl":"https://doi.org/10.48550/ARXIV.2506.23440","pages":null,"arxivId":"2506.23440","arxivUrl":"https://arxiv.org/abs/2506.23440"},{"key":"journals/corr/abs-2507-11321","title":"A Mixed-Primitive-based Gaussian Splatting Method for Surface Reconstruction.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2507.11321","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2507-11321","documentUrl":"https://doi.org/10.48550/ARXIV.2507.11321","pages":null,"arxivId":"2507.11321","arxivUrl":"https://arxiv.org/abs/2507.11321"},{"key":"journals/corr/abs-2507-20890","title":"A2R2: Advancing Img2LaTeX Conversion via Visual Reasoning with Attention-Guided Refinement.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2507.20890","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2507-20890","documentUrl":"https://doi.org/10.48550/ARXIV.2507.20890","pages":null,"arxivId":"2507.20890","arxivUrl":"https://arxiv.org/abs/2507.20890"},{"key":"journals/corr/abs-2507-22522","title":"Recognizing Actions from Robotic View for Natural Human-Robot Interaction.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2507.22522","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2507-22522","documentUrl":"https://doi.org/10.48550/ARXIV.2507.22522","pages":null,"arxivId":"2507.22522","arxivUrl":"https://arxiv.org/abs/2507.22522"},{"key":"journals/corr/abs-2508-08179","title":"PP-Motion: Physical-Perceptual Fidelity Evaluation for Human Motion Generation.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2508.08179","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-08179","documentUrl":"https://doi.org/10.48550/ARXIV.2508.08179","pages":null,"arxivId":"2508.08179","arxivUrl":"https://arxiv.org/abs/2508.08179"},{"key":"journals/corr/abs-2508-14604","title":"UST-SSM: Unified Spatio-Temporal State Space Models for Point Cloud Video Modeling.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2508.14604","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-14604","documentUrl":"https://doi.org/10.48550/ARXIV.2508.14604","pages":null,"arxivId":"2508.14604","arxivUrl":"https://arxiv.org/abs/2508.14604"},{"key":"journals/corr/abs-2509-01028","title":"CompSlider: Compositional Slider for Disentangled Multiple-Attribute Image Generation.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2509.01028","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-01028","documentUrl":"https://doi.org/10.48550/ARXIV.2509.01028","pages":null,"arxivId":"2509.01028","arxivUrl":"https://arxiv.org/abs/2509.01028"},{"key":"journals/corr/abs-2509-18538","title":"GeoRemover: Removing Objects and Their Causal Visual Artifacts.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2509.18538","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-18538","documentUrl":"https://doi.org/10.48550/ARXIV.2509.18538","pages":null,"arxivId":"2509.18538","arxivUrl":"https://arxiv.org/abs/2509.18538"},{"key":"journals/corr/abs-2509-21749","title":"Thinking with Sound: Audio Chain-of-Thought Enables Multimodal Reasoning in Large Audio-Language Models.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2509.21749","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-21749","documentUrl":"https://doi.org/10.48550/ARXIV.2509.21749","pages":null,"arxivId":"2509.21749","arxivUrl":"https://arxiv.org/abs/2509.21749"},{"key":"journals/corr/abs-2509-24133","title":"Generalist Scanner Meets Specialist Locator: A Synergistic Coarse-to-Fine Framework for Robust GUI Grounding.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2509.24133","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-24133","documentUrl":"https://doi.org/10.48550/ARXIV.2509.24133","pages":null,"arxivId":"2509.24133","arxivUrl":"https://arxiv.org/abs/2509.24133"},{"key":"journals/corr/abs-2510-12287","title":"Vision Language Models Map Logos to Text via Semantic Entanglement in the Visual Projector.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2510.12287","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-12287","documentUrl":"https://doi.org/10.48550/ARXIV.2510.12287","pages":null,"arxivId":"2510.12287","arxivUrl":"https://arxiv.org/abs/2510.12287"},{"key":"journals/corr/abs-2510-25345","title":"Informative Sample Selection Model for Skeleton-based Action Recognition with Limited Training Samples.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2510.25345","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-25345","documentUrl":"https://doi.org/10.48550/ARXIV.2510.25345","pages":null,"arxivId":"2510.25345","arxivUrl":"https://arxiv.org/abs/2510.25345"},{"key":"journals/corr/abs-2511-20651","title":"RubricRL: Simple Generalizable Rewards for Text-to-Image Generation.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2511.20651","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2511-20651","documentUrl":"https://doi.org/10.48550/ARXIV.2511.20651","pages":null,"arxivId":"2511.20651","arxivUrl":"https://arxiv.org/abs/2511.20651"},{"key":"journals/corr/abs-2512-01373","title":"SRAM: Shape-Realism Alignment Metric for No Reference 3D Shape Evaluation.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2512.01373","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-01373","documentUrl":"https://doi.org/10.48550/ARXIV.2512.01373","pages":null,"arxivId":"2512.01373","arxivUrl":"https://arxiv.org/abs/2512.01373"},{"key":"journals/corr/abs-2512-01380","title":"Textured Geometry Evaluation: Perceptual 3D Textured Shape Metric via 3D Latent-Geometry Network.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2512.01380","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-01380","documentUrl":"https://doi.org/10.48550/ARXIV.2512.01380","pages":null,"arxivId":"2512.01380","arxivUrl":"https://arxiv.org/abs/2512.01380"},{"key":"journals/corr/abs-2512-16494","title":"PoseMoE: Mixture-of-Experts Network for Monocular 3D Human Pose Estimation.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2512.16494","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-16494","documentUrl":"https://doi.org/10.48550/ARXIV.2512.16494","pages":null,"arxivId":"2512.16494","arxivUrl":"https://arxiv.org/abs/2512.16494"}],"excludedFormal":[{"key":"conf/richmediagai/Yuan25","title":"Disentangling Appearance, Geometry, and Motion for Video Modeling and Generation.","type":"Inproceedings","venue":"RichMediaGAI@MM","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1145/3746262.3761970","sourceUrl":"https://dblp.org/rec/conf/richmediagai/Yuan25","documentUrl":"https://doi.org/10.1145/3746262.3761970","pages":"40","exclusionReason":"Single-page invited keynote abstract (page 40). The original 2025 workshop program explicitly labels the same talk by Junsong Yuan as Keynote.","exclusionSource":"https://richmediagai.github.io/richmediagai2025/program.html"},{"key":"journals/spm/AlRegibCCFLMRWYY25","title":"The IEEE Signal Processing Society (SPS) Announces the 2026 Class of Distinguished Lecturers and Distinguished Industry Speakers [Contributors].","type":"Article","venue":"IEEE Signal Process. Mag.","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.1109/MSP.2025.3650064","sourceUrl":"https://dblp.org/rec/journals/spm/AlRegibCCFLMRWYY25","documentUrl":"https://doi.org/10.1109/MSP.2025.3650064","pages":"8-12","exclusionReason":"IEEE society contributor/lecturer announcement, not a research paper. Publisher abstract identifies it as society information.","exclusionSource":"https://ieeexplore.ieee.org/abstract/document/11364187"}],"labName":"Visual Computing Lab","labUrl":null,"labEvidence":"2025 原始会议讲者简介明确写 Junsong Yuan 为 SUNY Buffalo Visual Computing Lab director；未在该缓存页取得 Lab 专属网址。","labSourceUrl":"https://richmediagai.github.io/richmediagai2025/speakers.html","affiliationZh":"University at Buffalo, State University of New York","sourceWarning":true,"excludedOther":[],"excludedHomonyms":[],"unassignedCandidates":[],"knownPreprintMinimum2025":null,"excludedMisattributed":[],"displayNotes":"身份已核对。已排除主旨演讲摘要和讲者名单类条目，它们不是研究论文；ORCID 不同本身不被当作同名证据。计入 30 条（会议 15、期刊 15）；预印本 22 条单列，不加总。","labDisplayNotes":"2025 年一场会议的讲者简介写明其为 SUNY Buffalo Visual Computing Lab 主任，据此归组；未取得实验室专属网址。"},{"index":27,"name":"Bolei Zhou","nameZh":"Bolei Zhou","role":"Associate Professor","affiliation":"University of California, Los Angeles","source":"DBLP official SPARQL","profileUrl":"https://dblp.org/pid/46/8066","identifier":"46/8066","identityEvidence":[{"url":"https://dblp.org/pid/46/8066","evidence":"DBLP 唯一同名作者档案；通过作者/机构主页与发表题名交叉核对。"},{"url":"https://boleizhou.github.io/","evidence":"作者本人主页确认姓名与声明中的任职机构；发表列表与 DBLP 档案交叉核对。"},{"url":"https://vail-ucla.github.io/publications","evidence":"作者/机构页面与该 DBLP 档案交叉匹配的题名示例：Efficient 3D Articulated Human Generation with Layered Surface Volumes.；Every Frame Counts: Joint Learning of Video Segmentation and Optical Flow.","matchedPaperKeys":["conf/3dim/XuYBCZW24","conf/aaai/DingWZSL020"]}],"count2025":20,"conference2025":19,"journal2025":1,"preprint2025":22,"status":"verified","notes":"身份已通过机构/个人主页或 DBLP 机构信息核对；篇数为数据库记录统计，不表示每篇均由本人主导。","retrievedAt":"2026-10-19","yearPolicy":"DBLP yearOfPublication = 2025","queryUrl":"https://sparql.dblp.org/sparql?query=PREFIX%20dblp%3A%20%3Chttps%3A//dblp.org/rdf/schema%23%3E%20PREFIX%20xsd%3A%20%3Chttp%3A//www.w3.org/2001/XMLSchema%23%3E%20SELECT%20%3Fpub%20%3Ftitle%20%3Ftype%20%3Fvenue%20WHERE%20%7B%20%3Fpub%20dblp%3AauthoredBy%20%3Chttps%3A//dblp.org/pid/46/8066%3E%3B%20dblp%3AyearOfPublication%20%222025%22%5E%5Exsd%3AgYear%3B%20dblp%3Atitle%20%3Ftitle%3B%20a%20%3Ftype%20.%20OPTIONAL%20%7B%20%3Fpub%20dblp%3ApublishedIn%20%3Fvenue%20%7D%20%7D&format=json","papers":[{"key":"conf/cvpr/WangDPLZ25","title":"Embodied Scene Understanding for Vision Language Models via MetaVQA.","type":"Inproceedings","venue":"CVPR","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/CVPR52734.2025.02091","sourceUrl":"https://dblp.org/rec/conf/cvpr/WangDPLZ25","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Wang_Embodied_Scene_Understanding_for_Vision_Language_Models_via_MetaVQA_CVPR_2025_paper.html","pages":"22453-22464"},{"key":"conf/cvpr/WuHZHZGLZ25","title":"Towards Autonomous Micromobility through Scalable Urban Simulation.","type":"Inproceedings","venue":"CVPR","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/CVPR52734.2025.02566","sourceUrl":"https://dblp.org/rec/conf/cvpr/WuHZHZGLZ25","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Wu_Towards_Autonomous_Micromobility_through_Scalable_Urban_Simulation_CVPR_2025_paper.html","pages":"27553-27563"},{"key":"conf/cvpr/XieLPWZ25","title":"Vid2Sim: Realistic and Interactive Simulation from Video for Urban Navigation.","type":"Inproceedings","venue":"CVPR","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/CVPR52734.2025.00155","sourceUrl":"https://dblp.org/rec/conf/cvpr/XieLPWZ25","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Xie_Vid2Sim_Realistic_and_Interactive_Simulation_from_Video_for_Urban_Navigation_CVPR_2025_paper.html","pages":"1581-1591"},{"key":"conf/iccv/LengYYZ25","title":"Occupancy Learning with Spatiotemporal Memory.","type":"Inproceedings","venue":"ICCV","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/ICCV51701.2025.02466","sourceUrl":"https://dblp.org/rec/conf/iccv/LengYYZ25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.02466","pages":"26569-26578"},{"key":"conf/iccv/MoNHILLTSSLZL25","title":"X-Fusion: Introducing New Modality to Frozen Large Language Models.","type":"Inproceedings","venue":"ICCV","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/ICCV51701.2025.00029","sourceUrl":"https://dblp.org/rec/conf/iccv/MoNHILLTSSLZL25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.00029","pages":"228-238"},{"key":"conf/iccv/YangYHJPZC25","title":"Verbalized Representation Learning for Interpretable Few-Shot Generalization.","type":"Inproceedings","venue":"ICCV","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/ICCV51701.2025.00157","sourceUrl":"https://dblp.org/rec/conf/iccv/YangYHJPZC25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.00157","pages":"1602-1612"},{"key":"conf/iccv/ZhouXZZLZCLLBXHZM25","title":"V2XPnP: Vehicle-to-Everything Spatio-Temporal Fusion for Multi-Agent Perception and Prediction.","type":"Inproceedings","venue":"ICCV","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/ICCV51701.2025.02356","sourceUrl":"https://dblp.org/rec/conf/iccv/ZhouXZZLZCLLBXHZM25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.02356","pages":"25399-25409"},{"key":"conf/iccv/ZhouZCHZM25","title":"TurboTrain: Towards Efficient and Balanced Multi-Task Learning for Multi-Agent Perception and Prediction.","type":"Inproceedings","venue":"ICCV","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/ICCV51701.2025.00418","sourceUrl":"https://dblp.org/rec/conf/iccv/ZhouZCHZM25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.00418","pages":"4391-4402"},{"key":"conf/iclr/LiuLWZ25","title":"Learning to Generate Diverse Pedestrian Movements from Web Videos with Noisy Labels.","type":"Inproceedings","venue":"ICLR","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":null,"sourceUrl":"https://dblp.org/rec/conf/iclr/LiuLWZ25","documentUrl":"https://openreview.net/forum?id=DydCqKa6AH","pages":null},{"key":"conf/iclr/WuHHWDLLZ25","title":"MetaUrban: An Embodied AI Simulation Platform for Urban Micromobility.","type":"Inproceedings","venue":"ICLR","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":null,"sourceUrl":"https://dblp.org/rec/conf/iclr/WuHHWDLLZ25","documentUrl":"https://openreview.net/forum?id=kFsWpSxkFz","pages":null},{"key":"conf/iclr/ZhangX00WZY25","title":"3DitScene: Editing Any Scene via Language-guided Disentangled Gaussian Splatting.","type":"Inproceedings","venue":"ICLR","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":null,"sourceUrl":"https://dblp.org/rec/conf/iclr/ZhangX00WZY25","documentUrl":"https://openreview.net/forum?id=iKDbLpVgQc","pages":null},{"key":"conf/icml/CaiPZ25","title":"Robot-Gated Interactive Imitation Learning with Adaptive Intervention Mechanism.","type":"Inproceedings","venue":"ICML","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":null,"sourceUrl":"https://dblp.org/rec/conf/icml/CaiPZ25","documentUrl":"https://proceedings.mlr.press/v267/cai25e.html","pages":null},{"key":"conf/icml/LiFGZLXYTZ0DZ25","title":"WOMD-Reasoning: A Large-Scale Dataset for Interaction Reasoning in Driving.","type":"Inproceedings","venue":"ICML","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":null,"sourceUrl":"https://dblp.org/rec/conf/icml/LiFGZLXYTZ0DZ25","documentUrl":"https://proceedings.mlr.press/v267/li25l.html","pages":null},{"key":"conf/icml/WangLLAZ025","title":"Hyper: Hyperparameter Robust Efficient Exploration in Reinforcement Learning.","type":"Inproceedings","venue":"ICML","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":null,"sourceUrl":"https://dblp.org/rec/conf/icml/WangLLAZ025","documentUrl":"https://proceedings.mlr.press/v267/wang25bo.html","pages":null},{"key":"conf/icra/PengLZ25","title":"Data-Efficient Learning from Human Interventions for Mobile Robots.","type":"Inproceedings","venue":"ICRA","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/ICRA55743.2025.11128012","sourceUrl":"https://dblp.org/rec/conf/icra/PengLZ25","documentUrl":"https://doi.org/10.1109/ICRA55743.2025.11128012","pages":"7407-7414"},{"key":"conf/iros/ZhaoXXXZM25","title":"CooPre: Cooperative Pretraining for V2X Cooperative Perception.","type":"Inproceedings","venue":"IROS","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/IROS60139.2025.11246787","sourceUrl":"https://dblp.org/rec/conf/iros/ZhaoXXXZM25","documentUrl":"https://doi.org/10.1109/IROS60139.2025.11246787","pages":"11765-11772"},{"key":"conf/nips/CaiPZ25","title":"Predictive Preference Learning from Human Interventions.","type":"Inproceedings","venue":"NeurIPS","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":null,"sourceUrl":"https://dblp.org/rec/conf/nips/CaiPZ25","documentUrl":"http://papers.nips.cc/paper_files/paper/2025/hash/4f7b1f51ef415f09e171f632172284ff-Abstract-Conference.html","pages":null},{"key":"conf/nips/LiuPCZ25","title":"Adv-BMT: Bidirectional Motion Transformer for Safety-Critical Traffic Scenario Generation.","type":"Inproceedings","venue":"NeurIPS","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":null,"sourceUrl":"https://dblp.org/rec/conf/nips/LiuPCZ25","documentUrl":"http://papers.nips.cc/paper_files/paper/2025/hash/4faa13a048b13a42ee093c26cf062993-Abstract-Conference.html","pages":null},{"key":"conf/nips/ZhouCZZHZM25","title":"AutoVLA: A Vision-Language-Action Model for End-to-End Autonomous Driving with Adaptive Reasoning and Reinforcement Fine-Tuning.","type":"Inproceedings","venue":"NeurIPS","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":null,"sourceUrl":"https://dblp.org/rec/conf/nips/ZhouCZZHZM25","documentUrl":"http://papers.nips.cc/paper_files/paper/2025/hash/2843fccca5bedd369a4764848b9bd546-Abstract-Conference.html","pages":null},{"key":"journals/ral/LengYRZ25","title":"BEVCon: Advancing Bird's Eye View Perception With Contrastive Learning.","type":"Article","venue":"IEEE Robotics Autom. Lett.","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.1109/LRA.2025.3540386","sourceUrl":"https://dblp.org/rec/journals/ral/LengYRZ25","documentUrl":"https://doi.org/10.1109/LRA.2025.3540386","pages":"3158-3165"}],"preprints":[{"key":"journals/corr/abs-2501-02158","title":"Joint Optimization for 4D Human-Scene Reconstruction in the Wild.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2501.02158","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2501-02158","documentUrl":"https://doi.org/10.48550/ARXIV.2501.02158","pages":null,"arxivId":"2501.02158","arxivUrl":"https://arxiv.org/abs/2501.02158"},{"key":"journals/corr/abs-2501-06693","title":"Vid2Sim: Realistic and Interactive Simulation from Video for Urban Navigation.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2501.06693","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2501-06693","documentUrl":"https://doi.org/10.48550/ARXIV.2501.06693","pages":null,"arxivId":"2501.06693","arxivUrl":"https://arxiv.org/abs/2501.06693"},{"key":"journals/corr/abs-2501-09167","title":"Embodied Scene Understanding for Vision Language Models via MetaVQA.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2501.09167","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2501-09167","documentUrl":"https://doi.org/10.48550/ARXIV.2501.09167","pages":null,"arxivId":"2501.09167","arxivUrl":"https://arxiv.org/abs/2501.09167"},{"key":"journals/corr/abs-2502-03369","title":"Learning from Active Human Involvement through Proxy Value Propagation.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2502.03369","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2502-03369","documentUrl":"https://doi.org/10.48550/ARXIV.2502.03369","pages":null,"arxivId":"2502.03369","arxivUrl":"https://arxiv.org/abs/2502.03369"},{"key":"journals/corr/abs-2503-04969","title":"Data-Efficient Learning from Human Interventions for Mobile Robots.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2503.04969","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-04969","documentUrl":"https://doi.org/10.48550/ARXIV.2503.04969","pages":null,"arxivId":"2503.04969","arxivUrl":"https://arxiv.org/abs/2503.04969"},{"key":"journals/corr/abs-2504-20996","title":"X-Fusion: Introducing New Modality to Frozen Large Language Models.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2504.20996","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2504-20996","documentUrl":"https://doi.org/10.48550/ARXIV.2504.20996","pages":null,"arxivId":"2504.20996","arxivUrl":"https://arxiv.org/abs/2504.20996"},{"key":"journals/corr/abs-2505-00690","title":"Towards Autonomous Micromobility through Scalable Urban Simulation.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2505.00690","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-00690","documentUrl":"https://doi.org/10.48550/ARXIV.2505.00690","pages":null,"arxivId":"2505.00690","arxivUrl":"https://arxiv.org/abs/2505.00690"},{"key":"journals/corr/abs-2506-08006","title":"Dreamland: Controllable World Creation with Simulator and Generative Models.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2506.08006","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-08006","documentUrl":"https://doi.org/10.48550/ARXIV.2506.08006","pages":null,"arxivId":"2506.08006","arxivUrl":"https://arxiv.org/abs/2506.08006"},{"key":"journals/corr/abs-2506-09176","title":"Robot-Gated Interactive Imitation Learning with Adaptive Intervention Mechanism.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2506.09176","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-09176","documentUrl":"https://doi.org/10.48550/ARXIV.2506.09176","pages":null,"arxivId":"2506.09176","arxivUrl":"https://arxiv.org/abs/2506.09176"},{"key":"journals/corr/abs-2506-09485","title":"Adv-BMT: Bidirectional Motion Transformer for Safety-Critical Traffic Scenario Generation.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2506.09485","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-09485","documentUrl":"https://doi.org/10.48550/ARXIV.2506.09485","pages":null,"arxivId":"2506.09485","arxivUrl":"https://arxiv.org/abs/2506.09485"},{"key":"journals/corr/abs-2506-13757","title":"AutoVLA: A Vision-Language-Action Model for End-to-End Autonomous Driving with Adaptive Reasoning and Reinforcement Fine-Tuning.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2506.13757","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-13757","documentUrl":"https://doi.org/10.48550/ARXIV.2506.13757","pages":null,"arxivId":"2506.13757","arxivUrl":"https://arxiv.org/abs/2506.13757"},{"key":"journals/corr/abs-2506-23316","title":"InfGen: Scenario Generation as Next Token Group Prediction.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2506.23316","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-23316","documentUrl":"https://doi.org/10.48550/ARXIV.2506.23316","pages":null,"arxivId":"2506.23316","arxivUrl":"https://arxiv.org/abs/2506.23316"},{"key":"journals/corr/abs-2507-22028","title":"From Seeing to Experiencing: Scaling Navigation Foundation Models with Reinforcement Learning.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2507.22028","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2507-22028","documentUrl":"https://doi.org/10.48550/ARXIV.2507.22028","pages":null,"arxivId":"2507.22028","arxivUrl":"https://arxiv.org/abs/2507.22028"},{"key":"journals/corr/abs-2508-04682","title":"TurboTrain: Towards Efficient and Balanced Multi-Task Learning for Multi-Agent Perception and Prediction.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2508.04682","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-04682","documentUrl":"https://doi.org/10.48550/ARXIV.2508.04682","pages":null,"arxivId":"2508.04682","arxivUrl":"https://arxiv.org/abs/2508.04682"},{"key":"journals/corr/abs-2508-04702","title":"BEVCon: Advancing Bird's Eye View Perception with Contrastive Learning.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2508.04702","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-04702","documentUrl":"https://doi.org/10.48550/ARXIV.2508.04702","pages":null,"arxivId":"2508.04702","arxivUrl":"https://arxiv.org/abs/2508.04702"},{"key":"journals/corr/abs-2508-04705","title":"Occupancy Learning with Spatiotemporal Memory.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2508.04705","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-04705","documentUrl":"https://doi.org/10.48550/ARXIV.2508.04705","pages":null,"arxivId":"2508.04705","arxivUrl":"https://arxiv.org/abs/2508.04705"},{"key":"journals/corr/abs-2509-03704","title":"QuantV2X: A Fully Quantized Multi-Agent System for Cooperative Perception.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2509.03704","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-03704","documentUrl":"https://doi.org/10.48550/ARXIV.2509.03704","pages":null,"arxivId":"2509.03704","arxivUrl":"https://arxiv.org/abs/2509.03704"},{"key":"journals/corr/abs-2510-01545","title":"Predictive Preference Learning from Human Interventions.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2510.01545","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-01545","documentUrl":"https://doi.org/10.48550/ARXIV.2510.01545","pages":null,"arxivId":"2510.01545","arxivUrl":"https://arxiv.org/abs/2510.01545"},{"key":"journals/corr/abs-2510-15018","title":"UrbanVerse: Scaling Urban Simulation by Watching City-Tour Videos.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2510.15018","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-15018","documentUrl":"https://doi.org/10.48550/ARXIV.2510.15018","pages":null,"arxivId":"2510.15018","arxivUrl":"https://arxiv.org/abs/2510.15018"},{"key":"journals/corr/abs-2512-10954","title":"Group Diffusion: Enhancing Image Generation by Unlocking Cross-Sample Collaboration.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2512.10954","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-10954","documentUrl":"https://doi.org/10.48550/ARXIV.2512.10954","pages":null,"arxivId":"2512.10954","arxivUrl":"https://arxiv.org/abs/2512.10954"},{"key":"journals/corr/abs-2512-14133","title":"AnimaMimic: Imitating 3D Animation from Video Priors.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2512.14133","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-14133","documentUrl":"https://doi.org/10.48550/ARXIV.2512.14133","pages":null,"arxivId":"2512.14133","arxivUrl":"https://arxiv.org/abs/2512.14133"},{"key":"journals/corr/abs-2512-24426","title":"Counterfactual VLA: Self-Reflective Vision-Language-Action Model with Adaptive Reasoning.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2512.24426","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-24426","documentUrl":"https://doi.org/10.48550/ARXIV.2512.24426","pages":null,"arxivId":"2512.24426","arxivUrl":"https://arxiv.org/abs/2512.24426"}],"excludedFormal":[],"labName":"Vision and Autonomy Intelligence Lab (VAIL)","labUrl":"https://vail-ucla.github.io/","labEvidence":"本人主页明确写 direct the Vision and Autonomy Intelligence Lab (VAIL)，并直接链接。","labSourceUrl":"https://boleizhou.github.io/","affiliationZh":"University of California, Los Angeles","sourceWarning":false,"excludedOther":[],"excludedHomonyms":[],"unassignedCandidates":[],"knownPreprintMinimum2025":null,"excludedMisattributed":[],"displayNotes":"身份已经机构或个人主页核对。2025 年正式记录 20 条（会议 19、期刊 1），所有作者位置均计入，不表示主导或贡献份额；预印本 22 条单列，不加总。","labDisplayNotes":"个人主页写明其主持 Vision and Autonomy Intelligence Lab（VAIL），并直接链接，据此归组。"},{"index":28,"name":"Jun-Yan Zhu","nameZh":"Jun-Yan Zhu","role":"Associate Professor","affiliation":"Carnegie Mellon University","source":"DBLP official SPARQL","profileUrl":"https://dblp.org/pid/117/4782","identifier":"117/4782","identityEvidence":[{"url":"https://dblp.org/pid/117/4782","evidence":"DBLP 唯一同名作者档案；通过作者/机构主页与发表题名交叉核对。"},{"url":"https://www.cs.cmu.edu/~junyanz/","evidence":"作者/机构页面与该 DBLP 档案交叉匹配的题名示例：Anycost GANs for Interactive Image Synthesis and Editing.；Dataset Distillation by Matching Training Trajectories.","matchedPaperKeys":["conf/cvpr/00020G0Z21","conf/cvpr/Cazenavette00EZ22a"]}],"count2025":14,"conference2025":13,"journal2025":1,"preprint2025":14,"status":"verified","notes":"身份已通过机构/个人主页或 DBLP 机构信息核对；篇数为数据库记录统计，不表示每篇均由本人主导。","retrievedAt":"2026-10-19","yearPolicy":"DBLP yearOfPublication = 2025","queryUrl":"https://sparql.dblp.org/sparql?query=PREFIX%20dblp%3A%20%3Chttps%3A//dblp.org/rdf/schema%23%3E%20PREFIX%20xsd%3A%20%3Chttp%3A//www.w3.org/2001/XMLSchema%23%3E%20SELECT%20%3Fpub%20%3Ftitle%20%3Ftype%20%3Fvenue%20WHERE%20%7B%20%3Fpub%20dblp%3AauthoredBy%20%3Chttps%3A//dblp.org/pid/117/4782%3E%3B%20dblp%3AyearOfPublication%20%222025%22%5E%5Exsd%3AgYear%3B%20dblp%3Atitle%20%3Ftitle%3B%20a%20%3Ftype%20.%20OPTIONAL%20%7B%20%3Fpub%20dblp%3ApublishedIn%20%3Fvenue%20%7D%20%7D&format=json","papers":[{"key":"conf/cvpr/ChenSMFLSAZ0T25","title":"Multi-subject Open-set Personalization in Video Generation.","type":"Inproceedings","venue":"CVPR","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/CVPR52734.2025.00572","sourceUrl":"https://dblp.org/rec/conf/cvpr/ChenSMFLSAZ0T25","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Chen_Multi-subject_Open-set_Personalization_in_Video_Generation_CVPR_2025_paper.html","pages":"6099-6110"},{"key":"conf/cvpr/LiuKSZ25","title":"Generative Photomontage.","type":"Inproceedings","venue":"CVPR","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/CVPR52734.2025.00743","sourceUrl":"https://dblp.org/rec/conf/cvpr/LiuKSZ25","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Liu_Generative_Photomontage_CVPR_2025_paper.html","pages":"7931-7941"},{"key":"conf/eccv/DengOWRZZA24","title":"FlashTex: Fast Relightable Mesh Texturing with LightControlNet.","type":"Inproceedings","venue":"ECCV (27)","year":2025,"yearOfPublication":2025,"yearOfEvent":2024,"doi":"https://doi.org/10.1007/978-3-031-73383-3_6","sourceUrl":"https://dblp.org/rec/conf/eccv/DengOWRZZA24","documentUrl":"https://doi.org/10.1007/978-3-031-73383-3_6","pages":"90-107"},{"key":"conf/eccv/KangZBPKPSZP24","title":"Distilling Diffusion Models Into Conditional GANs.","type":"Inproceedings","venue":"ECCV (28)","year":2025,"yearOfPublication":2025,"yearOfEvent":2024,"doi":"https://doi.org/10.1007/978-3-031-73390-1_25","sourceUrl":"https://dblp.org/rec/conf/eccv/KangZBPKPSZP24","documentUrl":"https://doi.org/10.1007/978-3-031-73390-1_25","pages":"428-447"},{"key":"conf/eccv/MahapatraMLCDWZCHX24","title":"Co-speech Gesture Video Generation with 3D Human Meshes.","type":"Inproceedings","venue":"ECCV (89)","year":2025,"yearOfPublication":2025,"yearOfEvent":2024,"doi":"https://doi.org/10.1007/978-3-031-73024-5_11","sourceUrl":"https://dblp.org/rec/conf/eccv/MahapatraMLCDWZCHX24","documentUrl":"https://doi.org/10.1007/978-3-031-73024-5_11","pages":"172-189"},{"key":"conf/iccv/DengLZSSBRZAZ25","title":"Efficient Autoregressive Shape Generation Via Octree-Based Adaptive Tokenization.","type":"Inproceedings","venue":"ICCV","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/ICCV51701.2025.01087","sourceUrl":"https://dblp.org/rec/conf/iccv/DengLZSSBRZAZ25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.01087","pages":"11685-11696"},{"key":"conf/iccv/KumariYZMA25","title":"Generating Multi-Image Synthetic Data for Text-to-Image Customization.","type":"Inproceedings","venue":"ICCV","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/ICCV51701.2025.01534","sourceUrl":"https://dblp.org/rec/conf/iccv/KumariYZMA25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.01534","pages":"16524-16534"},{"key":"conf/iccv/PunDLRLZ25","title":"Generating Physically Stable and Buildable Brick Structures from Text.","type":"Inproceedings","venue":"ICCV","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/ICCV51701.2025.01373","sourceUrl":"https://dblp.org/rec/conf/iccv/PunDLRLZ25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.01373","pages":"14798-14809"},{"key":"conf/iclr/Li0ZCLGXMZ025","title":"SVDQuant: Absorbing Outliers by Low-Rank Component for 4-Bit Diffusion Models.","type":"Inproceedings","venue":"ICLR","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":null,"sourceUrl":"https://dblp.org/rec/conf/iclr/Li0ZCLGXMZ025","documentUrl":"https://openreview.net/forum?id=vWR3KuiQur","pages":null},{"key":"conf/mm/PerezYZMTMSPKVW25","title":"CReLeRI: Explainable, Concept-centric, Representation, Learning, Reasoning, and Interaction Video Analysis System.","type":"Inproceedings","venue":"ACM Multimedia","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1145/3746027.3754479","sourceUrl":"https://dblp.org/rec/conf/mm/PerezYZMTMSPKVW25","documentUrl":"https://doi.org/10.1145/3746027.3754479","pages":"13528-13530"},{"key":"conf/nips/WangHEZZ25","title":"Fast Data Attribution for Text-to-Image Models.","type":"Inproceedings","venue":"NeurIPS","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":null,"sourceUrl":"https://dblp.org/rec/conf/nips/WangHEZZ25","documentUrl":"http://papers.nips.cc/paper_files/paper/2025/hash/5ce3a49415f78db65a714b4f05c62f4e-Abstract-Conference.html","pages":null},{"key":"conf/siggrapha/Lu00Z25","title":"Input-Aware Sparse Attention for Real-Time Co-Speech Video Generation.","type":"Inproceedings","venue":"SIGGRAPH Asia","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1145/3757377.3763831","sourceUrl":"https://dblp.org/rec/conf/siggrapha/Lu00Z25","documentUrl":"https://doi.org/10.1145/3757377.3763831","pages":"6:1-6:11"},{"key":"conf/siggrapha/ParmarPWONZCA25","title":"Object-level Visual Prompts for Compositional Image Generation.","type":"Inproceedings","venue":"SIGGRAPH Asia","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1145/3757377.3763867","sourceUrl":"https://dblp.org/rec/conf/siggrapha/ParmarPWONZCA25","documentUrl":"https://doi.org/10.1145/3757377.3763867","pages":"101:1-101:12"},{"key":"journals/ijcv/GePZH25","title":"Expressive Image Generation and Editing with Rich Text.","type":"Article","venue":"Int. J. Comput. Vis.","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.1007/S11263-025-02361-2","sourceUrl":"https://dblp.org/rec/journals/ijcv/GePZH25","documentUrl":"https://doi.org/10.1007/S11263-025-02361-2","pages":"4604-4622"}],"preprints":[{"key":"journals/corr/abs-2501-01424","title":"Object-level Visual Prompts for Compositional Image Generation.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2501.01424","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2501-01424","documentUrl":"https://doi.org/10.48550/ARXIV.2501.01424","pages":null,"arxivId":"2501.01424","arxivUrl":"https://arxiv.org/abs/2501.01424"},{"key":"journals/corr/abs-2501-06187","title":"Multi-subject Open-set Personalization in Video Generation.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2501.06187","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2501-06187","documentUrl":"https://doi.org/10.48550/ARXIV.2501.06187","pages":null,"arxivId":"2501.06187","arxivUrl":"https://arxiv.org/abs/2501.06187"},{"key":"journals/corr/abs-2502-01720","title":"Generating Multi-Image Synthetic Data for Text-to-Image Customization.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2502.01720","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2502-01720","documentUrl":"https://doi.org/10.48550/ARXIV.2502.01720","pages":null,"arxivId":"2502.01720","arxivUrl":"https://arxiv.org/abs/2502.01720"},{"key":"journals/corr/abs-2504-02817","title":"Efficient Autoregressive Shape Generation via Octree-Based Adaptive Tokenization.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2504.02817","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2504-02817","documentUrl":"https://doi.org/10.48550/ARXIV.2504.02817","pages":null,"arxivId":"2504.02817","arxivUrl":"https://arxiv.org/abs/2504.02817"},{"key":"journals/corr/abs-2505-05469","title":"Generating Physically Stable and Buildable LEGO Designs from Text.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2505.05469","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-05469","documentUrl":"https://doi.org/10.48550/ARXIV.2505.05469","pages":null,"arxivId":"2505.05469","arxivUrl":"https://arxiv.org/abs/2505.05469"},{"key":"journals/corr/abs-2507-18633","title":"Identifying Prompted Artist Names from Generated Images.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2507.18633","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2507-18633","documentUrl":"https://doi.org/10.48550/ARXIV.2507.18633","pages":null,"arxivId":"2507.18633","arxivUrl":"https://arxiv.org/abs/2507.18633"},{"key":"journals/corr/abs-2508-15773","title":"Scaling Group Inference for Diverse and High-Quality Generation.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2508.15773","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-15773","documentUrl":"https://doi.org/10.48550/ARXIV.2508.15773","pages":null,"arxivId":"2508.15773","arxivUrl":"https://arxiv.org/abs/2508.15773"},{"key":"journals/corr/abs-2508-21063","title":"Prompt-to-Product: Generative Assembly via Bimanual Manipulation.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2508.21063","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-21063","documentUrl":"https://doi.org/10.48550/ARXIV.2508.21063","pages":null,"arxivId":"2508.21063","arxivUrl":"https://arxiv.org/abs/2508.21063"},{"key":"journals/corr/abs-2510-02617","title":"Input-Aware Sparse Attention for Real-Time Co-Speech Video Generation.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2510.02617","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-02617","documentUrl":"https://doi.org/10.48550/ARXIV.2510.02617","pages":null,"arxivId":"2510.02617","arxivUrl":"https://arxiv.org/abs/2510.02617"},{"key":"journals/corr/abs-2510-14978","title":"Learning an Image Editing Model without Image Editing Pairs.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2510.14978","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-14978","documentUrl":"https://doi.org/10.48550/ARXIV.2510.14978","pages":null,"arxivId":"2510.14978","arxivUrl":"https://arxiv.org/abs/2510.14978"},{"key":"journals/corr/abs-2511-01266","title":"MotionStream: Real-Time Video Generation with Interactive Motion Controls.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2511.01266","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2511-01266","documentUrl":"https://doi.org/10.48550/ARXIV.2511.01266","pages":null,"arxivId":"2511.01266","arxivUrl":"https://arxiv.org/abs/2511.01266"},{"key":"journals/corr/abs-2511-10721","title":"Fast Data Attribution for Text-to-Image Models.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2511.10721","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2511-10721","documentUrl":"https://doi.org/10.48550/ARXIV.2511.10721","pages":null,"arxivId":"2511.10721","arxivUrl":"https://arxiv.org/abs/2511.10721"},{"key":"journals/corr/abs-2511-21978","title":"PAT3D: Physics-Augmented Text-to-3D Scene Generation.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2511.21978","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2511-21978","documentUrl":"https://doi.org/10.48550/ARXIV.2511.21978","pages":null,"arxivId":"2511.21978","arxivUrl":"https://arxiv.org/abs/2511.21978"},{"key":"journals/corr/abs-2512-10955","title":"Omni-Attribute: Open-vocabulary Attribute Encoder for Visual Concept Personalization.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2512.10955","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-10955","documentUrl":"https://doi.org/10.48550/ARXIV.2512.10955","pages":null,"arxivId":"2512.10955","arxivUrl":"https://arxiv.org/abs/2512.10955"}],"excludedFormal":[],"labName":"Generative Intelligence Lab","labUrl":"https://www.cs.cmu.edu/~generative-intelligence-lab/","labEvidence":"本人主页以 Generative Intelligence Lab 为研究组标题，Lab 导航直接链接该网站。","labSourceUrl":"https://www.cs.cmu.edu/~junyanz/","affiliationZh":"Carnegie Mellon University","sourceWarning":false,"excludedOther":[],"excludedHomonyms":[],"unassignedCandidates":[],"knownPreprintMinimum2025":null,"excludedMisattributed":[],"displayNotes":"身份已经机构或个人主页核对。2025 年正式记录 14 条（会议 13、期刊 1），所有作者位置均计入，不表示主导或贡献份额；预印本 14 条单列，不加总。","labDisplayNotes":"个人主页以 Generative Intelligence Lab 作为研究组并直接链接。它与港中文（深圳）刘圳的 GenLab 是不同实验室，不合并。"},{"index":29,"name":"Wanxiang Che","nameZh":"车万翔","role":"Professor","affiliation":"Harbin Institute of Technology","source":"DBLP official SPARQL","profileUrl":"https://dblp.org/pid/98/4640","identifier":"98/4640","identityEvidence":[{"url":"https://dblp.org/pid/98/4640","evidence":"DBLP 唯一同名作者档案；通过作者/机构主页与发表题名交叉核对。"},{"url":"https://chewanxiang.com/en/","evidence":"作者/机构页面与该 DBLP 档案交叉匹配的题名示例：Deep Learning in Lexical Analysis and Parsing.","matchedPaperKeys":["conf/ijcnlp/CheZ17"]}],"count2025":33,"conference2025":22,"journal2025":11,"preprint2025":48,"status":"verified","notes":"身份已通过机构/个人主页或 DBLP 机构信息核对；篇数为数据库记录统计，不表示每篇均由本人主导。","retrievedAt":"2026-10-19","yearPolicy":"DBLP yearOfPublication = 2025","queryUrl":"https://sparql.dblp.org/sparql?query=PREFIX%20dblp%3A%20%3Chttps%3A//dblp.org/rdf/schema%23%3E%20PREFIX%20xsd%3A%20%3Chttp%3A//www.w3.org/2001/XMLSchema%23%3E%20SELECT%20%3Fpub%20%3Ftitle%20%3Ftype%20%3Fvenue%20WHERE%20%7B%20%3Fpub%20dblp%3AauthoredBy%20%3Chttps%3A//dblp.org/pid/98/4640%3E%3B%20dblp%3AyearOfPublication%20%222025%22%5E%5Exsd%3AgYear%3B%20dblp%3Atitle%20%3Ftitle%3B%20a%20%3Ftype%20.%20OPTIONAL%20%7B%20%3Fpub%20dblp%3ApublishedIn%20%3Fvenue%20%7D%20%7D&format=json","papers":[{"key":"conf/aaai/0001CZW0CL25","title":"Divide-Solve-Combine: An Interpretable and Accurate Prompting Framework for Zero-shot Multi-Intent Detection.","type":"Inproceedings","venue":"AAAI","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1609/AAAI.V39I23.34688","sourceUrl":"https://dblp.org/rec/conf/aaai/0001CZW0CL25","documentUrl":"https://doi.org/10.1609/AAAI.V39I23.34688","pages":"25038-25046"},{"key":"conf/aaai/ChengCZ0FCL025","title":"CoMT: A Novel Benchmark for Chain of Multi-modal Thought on Large Vision-Language Models.","type":"Inproceedings","venue":"AAAI","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1609/AAAI.V39I22.34538","sourceUrl":"https://dblp.org/rec/conf/aaai/ChengCZ0FCL025","documentUrl":"https://doi.org/10.1609/AAAI.V39I22.34538","pages":"23678-23686"},{"key":"conf/aaai/WangLYHLWCC25","title":"CVLUE: A New Benchmark Dataset for Chinese Vision-Language Understanding Evaluation.","type":"Inproceedings","venue":"AAAI","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1609/AAAI.V39I8.32884","sourceUrl":"https://dblp.org/rec/conf/aaai/WangLYHLWCC25","documentUrl":"https://doi.org/10.1609/AAAI.V39I8.32884","pages":"8196-8204"},{"key":"conf/acl/XuWZZC25","title":"Abacus-SQL: A Text-to-SQL System Empowering Cross-Domain and Open-Domain Database Retrieval.","type":"Inproceedings","venue":"ACL (3)","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.18653/V1/2025.ACL-DEMO.12","sourceUrl":"https://dblp.org/rec/conf/acl/XuWZZC25","documentUrl":"https://doi.org/10.18653/V1/2025.ACL-DEMO.12","pages":"118-128"},{"key":"conf/coling/LiGDFWXWCWXZ0ZZ25","title":"Can Large Language Models Understand You Better? An MBTI Personality Detection Dataset Aligned with Population Traits.","type":"Inproceedings","venue":"COLING","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":null,"sourceUrl":"https://dblp.org/rec/conf/coling/LiGDFWXWCWXZ0ZZ25","documentUrl":"https://aclanthology.org/2025.coling-main.339/","pages":"5071-5081"},{"key":"conf/coling/ZhangWDZC25","title":"MURRE: Multi-Hop Table Retrieval with Removal for Open-Domain Text-to-SQL.","type":"Inproceedings","venue":"COLING","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":null,"sourceUrl":"https://dblp.org/rec/conf/coling/ZhangWDZC25","documentUrl":"https://aclanthology.org/2025.coling-main.386/","pages":"5789-5806"},{"key":"conf/emnlp/ChenYMCLSLFHXLS25","title":"ClueAnchor: Clue-Anchored Knowledge Reasoning Exploration and Optimization for Retrieval-Augmented Generation.","type":"Inproceedings","venue":"EMNLP (Findings)","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.18653/V1/2025.FINDINGS-EMNLP.1049","sourceUrl":"https://dblp.org/rec/conf/emnlp/ChenYMCLSLFHXLS25","documentUrl":"https://doi.org/10.18653/V1/2025.FINDINGS-EMNLP.1049","pages":"19258-19278"},{"key":"conf/emnlp/NiuCWXYZWWC25","title":"Chart2Code53: A Large-Scale Diverse and Complex Dataset for Enhancing Chart-to-Code Generation.","type":"Inproceedings","venue":"EMNLP","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.18653/V1/2025.EMNLP-MAIN.799","sourceUrl":"https://dblp.org/rec/conf/emnlp/NiuCWXYZWWC25","documentUrl":"https://doi.org/10.18653/V1/2025.EMNLP-MAIN.799","pages":"15828-15844"},{"key":"conf/emnlp/PengZCLCQC25","title":"DLPO: Towards a Robust, Efficient, and Generalizable Prompt Optimization Framework from a Deep-Learning Perspective.","type":"Inproceedings","venue":"EMNLP (Findings)","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.18653/V1/2025.FINDINGS-EMNLP.441","sourceUrl":"https://dblp.org/rec/conf/emnlp/PengZCLCQC25","documentUrl":"https://doi.org/10.18653/V1/2025.FINDINGS-EMNLP.441","pages":"8311-8334"},{"key":"conf/emnlp/WangDZZC25","title":"DAC: Decomposed Automation Correction for Text-to-SQL.","type":"Inproceedings","venue":"EMNLP (Findings)","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.18653/V1/2025.FINDINGS-EMNLP.22","sourceUrl":"https://dblp.org/rec/conf/emnlp/WangDZZC25","documentUrl":"https://doi.org/10.18653/V1/2025.FINDINGS-EMNLP.22","pages":"385-402"},{"key":"conf/emnlp/WangJLXXZC25","title":"Lookahead Q-Cache: Achieving More Consistent KV Cache Eviction via Pseudo Query.","type":"Inproceedings","venue":"EMNLP","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.18653/V1/2025.EMNLP-MAIN.1732","sourceUrl":"https://dblp.org/rec/conf/emnlp/WangJLXXZC25","documentUrl":"https://doi.org/10.18653/V1/2025.EMNLP-MAIN.1732","pages":"34158-34174"},{"key":"conf/emnlp/ZhangWXZC25","title":"RoT: Enhancing Table Reasoning with Iterative Row-Wise Traversals.","type":"Inproceedings","venue":"EMNLP","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.18653/V1/2025.EMNLP-MAIN.29","sourceUrl":"https://dblp.org/rec/conf/emnlp/ZhangWXZC25","documentUrl":"https://doi.org/10.18653/V1/2025.EMNLP-MAIN.29","pages":"559-579"},{"key":"conf/emnlp/ZhangWXZC25a","title":"MULTITAT: Benchmarking Multilingual Table-and-Text Question Answering.","type":"Inproceedings","venue":"EMNLP (Findings)","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.18653/V1/2025.FINDINGS-EMNLP.33","sourceUrl":"https://dblp.org/rec/conf/emnlp/ZhangWXZC25a","documentUrl":"https://doi.org/10.18653/V1/2025.FINDINGS-EMNLP.33","pages":"626-647"},{"key":"conf/icassp/0001WCZHSLC25","title":"CroPrompt: Cross-task Interactive Prompting for Zero-shot Spoken Language Understanding.","type":"Inproceedings","venue":"ICASSP","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/ICASSP49660.2025.10889329","sourceUrl":"https://dblp.org/rec/conf/icassp/0001WCZHSLC25","documentUrl":"https://doi.org/10.1109/ICASSP49660.2025.10889329","pages":"1-5"},{"key":"conf/ijcai/WangLZC00LC025","title":"Improving Consistency Identification in Task-oriented Dialogue Through Multi-Agent Collaboration.","type":"Inproceedings","venue":"IJCAI","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.24963/IJCAI.2025/918","sourceUrl":"https://dblp.org/rec/conf/ijcai/WangLZC00LC025","documentUrl":"https://doi.org/10.24963/IJCAI.2025/918","pages":"8259-8267"},{"key":"conf/kdd/00060LHZC25","title":"Advancing Tool-Augmented Large Language Models via Meta-Verification and Reflection Learning.","type":"Inproceedings","venue":"KDD (2)","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1145/3711896.3736835","sourceUrl":"https://dblp.org/rec/conf/kdd/00060LHZC25","documentUrl":"https://doi.org/10.1145/3711896.3736835","pages":"2078-2089"},{"key":"conf/mm/JiCCW0C25","title":"MPCC: A Novel Benchmark for Multimodal Planning with Complex Constraints in Multimodal Large Language Models.","type":"Inproceedings","venue":"ACM Multimedia","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1145/3746027.3755790","sourceUrl":"https://dblp.org/rec/conf/mm/JiCCW0C25","documentUrl":"https://doi.org/10.1145/3746027.3755790","pages":"5188-5197"},{"key":"conf/mm/ZhangLTC0C025","title":"ViTCoT: Video-Text Interleaved Chain-of-Thought for Boosting Video Understanding in Large Language Models.","type":"Inproceedings","venue":"ACM Multimedia","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1145/3746027.3755837","sourceUrl":"https://dblp.org/rec/conf/mm/ZhangLTC0C025","documentUrl":"https://doi.org/10.1145/3746027.3755837","pages":"5267-5276"},{"key":"conf/naacl/MuHZFXQSLHSZC25","title":"Stealthy Jailbreak Attacks on Large Language Models via Benign Data Mirroring.","type":"Inproceedings","venue":"NAACL (Long Papers)","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.18653/V1/2025.NAACL-LONG.88","sourceUrl":"https://dblp.org/rec/conf/naacl/MuHZFXQSLHSZC25","documentUrl":"https://doi.org/10.18653/V1/2025.NAACL-LONG.88","pages":"1784-1799"},{"key":"conf/naacl/ShiLLZLWLCW25","title":"KwaiChat: A Large-Scale Video-Driven Multilingual Mixed-Type Dialogue Corpus.","type":"Inproceedings","venue":"NAACL (Findings)","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.18653/V1/2025.FINDINGS-NAACL.121","sourceUrl":"https://dblp.org/rec/conf/naacl/ShiLLZLWLCW25","documentUrl":"https://doi.org/10.18653/V1/2025.FINDINGS-NAACL.121","pages":"2279-2294"},{"key":"conf/nips/ChengCXWWFWWCCQ25","title":"Visual Thoughts: A Unified Perspective of Understanding Multimodal Chain-of-Thought.","type":"Inproceedings","venue":"NeurIPS","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":null,"sourceUrl":"https://dblp.org/rec/conf/nips/ChengCXWWFWWCCQ25","documentUrl":"http://papers.nips.cc/paper_files/paper/2025/hash/8a57d66b8e0cc468dbb6574114f60f0c-Abstract-Conference.html","pages":null},{"key":"conf/nips/ZhaoGDWZHSZCQCL25","title":"When Less Language is More: Language-Reasoning Disentanglement Makes LLMs Better Multilingual Reasoners.","type":"Inproceedings","venue":"NeurIPS","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":null,"sourceUrl":"https://dblp.org/rec/conf/nips/ZhaoGDWZHSZCQCL25","documentUrl":"http://papers.nips.cc/paper_files/paper/2025/hash/372bd0e47f2d5bceca7e300e1446849c-Abstract-Conference.html","pages":null},{"key":"journals/chinaf/LiuWLNWC25","title":"Towards few-shot mixed-type dialogue generation.","type":"Article","venue":"Sci. China Inf. Sci.","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.1007/S11432-023-4069-X","sourceUrl":"https://dblp.org/rec/journals/chinaf/LiuWLNWC25","documentUrl":"https://doi.org/10.1007/S11432-023-4069-X","pages":null},{"key":"journals/chinaf/YangZWWZZMCWWQ25","title":"Large language models meet text-centric multimodal sentiment analysis: a survey.","type":"Article","venue":"Sci. China Inf. Sci.","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.1007/S11432-024-4593-8","sourceUrl":"https://dblp.org/rec/journals/chinaf/YangZWWZZMCWWQ25","documentUrl":"https://doi.org/10.1007/S11432-024-4593-8","pages":null},{"key":"journals/chinaf/YangZZWYCWWQ25","title":"From unimodal to multimodal: a framework for generating high-quality multimodal emotional chit-chat dialogue.","type":"Article","venue":"Sci. China Inf. Sci.","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.1007/S11432-024-4591-X","sourceUrl":"https://dblp.org/rec/journals/chinaf/YangZZWYCWWQ25","documentUrl":"https://doi.org/10.1007/S11432-024-4591-X","pages":null},{"key":"journals/fcsc/QinHCLCX25","title":"MPFToD: a modularized pre-training framework for consistency identification in task-oriented dialogue.","type":"Article","venue":"Frontiers Comput. Sci.","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.1007/S11704-024-3778-9","sourceUrl":"https://dblp.org/rec/journals/fcsc/QinHCLCX25","documentUrl":"https://doi.org/10.1007/S11704-024-3778-9","pages":"1910351"},{"key":"journals/fcsc/ZhangWDZC25","title":"A survey of table reasoning with large language models.","type":"Article","venue":"Frontiers Comput. Sci.","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.1007/S11704-024-40330-Z","sourceUrl":"https://dblp.org/rec/journals/fcsc/ZhangWDZC25","documentUrl":"https://doi.org/10.1007/S11704-024-40330-Z","pages":"199348"},{"key":"journals/jair/LinMZWWWGZCBHL25","title":"Against The Achilles' Heel: A Survey on Red Teaming for Generative Models.","type":"Article","venue":"J. Artif. Intell. Res.","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.1613/JAIR.1.17654","sourceUrl":"https://dblp.org/rec/journals/jair/LinMZWWWGZCBHL25","documentUrl":"https://doi.org/10.1613/JAIR.1.17654","pages":"687-775"},{"key":"journals/mlc/LiDHFMWZSC25","title":"MixPro: Simple yet Effective Data Augmentation for Prompt-based Learning.","type":"Article","venue":"Int. J. Mach. Learn. Cybern.","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.1007/S13042-025-02548-6","sourceUrl":"https://dblp.org/rec/journals/mlc/LiDHFMWZSC25","documentUrl":"https://doi.org/10.1007/S13042-025-02548-6","pages":"4879-4898"},{"key":"journals/patterns/QinCZCLLLCY25","title":"A survey of multilingual large language models.","type":"Article","venue":"Patterns","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.1016/J.PATTER.2024.101118","sourceUrl":"https://dblp.org/rec/journals/patterns/QinCZCLLLCY25","documentUrl":"https://doi.org/10.1016/J.PATTER.2024.101118","pages":"101118"},{"key":"journals/tacl/XuJZC25","title":"CRVQ: Channel-Relaxed Vector Quantization for Extreme Compression of LLMs.","type":"Article","venue":"Trans. Assoc. Comput. Linguistics","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.1162/TACL.A.45","sourceUrl":"https://dblp.org/rec/journals/tacl/XuJZC25","documentUrl":"https://doi.org/10.1162/TACL.A.45","pages":"1488-1506"},{"key":"journals/tcsv/XuQCK25","title":"Manager: Aggregating Insights From Unimodal Experts in Two-Tower VLMs and MLLMs.","type":"Article","venue":"IEEE Trans. Circuits Syst. Video Technol.","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.1109/TCSVT.2025.3578266","sourceUrl":"https://dblp.org/rec/journals/tcsv/XuQCK25","documentUrl":"https://doi.org/10.1109/TCSVT.2025.3578266","pages":"12278-12291"},{"key":"journals/tois/LiuPZLCR25","title":"Augmentation with Neighboring Information for Conversational Recommendation.","type":"Article","venue":"ACM Trans. Inf. Syst.","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.1145/3712588","sourceUrl":"https://dblp.org/rec/journals/tois/LiuPZLCR25","documentUrl":"https://doi.org/10.1145/3712588","pages":"62:1-62:49"}],"preprints":[{"key":"journals/corr/abs-2501-06598","title":"ChartCoder: Advancing Multimodal Large Language Model for Chart-to-Code Generation.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2501.06598","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2501-06598","documentUrl":"https://doi.org/10.48550/ARXIV.2501.06598","pages":null,"arxivId":"2501.06598","arxivUrl":"https://arxiv.org/abs/2501.06598"},{"key":"journals/corr/abs-2502-03325","title":"ECM: A Unified Electronic Circuit Model for Explaining the Emergence of In-Context Learning and Chain-of-Thought in Large Language Model.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2502.03325","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2502-03325","documentUrl":"https://doi.org/10.48550/ARXIV.2502.03325","pages":null,"arxivId":"2502.03325","arxivUrl":"https://arxiv.org/abs/2502.03325"},{"key":"journals/corr/abs-2502-12221","title":"ReF Decompile: Relabeling and Function Call Enhanced Decompile.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2502.12221","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2502-12221","documentUrl":"https://doi.org/10.48550/ARXIV.2502.12221","pages":null,"arxivId":"2502.12221","arxivUrl":"https://arxiv.org/abs/2502.12221"},{"key":"journals/corr/abs-2502-17253","title":"MULTITAT: Benchmarking Multilingual Table-and-Text Question Answering.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2502.17253","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2502-17253","documentUrl":"https://doi.org/10.48550/ARXIV.2502.17253","pages":null,"arxivId":"2502.17253","arxivUrl":"https://arxiv.org/abs/2502.17253"},{"key":"journals/corr/abs-2503-06899","title":"KwaiChat: A Large-Scale Video-Driven Multilingual Mixed-Type Dialogue Corpus.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2503.06899","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-06899","documentUrl":"https://doi.org/10.48550/ARXIV.2503.06899","pages":null,"arxivId":"2503.06899","arxivUrl":"https://arxiv.org/abs/2503.06899"},{"key":"journals/corr/abs-2503-09567","title":"Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Models.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2503.09567","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-09567","documentUrl":"https://doi.org/10.48550/ARXIV.2503.09567","pages":null,"arxivId":"2503.09567","arxivUrl":"https://arxiv.org/abs/2503.09567"},{"key":"journals/corr/abs-2503-17979","title":"Trade-offs in Large Reasoning Models: An Empirical Analysis of Deliberative and Adaptive Reasoning over Foundational Capabilities.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2503.17979","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-17979","documentUrl":"https://doi.org/10.48550/ARXIV.2503.17979","pages":null,"arxivId":"2503.17979","arxivUrl":"https://arxiv.org/abs/2503.17979"},{"key":"journals/corr/abs-2504-03612","title":"AIR: A Systematic Analysis of Annotations, Instructions, and Response Pairs in Preference Dataset.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2504.03612","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2504-03612","documentUrl":"https://doi.org/10.48550/ARXIV.2504.03612","pages":null,"arxivId":"2504.03612","arxivUrl":"https://arxiv.org/abs/2504.03612"},{"key":"journals/corr/abs-2504-09824","title":"Abacus-SQL: A Text-to-SQL System Empowering Cross-Domain and Open-Domain Database Retrieval.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2504.09824","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2504-09824","documentUrl":"https://doi.org/10.48550/ARXIV.2504.09824","pages":null,"arxivId":"2504.09824","arxivUrl":"https://arxiv.org/abs/2504.09824"},{"key":"journals/corr/abs-2505-11441","title":"Is Compression Really Linear with Code Intelligence?","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2505.11441","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-11441","documentUrl":"https://doi.org/10.48550/ARXIV.2505.11441","pages":null,"arxivId":"2505.11441","arxivUrl":"https://arxiv.org/abs/2505.11441"},{"key":"journals/corr/abs-2505-13307","title":"RBF++: Quantifying and Optimizing Reasoning Boundaries across Measurable and Unmeasurable Capabilities for Chain-of-Thought Reasoning.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2505.13307","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-13307","documentUrl":"https://doi.org/10.48550/ARXIV.2505.13307","pages":null,"arxivId":"2505.13307","arxivUrl":"https://arxiv.org/abs/2505.13307"},{"key":"journals/corr/abs-2505-14597","title":"Success is in the Details: Evaluate and Enhance Details Sensitivity of Code LLMs through Counterfactuals.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2505.14597","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-14597","documentUrl":"https://doi.org/10.48550/ARXIV.2505.14597","pages":null,"arxivId":"2505.14597","arxivUrl":"https://arxiv.org/abs/2505.14597"},{"key":"journals/corr/abs-2505-15110","title":"RoT: Enhancing Table Reasoning with Iterative Row-Wise Traversals.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2505.15110","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-15110","documentUrl":"https://doi.org/10.48550/ARXIV.2505.15110","pages":null,"arxivId":"2505.15110","arxivUrl":"https://arxiv.org/abs/2505.15110"},{"key":"journals/corr/abs-2505-15257","title":"When Less Language is More: Language-Reasoning Disentanglement Makes LLMs Better Multilingual Reasoners.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2505.15257","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-15257","documentUrl":"https://doi.org/10.48550/ARXIV.2505.15257","pages":null,"arxivId":"2505.15257","arxivUrl":"https://arxiv.org/abs/2505.15257"},{"key":"journals/corr/abs-2505-15510","title":"Visual Thoughts: A Unified Perspective of Understanding Multimodal Chain-of-Thought.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2505.15510","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-15510","documentUrl":"https://doi.org/10.48550/ARXIV.2505.15510","pages":null,"arxivId":"2505.15510","arxivUrl":"https://arxiv.org/abs/2505.15510"},{"key":"journals/corr/abs-2505-18629","title":"Think Before You Accept: Semantic Reflective Verification for Faster Speculative Decoding.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2505.18629","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-18629","documentUrl":"https://doi.org/10.48550/ARXIV.2505.18629","pages":null,"arxivId":"2505.18629","arxivUrl":"https://arxiv.org/abs/2505.18629"},{"key":"journals/corr/abs-2505-20334","title":"Lookahead Q-Cache: Achieving More Consistent KV Cache Eviction via Pseudo Query.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2505.20334","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-20334","documentUrl":"https://doi.org/10.48550/ARXIV.2505.20334","pages":null,"arxivId":"2505.20334","arxivUrl":"https://arxiv.org/abs/2505.20334"},{"key":"journals/corr/abs-2505-24388","title":"ClueAnchor: Clue-Anchored Knowledge Reasoning Exploration and Optimization for Retrieval-Augmented Generation.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2505.24388","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-24388","documentUrl":"https://doi.org/10.48550/ARXIV.2505.24388","pages":null,"arxivId":"2505.24388","arxivUrl":"https://arxiv.org/abs/2505.24388"},{"key":"journals/corr/abs-2506-04625","title":"Advancing Tool-Augmented Large Language Models via Meta-Verification and Reflection Learning.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2506.04625","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-04625","documentUrl":"https://doi.org/10.48550/ARXIV.2506.04625","pages":null,"arxivId":"2506.04625","arxivUrl":"https://arxiv.org/abs/2506.04625"},{"key":"journals/corr/abs-2506-11515","title":"Manager: Aggregating Insights from Unimodal Experts in Two-Tower VLMs and MLLMs.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2506.11515","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-11515","documentUrl":"https://doi.org/10.48550/ARXIV.2506.11515","pages":null,"arxivId":"2506.11515","arxivUrl":"https://arxiv.org/abs/2506.11515"},{"key":"journals/corr/abs-2506-15647","title":"Exploring and Exploiting the Inherent Efficiency within Large Reasoning Models for Self-Guided Efficiency Enhancement.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2506.15647","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-15647","documentUrl":"https://doi.org/10.48550/ARXIV.2506.15647","pages":null,"arxivId":"2506.15647","arxivUrl":"https://arxiv.org/abs/2506.15647"},{"key":"journals/corr/abs-2506-23133","title":"Format-Adapter: Improving Reasoning Capability of LLMs by Adapting Suitable Format.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2506.23133","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-23133","documentUrl":"https://doi.org/10.48550/ARXIV.2506.23133","pages":null,"arxivId":"2506.23133","arxivUrl":"https://arxiv.org/abs/2506.23133"},{"key":"journals/corr/abs-2506-23146","title":"Learning-to-Context Slope: Evaluating In-Context Learning Effectiveness Beyond Performance Illusions.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2506.23146","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-23146","documentUrl":"https://doi.org/10.48550/ARXIV.2506.23146","pages":null,"arxivId":"2506.23146","arxivUrl":"https://arxiv.org/abs/2506.23146"},{"key":"journals/corr/abs-2506-23149","title":"V-SYNTHESIS: Task-Agnostic Synthesis of Consistent and Diverse In-Context Demonstrations from Scratch via V-Entropy.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2506.23149","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-23149","documentUrl":"https://doi.org/10.48550/ARXIV.2506.23149","pages":null,"arxivId":"2506.23149","arxivUrl":"https://arxiv.org/abs/2506.23149"},{"key":"journals/corr/abs-2507-01903","title":"AI4Research: A Survey of Artificial Intelligence for Scientific Research.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2507.01903","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2507-01903","documentUrl":"https://doi.org/10.48550/ARXIV.2507.01903","pages":null,"arxivId":"2507.01903","arxivUrl":"https://arxiv.org/abs/2507.01903"},{"key":"journals/corr/abs-2507-05687","title":"AutoTriton: Automatic Triton Programming with Reinforcement Learning in LLMs.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2507.05687","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2507-05687","documentUrl":"https://doi.org/10.48550/ARXIV.2507.05687","pages":null,"arxivId":"2507.05687","arxivUrl":"https://arxiv.org/abs/2507.05687"},{"key":"journals/corr/abs-2507-09876","title":"ViTCoT: Video-Text Interleaved Chain-of-Thought for Boosting Video Understanding in Large Language Models.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2507.09876","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2507-09876","documentUrl":"https://doi.org/10.48550/ARXIV.2507.09876","pages":null,"arxivId":"2507.09876","arxivUrl":"https://arxiv.org/abs/2507.09876"},{"key":"journals/corr/abs-2507-23382","title":"MPCC: A Novel Benchmark for Multimodal Planning with Complex Constraints in Multimodal Large Language Models.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2507.23382","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2507-23382","documentUrl":"https://doi.org/10.48550/ARXIV.2507.23382","pages":null,"arxivId":"2507.23382","arxivUrl":"https://arxiv.org/abs/2507.23382"},{"key":"journals/corr/abs-2508-00385","title":"Multi-Layer Attention is the Amplifier of Demonstration Effectiveness.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2508.00385","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-00385","documentUrl":"https://doi.org/10.48550/ARXIV.2508.00385","pages":null,"arxivId":"2508.00385","arxivUrl":"https://arxiv.org/abs/2508.00385"},{"key":"journals/corr/abs-2508-02322","title":"CAMERA: Multi-Matrix Joint Compression for MoE Models via Micro-Expert Redundancy Analysis.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2508.02322","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-02322","documentUrl":"https://doi.org/10.48550/ARXIV.2508.02322","pages":null,"arxivId":"2508.02322","arxivUrl":"https://arxiv.org/abs/2508.02322"},{"key":"journals/corr/abs-2508-11582","title":"Aware First, Think Less: Dynamic Boundary Self-Awareness Drives Extreme Reasoning Efficiency in Large Language Models.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2508.11582","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-11582","documentUrl":"https://doi.org/10.48550/ARXIV.2508.11582","pages":null,"arxivId":"2508.11582","arxivUrl":"https://arxiv.org/abs/2508.11582"},{"key":"journals/corr/abs-2508-16134","title":"CommonKV: Compressing KV Cache with Cross-layer Parameter Sharing.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2508.16134","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-16134","documentUrl":"https://doi.org/10.48550/ARXIV.2508.16134","pages":null,"arxivId":"2508.16134","arxivUrl":"https://arxiv.org/abs/2508.16134"},{"key":"journals/corr/abs-2509-10798","title":"Judge Q: Trainable Queries for Optimized Information Retention in KV Cache Eviction.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2509.10798","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-10798","documentUrl":"https://doi.org/10.48550/ARXIV.2509.10798","pages":null,"arxivId":"2509.10798","arxivUrl":"https://arxiv.org/abs/2509.10798"},{"key":"journals/corr/abs-2509-21284","title":"Bounds of Chain-of-Thought Robustness: Reasoning Steps, Embed Norms, and Beyond.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2509.21284","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-21284","documentUrl":"https://doi.org/10.48550/ARXIV.2509.21284","pages":null,"arxivId":"2509.21284","arxivUrl":"https://arxiv.org/abs/2509.21284"},{"key":"journals/corr/abs-2509-24745","title":"ProxyAttn: Guided Sparse Attention via Representative Heads.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2509.24745","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-24745","documentUrl":"https://doi.org/10.48550/ARXIV.2509.24745","pages":null,"arxivId":"2509.24745","arxivUrl":"https://arxiv.org/abs/2509.24745"},{"key":"journals/corr/abs-2509-26038","title":"RE2: Improving Chinese Grammatical Error Correction via Retrieving Appropriate Examples with Explanation.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2509.26038","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-26038","documentUrl":"https://doi.org/10.48550/ARXIV.2509.26038","pages":null,"arxivId":"2509.26038","arxivUrl":"https://arxiv.org/abs/2509.26038"},{"key":"journals/corr/abs-2510-08702","title":"Scaling Laws for Code: A More Data-Hungry Regime.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2510.08702","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-08702","documentUrl":"https://doi.org/10.48550/ARXIV.2510.08702","pages":null,"arxivId":"2510.08702","arxivUrl":"https://arxiv.org/abs/2510.08702"},{"key":"journals/corr/abs-2510-08720","title":"How Many Code and Test Cases Are Enough? Evaluating Test Cases Generation from a Binary-Matrix Perspective.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2510.08720","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-08720","documentUrl":"https://doi.org/10.48550/ARXIV.2510.08720","pages":null,"arxivId":"2510.08720","arxivUrl":"https://arxiv.org/abs/2510.08720"},{"key":"journals/corr/abs-2510-09544","title":"Beyond Surface Reasoning: Unveiling the True Long Chain-of-Thought Capacity of Diffusion Large Language Models.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2510.09544","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-09544","documentUrl":"https://doi.org/10.48550/ARXIV.2510.09544","pages":null,"arxivId":"2510.09544","arxivUrl":"https://arxiv.org/abs/2510.09544"},{"key":"journals/corr/abs-2510-09558","title":"AutoPR: Let's Automate Your Academic Promotion!","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2510.09558","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-09558","documentUrl":"https://doi.org/10.48550/ARXIV.2510.09558","pages":null,"arxivId":"2510.09558","arxivUrl":"https://arxiv.org/abs/2510.09558"},{"key":"journals/corr/abs-2510-14616","title":"Beyond Correctness: Evaluating Subjective Writing Preferences Across Cultures.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2510.14616","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-14616","documentUrl":"https://doi.org/10.48550/ARXIV.2510.14616","pages":null,"arxivId":"2510.14616","arxivUrl":"https://arxiv.org/abs/2510.14616"},{"key":"journals/corr/abs-2510-14763","title":"COIG-Writer: A High-Quality Dataset for Chinese Creative Writing with Thought Processes.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2510.14763","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-14763","documentUrl":"https://doi.org/10.48550/ARXIV.2510.14763","pages":null,"arxivId":"2510.14763","arxivUrl":"https://arxiv.org/abs/2510.14763"},{"key":"journals/corr/abs-2510-15004","title":"Automated Snippet-Alignment Data Augmentation for Code Translation.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2510.15004","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-15004","documentUrl":"https://doi.org/10.48550/ARXIV.2510.15004","pages":null,"arxivId":"2510.15004","arxivUrl":"https://arxiv.org/abs/2510.15004"},{"key":"journals/corr/abs-2510-21623","title":"The Universal Landscape of Human Reasoning.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2510.21623","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-21623","documentUrl":"https://doi.org/10.48550/ARXIV.2510.21623","pages":null,"arxivId":"2510.21623","arxivUrl":"https://arxiv.org/abs/2510.21623"},{"key":"journals/corr/abs-2511-09345","title":"Seer Self-Consistency: Advance Budget Estimation for Adaptive Test-Time Scaling.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2511.09345","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2511-09345","documentUrl":"https://doi.org/10.48550/ARXIV.2511.09345","pages":null,"arxivId":"2511.09345","arxivUrl":"https://arxiv.org/abs/2511.09345"},{"key":"journals/corr/abs-2512-01661","title":"Learning the Boundary of Solvability: Aligning LLMs to Detect Unsolvable Problems.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2512.01661","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-01661","documentUrl":"https://doi.org/10.48550/ARXIV.2512.01661","pages":null,"arxivId":"2512.01661","arxivUrl":"https://arxiv.org/abs/2512.01661"},{"key":"journals/corr/abs-2512-01725","title":"Beware of Reasoning Overconfidence: Pitfalls in the Reasoning Process for Multi-solution Tasks.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2512.01725","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-01725","documentUrl":"https://doi.org/10.48550/ARXIV.2512.01725","pages":null,"arxivId":"2512.01725","arxivUrl":"https://arxiv.org/abs/2512.01725"},{"key":"journals/corr/abs-2512-20164","title":"AI Security Beyond Core Domains: Resume Screening as a Case Study of Adversarial Vulnerabilities in Specialized LLM Applications.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2512.20164","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-20164","documentUrl":"https://doi.org/10.48550/ARXIV.2512.20164","pages":null,"arxivId":"2512.20164","arxivUrl":"https://arxiv.org/abs/2512.20164"}],"excludedFormal":[],"labName":"Language Agent Group","labUrl":"https://hit-scir-la.github.io/","labEvidence":"本人主页现职及发表列表都明确标识 Language Agent Group，并直接链接；非对其历年团队名称的追溯。","labSourceUrl":"https://chewanxiang.com/en/","affiliationZh":"哈尔滨工业大学","sourceWarning":false,"excludedOther":[],"excludedHomonyms":[],"unassignedCandidates":[],"knownPreprintMinimum2025":null,"excludedMisattributed":[],"displayNotes":"身份已经机构或个人主页核对。2025 年正式记录 33 条（会议 22、期刊 11），所有作者位置均计入，不表示主导或贡献份额；预印本 48 条单列，不加总。","labDisplayNotes":"本人主页的现职信息与发表列表均标明 Language Agent Group，并直接链接；这里只用当前名称，不追溯历年团队名。"},{"index":30,"name":"Anpei Chen","nameZh":"陈安沛","role":"Assistant Professor","affiliation":"Westlake University","source":"DBLP official SPARQL","profileUrl":"https://dblp.org/pid/210/2592","identifier":"210/2592","identityEvidence":[{"url":"https://dblp.org/pid/210/2592","evidence":"DBLP 唯一同名作者档案；通过作者/机构主页与发表题名交叉核对。"},{"url":"https://apchenstu.github.io/","evidence":"作者/机构页面与该 DBLP 档案交叉匹配的题名示例：Sparse Photometric 3D Face Reconstruction Guided by Morphable Models.；Feat2GS: Probing Visual Foundation Models with Gaussian Splatting.","matchedPaperKeys":["conf/cvpr/CaoCCCLY18","conf/cvpr/ChenCCPX25"]}],"count2025":10,"conference2025":10,"journal2025":0,"preprint2025":9,"status":"verified","notes":"身份已通过机构/个人主页或 DBLP 机构信息核对；篇数为数据库记录统计，不表示每篇均由本人主导。","retrievedAt":"2026-10-19","yearPolicy":"DBLP yearOfPublication = 2025","queryUrl":"https://sparql.dblp.org/sparql?query=PREFIX%20dblp%3A%20%3Chttps%3A//dblp.org/rdf/schema%23%3E%20PREFIX%20xsd%3A%20%3Chttp%3A//www.w3.org/2001/XMLSchema%23%3E%20SELECT%20%3Fpub%20%3Ftitle%20%3Ftype%20%3Fvenue%20WHERE%20%7B%20%3Fpub%20dblp%3AauthoredBy%20%3Chttps%3A//dblp.org/pid/210/2592%3E%3B%20dblp%3AyearOfPublication%20%222025%22%5E%5Exsd%3AgYear%3B%20dblp%3Atitle%20%3Ftitle%3B%20a%20%3Ftype%20.%20OPTIONAL%20%7B%20%3Fpub%20dblp%3ApublishedIn%20%3Fvenue%20%7D%20%7D&format=json","papers":[{"key":"conf/cvpr/ChenCCPX25","title":"Feat2GS: Probing Visual Foundation Models with Gaussian Splatting.","type":"Inproceedings","venue":"CVPR","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/CVPR52734.2025.00595","sourceUrl":"https://dblp.org/rec/conf/cvpr/ChenCCPX25","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Chen_Feat2GS_Probing_Visual_Foundation_Models_with_Gaussian_Splatting_CVPR_2025_paper.html","pages":"6348-6361"},{"key":"conf/cvpr/EspositoCRBPSRZ25","title":"Volumetric Surfaces: Representing Fuzzy Geometries with Layered Meshes.","type":"Inproceedings","venue":"CVPR","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/CVPR52734.2025.01991","sourceUrl":"https://dblp.org/rec/conf/cvpr/EspositoCRBPSRZ25","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Esposito_Volumetric_Surfaces_Representing_Fuzzy_Geometries_with_Layered_Meshes_CVPR_2025_paper.html","pages":"21370-21380"},{"key":"conf/cvpr/WuXH0C25","title":"GenFusion: Closing the Loop between Reconstruction and Generation via Videos.","type":"Inproceedings","venue":"CVPR","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/CVPR52734.2025.00570","sourceUrl":"https://dblp.org/rec/conf/cvpr/WuXH0C25","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Wu_GenFusion_Closing_the_Loop_between_Reconstruction_and_Generation_via_Videos_CVPR_2025_paper.html","pages":"6078-6088"},{"key":"conf/cvpr/ZhangCWSYL025","title":"Ref-GS: Directional Factorization for 2D Gaussian Splatting.","type":"Inproceedings","venue":"CVPR","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/CVPR52734.2025.02466","sourceUrl":"https://dblp.org/rec/conf/cvpr/ZhangCWSYL025","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Zhang_Ref-GS_Directional_Factorization_for_2D_Gaussian_Splatting_CVPR_2025_paper.html","pages":"26483-26492"},{"key":"conf/eccv/ChenXETG24","title":"LaRa: Efficient Large-Baseline Radiance Fields.","type":"Inproceedings","venue":"ECCV (11)","year":2025,"yearOfPublication":2025,"yearOfEvent":2024,"doi":"https://doi.org/10.1007/978-3-031-73247-8_20","sourceUrl":"https://dblp.org/rec/conf/eccv/ChenXETG24","documentUrl":"https://doi.org/10.1007/978-3-031-73247-8_20","pages":"338-355"},{"key":"conf/iccv/ChenCXGC25","title":"Easi3R: Estimating Disentangled Motion from DUSt3R Without Training.","type":"Inproceedings","venue":"ICCV","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/ICCV51701.2025.00856","sourceUrl":"https://dblp.org/rec/conf/iccv/ChenCXGC25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.00856","pages":"9158-9168"},{"key":"conf/iccv/HuangCHGZ25","title":"LoftUp: Learning a Coordinate-Based Feature Upsampler for Vision Foundation Models.","type":"Inproceedings","venue":"ICCV","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/ICCV51701.2025.00924","sourceUrl":"https://dblp.org/rec/conf/iccv/HuangCHGZ25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.00924","pages":"9913-9923"},{"key":"conf/iccv/ZhangCXDSX25","title":"Neural Shell Texture Splatting: More Details and Fewer Primitives.","type":"Inproceedings","venue":"ICCV","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/ICCV51701.2025.02340","sourceUrl":"https://dblp.org/rec/conf/iccv/ZhangCXDSX25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.02340","pages":"25229-25238"},{"key":"conf/siggraph/0001GC0D25","title":"GaVS: 3D-Grounded Video Stabilization via Temporally-Consistent Local Reconstruction and Rendering.","type":"Inproceedings","venue":"SIGGRAPH (Conference Paper Track)","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1145/3721238.3730757","sourceUrl":"https://dblp.org/rec/conf/siggraph/0001GC0D25","documentUrl":"https://doi.org/10.1145/3721238.3730757","pages":"5:1-5:12"},{"key":"conf/wacv/WeiXBCSX025","title":"NeuManifold: Neural Watertight Manifold Reconstruction with Efficient and High-Quality Rendering Support.","type":"Inproceedings","venue":"WACV","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/WACV61041.2025.00081","sourceUrl":"https://dblp.org/rec/conf/wacv/WeiXBCSX025","documentUrl":"https://doi.org/10.1109/WACV61041.2025.00081","pages":"731-741"}],"preprints":[{"key":"journals/corr/abs-2503-21219","title":"GenFusion: Closing the Loop between Reconstruction and Generation via Videos.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2503.21219","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-21219","documentUrl":"https://doi.org/10.48550/ARXIV.2503.21219","pages":null,"arxivId":"2503.21219","arxivUrl":"https://arxiv.org/abs/2503.21219"},{"key":"journals/corr/abs-2503-24391","title":"Easi3R: Estimating Disentangled Motion from DUSt3R Without Training.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2503.24391","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-24391","documentUrl":"https://doi.org/10.48550/ARXIV.2503.24391","pages":null,"arxivId":"2503.24391","arxivUrl":"https://arxiv.org/abs/2503.24391"},{"key":"journals/corr/abs-2504-14032","title":"LoftUp: Learning a Coordinate-Based Feature Upsampler for Vision Foundation Models.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2504.14032","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2504-14032","documentUrl":"https://doi.org/10.48550/ARXIV.2504.14032","pages":null,"arxivId":"2504.14032","arxivUrl":"https://arxiv.org/abs/2504.14032"},{"key":"journals/corr/abs-2506-23957","title":"GaVS: 3D-Grounded Video Stabilization via Temporally-Consistent Local Reconstruction and Rendering.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2506.23957","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-23957","documentUrl":"https://doi.org/10.48550/ARXIV.2506.23957","pages":null,"arxivId":"2506.23957","arxivUrl":"https://arxiv.org/abs/2506.23957"},{"key":"journals/corr/abs-2507-14501","title":"Advances in Feed-Forward 3D Reconstruction and View Synthesis: A Survey.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2507.14501","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2507-14501","documentUrl":"https://doi.org/10.48550/ARXIV.2507.14501","pages":null,"arxivId":"2507.14501","arxivUrl":"https://arxiv.org/abs/2507.14501"},{"key":"journals/corr/abs-2507-20200","title":"Neural Shell Texture Splatting: More Details and Fewer Primitives.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2507.20200","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2507-20200","documentUrl":"https://doi.org/10.48550/ARXIV.2507.20200","pages":null,"arxivId":"2507.20200","arxivUrl":"https://arxiv.org/abs/2507.20200"},{"key":"journals/corr/abs-2509-26645","title":"TTT3R: 3D Reconstruction as Test-Time Training.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2509.26645","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-26645","documentUrl":"https://doi.org/10.48550/ARXIV.2509.26645","pages":null,"arxivId":"2509.26645","arxivUrl":"https://arxiv.org/abs/2509.26645"},{"key":"journals/corr/abs-2510-06219","title":"Human3R: Everyone Everywhere All at Once.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2510.06219","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-06219","documentUrl":"https://doi.org/10.48550/ARXIV.2510.06219","pages":null,"arxivId":"2510.06219","arxivUrl":"https://arxiv.org/abs/2510.06219"},{"key":"journals/corr/abs-2511-06810","title":"ConeGS: Error-Guided Densification Using Pixel Cones for Improved Reconstruction with Fewer Primitives.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2511.06810","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2511-06810","documentUrl":"https://doi.org/10.48550/ARXIV.2511.06810","pages":null,"arxivId":"2511.06810","arxivUrl":"https://arxiv.org/abs/2511.06810"}],"excludedFormal":[],"labName":"Inception3D Lab","labUrl":"http://www.inception3d.fun/","labEvidence":"本人主页明确写 Lead of Inception3D Lab 并直接链接。","labSourceUrl":"https://apchenstu.github.io/","affiliationZh":"西湖大学","sourceWarning":false,"excludedOther":[],"excludedHomonyms":[],"unassignedCandidates":[],"knownPreprintMinimum2025":null,"excludedMisattributed":[],"displayNotes":"身份已经机构或个人主页核对。2025 年正式记录 10 条，均为会议论文，所有作者位置均计入；预印本 9 条单列，不加总。","labDisplayNotes":"个人主页写明其为 Inception3D Lab 负责人，并直接链接，据此归组。"},{"index":31,"name":"Qifeng Chen","nameZh":"陈启峰","role":"Associate Professor","affiliation":"The Hong Kong University of Science and Technology","source":"DBLP official SPARQL","profileUrl":"https://dblp.org/pid/117/4819-1","identifier":"117/4819-1","identityEvidence":[{"url":"https://dblp.org/pid/117/4819-1","evidence":"DBLP 档案名 Qifeng Chen 0001；机构/履历：Hong Kong University of Science and Technology, Hong Kong；Stanford University, Department of Computer Science, CA, USA"}],"count2025":44,"conference2025":41,"journal2025":3,"preprint2025":39,"status":"verified","notes":"身份已通过机构/个人主页或 DBLP 机构信息核对；篇数为数据库记录统计，不表示每篇均由本人主导。","retrievedAt":"2026-10-19","yearPolicy":"DBLP yearOfPublication = 2025","queryUrl":"https://sparql.dblp.org/sparql?query=PREFIX%20dblp%3A%20%3Chttps%3A//dblp.org/rdf/schema%23%3E%20PREFIX%20xsd%3A%20%3Chttp%3A//www.w3.org/2001/XMLSchema%23%3E%20SELECT%20%3Fpub%20%3Ftitle%20%3Ftype%20%3Fvenue%20WHERE%20%7B%20%3Fpub%20dblp%3AauthoredBy%20%3Chttps%3A//dblp.org/pid/117/4819-1%3E%3B%20dblp%3AyearOfPublication%20%222025%22%5E%5Exsd%3AgYear%3B%20dblp%3Atitle%20%3Ftitle%3B%20a%20%3Ftype%20.%20OPTIONAL%20%7B%20%3Fpub%20dblp%3ApublishedIn%20%3Fvenue%20%7D%20%7D&format=json","papers":[{"key":"conf/3dim/ChengWSZXOCS25","title":"Learning Naturally Aggregated Appearance for Efficient 3D Editing.","type":"Inproceedings","venue":"3DV","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/3DV66043.2025.00075","sourceUrl":"https://dblp.org/rec/conf/3dim/ChengWSZXOCS25","documentUrl":"https://doi.org/10.1109/3DV66043.2025.00075","pages":"758-768"},{"key":"conf/aaai/ChenMWYZTWMCL25","title":"Infinite-Canvas: Higher-Resolution Video Outpainting with Extensive Content Generation.","type":"Inproceedings","venue":"AAAI","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1609/AAAI.V39I2.32213","sourceUrl":"https://dblp.org/rec/conf/aaai/ChenMWYZTWMCL25","documentUrl":"https://doi.org/10.1609/AAAI.V39I2.32213","pages":"2150-2158"},{"key":"conf/aaai/FengMWQCC025","title":"DiT4Edit: Diffusion Transformer for Image Editing.","type":"Inproceedings","venue":"AAAI","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1609/AAAI.V39I3.32304","sourceUrl":"https://dblp.org/rec/conf/aaai/FengMWQCC025","documentUrl":"https://doi.org/10.1609/AAAI.V39I3.32304","pages":"2969-2977"},{"key":"conf/aaai/MaHWWSQYC0SLC25","title":"Follow-Your-Click: Open-domain Regional Image Animation via Motion Prompts.","type":"Inproceedings","venue":"AAAI","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1609/AAAI.V39I6.32643","sourceUrl":"https://dblp.org/rec/conf/aaai/MaHWWSQYC0SLC25","documentUrl":"https://doi.org/10.1609/AAAI.V39I6.32643","pages":"6018-6026"},{"key":"conf/cvm/ChenHHWZLX25","title":"HR Human: Modeling Human Avatars with Triangular Mesh and High-Resolution Textures from Videos.","type":"Inproceedings","venue":"CVM (2)","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1007/978-981-96-5812-1_9","sourceUrl":"https://dblp.org/rec/conf/cvm/ChenHHWZLX25","documentUrl":"https://doi.org/10.1007/978-981-96-5812-1_9","pages":"147-171"},{"key":"conf/cvpr/0001YZXSZCS25","title":"Exploring Sparse MoE in GANs for Text-conditioned Image Synthesis.","type":"Inproceedings","venue":"CVPR","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/CVPR52734.2025.01716","sourceUrl":"https://dblp.org/rec/conf/cvpr/0001YZXSZCS25","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Zhu_Exploring_Sparse_MoE_in_GANs_for_Text-conditioned_Image_Synthesis_CVPR_2025_paper.html","pages":"18411-18423"},{"key":"conf/cvpr/Liu0WMCFSSC25","title":"AvatarArtist: Open-Domain 4D Avatarization.","type":"Inproceedings","venue":"CVPR","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/CVPR52734.2025.01005","sourceUrl":"https://dblp.org/rec/conf/cvpr/Liu0WMCFSSC25","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Liu_AvatarArtist_Open-Domain_4D_Avatarization_CVPR_2025_paper.html","pages":"10758-10769"},{"key":"conf/cvpr/LiuCC0OZLSCL25","title":"MangaNinja: Line Art Colorization with Precise Reference Following.","type":"Inproceedings","venue":"CVPR","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/CVPR52734.2025.00532","sourceUrl":"https://dblp.org/rec/conf/cvpr/LiuCC0OZLSCL25","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Liu_MangaNinja_Line_Art_Colorization_with_Precise_Reference_Following_CVPR_2025_paper.html","pages":"5666-5677"},{"key":"conf/cvpr/LiuWZWHPC25","title":"VideoDPO: Omni-Preference Alignment for Video Diffusion Generation.","type":"Inproceedings","venue":"CVPR","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/CVPR52734.2025.00750","sourceUrl":"https://dblp.org/rec/conf/cvpr/LiuWZWHPC25","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Liu_VideoDPO_Omni-Preference_Alignment_for_Video_Diffusion_Generation_CVPR_2025_paper.html","pages":"8009-8019"},{"key":"conf/cvpr/LiuYOWCWLCS25","title":"MagicQuill: An Intelligent Interactive Image Editing System.","type":"Inproceedings","venue":"CVPR","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/CVPR52734.2025.01220","sourceUrl":"https://dblp.org/rec/conf/cvpr/LiuYOWCWLCS25","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Liu_MagicQuill_An_Intelligent_Interactive_Image_Editing_System_CVPR_2025_paper.html","pages":"13072-13082"},{"key":"conf/cvpr/Tian0YPL0CXG25","title":"VidMuse: A Simple Video-to-Music Generation Framework with Long-Short-Term Modeling.","type":"Inproceedings","venue":"CVPR","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/CVPR52734.2025.01750","sourceUrl":"https://dblp.org/rec/conf/cvpr/Tian0YPL0CXG25","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Tian_VidMuse_A_Simple_Video-to-Music_Generation_Framework_with_Long-Short-Term_Modeling_CVPR_2025_paper.html","pages":"18782-18793"},{"key":"conf/cvpr/WangOWWCCSW25","title":"LeviTor: 3D Trajectory Oriented Image-to-Video Synthesis.","type":"Inproceedings","venue":"CVPR","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/CVPR52734.2025.01165","sourceUrl":"https://dblp.org/rec/conf/cvpr/WangOWWCCSW25","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Wang_LeviTor_3D_Trajectory_Oriented_Image-to-Video_Synthesis_CVPR_2025_paper.html","pages":"12490-12500"},{"key":"conf/cvpr/WangZ0TZLLY0C0Z25","title":"SkillMimic: Learning Basketball Interaction Skills from Demonstrations.","type":"Inproceedings","venue":"CVPR","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/CVPR52734.2025.01634","sourceUrl":"https://dblp.org/rec/conf/cvpr/WangZ0TZLLY0C0Z25","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Wang_SkillMimic_Learning_Basketball_Interaction_Skills_from_Demonstrations_CVPR_2025_paper.html","pages":"17540-17549"},{"key":"conf/eccv/BaiSXOWYWWSC24","title":"Real-Time 3D-Aware Portrait Editing from a Single Image.","type":"Inproceedings","venue":"ECCV (51)","year":2025,"yearOfPublication":2025,"yearOfEvent":2024,"doi":"https://doi.org/10.1007/978-3-031-72983-6_20","sourceUrl":"https://dblp.org/rec/conf/eccv/BaiSXOWYWWSC24","documentUrl":"https://doi.org/10.1007/978-3-031-72983-6_20","pages":"344-362"},{"key":"conf/eccv/ChenHLCCW24","title":"TextDiffuser-2: Unleashing the Power of Language Models for Text Rendering.","type":"Inproceedings","venue":"ECCV (5)","year":2025,"yearOfPublication":2025,"yearOfEvent":2024,"doi":"https://doi.org/10.1007/978-3-031-72652-1_23","sourceUrl":"https://dblp.org/rec/conf/eccv/ChenHLCCW24","documentUrl":"https://doi.org/10.1007/978-3-031-72652-1_23","pages":"386-402"},{"key":"conf/eccv/ChenXYQZYC24","title":"Learning High-Resolution Vector Representation from Multi-camera Images for 3D Object Detection.","type":"Inproceedings","venue":"ECCV (35)","year":2025,"yearOfPublication":2025,"yearOfEvent":2024,"doi":"https://doi.org/10.1007/978-3-031-72761-0_22","sourceUrl":"https://dblp.org/rec/conf/eccv/ChenXYQZYC24","documentUrl":"https://doi.org/10.1007/978-3-031-72761-0_22","pages":"385-403"},{"key":"conf/eccv/ChenYXCC24","title":"PPAD: Iterative Interactions of Prediction and Planning for End-to-End Autonomous Driving.","type":"Inproceedings","venue":"ECCV (35)","year":2025,"yearOfPublication":2025,"yearOfEvent":2024,"doi":"https://doi.org/10.1007/978-3-031-72761-0_14","sourceUrl":"https://dblp.org/rec/conf/eccv/ChenYXCC24","documentUrl":"https://doi.org/10.1007/978-3-031-72761-0_14","pages":"239-256"},{"key":"conf/eccv/GuoHCXCWHZWCSW24","title":"Make a Cheap Scaling: A Self-Cascade Diffusion Model for Higher-Resolution Adaptation.","type":"Inproceedings","venue":"ECCV (36)","year":2025,"yearOfPublication":2025,"yearOfEvent":2024,"doi":"https://doi.org/10.1007/978-3-031-72764-1_3","sourceUrl":"https://dblp.org/rec/conf/eccv/GuoHCXCWHZWCSW24","documentUrl":"https://doi.org/10.1007/978-3-031-72764-1_3","pages":"39-55"},{"key":"conf/eccv/HeXCCGXZWWSC24","title":"Storytelling Video Generation with Retrieval Augmentation and Character Consistency.","type":"Inproceedings","venue":"ECCV Workshops (5)","year":2025,"yearOfPublication":2025,"yearOfEvent":2024,"doi":"https://doi.org/10.1007/978-3-031-92808-6_14","sourceUrl":"https://dblp.org/rec/conf/eccv/HeXCCGXZWWSC24","documentUrl":"https://doi.org/10.1007/978-3-031-92808-6_14","pages":"218-234"},{"key":"conf/eccv/LiuKGCTP24","title":"Latent Guard: A Safety Framework for Text-to-Image Generation.","type":"Inproceedings","venue":"ECCV (26)","year":2025,"yearOfPublication":2025,"yearOfEvent":2024,"doi":"https://doi.org/10.1007/978-3-031-73347-5_6","sourceUrl":"https://dblp.org/rec/conf/eccv/LiuKGCTP24","documentUrl":"https://doi.org/10.1007/978-3-031-73347-5_6","pages":"93-109"},{"key":"conf/eccv/LiuLGCLZLCQDW24","title":"ControlLLM: Augment Language Models with Tools by Searching on Graphs.","type":"Inproceedings","venue":"ECCV (12)","year":2025,"yearOfPublication":2025,"yearOfEvent":2024,"doi":"https://doi.org/10.1007/978-3-031-73254-6_6","sourceUrl":"https://dblp.org/rec/conf/eccv/LiuLGCLZLCQDW24","documentUrl":"https://doi.org/10.1007/978-3-031-73254-6_6","pages":"89-105"},{"key":"conf/eccv/QiTYDMCT24","title":"SPIRE: Semantic Prompt-Driven Image Restoration.","type":"Inproceedings","venue":"ECCV (40)","year":2025,"yearOfPublication":2025,"yearOfEvent":2024,"doi":"https://doi.org/10.1007/978-3-031-73661-2_25","sourceUrl":"https://dblp.org/rec/conf/eccv/QiTYDMCT24","documentUrl":"https://doi.org/10.1007/978-3-031-73661-2_25","pages":"446-464"},{"key":"conf/iccv/BaiOXWYCSC25","title":"Edicho: Consistent Image Editing in the Wild.","type":"Inproceedings","venue":"ICCV","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/ICCV51701.2025.01417","sourceUrl":"https://dblp.org/rec/conf/iccv/BaiOXWYCSC25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.01417","pages":"15277-15287"},{"key":"conf/iccv/ChenWZZLYC25","title":"Rethinking Layered Graphic Design Generation with a Top-Down Approach.","type":"Inproceedings","venue":"ICCV","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/ICCV51701.2025.01566","sourceUrl":"https://dblp.org/rec/conf/iccv/ChenWZZLYC25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.01566","pages":"16861-16870"},{"key":"conf/iccv/ChenZHCDLCW25","title":"Model as a Game: On Numerical and Spatial Consistency for Generative Games.","type":"Inproceedings","venue":"ICCVW","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/ICCVW69036.2025.00205","sourceUrl":"https://dblp.org/rec/conf/iccv/ChenZHCDLCW25","documentUrl":"https://doi.org/10.1109/ICCVW69036.2025.00205","pages":"1958-1967"},{"key":"conf/iccv/DuLCCMY25","title":"RGE-GS: Reward-Guided Expansive Driving Scene Reconstruction via Diffusion Priors.","type":"Inproceedings","venue":"ICCV","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/ICCV51701.2025.02389","sourceUrl":"https://dblp.org/rec/conf/iccv/DuLCCMY25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.02389","pages":"25756-25764"},{"key":"conf/iccv/LiuCGZPCTKP25","title":"AlignGuard: Scalable Safety Alignment for Text-to-Image Generation.","type":"Inproceedings","venue":"ICCV","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/ICCV51701.2025.01581","sourceUrl":"https://dblp.org/rec/conf/iccv/LiuCGZPCTKP25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.01581","pages":"17024-17034"},{"key":"conf/iccv/XingFHCXCC25","title":"VideoVAE+: Large Motion Video Autoencoding with Cross-Modal Video VAE.","type":"Inproceedings","venue":"ICCV","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/ICCV51701.2025.01668","sourceUrl":"https://dblp.org/rec/conf/iccv/XingFHCXCC25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.01668","pages":"17951-17960"},{"key":"conf/iccv/YanMZCCZ25","title":"EEdit ⚡: Rethinking the Spatial and Temporal Redundancy for Efficient Image Editing.","type":"Inproceedings","venue":"ICCV","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/ICCV51701.2025.01623","sourceUrl":"https://dblp.org/rec/conf/iccv/YanMZCCZ25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.01623","pages":"17474-17484"},{"key":"conf/iccv/ZhouGCYCCQ25","title":"Hints of Prompt: Enhancing Visual Representation for Multimodal LLMs in Autonomous Driving.","type":"Inproceedings","venue":"ICCV","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/ICCV51701.2025.00582","sourceUrl":"https://dblp.org/rec/conf/iccv/ZhouGCYCCQ25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.00582","pages":"6165-6175"},{"key":"conf/iclr/00070MTFCCL25","title":"InstantSwap: Fast Customized Concept Swapping across Sharp Shape Differences.","type":"Inproceedings","venue":"ICLR","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":null,"sourceUrl":"https://dblp.org/rec/conf/iclr/00070MTFCCL25","documentUrl":"https://openreview.net/forum?id=UFrHWzZENz","pages":null},{"key":"conf/icra/WenRXC25","title":"LDM-ISP: Enhancing Neural ISP for Low Light with Latent Diffusion Models.","type":"Inproceedings","venue":"ICRA","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/ICRA55743.2025.11127546","sourceUrl":"https://dblp.org/rec/conf/icra/WenRXC25","documentUrl":"https://doi.org/10.1109/ICRA55743.2025.11127546","pages":"13297-13303"},{"key":"conf/icra/ZhaoJLZYWC25","title":"Master Rules from Chaos: Learning to Reason, Plan, and Interact from Chaos for Tangram Assembly.","type":"Inproceedings","venue":"ICRA","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/ICRA55743.2025.11127610","sourceUrl":"https://dblp.org/rec/conf/icra/ZhaoJLZYWC25","documentUrl":"https://doi.org/10.1109/ICRA55743.2025.11127610","pages":"11503-11509"},{"key":"conf/iros/ZengDCLSGLXXCZCXZYL25","title":"Industrial-Grade Sensor Simulation via Gaussian Splatting: A Modular Framework for Scalable Editing and Full-Stack Validation.","type":"Inproceedings","venue":"IROS","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/IROS60139.2025.11246621","sourceUrl":"https://dblp.org/rec/conf/iros/ZengDCLSGLXXCZCXZYL25","documentUrl":"https://doi.org/10.1109/IROS60139.2025.11246621","pages":"6264-6271"},{"key":"conf/mm/0001HX0025","title":"SpA2V: Harnessing Spatial Auditory Cues for Audio-driven Spatially-aware Video Generation.","type":"Inproceedings","venue":"ACM Multimedia","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1145/3746027.3755705","sourceUrl":"https://dblp.org/rec/conf/mm/0001HX0025","documentUrl":"https://doi.org/10.1145/3746027.3755705","pages":"10476-10485"},{"key":"conf/nips/ChenHCYL25","title":"Hierarchical Fine-grained Preference Optimization for Physically Plausible Video Generation.","type":"Inproceedings","venue":"NeurIPS","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":null,"sourceUrl":"https://dblp.org/rec/conf/nips/ChenHCYL25","documentUrl":"http://papers.nips.cc/paper_files/paper/2025/hash/c25fe7eb6d6cc6931b93236f5599aa97-Abstract-Conference.html","pages":null},{"key":"conf/siggraph/0003WZT00025","title":"SkillMimic-V2: Learning Robust and Generalizable Interaction Skills from Sparse and Noisy Demonstrations.","type":"Inproceedings","venue":"SIGGRAPH (Conference Paper Track)","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1145/3721238.3730640","sourceUrl":"https://dblp.org/rec/conf/siggraph/0003WZT00025","documentUrl":"https://doi.org/10.1145/3721238.3730640","pages":"115:1-115:11"},{"key":"conf/siggrapha/XingQZ025","title":"Invertible Video Signal Processing.","type":"Inproceedings","venue":"SIGGRAPH Asia Posters","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1145/3757374.3771527","sourceUrl":"https://dblp.org/rec/conf/siggrapha/XingQZ025","documentUrl":"https://doi.org/10.1145/3757374.3771527","pages":"53:1-53:3"},{"key":"conf/vr/WangMCCLMC025","title":"MagicScroll: Enhancing Immersive Storytelling with Controllable Scroll Image Generation.","type":"Inproceedings","venue":"VR","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/VR59515.2025.00067","sourceUrl":"https://dblp.org/rec/conf/vr/WangMCCLMC025","documentUrl":"https://doi.org/10.1109/VR59515.2025.00067","pages":"431-441"},{"key":"conf/wacv/MaCLXHQCC25","title":"MagicStick: Controllable Video Editing via Control Handle Transformations.","type":"Inproceedings","venue":"WACV","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/WACV61041.2025.00909","sourceUrl":"https://dblp.org/rec/conf/wacv/MaCLXHQCC25","documentUrl":"https://doi.org/10.1109/WACV61041.2025.00909","pages":"9385-9395"},{"key":"conf/wacv/RaoZLC25","title":"Robust Portrait Image Matting and Depth-of-field Synthesis via Multiplane Images.","type":"Inproceedings","venue":"WACV","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/WACV61041.2025.00930","sourceUrl":"https://dblp.org/rec/conf/wacv/RaoZLC25","documentUrl":"https://doi.org/10.1109/WACV61041.2025.00930","pages":"9607-9617"},{"key":"journals/csur/WangCW25","title":"Diffusion-Based Visual Art Creation: A Survey and New Perspectives.","type":"Article","venue":"ACM Comput. Surv.","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.1145/3728459","sourceUrl":"https://dblp.org/rec/journals/csur/WangCW25","documentUrl":"https://doi.org/10.1145/3728459","pages":"268:1-268:37"},{"key":"journals/ijcv/WenRLSYLLC25","title":"Enhancing HDR Imaging with Joint Denoising and Deblurring.","type":"Article","venue":"Int. J. Comput. Vis.","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.1007/S11263-025-02537-W","sourceUrl":"https://dblp.org/rec/journals/ijcv/WenRLSYLLC25","documentUrl":"https://doi.org/10.1007/S11263-025-02537-W","pages":"7536-7552"},{"key":"journals/trob/ZhaoJLYCY25","title":"Learning Thin Deformable Object Manipulation With a Multisensory Integrated Soft Hand.","type":"Article","venue":"IEEE Trans. Robotics","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.1109/TRO.2025.3588448","sourceUrl":"https://dblp.org/rec/journals/trob/ZhaoJLYCY25","documentUrl":"https://doi.org/10.1109/TRO.2025.3588448","pages":"4606-4621"}],"preprints":[{"key":"journals/corr/abs-2501-08332","title":"MangaNinja: Line Art Colorization with Precise Reference Following.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2501.08332","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2501-08332","documentUrl":"https://doi.org/10.48550/ARXIV.2501.08332","pages":null,"arxivId":"2501.08332","arxivUrl":"https://arxiv.org/abs/2501.08332"},{"key":"journals/corr/abs-2503-03464","title":"Generative Artificial Intelligence in Robotic Manipulation: A Survey.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2503.03464","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-03464","documentUrl":"https://doi.org/10.48550/ARXIV.2503.03464","pages":null,"arxivId":"2503.03464","arxivUrl":"https://arxiv.org/abs/2503.03464"},{"key":"journals/corr/abs-2503-10270","title":"EEdit: Rethinking the Spatial and Temporal Redundancy for Efficient Image Editing.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2503.10270","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-10270","documentUrl":"https://doi.org/10.48550/ARXIV.2503.10270","pages":null,"arxivId":"2503.10270","arxivUrl":"https://arxiv.org/abs/2503.10270"},{"key":"journals/corr/abs-2503-10522","title":"AudioX: Diffusion Transformer for Anything-to-Audio Generation.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2503.10522","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-10522","documentUrl":"https://doi.org/10.48550/ARXIV.2503.10522","pages":null,"arxivId":"2503.10522","arxivUrl":"https://arxiv.org/abs/2503.10522"},{"key":"journals/corr/abs-2503-11731","title":"Industrial-Grade Sensor Simulation via Gaussian Splatting: A Modular Framework for Scalable Editing and Full-Stack Validation.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2503.11731","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-11731","documentUrl":"https://doi.org/10.48550/ARXIV.2503.11731","pages":null,"arxivId":"2503.11731","arxivUrl":"https://arxiv.org/abs/2503.11731"},{"key":"journals/corr/abs-2503-16948","title":"MagicColor: Multi-Instance Sketch Colorization.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2503.16948","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-16948","documentUrl":"https://doi.org/10.48550/ARXIV.2503.16948","pages":null,"arxivId":"2503.16948","arxivUrl":"https://arxiv.org/abs/2503.16948"},{"key":"journals/corr/abs-2503-19906","title":"AvatarArtist: Open-Domain 4D Avatarization.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2503.19906","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-19906","documentUrl":"https://doi.org/10.48550/ARXIV.2503.19906","pages":null,"arxivId":"2503.19906","arxivUrl":"https://arxiv.org/abs/2503.19906"},{"key":"journals/corr/abs-2503-21172","title":"Model as a Game: On Numerical and Spatial Consistency for Generative Games.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2503.21172","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-21172","documentUrl":"https://doi.org/10.48550/ARXIV.2503.21172","pages":null,"arxivId":"2503.21172","arxivUrl":"https://arxiv.org/abs/2503.21172"},{"key":"journals/corr/abs-2505-02094","title":"SkillMimic-V2: Learning Robust and Generalizable Interaction Skills from Sparse and Noisy Demonstrations.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2505.02094","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-02094","documentUrl":"https://doi.org/10.48550/ARXIV.2505.02094","pages":null,"arxivId":"2505.02094","arxivUrl":"https://arxiv.org/abs/2505.02094"},{"key":"journals/corr/abs-2505-11818","title":"Master Rules from Chaos: Learning to Reason, Plan, and Interact from Chaos for Tangram Assembly.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2505.11818","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-11818","documentUrl":"https://doi.org/10.48550/ARXIV.2505.11818","pages":null,"arxivId":"2505.11818","arxivUrl":"https://arxiv.org/abs/2505.11818"},{"key":"journals/corr/abs-2506-04213","title":"FullDiT2: Efficient In-Context Conditioning for Video Diffusion Transformers.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2506.04213","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-04213","documentUrl":"https://doi.org/10.48550/ARXIV.2506.04213","pages":null,"arxivId":"2506.04213","arxivUrl":"https://arxiv.org/abs/2506.04213"},{"key":"journals/corr/abs-2506-04216","title":"UNIC: Unified In-Context Video Editing.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2506.04216","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-04216","documentUrl":"https://doi.org/10.48550/ARXIV.2506.04216","pages":null,"arxivId":"2506.04216","arxivUrl":"https://arxiv.org/abs/2506.04216"},{"key":"journals/corr/abs-2506-04590","title":"Follow-Your-Creation: Empowering 4D Creation through Video Inpainting.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2506.04590","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-04590","documentUrl":"https://doi.org/10.48550/ARXIV.2506.04590","pages":null,"arxivId":"2506.04590","arxivUrl":"https://arxiv.org/abs/2506.04590"},{"key":"journals/corr/abs-2506-05207","title":"Follow-Your-Motion: Video Motion Transfer via Efficient Spatial-Temporal Decoupled Finetuning.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2506.05207","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-05207","documentUrl":"https://doi.org/10.48550/ARXIV.2506.05207","pages":null,"arxivId":"2506.05207","arxivUrl":"https://arxiv.org/abs/2506.05207"},{"key":"journals/corr/abs-2506-09373","title":"LPO: Towards Accurate GUI Agent Interaction via Location Preference Optimization.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2506.09373","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-09373","documentUrl":"https://doi.org/10.48550/ARXIV.2506.09373","pages":null,"arxivId":"2506.09373","arxivUrl":"https://arxiv.org/abs/2506.09373"},{"key":"journals/corr/abs-2506-13846","title":"Fake it till You Make it: Reward Modeling as Discriminative Prediction.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2506.13846","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-13846","documentUrl":"https://doi.org/10.48550/ARXIV.2506.13846","pages":null,"arxivId":"2506.13846","arxivUrl":"https://arxiv.org/abs/2506.13846"},{"key":"journals/corr/abs-2506-22800","title":"RGE-GS: Reward-Guided Expansive Driving Scene Reconstruction via Diffusion Priors.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2506.22800","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-22800","documentUrl":"https://doi.org/10.48550/ARXIV.2506.22800","pages":null,"arxivId":"2506.22800","arxivUrl":"https://arxiv.org/abs/2506.22800"},{"key":"journals/corr/abs-2506-24123","title":"Calligrapher: Freestyle Text Image Customization.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2506.24123","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-24123","documentUrl":"https://doi.org/10.48550/ARXIV.2506.24123","pages":null,"arxivId":"2506.24123","arxivUrl":"https://arxiv.org/abs/2506.24123"},{"key":"journals/corr/abs-2507-05601","title":"Rethinking Layered Graphic Design Generation with a Top-Down Approach.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2507.05601","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2507-05601","documentUrl":"https://doi.org/10.48550/ARXIV.2507.05601","pages":null,"arxivId":"2507.05601","arxivUrl":"https://arxiv.org/abs/2507.05601"},{"key":"journals/corr/abs-2507-16869","title":"Controllable Video Generation: A Survey.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2507.16869","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2507-16869","documentUrl":"https://doi.org/10.48550/ARXIV.2507.16869","pages":null,"arxivId":"2507.16869","arxivUrl":"https://arxiv.org/abs/2507.16869"},{"key":"journals/corr/abs-2508-00782","title":"SpA2V: Harnessing Spatial Auditory Cues for Audio-driven Spatially-aware Video Generation.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2508.00782","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-00782","documentUrl":"https://doi.org/10.48550/ARXIV.2508.00782","pages":null,"arxivId":"2508.00782","arxivUrl":"https://arxiv.org/abs/2508.00782"},{"key":"journals/corr/abs-2508-05580","title":"Follow-Your-Instruction: A Comprehensive MLLM Agent for World Data Synthesis.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2508.05580","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-05580","documentUrl":"https://doi.org/10.48550/ARXIV.2508.05580","pages":null,"arxivId":"2508.05580","arxivUrl":"https://arxiv.org/abs/2508.05580"},{"key":"journals/corr/abs-2508-08134","title":"Follow-Your-Shape: Shape-Aware Image Editing via Trajectory-Guided Region Control.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2508.08134","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-08134","documentUrl":"https://doi.org/10.48550/ARXIV.2508.08134","pages":null,"arxivId":"2508.08134","arxivUrl":"https://arxiv.org/abs/2508.08134"},{"key":"journals/corr/abs-2508-10858","title":"Hierarchical Fine-grained Preference Optimization for Physically Plausible Video Generation.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2508.10858","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-10858","documentUrl":"https://doi.org/10.48550/ARXIV.2508.10858","pages":null,"arxivId":"2508.10858","arxivUrl":"https://arxiv.org/abs/2508.10858"},{"key":"journals/corr/abs-2509-15221","title":"ScaleCUA: Scaling Open-Source Computer Use Agents with Cross-Platform Data.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2509.15221","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-15221","documentUrl":"https://doi.org/10.48550/ARXIV.2509.15221","pages":null,"arxivId":"2509.15221","arxivUrl":"https://arxiv.org/abs/2509.15221"},{"key":"journals/corr/abs-2509-16630","title":"Follow-Your-Emoji-Faster: Towards Efficient, Fine-Controllable, and Expressive Freestyle Portrait Animation.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2509.16630","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-16630","documentUrl":"https://doi.org/10.48550/ARXIV.2509.16630","pages":null,"arxivId":"2509.16630","arxivUrl":"https://arxiv.org/abs/2509.16630"},{"key":"journals/corr/abs-2509-17042","title":"Orchestrate, Generate, Reflect: A VLM-Based Multi-Agent Collaboration Framework for Automated Driving Policy Learning.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2509.17042","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-17042","documentUrl":"https://doi.org/10.48550/ARXIV.2509.17042","pages":null,"arxivId":"2509.17042","arxivUrl":"https://arxiv.org/abs/2509.17042"},{"key":"journals/corr/abs-2510-06231","title":"CML-Bench: A Framework for Evaluating and Enhancing LLM-Powered Movie Scripts Generation.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2510.06231","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-06231","documentUrl":"https://doi.org/10.48550/ARXIV.2510.06231","pages":null,"arxivId":"2510.06231","arxivUrl":"https://arxiv.org/abs/2510.06231"},{"key":"journals/corr/abs-2510-11072","title":"PhysHSI: Towards a Real-World Generalizable and Natural Humanoid-Scene Interaction System.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2510.11072","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-11072","documentUrl":"https://doi.org/10.48550/ARXIV.2510.11072","pages":null,"arxivId":"2510.11072","arxivUrl":"https://arxiv.org/abs/2510.11072"},{"key":"journals/corr/abs-2510-15742","title":"Scaling Instruction-Based Video Editing with a High-Quality Synthetic Dataset.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2510.15742","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-15742","documentUrl":"https://doi.org/10.48550/ARXIV.2510.15742","pages":null,"arxivId":"2510.15742","arxivUrl":"https://arxiv.org/abs/2510.15742"},{"key":"journals/corr/abs-2511-12304","title":"LiDAR-GS++:Improving LiDAR Gaussian Reconstruction via Diffusion Priors.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2511.12304","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2511-12304","documentUrl":"https://doi.org/10.48550/ARXIV.2511.12304","pages":null,"arxivId":"2511.12304","arxivUrl":"https://arxiv.org/abs/2511.12304"},{"key":"journals/corr/abs-2511-14719","title":"Zero-shot Synthetic Video Realism Enhancement via Structure-aware Denoising.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2511.14719","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2511-14719","documentUrl":"https://doi.org/10.48550/ARXIV.2511.14719","pages":null,"arxivId":"2511.14719","arxivUrl":"https://arxiv.org/abs/2511.14719"},{"key":"journals/corr/abs-2511-22847","title":"Threat-Aware UAV Dodging of Human-Thrown Projectiles with an RGB-D Camera.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2511.22847","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2511-22847","documentUrl":"https://doi.org/10.48550/ARXIV.2511.22847","pages":null,"arxivId":"2511.22847","arxivUrl":"https://arxiv.org/abs/2511.22847"},{"key":"journals/corr/abs-2512-03046","title":"MagicQuillV2: Precise and Interactive Image Editing with Layered Visual Cues.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2512.03046","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-03046","documentUrl":"https://doi.org/10.48550/ARXIV.2512.03046","pages":null,"arxivId":"2512.03046","arxivUrl":"https://arxiv.org/abs/2512.03046"},{"key":"journals/corr/abs-2512-16924","title":"The World is Your Canvas: Painting Promptable Events with Reference Images, Trajectories, and Text.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2512.16924","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-16924","documentUrl":"https://doi.org/10.48550/ARXIV.2512.16924","pages":null,"arxivId":"2512.16924","arxivUrl":"https://arxiv.org/abs/2512.16924"},{"key":"journals/corr/abs-2512-17532","title":"Robust-R1: Degradation-Aware Reasoning for Robust Visual Understanding.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2512.17532","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-17532","documentUrl":"https://doi.org/10.48550/ARXIV.2512.17532","pages":null,"arxivId":"2512.17532","arxivUrl":"https://arxiv.org/abs/2512.17532"},{"key":"journals/corr/abs-2512-19583","title":"Learning Generalizable Hand-Object Tracking from Synthetic Demonstrations.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2512.19583","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-19583","documentUrl":"https://doi.org/10.48550/ARXIV.2512.19583","pages":null,"arxivId":"2512.19583","arxivUrl":"https://arxiv.org/abs/2512.19583"},{"key":"journals/corr/abs-2512-20615","title":"Active Intelligence in Video Avatars via Closed-loop World Modeling.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2512.20615","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-20615","documentUrl":"https://doi.org/10.48550/ARXIV.2512.20615","pages":null,"arxivId":"2512.20615","arxivUrl":"https://arxiv.org/abs/2512.20615"},{"key":"journals/corr/abs-2512-20618","title":"LongVideoAgent: Multi-Agent Reasoning with Long Videos.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2512.20618","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-20618","documentUrl":"https://doi.org/10.48550/ARXIV.2512.20618","pages":null,"arxivId":"2512.20618","arxivUrl":"https://arxiv.org/abs/2512.20618"}],"excludedFormal":[],"labName":"Visual Intelligence Lab","labUrl":"https://ri.hkust.edu.hk/research/visual-intelligence","labEvidence":"HKUST Robotics Institute 官方首页以 Visual Intelligence Lab 为团队标题，紧接正文明确为 Prof. Qifeng Chen 的研究，并直接链接该研究页。","labSourceUrl":"https://ri.hkust.edu.hk/index.php/","affiliationZh":"香港科技大学","sourceWarning":false,"excludedOther":[],"excludedHomonyms":[],"unassignedCandidates":[],"knownPreprintMinimum2025":null,"excludedMisattributed":[],"displayNotes":"身份已经机构或个人主页核对。2025 年正式记录 44 条（会议 41、期刊 3），所有作者位置均计入，不表示主导或贡献份额；预印本 39 条单列，不加总。","labDisplayNotes":"港科大机器人研究院官方首页以 Visual Intelligence Lab 为题介绍陈启峰教授的研究，并链接研究页，据此归组。"},{"index":32,"name":"Xiang Chen","nameZh":"陈翔","role":"Associate Professor","affiliation":"Nanjing University of Science and Technology","source":"DBLP official SPARQL","profileUrl":"https://dblp.org/pid/64/3062-15","identifier":"64/3062-15","identityEvidence":[{"url":"https://dblp.org/pid/64/3062-15","evidence":"DBLP 档案名 Xiang Chen 0015；机构/履历：Nanjing University of Science and Technology, School of Computer Science and Engineering, Nanjing, China；Shenyang Aerospace University, College of Electronic and Information Engineering, Shenyang, China"}],"count2025":12,"conference2025":9,"journal2025":3,"preprint2025":9,"status":"verified","notes":"身份已通过机构/个人主页或 DBLP 机构信息核对；篇数为数据库记录统计，不表示每篇均由本人主导。","retrievedAt":"2026-10-19","yearPolicy":"DBLP yearOfPublication = 2025","queryUrl":"https://sparql.dblp.org/sparql?query=PREFIX%20dblp%3A%20%3Chttps%3A//dblp.org/rdf/schema%23%3E%20PREFIX%20xsd%3A%20%3Chttp%3A//www.w3.org/2001/XMLSchema%23%3E%20SELECT%20%3Fpub%20%3Ftitle%20%3Ftype%20%3Fvenue%20WHERE%20%7B%20%3Fpub%20dblp%3AauthoredBy%20%3Chttps%3A//dblp.org/pid/64/3062-15%3E%3B%20dblp%3AyearOfPublication%20%222025%22%5E%5Exsd%3AgYear%3B%20dblp%3Atitle%20%3Ftitle%3B%20a%20%3Ftype%20.%20OPTIONAL%20%7B%20%3Fpub%20dblp%3ApublishedIn%20%3Fvenue%20%7D%20%7D&format=json","papers":[{"key":"conf/aaai/FanWYCGLY25","title":"Depth-Centric Dehazing and Depth-Estimation from Real-World Hazy Driving Video.","type":"Inproceedings","venue":"AAAI","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1609/AAAI.V39I3.32291","sourceUrl":"https://dblp.org/rec/conf/aaai/FanWYCGLY25","documentUrl":"https://doi.org/10.1609/AAAI.V39I3.32291","pages":"2852-2860"},{"key":"conf/aaai/LiuC0XL25","title":"DeRainGS: Gaussian Splatting for Enhanced Scene Reconstruction in Rainy Environments.","type":"Inproceedings","venue":"AAAI","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1609/AAAI.V39I5.32592","sourceUrl":"https://dblp.org/rec/conf/aaai/LiuC0XL25","documentUrl":"https://doi.org/10.1609/AAAI.V39I5.32592","pages":"5558-5566"},{"key":"conf/cvpr/0082JJWLWYL0WTT25","title":"NTIRE 2025 Challenge on Day and Night Raindrop Removal for Dual-Focused Images: Methods and Results.","type":"Inproceedings","venue":"CVPR Workshops","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":null,"sourceUrl":"https://dblp.org/rec/conf/cvpr/0082JJWLWYL0WTT25","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025W/NTIRE/html/Li_NTIRE_2025_Challenge_on_Day_and_Night_Raindrop_Removal_for_CVPRW_2025_paper.html","pages":"1172-1183"},{"key":"conf/iccv/CiubotariuVZMTWSKYPDTCF25","title":"AIM 2025 Challenge on High FPS Motion Deblurring: Methods and Results.","type":"Inproceedings","venue":"ICCVW","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/ICCVW69036.2025.00586","sourceUrl":"https://dblp.org/rec/conf/iccv/CiubotariuVZMTWSKYPDTCF25","documentUrl":"https://doi.org/10.1109/ICCVW69036.2025.00586","pages":"5600-5609"},{"key":"conf/iccv/LiCDTP25","title":"FoundIR: Unleashing Million-Scale Training Data to Advance Foundation Models for Image Restoration.","type":"Inproceedings","venue":"ICCV","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/ICCV51701.2025.01173","sourceUrl":"https://dblp.org/rec/conf/iccv/LiCDTP25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.01173","pages":"12626-12636"},{"key":"conf/ijcai/RenZCLL025","title":"K-Buffers: A Plug-in Method for Enhancing Neural Fields with Multiple Buffers.","type":"Inproceedings","venue":"IJCAI","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.24963/IJCAI.2025/203","sourceUrl":"https://dblp.org/rec/conf/ijcai/RenZCLL025","documentUrl":"https://doi.org/10.24963/IJCAI.2025/203","pages":"1820-1828"},{"key":"conf/mm/GuanYC0JJ25","title":"WeatherBench: A Real-World Benchmark Dataset for All-in-One Adverse Weather Image Restoration.","type":"Inproceedings","venue":"ACM Multimedia","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1145/3746027.3758196","sourceUrl":"https://dblp.org/rec/conf/mm/GuanYC0JJ25","documentUrl":"https://doi.org/10.1145/3746027.3758196","pages":"12607-12613"},{"key":"conf/mm/JinYWCLC25","title":"SmokeBench: A Real-World Dataset for Surveillance Image Desmoking in Early-Stage Fire Scenes.","type":"Inproceedings","venue":"ACM Multimedia","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1145/3746027.3758211","sourceUrl":"https://dblp.org/rec/conf/mm/JinYWCLC25","documentUrl":"https://doi.org/10.1145/3746027.3758211","pages":"12722-12728"},{"key":"conf/nips/GuanCJJFSP25","title":"Rethinking Nighttime Image Deraining via Learnable Color Space Transformation.","type":"Inproceedings","venue":"NeurIPS","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":null,"sourceUrl":"https://dblp.org/rec/conf/nips/GuanCJJFSP25","documentUrl":"http://papers.nips.cc/paper_files/paper/2025/hash/04b7126c370f175204442098356dc239-Abstract-Conference.html","pages":null},{"key":"journals/dsp/WuCCX25","title":"Multi-scale transformer with conditioned prompt for image deraining.","type":"Article","venue":"Digit. Signal Process.","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.1016/J.DSP.2024.104847","sourceUrl":"https://dblp.org/rec/journals/dsp/WuCCX25","documentUrl":"https://doi.org/10.1016/J.DSP.2024.104847","pages":"104847"},{"key":"journals/pami/ChenPDT25","title":"Towards Unified Deep Image Deraining: A Survey and a New Benchmark.","type":"Article","venue":"IEEE Trans. Pattern Anal. Mach. Intell.","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.1109/TPAMI.2025.3556133","sourceUrl":"https://dblp.org/rec/journals/pami/ChenPDT25","documentUrl":"https://doi.org/10.1109/TPAMI.2025.3556133","pages":"5414-5433"},{"key":"journals/sivp/HuangZQWGC25","title":"UHD-RealHaze: A Real-World Benchmark Dataset for Ultra-High-Definition Image Dehazing.","type":"Article","venue":"Signal Image Video Process.","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.1007/S11760-025-04478-W","sourceUrl":"https://dblp.org/rec/journals/sivp/HuangZQWGC25","documentUrl":"https://doi.org/10.1007/S11760-025-04478-W","pages":"848"}],"preprints":[{"key":"journals/corr/abs-2504-12711","title":"NTIRE 2025 Challenge on Day and Night Raindrop Removal for Dual-Focused Images: Methods and Results.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2504.12711","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2504-12711","documentUrl":"https://doi.org/10.48550/ARXIV.2504.12711","pages":null,"arxivId":"2504.12711","arxivUrl":"https://arxiv.org/abs/2504.12711"},{"key":"journals/corr/abs-2505-19564","title":"K-Buffers: A Plug-in Method for Enhancing Neural Fields with Multiple Buffers.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2505.19564","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-19564","documentUrl":"https://doi.org/10.48550/ARXIV.2505.19564","pages":null,"arxivId":"2505.19564","arxivUrl":"https://arxiv.org/abs/2505.19564"},{"key":"journals/corr/abs-2509-06793","title":"AIM 2025 Challenge on High FPS Motion Deblurring: Methods and Results.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2509.06793","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-06793","documentUrl":"https://doi.org/10.48550/ARXIV.2509.06793","pages":null,"arxivId":"2509.06793","arxivUrl":"https://arxiv.org/abs/2509.06793"},{"key":"journals/corr/abs-2509-11642","title":"WeatherBench: A Real-World Benchmark Dataset for All-in-One Adverse Weather Image Restoration.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2509.11642","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-11642","documentUrl":"https://doi.org/10.48550/ARXIV.2509.11642","pages":null,"arxivId":"2509.11642","arxivUrl":"https://arxiv.org/abs/2509.11642"},{"key":"journals/corr/abs-2509-12701","title":"SmokeBench: A Real-World Dataset for Surveillance Image Desmoking in Early-Stage Fire Scenes.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2509.12701","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-12701","documentUrl":"https://doi.org/10.48550/ARXIV.2509.12701","pages":null,"arxivId":"2509.12701","arxivUrl":"https://arxiv.org/abs/2509.12701"},{"key":"journals/corr/abs-2509-21719","title":"DeLiVR: Differential Spatiotemporal Lie Bias for Efficient Video Deraining.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2509.21719","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-21719","documentUrl":"https://doi.org/10.48550/ARXIV.2509.21719","pages":null,"arxivId":"2509.21719","arxivUrl":"https://arxiv.org/abs/2509.21719"},{"key":"journals/corr/abs-2510-17440","title":"Rethinking Nighttime Image Deraining via Learnable Color Space Transformation.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2510.17440","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-17440","documentUrl":"https://doi.org/10.48550/ARXIV.2510.17440","pages":null,"arxivId":"2510.17440","arxivUrl":"https://arxiv.org/abs/2510.17440"},{"key":"journals/corr/abs-2511-06734","title":"Rethinking Rainy 3D Scene Reconstruction via Perspective Transforming and Brightness Tuning.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2511.06734","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2511-06734","documentUrl":"https://doi.org/10.48550/ARXIV.2511.06734","pages":null,"arxivId":"2511.06734","arxivUrl":"https://arxiv.org/abs/2511.06734"},{"key":"journals/corr/abs-2512-09282","title":"FoundIR-v2: Optimizing Pre-Training Data Mixtures for Image Restoration Foundation Model.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2512.09282","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-09282","documentUrl":"https://doi.org/10.48550/ARXIV.2512.09282","pages":null,"arxivId":"2512.09282","arxivUrl":"https://arxiv.org/abs/2512.09282"}],"excludedFormal":[],"labName":null,"labUrl":null,"labEvidence":"本人当前主页称 our group，没有具名 Lab；同名检索所得 NJUST 材料学 Tribo-Lab 属另一位 Xiang Chen，不能采用。过去博士阶段的 IMAG 线索也不足以证明当前组名。","labSourceUrl":"https://cschenxiang.github.io/","affiliationZh":"南京理工大学","sourceWarning":false,"excludedOther":[],"excludedHomonyms":[],"unassignedCandidates":[],"knownPreprintMinimum2025":null,"excludedMisattributed":[],"displayNotes":"身份已经机构或个人主页核对。2025 年正式记录 12 条（会议 9、期刊 3），所有作者位置均计入，不表示主导或贡献份额；预印本 9 条单列，不加总。","labDisplayNotes":"本人主页只称 our group。检索到的南理工 Tribo-Lab 属于另一位同名材料学者，不采用；博士阶段的团队也不作为当前组名。图中以「姓名及合作者」单列。"},{"index":33,"name":"Ying-Cong Chen","nameZh":"陈颖聪","role":"Assistant Professor","affiliation":"Hong Kong University of Science and Technology (Guangzhou)","source":"DBLP official SPARQL","profileUrl":"https://dblp.org/pid/137/6578","identifier":"137/6578","identityEvidence":[{"url":"https://dblp.org/pid/137/6578","evidence":"DBLP 唯一同名作者档案；通过作者/机构主页与发表题名交叉核对。"},{"url":"https://www.yingcong.me/","evidence":"作者/机构页面与该 DBLP 档案交叉匹配的题名示例：Kiss3DGen: Repurposing Image Diffusion Models for 3D Asset Generation.；TransPixeler: Advancing Text-to-Video Generation with Transparency.","matchedPaperKeys":["conf/cvpr/Lin0CXYWXXZC25","conf/cvpr/Wang0CWZZLC25"]},{"url":"https://academic.oup.com/bioinformatics/article/41/Supplement_1/i382/8199395","evidence":"DivPro 正文列出 Yingcong Chen 的 HKUST Guangzhou 与 HKUST Clear Water Bay 机构，确认此跨领域记录属于该作者。"},{"url":"https://www.yingcong.me/publication/2025-zhou-divpro/","evidence":"作者个人发表页列出 DivPro，年份 2025。"}],"count2025":39,"conference2025":33,"journal2025":6,"preprint2025":38,"status":"verified","notes":"DBLP 显示 ORCID 冲突提示；2025 正式记录经题名审阅未见明显异域错配。其中 DivPro 蛋白设计论文由出版社全文和作者个人发表页确认 HKUST(GZ) 身份。","retrievedAt":"2026-10-19","yearPolicy":"DBLP yearOfPublication = 2025","queryUrl":"https://sparql.dblp.org/sparql?query=PREFIX%20dblp%3A%20%3Chttps%3A//dblp.org/rdf/schema%23%3E%20PREFIX%20xsd%3A%20%3Chttp%3A//www.w3.org/2001/XMLSchema%23%3E%20SELECT%20%3Fpub%20%3Ftitle%20%3Ftype%20%3Fvenue%20WHERE%20%7B%20%3Fpub%20dblp%3AauthoredBy%20%3Chttps%3A//dblp.org/pid/137/6578%3E%3B%20dblp%3AyearOfPublication%20%222025%22%5E%5Exsd%3AgYear%3B%20dblp%3Atitle%20%3Ftitle%3B%20a%20%3Ftype%20.%20OPTIONAL%20%7B%20%3Fpub%20dblp%3ApublishedIn%20%3Fvenue%20%7D%20%7D&format=json","papers":[{"key":"conf/aaai/LuZWLDC25","title":"Towards Generalizable Multi-Camera 3D Object Detection via Perspective Rendering.","type":"Inproceedings","venue":"AAAI","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1609/AAAI.V39I6.32620","sourceUrl":"https://dblp.org/rec/conf/aaai/LuZWLDC25","documentUrl":"https://doi.org/10.1609/AAAI.V39I6.32620","pages":"5811-5819"},{"key":"conf/cvpr/0003X0R0LCZW25","title":"POSTA: A Go-to Framework for Customized Artistic Poster Generation.","type":"Inproceedings","venue":"CVPR","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/CVPR52734.2025.02672","sourceUrl":"https://dblp.org/rec/conf/cvpr/0003X0R0LCZW25","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Chen_POSTA_A_Go-to_Framework_for_Customized_Artistic_Poster_Generation_CVPR_2025_paper.html","pages":"28694-28704"},{"key":"conf/cvpr/ChenXGWYHWZZC25","title":"Uni-Renderer: Unifying Rendering and Inverse Rendering Via Dual Stream Diffusion.","type":"Inproceedings","venue":"CVPR","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/CVPR52734.2025.02468","sourceUrl":"https://dblp.org/rec/conf/cvpr/ChenXGWYHWZZC25","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Chen_Uni-Renderer_Unifying_Rendering_and_Inverse_Rendering_Via_Dual_Stream_Diffusion_CVPR_2025_paper.html","pages":"26504-26513"},{"key":"conf/cvpr/Lin0CXYWXXZC25","title":"Kiss3DGen: Repurposing Image Diffusion Models for 3D Asset Generation.","type":"Inproceedings","venue":"CVPR","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/CVPR52734.2025.00551","sourceUrl":"https://dblp.org/rec/conf/cvpr/Lin0CXYWXXZC25","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Lin_Kiss3DGen_Repurposing_Image_Diffusion_Models_for_3D_Asset_Generation_CVPR_2025_paper.html","pages":"5870-5880"},{"key":"conf/cvpr/Ma0000ZWFC0025","title":"SURGEON: Memory-Adaptive Fully Test-Time Adaptation via Dynamic Activation Sparsity.","type":"Inproceedings","venue":"CVPR","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/CVPR52734.2025.02841","sourceUrl":"https://dblp.org/rec/conf/cvpr/Ma0000ZWFC0025","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Ma_SURGEON_Memory-Adaptive_Fully_Test-Time_Adaptation_via_Dynamic_Activation_Sparsity_CVPR_2025_paper.html","pages":"30514-30523"},{"key":"conf/cvpr/Wang0CWZZLC25","title":"TransPixeler: Advancing Text-to-Video Generation with Transparency.","type":"Inproceedings","venue":"CVPR","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/CVPR52734.2025.01699","sourceUrl":"https://dblp.org/rec/conf/cvpr/Wang0CWZZLC25","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Wang_TransPixeler_Advancing_Text-to-Video_Generation_with_Transparency_CVPR_2025_paper.html","pages":"18229-18239"},{"key":"conf/eccv/LiLC24","title":"Bi-TTA: Bidirectional Test-Time Adapter for Remote Physiological Measurement.","type":"Inproceedings","venue":"ECCV (11)","year":2025,"yearOfPublication":2025,"yearOfEvent":2024,"doi":"https://doi.org/10.1007/978-3-031-73247-8_21","sourceUrl":"https://dblp.org/rec/conf/eccv/LiLC24","documentUrl":"https://doi.org/10.1007/978-3-031-73247-8_21","pages":"356-374"},{"key":"conf/eccv/LinJCZLC24","title":"MTMamba: Enhancing Multi-task Dense Scene Understanding by Mamba-Based Decoders.","type":"Inproceedings","venue":"ECCV (70)","year":2025,"yearOfPublication":2025,"yearOfEvent":2024,"doi":"https://doi.org/10.1007/978-3-031-72897-6_18","sourceUrl":"https://dblp.org/rec/conf/eccv/LinJCZLC24","documentUrl":"https://doi.org/10.1007/978-3-031-72897-6_18","pages":"314-330"},{"key":"conf/eccv/TangLXWHZCGCT24","title":"An Incremental Unified Framework for Small Defect Inspection.","type":"Inproceedings","venue":"ECCV (31)","year":2025,"yearOfPublication":2025,"yearOfEvent":2024,"doi":"https://doi.org/10.1007/978-3-031-72751-1_18","sourceUrl":"https://dblp.org/rec/conf/eccv/TangLXWHZCGCT24","documentUrl":"https://doi.org/10.1007/978-3-031-72751-1_18","pages":"307-324"},{"key":"conf/eccv/WangSGCLC24","title":"Text-Anchored Score Composition: Tackling Condition Misalignment in Text-to-Image Diffusion Models.","type":"Inproceedings","venue":"ECCV (47)","year":2025,"yearOfPublication":2025,"yearOfEvent":2024,"doi":"https://doi.org/10.1007/978-3-031-72970-6_2","sourceUrl":"https://dblp.org/rec/conf/eccv/WangSGCLC24","documentUrl":"https://doi.org/10.1007/978-3-031-72970-6_2","pages":"21-37"},{"key":"conf/eccv/YangCCFLLC24","title":"Defect Spectrum: A Granular Look of Large-Scale Defect Datasets with Rich Semantics.","type":"Inproceedings","venue":"ECCV (7)","year":2025,"yearOfPublication":2025,"yearOfEvent":2024,"doi":"https://doi.org/10.1007/978-3-031-72667-5_11","sourceUrl":"https://dblp.org/rec/conf/eccv/YangCCFLLC24","documentUrl":"https://doi.org/10.1007/978-3-031-72667-5_11","pages":"187-203"},{"key":"conf/emnlp/XuXCCZC25","title":"PreGenie: An Agentic Framework for High-quality Visual Presentation Generation.","type":"Inproceedings","venue":"EMNLP (Findings)","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.18653/V1/2025.FINDINGS-EMNLP.165","sourceUrl":"https://dblp.org/rec/conf/emnlp/XuXCCZC25","documentUrl":"https://doi.org/10.18653/V1/2025.FINDINGS-EMNLP.165","pages":"3045-3063"},{"key":"conf/emnlp/ZhangXXZLC25","title":"Orchestrating Audio: Multi-Agent Framework for Long-Video Audio Synthesis.","type":"Inproceedings","venue":"EMNLP","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.18653/V1/2025.EMNLP-MAIN.1133","sourceUrl":"https://dblp.org/rec/conf/emnlp/ZhangXXZLC25","documentUrl":"https://doi.org/10.18653/V1/2025.EMNLP-MAIN.1133","pages":"22267-22282"},{"key":"conf/iccv/FuWTNYXCZ25","title":"Co-Painter: Fine-Grained Controllable Image Stylization via Implicit Decoupling and Adaptive Injection.","type":"Inproceedings","venue":"ICCV","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/ICCV51701.2025.01563","sourceUrl":"https://dblp.org/rec/conf/iccv/FuWTNYXCZ25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.01563","pages":"16830-16839"},{"key":"conf/iccv/GeLSFHXC25","title":"PRM: Photometric Stereo Based Large Reconstruction Model.","type":"Inproceedings","venue":"ICCV","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/ICCV51701.2025.02319","sourceUrl":"https://dblp.org/rec/conf/iccv/GeLSFHXC25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.02319","pages":"25009-25018"},{"key":"conf/iccv/HuaJCZ25","title":"Sat2City: 3D City Generation from a Single Satellite Image with Cascaded Latent Diffusion.","type":"Inproceedings","venue":"ICCV","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/ICCV51701.2025.02597","sourceUrl":"https://dblp.org/rec/conf/iccv/HuaJCZ25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.02597","pages":"27978-27988"},{"key":"conf/iccv/LiWCLKCL25","title":"StreamGS: Online Generalizable Gaussian Splatting Reconstruction for Unposed Image Streams.","type":"Inproceedings","venue":"ICCV","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/ICCV51701.2025.02397","sourceUrl":"https://dblp.org/rec/conf/iccv/LiWCLKCL25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.02397","pages":"25841-25850"},{"key":"conf/iccv/LuZTFGWWC25","title":"Rhythmguassian: Repurposing Generalizable Gaussian Model for Remote Physiological Measurement.","type":"Inproceedings","venue":"ICCV","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/ICCV51701.2025.01932","sourceUrl":"https://dblp.org/rec/conf/iccv/LuZTFGWWC25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.01932","pages":"20780-20790"},{"key":"conf/iccv/ShenWLGZTZWCLC25","title":"Scene Graph Guided Generation: Enable Accurate Relations Generation in Text-to-Image Models via Textural Rectification.","type":"Inproceedings","venue":"ICCV","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/ICCV51701.2025.01432","sourceUrl":"https://dblp.org/rec/conf/iccv/ShenWLGZTZWCLC25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.01432","pages":"15437-15446"},{"key":"conf/iccv/XuGLFXZZC25","title":"FlexGen: Flexible Multi-View Generation from Text and Image Inputs.","type":"Inproceedings","venue":"ICCV","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/ICCV51701.2025.01739","sourceUrl":"https://dblp.org/rec/conf/iccv/XuGLFXZZC25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.01739","pages":"18714-18724"},{"key":"conf/iccv/XuGQCYLZZZLC25","title":"GaussianProperty: Integrating Physical Properties to 3D Gaussians with LMMs.","type":"Inproceedings","venue":"ICCV","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/ICCV51701.2025.00679","sourceUrl":"https://dblp.org/rec/conf/iccv/XuGQCYLZZZLC25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.00679","pages":"7231-7240"},{"key":"conf/iccv/YangGLCGSC25","title":"SEED-Story: Multimodal Long Story Generation with Large Language Model.","type":"Inproceedings","venue":"ICCVW","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/ICCVW69036.2025.00197","sourceUrl":"https://dblp.org/rec/conf/iccv/YangGLCGSC25","documentUrl":"https://doi.org/10.1109/ICCVW69036.2025.00197","pages":"1871-1881"},{"key":"conf/iclr/HeL0LLZZLC25","title":"Lotus: Diffusion-based Visual Foundation Model for High-quality Dense Prediction.","type":"Inproceedings","venue":"ICLR","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":null,"sourceUrl":"https://dblp.org/rec/conf/iclr/HeL0LLZZLC25","documentUrl":"https://openreview.net/forum?id=stK7iOPH9Q","pages":null},{"key":"conf/iclr/HeLhSCQC25","title":"DisEnvisioner: Disentangled and Enriched Visual Prompt for Customized Image Generation.","type":"Inproceedings","venue":"ICLR","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":null,"sourceUrl":"https://dblp.org/rec/conf/iclr/HeLhSCQC25","documentUrl":"https://openreview.net/forum?id=vQxqcVGrhR","pages":null},{"key":"conf/icml/LinJXCC25","title":"PARM: Multi-Objective Test-Time Alignment via Preference-Aware Autoregressive Reward Model.","type":"Inproceedings","venue":"ICML","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":null,"sourceUrl":"https://dblp.org/rec/conf/icml/LinJXCC25","documentUrl":"https://proceedings.mlr.press/v267/lin25h.html","pages":null},{"key":"conf/icra/XuLYCLC25","title":"Occ-LLM: Enhancing Autonomous Driving with Occupancy-Based Large Language Models.","type":"Inproceedings","venue":"ICRA","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/ICRA55743.2025.11127665","sourceUrl":"https://dblp.org/rec/conf/icra/XuLYCLC25","documentUrl":"https://doi.org/10.1109/ICRA55743.2025.11127665","pages":"8434-8441"},{"key":"conf/mm/LinJXXLHC025","title":"Graph-Guided Dual-Level Augmentation for 3D Scene Segmentation.","type":"Inproceedings","venue":"ACM Multimedia","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1145/3746027.3755547","sourceUrl":"https://dblp.org/rec/conf/mm/LinJXXLHC025","documentUrl":"https://doi.org/10.1145/3746027.3755547","pages":"8517-8526"},{"key":"conf/nips/ChenZLJWC25","title":"Event-Guided Consistent Video Enhancement with Modality-Adaptive Diffusion Pipeline.","type":"Inproceedings","venue":"NeurIPS","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":null,"sourceUrl":"https://dblp.org/rec/conf/nips/ChenZLJWC25","documentUrl":"http://papers.nips.cc/paper_files/paper/2025/hash/dc3be1574e0f86d76e32a0229bb1f6be-Abstract-Conference.html","pages":null},{"key":"conf/nips/GuoXWLZZSC25","title":"ComfyMind: Toward General-Purpose Generation via Tree-Based Planning and Reactive Feedback.","type":"Inproceedings","venue":"NeurIPS","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":null,"sourceUrl":"https://dblp.org/rec/conf/nips/GuoXWLZZSC25","documentUrl":"http://papers.nips.cc/paper_files/paper/2025/hash/40168e00bf87869c5d153e934d8a3602-Abstract-Conference.html","pages":null},{"key":"conf/nips/LuXZZZDTKC25","title":"DrivingRecon: Large 4D Gaussian Reconstruction Model For Autonomous Driving.","type":"Inproceedings","venue":"NeurIPS","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":null,"sourceUrl":"https://dblp.org/rec/conf/nips/LuXZZZDTKC25","documentUrl":"http://papers.nips.cc/paper_files/paper/2025/hash/f5717c76feff4f751604c0678c46627b-Abstract-Conference.html","pages":null},{"key":"conf/nips/WangYHTLHWCW25","title":"PhysDrive: A Multimodal Remote Physiological Measurement Dataset for In-vehicle Driver Monitoring.","type":"Inproceedings","venue":"NeurIPS","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":null,"sourceUrl":"https://dblp.org/rec/conf/nips/WangYHTLHWCW25","documentUrl":"http://papers.nips.cc/paper_files/paper/2025/hash/3446e07569081f0f8a144e68bfa7afdf-Abstract-Datasets_and_Benchmarks_Track.html","pages":null},{"key":"conf/pg/GeFSC25","title":"Uni-IR: One Stage is Enough for Ambiguity-Reduced Inverse Rendering.","type":"Inproceedings","venue":"PG (Short Papers, Posters, and Demos)","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.2312/PG.20251295","sourceUrl":"https://dblp.org/rec/conf/pg/GeFSC25","documentUrl":"https://doi.org/10.2312/PG.20251295","pages":null},{"key":"conf/siggraph/WangMSL0000C25","title":"Motion Inversion for Video Customization.","type":"Inproceedings","venue":"SIGGRAPH (Conference Paper Track)","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1145/3721238.3730735","sourceUrl":"https://dblp.org/rec/conf/siggraph/WangMSL0000C25","documentUrl":"https://doi.org/10.1145/3721238.3730735","pages":"4:1-4:12"},{"key":"journals/bioinformatics/0010SCCH25","title":"DivPro: diverse protein sequence design with direct structure recovery guidance.","type":"Article","venue":"Bioinform.","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.1093/BIOINFORMATICS/BTAF258","sourceUrl":"https://dblp.org/rec/journals/bioinformatics/0010SCCH25","documentUrl":"https://doi.org/10.1093/BIOINFORMATICS/BTAF258","pages":"i382-i290"},{"key":"journals/cgf/HeLWCXGWC25","title":"LucidFusion: Reconstructing 3D Gaussians with Arbitrary Unposed Images.","type":"Article","venue":"Comput. Graph. Forum","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.1111/CGF.70227","sourceUrl":"https://dblp.org/rec/journals/cgf/HeLWCXGWC25","documentUrl":"https://doi.org/10.1111/CGF.70227","pages":null},{"key":"journals/pami/LinJCLC25","title":"MTMamba++: Enhancing Multi-Task Dense Scene Understanding via Mamba-Based Decoders.","type":"Article","venue":"IEEE Trans. Pattern Anal. Mach. Intell.","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.1109/TPAMI.2025.3593621","sourceUrl":"https://dblp.org/rec/journals/pami/LinJCLC25","documentUrl":"https://doi.org/10.1109/TPAMI.2025.3593621","pages":"10633-10645"},{"key":"journals/pami/WangLWYCHW25","title":"PhysMLE: Generalizable and Priors-Inclusive Multi-Task Remote Physiological Measurement.","type":"Article","venue":"IEEE Trans. Pattern Anal. Mach. Intell.","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.1109/TPAMI.2025.3545598","sourceUrl":"https://dblp.org/rec/journals/pami/WangLWYCHW25","documentUrl":"https://doi.org/10.1109/TPAMI.2025.3545598","pages":"4908-4925"},{"key":"journals/tim/WangLHCHW25","title":"Generalizable Remote Physiological Measurement via Semantic-Sheltered Alignment and Plausible Style Randomization.","type":"Article","venue":"IEEE Trans. Instrum. Meas.","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.1109/TIM.2024.3497058","sourceUrl":"https://dblp.org/rec/journals/tim/WangLHCHW25","documentUrl":"https://doi.org/10.1109/TIM.2024.3497058","pages":"1-14"},{"key":"journals/tip/ZhangLLCW25","title":"Advancing Generalizable Remote Physiological Measurement Through the Integration of Explicit and Implicit Prior Knowledge.","type":"Article","venue":"IEEE Trans. Image Process.","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.1109/TIP.2025.3576490","sourceUrl":"https://dblp.org/rec/journals/tip/ZhangLLCW25","documentUrl":"https://doi.org/10.1109/TIP.2025.3576490","pages":"3764-3778"}],"preprints":[{"key":"journals/corr/abs-2501-03006","title":"TransPixeler: Advancing Text-to-Video Generation with Transparency.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2501.03006","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2501-03006","documentUrl":"https://doi.org/10.48550/ARXIV.2501.03006","pages":null,"arxivId":"2501.03006","arxivUrl":"https://arxiv.org/abs/2501.03006"},{"key":"journals/corr/abs-2502-06419","title":"Occ-LLM: Enhancing Autonomous Driving with Occupancy-Based Large Language Models.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2502.06419","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2502-06419","documentUrl":"https://doi.org/10.48550/ARXIV.2502.06419","pages":null,"arxivId":"2502.06419","arxivUrl":"https://arxiv.org/abs/2502.06419"},{"key":"journals/corr/abs-2503-01370","title":"Kiss3DGen: Repurposing Image Diffusion Models for 3D Asset Generation.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2503.01370","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-01370","documentUrl":"https://doi.org/10.48550/ARXIV.2503.01370","pages":null,"arxivId":"2503.01370","arxivUrl":"https://arxiv.org/abs/2503.01370"},{"key":"journals/corr/abs-2503-02537","title":"RectifiedHR: Enable Efficient High-Resolution Image Generation via Energy Rectification.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2503.02537","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-02537","documentUrl":"https://doi.org/10.48550/ARXIV.2503.02537","pages":null,"arxivId":"2503.02537","arxivUrl":"https://arxiv.org/abs/2503.02537"},{"key":"journals/corr/abs-2503-06235","title":"StreamGS: Online Generalizable Gaussian Splatting Reconstruction for Unposed Image Streams.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2503.06235","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-06235","documentUrl":"https://doi.org/10.48550/ARXIV.2503.06235","pages":null,"arxivId":"2503.06235","arxivUrl":"https://arxiv.org/abs/2503.06235"},{"key":"journals/corr/abs-2503-10719","title":"Long-Video Audio Synthesis with Multi-Agent Collaboration.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2503.10719","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-10719","documentUrl":"https://doi.org/10.48550/ARXIV.2503.10719","pages":null,"arxivId":"2503.10719","arxivUrl":"https://arxiv.org/abs/2503.10719"},{"key":"journals/corr/abs-2503-14908","title":"POSTA: A Go-to Framework for Customized Artistic Poster Generation.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2503.14908","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-14908","documentUrl":"https://doi.org/10.48550/ARXIV.2503.14908","pages":null,"arxivId":"2503.14908","arxivUrl":"https://arxiv.org/abs/2503.14908"},{"key":"journals/corr/abs-2503-20354","title":"SURGEON: Memory-Adaptive Fully Test-Time Adaptation via Dynamic Activation Sparsity.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2503.20354","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-20354","documentUrl":"https://doi.org/10.48550/ARXIV.2503.20354","pages":null,"arxivId":"2503.20354","arxivUrl":"https://arxiv.org/abs/2503.20354"},{"key":"journals/corr/abs-2504-17670","title":"DiMeR: Disentangled Mesh Reconstruction Model.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2504.17670","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2504-17670","documentUrl":"https://doi.org/10.48550/ARXIV.2504.17670","pages":null,"arxivId":"2504.17670","arxivUrl":"https://arxiv.org/abs/2504.17670"},{"key":"journals/corr/abs-2505-06274","title":"PARM: Multi-Objective Test-Time Alignment via Preference-Aware Autoregressive Reward Model.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2505.06274","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-06274","documentUrl":"https://doi.org/10.48550/ARXIV.2505.06274","pages":null,"arxivId":"2505.06274","arxivUrl":"https://arxiv.org/abs/2505.06274"},{"key":"journals/corr/abs-2505-10257","title":"Sage Deer: A Super-Aligned Driving Generalist Is Your Copilot.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2505.10257","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-10257","documentUrl":"https://doi.org/10.48550/ARXIV.2505.10257","pages":null,"arxivId":"2505.10257","arxivUrl":"https://arxiv.org/abs/2505.10257"},{"key":"journals/corr/abs-2505-17908","title":"ComfyMind: Toward General-Purpose Generation via Tree-Based Planning and Reactive Feedback.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2505.17908","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-17908","documentUrl":"https://doi.org/10.48550/ARXIV.2505.17908","pages":null,"arxivId":"2505.17908","arxivUrl":"https://arxiv.org/abs/2505.17908"},{"key":"journals/corr/abs-2505-21050","title":"Advancing high-fidelity 3D and Texture Generation with 2.5D latents.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2505.21050","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-21050","documentUrl":"https://doi.org/10.48550/ARXIV.2505.21050","pages":null,"arxivId":"2505.21050","arxivUrl":"https://arxiv.org/abs/2505.21050"},{"key":"journals/corr/abs-2505-21660","title":"PreGenie: An Agentic Framework for High-quality Visual Presentation Generation.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2505.21660","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-21660","documentUrl":"https://doi.org/10.48550/ARXIV.2505.21660","pages":null,"arxivId":"2505.21660","arxivUrl":"https://arxiv.org/abs/2505.21660"},{"key":"journals/corr/abs-2506-02620","title":"FlexPainter: Flexible and Multi-View Consistent Texture Generation.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2506.02620","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-02620","documentUrl":"https://doi.org/10.48550/ARXIV.2506.02620","pages":null,"arxivId":"2506.02620","arxivUrl":"https://arxiv.org/abs/2506.02620"},{"key":"journals/corr/abs-2507-04403","title":"Sat2City: 3D City Generation from A Single Satellite Image with Cascaded Latent Diffusion.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2507.04403","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2507-04403","documentUrl":"https://doi.org/10.48550/ARXIV.2507.04403","pages":null,"arxivId":"2507.04403","arxivUrl":"https://arxiv.org/abs/2507.04403"},{"key":"journals/corr/abs-2507-19172","title":"PhysDrive: A Multimodal Remote Physiological Measurement Dataset for In-vehicle Driver Monitoring.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2507.19172","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2507-19172","documentUrl":"https://doi.org/10.48550/ARXIV.2507.19172","pages":null,"arxivId":"2507.19172","arxivUrl":"https://arxiv.org/abs/2507.19172"},{"key":"journals/corr/abs-2507-22668","title":"Graph-Guided Dual-Level Augmentation for 3D Scene Segmentation.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2507.22668","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2507-22668","documentUrl":"https://doi.org/10.48550/ARXIV.2507.22668","pages":null,"arxivId":"2507.22668","arxivUrl":"https://arxiv.org/abs/2507.22668"},{"key":"journals/corr/abs-2509-15273","title":"Embodied Arena: A Comprehensive, Unified, and Evolving Evaluation Platform for Embodied AI.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2509.15273","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-15273","documentUrl":"https://doi.org/10.48550/ARXIV.2509.15273","pages":null,"arxivId":"2509.15273","arxivUrl":"https://arxiv.org/abs/2509.15273"},{"key":"journals/corr/abs-2509-20251","title":"4D Driving Scene Generation With Stereo Forcing.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2509.20251","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-20251","documentUrl":"https://doi.org/10.48550/ARXIV.2509.20251","pages":null,"arxivId":"2509.20251","arxivUrl":"https://arxiv.org/abs/2509.20251"},{"key":"journals/corr/abs-2509-22622","title":"LongLive: Real-time Interactive Long Video Generation.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2509.22622","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-22622","documentUrl":"https://doi.org/10.48550/ARXIV.2509.22622","pages":null,"arxivId":"2509.22622","arxivUrl":"https://arxiv.org/abs/2509.22622"},{"key":"journals/corr/abs-2509-24980","title":"SDPose: Exploiting Diffusion Priors for Out-of-Domain and Robust Pose Estimation.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2509.24980","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-24980","documentUrl":"https://doi.org/10.48550/ARXIV.2509.24980","pages":null,"arxivId":"2509.24980","arxivUrl":"https://arxiv.org/abs/2509.24980"},{"key":"journals/corr/abs-2509-26376","title":"Go with Your Gut: Scaling Confidence for Autoregressive Image Generation.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2509.26376","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-26376","documentUrl":"https://doi.org/10.48550/ARXIV.2509.26376","pages":null,"arxivId":"2509.26376","arxivUrl":"https://arxiv.org/abs/2509.26376"},{"key":"journals/corr/abs-2509-26618","title":"DA2: Depth Anything in Any Direction.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2509.26618","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-26618","documentUrl":"https://doi.org/10.48550/ARXIV.2509.26618","pages":null,"arxivId":"2509.26618","arxivUrl":"https://arxiv.org/abs/2509.26618"},{"key":"journals/corr/abs-2510-09507","title":"PhysToolBench: Benchmarking Physical Tool Understanding for MLLMs.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2510.09507","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-09507","documentUrl":"https://doi.org/10.48550/ARXIV.2510.09507","pages":null,"arxivId":"2510.09507","arxivUrl":"https://arxiv.org/abs/2510.09507"},{"key":"journals/corr/abs-2510-13745","title":"UniCalli: A Unified Diffusion Framework for Column-Level Generation and Recognition of Chinese Calligraphy.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2510.13745","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-13745","documentUrl":"https://doi.org/10.48550/ARXIV.2510.13745","pages":null,"arxivId":"2510.13745","arxivUrl":"https://arxiv.org/abs/2510.13745"},{"key":"journals/corr/abs-2510-13940","title":"Less is More: Improving LLM Reasoning with Minimal Test-Time Intervention.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2510.13940","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-13940","documentUrl":"https://doi.org/10.48550/ARXIV.2510.13940","pages":null,"arxivId":"2510.13940","arxivUrl":"https://arxiv.org/abs/2510.13940"},{"key":"journals/corr/abs-2510-14588","title":"STANCE: Motion Coherent Video Generation Via Sparse-to-Dense Anchored Encoding.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2510.14588","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-14588","documentUrl":"https://doi.org/10.48550/ARXIV.2510.14588","pages":null,"arxivId":"2510.14588","arxivUrl":"https://arxiv.org/abs/2510.14588"},{"key":"journals/corr/abs-2511-08997","title":"T-Rex-Omni: Integrating Negative Visual Prompt in Generic Object Detection.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2511.08997","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2511-08997","documentUrl":"https://doi.org/10.48550/ARXIV.2511.08997","pages":null,"arxivId":"2511.08997","arxivUrl":"https://arxiv.org/abs/2511.08997"},{"key":"journals/corr/abs-2511-13704","title":"TiViBench: Benchmarking Think-in-Video Reasoning for Video Generative Models.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2511.13704","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2511-13704","documentUrl":"https://doi.org/10.48550/ARXIV.2511.13704","pages":null,"arxivId":"2511.13704","arxivUrl":"https://arxiv.org/abs/2511.13704"},{"key":"journals/corr/abs-2511-15253","title":"PresentCoach: Dual-Agent Presentation Coaching through Exemplars and Interactive Feedback.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2511.15253","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2511-15253","documentUrl":"https://doi.org/10.48550/ARXIV.2511.15253","pages":null,"arxivId":"2511.15253","arxivUrl":"https://arxiv.org/abs/2511.15253"},{"key":"journals/corr/abs-2511-16668","title":"V-ReasonBench: Toward Unified Reasoning Benchmark Suite for Video Generation Models.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2511.16668","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2511-16668","documentUrl":"https://doi.org/10.48550/ARXIV.2511.16668","pages":null,"arxivId":"2511.16668","arxivUrl":"https://arxiv.org/abs/2511.16668"},{"key":"journals/corr/abs-2511-23127","title":"DualCamCtrl: Dual-Branch Diffusion Model for Geometry-Aware Camera-Controlled Video Generation.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2511.23127","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2511-23127","documentUrl":"https://doi.org/10.48550/ARXIV.2511.23127","pages":null,"arxivId":"2511.23127","arxivUrl":"https://arxiv.org/abs/2511.23127"},{"key":"journals/corr/abs-2512-01030","title":"Lotus-2: Advancing Geometric Dense Prediction with Powerful Image Generative Model.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2512.01030","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-01030","documentUrl":"https://doi.org/10.48550/ARXIV.2512.01030","pages":null,"arxivId":"2512.01030","arxivUrl":"https://arxiv.org/abs/2512.01030"},{"key":"journals/corr/abs-2512-09864","title":"UniUGP: Unifying Understanding, Generation, and Planing For End-to-end Autonomous Driving.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2512.09864","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-09864","documentUrl":"https://doi.org/10.48550/ARXIV.2512.09864","pages":null,"arxivId":"2512.09864","arxivUrl":"https://arxiv.org/abs/2512.09864"},{"key":"journals/corr/abs-2512-14442","title":"A4-Agent: An Agentic Framework for Zero-Shot Affordance Reasoning.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2512.14442","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-14442","documentUrl":"https://doi.org/10.48550/ARXIV.2512.14442","pages":null,"arxivId":"2512.14442","arxivUrl":"https://arxiv.org/abs/2512.14442"},{"key":"journals/corr/abs-2512-16915","title":"StereoPilot: Learning Unified and Efficient Stereo Conversion via Generative Priors.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2512.16915","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-16915","documentUrl":"https://doi.org/10.48550/ARXIV.2512.16915","pages":null,"arxivId":"2512.16915","arxivUrl":"https://arxiv.org/abs/2512.16915"},{"key":"journals/corr/abs-2512-21185","title":"UltraShape 1.0: High-Fidelity 3D Shape Generation via Scalable Geometric Refinement.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2512.21185","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-21185","documentUrl":"https://doi.org/10.48550/ARXIV.2512.21185","pages":null,"arxivId":"2512.21185","arxivUrl":"https://arxiv.org/abs/2512.21185"}],"excludedFormal":[],"sourceWarning":true,"labName":"EnVision-Research","labUrl":"http://envision-research.hkust-gz.edu.cn","labEvidence":"本人主页写 For more information about my research group, please visit EnVision-Research，并直接链接；也列 Deep Vision Lab faculty member 身份，此处保留更直接的研究组入口。","labSourceUrl":"https://www.yingcong.me/","affiliationZh":"香港科技大学（广州）","excludedOther":[],"excludedHomonyms":[],"unassignedCandidates":[],"knownPreprintMinimum2025":null,"excludedMisattributed":[],"displayNotes":"DBLP 显示 ORCID 冲突提示。2025 年正式记录已逐条查看题名，未见明显的跨领域错配；其中 DivPro 蛋白设计论文经出版社全文和本人发表页确认为港科大（广州）身份。计入 39 条（会议 33、期刊 6）；预印本 38 条单列。","labDisplayNotes":"个人主页写明研究组信息见 EnVision-Research，并直接链接。其主页另列 Deep Vision Lab 成员身份，这里采用更直接的研究组入口。"},{"index":34,"name":"Zhaopeng Cui","nameZh":"崔兆鹏","role":"ZJU100 Young Professor","affiliation":"Zhejiang University","source":"DBLP official SPARQL","profileUrl":"https://dblp.org/pid/28/7484","identifier":"28/7484","identityEvidence":[{"url":"https://dblp.org/pid/28/7484","evidence":"DBLP 唯一同名作者档案；通过作者/机构主页与发表题名交叉核对。"},{"url":"https://zhpcui.github.io/","evidence":"作者/机构页面与该 DBLP 档案交叉匹配的题名示例：Free360: Layered Gaussian Splatting for Unbounded 360-Degree View Synthesis from Extremely Sparse and Unposed Views.；PhysSkin: Real-Time and Generalizable Physics-Based Animation via Self-Supervised Neural Skinning.","matchedPaperKeys":["conf/cvpr/Bao0YS0PC25","conf/cvpr/LeiCLZHHCBC26"]}],"count2025":23,"conference2025":17,"journal2025":6,"preprint2025":8,"status":"verified","notes":"身份已通过机构/个人主页或 DBLP 机构信息核对；篇数为数据库记录统计，不表示每篇均由本人主导。","retrievedAt":"2026-10-19","yearPolicy":"DBLP yearOfPublication = 2025","queryUrl":"https://sparql.dblp.org/sparql?query=PREFIX%20dblp%3A%20%3Chttps%3A//dblp.org/rdf/schema%23%3E%20PREFIX%20xsd%3A%20%3Chttp%3A//www.w3.org/2001/XMLSchema%23%3E%20SELECT%20%3Fpub%20%3Ftitle%20%3Ftype%20%3Fvenue%20WHERE%20%7B%20%3Fpub%20dblp%3AauthoredBy%20%3Chttps%3A//dblp.org/pid/28/7484%3E%3B%20dblp%3AyearOfPublication%20%222025%22%5E%5Exsd%3AgYear%3B%20dblp%3Atitle%20%3Ftitle%3B%20a%20%3Ftype%20.%20OPTIONAL%20%7B%20%3Fpub%20dblp%3ApublishedIn%20%3Fvenue%20%7D%20%7D&format=json","papers":[{"key":"conf/aaai/YangZSAZBYC25","title":"GURecon: Learning Detailed 3D Geometric Uncertainties for Neural Surface Reconstruction.","type":"Inproceedings","venue":"AAAI","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1609/AAAI.V39I9.33014","sourceUrl":"https://dblp.org/rec/conf/aaai/YangZSAZBYC25","documentUrl":"https://doi.org/10.1609/AAAI.V39I9.33014","pages":"9363-9372"},{"key":"conf/cikm/GaoZPBZC25","title":"Bidirectional Temporal-Aware Modeling with Multi-Scale Mixture-of-Experts for Multivariate Time Series Forecasting.","type":"Inproceedings","venue":"CIKM","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1145/3746252.3761273","sourceUrl":"https://dblp.org/rec/conf/cikm/GaoZPBZC25","documentUrl":"https://doi.org/10.1145/3746252.3761273","pages":"696-706"},{"key":"conf/cvpr/Bao0YS0PC25","title":"Free360: Layered Gaussian Splatting for Unbounded 360-Degree View Synthesis from Extremely Sparse and Unposed Views.","type":"Inproceedings","venue":"CVPR","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/CVPR52734.2025.01527","sourceUrl":"https://dblp.org/rec/conf/cvpr/Bao0YS0PC25","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Bao_Free360_Layered_Gaussian_Splatting_for_Unbounded_360-Degree_View_Synthesis_from_CVPR_2025_paper.html","pages":"16377-16387"},{"key":"conf/cvpr/LiBTCF025","title":"IM-Portrait: Learning 3D-aware Video Diffusion for Photorealistic Talking Heads from Monocular VideosC.","type":"Inproceedings","venue":"CVPR","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/CVPR52734.2025.01966","sourceUrl":"https://dblp.org/rec/conf/cvpr/LiBTCF025","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Li_IM-Portrait_Learning_3D-aware_Video_Diffusion_for_Photorealistic_Talking_Heads_from_CVPR_2025_paper.html","pages":"21107-21116"},{"key":"conf/eccv/HuCFLYBZC24","title":"CG-SLAM: Efficient Dense RGB-D SLAM in a Consistent Uncertainty-Aware 3D Gaussian Field.","type":"Inproceedings","venue":"ECCV (25)","year":2025,"yearOfPublication":2025,"yearOfEvent":2024,"doi":"https://doi.org/10.1007/978-3-031-72698-9_6","sourceUrl":"https://dblp.org/rec/conf/eccv/HuCFLYBZC24","documentUrl":"https://doi.org/10.1007/978-3-031-72698-9_6","pages":"93-112"},{"key":"conf/eccv/LiSHCBSWSBCZL24","title":"BlinkVision: A Benchmark for Optical Flow, Scene Flow and Point Tracking Estimation Using RGB Frames and Events.","type":"Inproceedings","venue":"ECCV (67)","year":2025,"yearOfPublication":2025,"yearOfEvent":2024,"doi":"https://doi.org/10.1007/978-3-031-72855-6_2","sourceUrl":"https://dblp.org/rec/conf/eccv/LiSHCBSWSBCZL24","documentUrl":"https://doi.org/10.1007/978-3-031-72855-6_2","pages":"19-36"},{"key":"conf/iccv/MaoSCZHBC25","title":"AccidentalGS: 3D Gaussian Splatting from Accidental Camera Motion.","type":"Inproceedings","venue":"ICCV","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/ICCV51701.2025.02548","sourceUrl":"https://dblp.org/rec/conf/iccv/MaoSCZHBC25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.02548","pages":"27445-27455"},{"key":"conf/iccv/ShenLCLHBCZ25","title":"BlinkTrack: Feature Tracking Over 80 FPS via Events and Images.","type":"Inproceedings","venue":"ICCV","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/ICCV51701.2025.00868","sourceUrl":"https://dblp.org/rec/conf/iccv/ShenLCLHBCZ25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.00868","pages":"9298-9308"},{"key":"conf/iccv/WangHBZBCZ25","title":"LightCity: An Urban Dataset for Outdoor Inverse Rendering and Reconstruction Under Multi-Illumination Conditions.","type":"Inproceedings","venue":"ICCV","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/ICCV51701.2025.02457","sourceUrl":"https://dblp.org/rec/conf/iccv/WangHBZBCZ25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.02457","pages":"26477-26487"},{"key":"conf/iccv/YangYCMDCCB25","title":"InstaScene: Towards Complete 3D Instance Decomposition and Reconstruction From Cluttered Scenes.","type":"Inproceedings","venue":"ICCV","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/ICCV51701.2025.00729","sourceUrl":"https://dblp.org/rec/conf/iccv/YangYCMDCCB25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.00729","pages":"7771-7781"},{"key":"conf/iccv/ZengZHSDBC25","title":"GaussianUpdate: Continual 3D Gaussian Splatting Update for Changing Environments.","type":"Inproceedings","venue":"ICCV","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/ICCV51701.2025.02393","sourceUrl":"https://dblp.org/rec/conf/iccv/ZengZHSDBC25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.02393","pages":"25800-25809"},{"key":"conf/icra/ZhaiZLPHCBZ25","title":"Neuraloc: Visual Localization in Neural Implicit Map With Dual Complementary Features.","type":"Inproceedings","venue":"ICRA","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/ICRA55743.2025.11127718","sourceUrl":"https://dblp.org/rec/conf/icra/ZhaiZLPHCBZ25","documentUrl":"https://doi.org/10.1109/ICRA55743.2025.11127718","pages":"11706-11713"},{"key":"conf/icxr/Chen0C024","title":"Learning Dynamic Cloth Deformation for Virtual Try-on.","type":"Inproceedings","venue":"ICXR","year":2025,"yearOfPublication":2025,"yearOfEvent":2024,"doi":"https://doi.org/10.1007/978-981-96-3679-2_5","sourceUrl":"https://dblp.org/rec/conf/icxr/Chen0C024","documentUrl":"https://doi.org/10.1007/978-981-96-3679-2_5","pages":"62-76"},{"key":"conf/iros/ChenGPSZBC25","title":"DW-VIO: Deep Weighted Visual-Inertial Odometry.","type":"Inproceedings","venue":"IROS","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/IROS60139.2025.11246552","sourceUrl":"https://dblp.org/rec/conf/iros/ChenGPSZBC25","documentUrl":"https://doi.org/10.1109/IROS60139.2025.11246552","pages":"15150-15157"},{"key":"conf/mir/Cui0DYBC25","title":"CFSynthesis: Controllable and Free-view 3D Human Video Synthesis.","type":"Inproceedings","venue":"ICMR","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1145/3731715.3733286","sourceUrl":"https://dblp.org/rec/conf/mir/Cui0DYBC25","documentUrl":"https://doi.org/10.1145/3731715.3733286","pages":"135-144"},{"key":"conf/mm/DongYYL0BMC25","title":"HiScene: Creating Hierarchical 3D Scenes with Isometric View Generation.","type":"Inproceedings","venue":"ACM Multimedia","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1145/3746027.3755132","sourceUrl":"https://dblp.org/rec/conf/mm/DongYYL0BMC25","documentUrl":"https://doi.org/10.1145/3746027.3755132","pages":"9783-9792"},{"key":"conf/nips/ZhangBCZDBCZ25","title":"AtlasGS: Atlanta-world Guided Surface Reconstruction with Implicit Structured Gaussians.","type":"Inproceedings","venue":"NeurIPS","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":null,"sourceUrl":"https://dblp.org/rec/conf/nips/ZhangBCZDBCZ25","documentUrl":"http://papers.nips.cc/paper_files/paper/2025/hash/171bbefe4954adf5d2758cfc27b7cad4-Abstract-Conference.html","pages":null},{"key":"journals/cmig/XuZXSSSWCW25","title":"AtlasSeg: Atlas prior guided dual-U-Net for tissue segmentation in fetal brain MRI.","type":"Article","venue":"Comput. Medical Imaging Graph.","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.1016/J.COMPMEDIMAG.2025.102662","sourceUrl":"https://dblp.org/rec/journals/cmig/XuZXSSSWCW25","documentUrl":"https://doi.org/10.1016/J.COMPMEDIMAG.2025.102662","pages":"102662"},{"key":"journals/cvm/DangDYYLMC25","title":"TexPro: Text-Guided PBR Texturing with Procedural Material Modeling.","type":"Article","venue":"Comput. Vis. Media","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.26599/CVM.2025.9450489","sourceUrl":"https://dblp.org/rec/journals/cvm/DangDYYLMC25","documentUrl":"https://doi.org/10.26599/CVM.2025.9450489","pages":"745-761"},{"key":"journals/mia/ZhengYCZAW25","title":"An extragradient and noise-tuning adaptive iterative network for diffusion MRI-based microstructural estimation.","type":"Article","venue":"Medical Image Anal.","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.1016/J.MEDIA.2025.103535","sourceUrl":"https://dblp.org/rec/journals/mia/ZhengYCZAW25","documentUrl":"https://doi.org/10.1016/J.MEDIA.2025.103535","pages":"103535"},{"key":"journals/pami/BaoLYSBCZZ25","title":"NeuMesh++: Toward Versatile and Efficient Volumetric Editing With Disentangled Neural Mesh-Based Implicit Field.","type":"Article","venue":"IEEE Trans. Pattern Anal. Mach. Intell.","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.1109/TPAMI.2025.3600473","sourceUrl":"https://dblp.org/rec/journals/pami/BaoLYSBCZZ25","documentUrl":"https://doi.org/10.1109/TPAMI.2025.3600473","pages":"11579-11595"},{"key":"journals/tcsv/RanLYHCBSC25","title":"CT-NeRF: Incremental Optimization of Neural Radiance Field and Camera Poses With Complex Trajectory.","type":"Article","venue":"IEEE Trans. Circuits Syst. Video Technol.","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.1109/TCSVT.2025.3560900","sourceUrl":"https://dblp.org/rec/journals/tcsv/RanLYHCBSC25","documentUrl":"https://doi.org/10.1109/TCSVT.2025.3560900","pages":"10110-10121"},{"key":"journals/tvcg/ZhaiZZLHCBZ25","title":"SplatLoc: 3D Gaussian Splatting-based Visual Localization for Augmented Reality.","type":"Article","venue":"IEEE Trans. Vis. Comput. Graph.","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.1109/TVCG.2025.3549563","sourceUrl":"https://dblp.org/rec/journals/tvcg/ZhaiZZLHCBZ25","documentUrl":"https://doi.org/10.1109/TVCG.2025.3549563","pages":"3591-3601"}],"preprints":[{"key":"journals/corr/abs-2503-06117","title":"NeuraLoc: Visual Localization in Neural Implicit Map with Dual Complementary Features.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2503.06117","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-06117","documentUrl":"https://doi.org/10.48550/ARXIV.2503.06117","pages":null,"arxivId":"2503.06117","arxivUrl":"https://arxiv.org/abs/2503.06117"},{"key":"journals/corr/abs-2503-24382","title":"Free360: Layered Gaussian Splatting for Unbounded 360-Degree View Synthesis from Extremely Sparse and Unposed Views.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2503.24382","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-24382","documentUrl":"https://doi.org/10.48550/ARXIV.2503.24382","pages":null,"arxivId":"2503.24382","arxivUrl":"https://arxiv.org/abs/2503.24382"},{"key":"journals/corr/abs-2504-13072","title":"HiScene: Creating Hierarchical 3D Scenes with Isometric View Generation.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2504.13072","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2504-13072","documentUrl":"https://doi.org/10.48550/ARXIV.2504.13072","pages":null,"arxivId":"2504.13072","arxivUrl":"https://arxiv.org/abs/2504.13072"},{"key":"journals/corr/abs-2504-19165","title":"IM-Portrait: Learning 3D-aware Video Diffusion for Photorealistic Talking Heads from Monocular Videos.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2504.19165","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2504-19165","documentUrl":"https://doi.org/10.48550/ARXIV.2504.19165","pages":null,"arxivId":"2504.19165","arxivUrl":"https://arxiv.org/abs/2504.19165"},{"key":"journals/corr/abs-2506-14315","title":"ImmerseGen: Agent-Guided Immersive World Generation with Alpha-Textured Proxies.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2506.14315","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-14315","documentUrl":"https://doi.org/10.48550/ARXIV.2506.14315","pages":null,"arxivId":"2506.14315","arxivUrl":"https://arxiv.org/abs/2506.14315"},{"key":"journals/corr/abs-2507-08416","title":"InstaScene: Towards Complete 3D Instance Decomposition and Reconstruction from Cluttered Scenes.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2507.08416","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2507-08416","documentUrl":"https://doi.org/10.48550/ARXIV.2507.08416","pages":null,"arxivId":"2507.08416","arxivUrl":"https://arxiv.org/abs/2507.08416"},{"key":"journals/corr/abs-2508-08867","title":"GaussianUpdate: Continual 3D Gaussian Splatting Update for Changing Environments.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2508.08867","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-08867","documentUrl":"https://doi.org/10.48550/ARXIV.2508.08867","pages":null,"arxivId":"2508.08867","arxivUrl":"https://arxiv.org/abs/2508.08867"},{"key":"journals/corr/abs-2510-25129","title":"AtlasGS: Atlanta-world Guided Surface Reconstruction with Implicit Structured Gaussians.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2510.25129","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-25129","documentUrl":"https://doi.org/10.48550/ARXIV.2510.25129","pages":null,"arxivId":"2510.25129","arxivUrl":"https://arxiv.org/abs/2510.25129"}],"excludedFormal":[],"labName":"State Key Laboratory of CAD&CG","labUrl":null,"labEvidence":"本人主页明确 affiliated with the State Key Laboratory of CAD&CG；这是公开所属的共享实验室，并非以个人命名或独占的组。缓存没有给出可确认的实验室网址。","labSourceUrl":"https://zhpcui.github.io/","affiliationZh":"浙江大学","sourceWarning":false,"excludedOther":[],"excludedHomonyms":[],"unassignedCandidates":[],"knownPreprintMinimum2025":null,"excludedMisattributed":[],"displayNotes":"身份已经机构或个人主页核对。2025 年正式记录 23 条（会议 17、期刊 6），所有作者位置均计入，不表示主导或贡献份额；预印本 8 条单列，不加总。","labDisplayNotes":"个人主页写明隶属 CAD&CG 全国重点实验室。该实验室在本页有 4 位联署者（崔兆鹏、沈春华、章国锋、周晓巍），按共同的上级实验室合为一组，去重后 112 条。这不是单一 PI 的团队，分组也远非全实验室的产量。"},{"index":35,"name":"Yuchao Dai","nameZh":"戴玉超","role":"Professor","affiliation":"Northwestern Polytechnical University","source":"DBLP official SPARQL","profileUrl":"https://dblp.org/pid/65/7804","identifier":"65/7804","identityEvidence":[{"url":"https://dblp.org/pid/65/7804","evidence":"DBLP 唯一同名作者档案；通过作者/机构主页与发表题名交叉核对。"},{"url":"https://sites.google.com/site/daiyuchao/","evidence":"作者本人主页确认姓名与声明中的任职机构；发表列表与 DBLP 档案交叉核对。"},{"url":"https://sites.google.com/site/daiyuchao/publication","evidence":"作者/机构页面与该 DBLP 档案交叉匹配的题名示例：Multi-Body Non-Rigid Structure-from-Motion.；Rotation Averaging with Application to Camera-Rig Calibration.","matchedPaperKeys":["conf/3dim/KumarDL16","conf/accv/DaiTLBH09"]}],"count2025":18,"conference2025":11,"journal2025":7,"preprint2025":10,"status":"verified","notes":"身份已通过机构/个人主页或 DBLP 机构信息核对；篇数为数据库记录统计，不表示每篇均由本人主导。","retrievedAt":"2026-10-19","yearPolicy":"DBLP yearOfPublication = 2025","queryUrl":"https://sparql.dblp.org/sparql?query=PREFIX%20dblp%3A%20%3Chttps%3A//dblp.org/rdf/schema%23%3E%20PREFIX%20xsd%3A%20%3Chttp%3A//www.w3.org/2001/XMLSchema%23%3E%20SELECT%20%3Fpub%20%3Ftitle%20%3Ftype%20%3Fvenue%20WHERE%20%7B%20%3Fpub%20dblp%3AauthoredBy%20%3Chttps%3A//dblp.org/pid/65/7804%3E%3B%20dblp%3AyearOfPublication%20%222025%22%5E%5Exsd%3AgYear%3B%20dblp%3Atitle%20%3Ftitle%3B%20a%20%3Ftype%20.%20OPTIONAL%20%7B%20%3Fpub%20dblp%3ApublishedIn%20%3Fvenue%20%7D%20%7D&format=json","papers":[{"key":"conf/aaai/DengSQZD25","title":"Deep Non-Rigid Structure-from-Motion Revisited: Canonicalization and Sequence Modeling.","type":"Inproceedings","venue":"AAAI","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1609/AAAI.V39I3.32272","sourceUrl":"https://dblp.org/rec/conf/aaai/DengSQZD25","documentUrl":"https://doi.org/10.1609/AAAI.V39I3.32272","pages":"2681-2689"},{"key":"conf/aaai/WangZHLD25","title":"Geometry-Aware 3D Salient Object Detection Network.","type":"Inproceedings","venue":"AAAI","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1609/AAAI.V39I7.32813","sourceUrl":"https://dblp.org/rec/conf/aaai/WangZHLD25","documentUrl":"https://doi.org/10.1609/AAAI.V39I7.32813","pages":"7554-7562"},{"key":"conf/apsipa/CaoHDH24","title":"LoFLAT: Local Feature Matching using Focused Linear Attention Transformer.","type":"Inproceedings","venue":"APSIPA","year":2025,"yearOfPublication":2025,"yearOfEvent":2024,"doi":"https://doi.org/10.1109/APSIPAASC63619.2025.10848757","sourceUrl":"https://dblp.org/rec/conf/apsipa/CaoHDH24","documentUrl":"https://doi.org/10.1109/APSIPAASC63619.2025.10848757","pages":"1-6"},{"key":"conf/apsipa/GaoLHD25","title":"DP-GS: Depth-prior & Perception-guided Gaussian Splatting for Sparse-view Novel View Synthesis.","type":"Inproceedings","venue":"APSIPA","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/APSIPAASC65261.2025.11249362","sourceUrl":"https://dblp.org/rec/conf/apsipa/GaoLHD25","documentUrl":"https://doi.org/10.1109/APSIPAASC65261.2025.11249362","pages":"1975-1980"},{"key":"conf/apsipa/HeDHD25","title":"Sequence Modeling and Generative Model Driven Non-Rigid 3D Reconstruction.","type":"Inproceedings","venue":"APSIPA","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/APSIPAASC65261.2025.11249041","sourceUrl":"https://dblp.org/rec/conf/apsipa/HeDHD25","documentUrl":"https://doi.org/10.1109/APSIPAASC65261.2025.11249041","pages":"2394-2399"},{"key":"conf/apsipa/HuangWLZHD24","title":"Ev3DGS: Event Enhanced 3D Gaussian Splatting from Blurry Images.","type":"Inproceedings","venue":"APSIPA","year":2025,"yearOfPublication":2025,"yearOfEvent":2024,"doi":"https://doi.org/10.1109/APSIPAASC63619.2025.10848695","sourceUrl":"https://dblp.org/rec/conf/apsipa/HuangWLZHD24","documentUrl":"https://doi.org/10.1109/APSIPAASC63619.2025.10848695","pages":"1-6"},{"key":"conf/apsipa/LanHD25","title":"DCB: An Efficient Approach for Building Long-Range Dependencies in CNNs.","type":"Inproceedings","venue":"APSIPA","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/APSIPAASC65261.2025.11249096","sourceUrl":"https://dblp.org/rec/conf/apsipa/LanHD25","documentUrl":"https://doi.org/10.1109/APSIPAASC65261.2025.11249096","pages":"2276-2281"},{"key":"conf/apsipa/Zhang0HD24","title":"A Two-Stage Method for 3D Architecture Wireframe Reconstruction from Airborne LiDAR Point Cloud.","type":"Inproceedings","venue":"APSIPA","year":2025,"yearOfPublication":2025,"yearOfEvent":2024,"doi":"https://doi.org/10.1109/APSIPAASC63619.2025.10849258","sourceUrl":"https://dblp.org/rec/conf/apsipa/Zhang0HD24","documentUrl":"https://doi.org/10.1109/APSIPAASC63619.2025.10849258","pages":"1-6"},{"key":"conf/iccv/LiuSDD25","title":"MixRI: Mixing Features of Reference Images for Novel Object Pose Estimation.","type":"Inproceedings","venue":"ICCV","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/ICCV51701.2025.00844","sourceUrl":"https://dblp.org/rec/conf/iccv/LiuSDD25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.00844","pages":"9024-9035"},{"key":"conf/iccv/RenXZD25","title":"PanoSplatt3R: Leveraging Perspective Pretraining for Generalized Unposed Wide-Baseline Panorama Reconstruction.","type":"Inproceedings","venue":"ICCV","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/ICCV51701.2025.02689","sourceUrl":"https://dblp.org/rec/conf/iccv/RenXZD25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.02689","pages":"28959-28969"},{"key":"conf/iccv/WanLDL25","title":"Event-Aided Dense and Continuous Point Tracking: Everywhere and Anytime.","type":"Inproceedings","venue":"ICCV","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/ICCV51701.2025.00744","sourceUrl":"https://dblp.org/rec/conf/iccv/WanLDL25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.00744","pages":"7936-7946"},{"key":"journals/bigdatama/WangDMD25","title":"ETV-MVS: Robust Visibility-Aware Multi-View Stereo with Epipolar Line-Based Transformer.","type":"Article","venue":"Big Data Min. Anal.","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.26599/BDMA.2024.9020075","sourceUrl":"https://dblp.org/rec/journals/bigdatama/WangDMD25","documentUrl":"https://doi.org/10.26599/BDMA.2024.9020075","pages":"520-533"},{"key":"journals/ijcv/WanFHDL25","title":"Instance-Level Moving Object Segmentation from a Single Image with Events.","type":"Article","venue":"Int. J. Comput. Vis.","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.1007/S11263-025-02380-Z","sourceUrl":"https://dblp.org/rec/journals/ijcv/WanFHDL25","documentUrl":"https://doi.org/10.1007/S11263-025-02380-Z","pages":"4042-4063"},{"key":"journals/pr/ShenLWRLDZ25","title":"Constraining multimodal distribution for domain adaptation in stereo matching.","type":"Article","venue":"Pattern Recognit.","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.1016/J.PATCOG.2025.111727","sourceUrl":"https://dblp.org/rec/journals/pr/ShenLWRLDZ25","documentUrl":"https://doi.org/10.1016/J.PATCOG.2025.111727","pages":"111727"},{"key":"journals/ral/WangDSXLLD25","title":"LoopRefine: Deep Camera Pose Estimation With Loop Consistency.","type":"Article","venue":"IEEE Robotics Autom. Lett.","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.1109/LRA.2025.3581044","sourceUrl":"https://dblp.org/rec/journals/ral/WangDSXLLD25","documentUrl":"https://doi.org/10.1109/LRA.2025.3581044","pages":"8003-8010"},{"key":"journals/tcsv/FanGDXS25","title":"Self-Supervised Learning for Rolling Shutter Temporal Super-Resolution.","type":"Article","venue":"IEEE Trans. Circuits Syst. Video Technol.","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.1109/TCSVT.2024.3462520","sourceUrl":"https://dblp.org/rec/journals/tcsv/FanGDXS25","documentUrl":"https://doi.org/10.1109/TCSVT.2024.3462520","pages":"769-782"},{"key":"journals/tcsv/MaoZWTLLD25","title":"Generative Transformer for Accurate and Reliable Salient Object Detection.","type":"Article","venue":"IEEE Trans. Circuits Syst. Video Technol.","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.1109/TCSVT.2024.3469286","sourceUrl":"https://dblp.org/rec/journals/tcsv/MaoZWTLLD25","documentUrl":"https://doi.org/10.1109/TCSVT.2024.3469286","pages":"1041-1054"},{"key":"journals/tip/MaoZXLLZD25","title":"Contrastive Conditional Latent Diffusion for Audio-Visual Segmentation.","type":"Article","venue":"IEEE Trans. Image Process.","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.1109/TIP.2025.3580269","sourceUrl":"https://dblp.org/rec/journals/tip/MaoZXLLZD25","documentUrl":"https://doi.org/10.1109/TIP.2025.3580269","pages":"4108-4119"}],"preprints":[{"key":"journals/corr/abs-2502-12975","title":"Instance-Level Moving Object Segmentation from a Single Image with Events.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2502.12975","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2502-12975","documentUrl":"https://doi.org/10.48550/ARXIV.2502.12975","pages":null,"arxivId":"2502.12975","arxivUrl":"https://arxiv.org/abs/2502.12975"},{"key":"journals/corr/abs-2502-16488","title":"Geometry-Aware 3D Salient Object Detection Network.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2502.16488","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2502-16488","documentUrl":"https://doi.org/10.48550/ARXIV.2502.16488","pages":null,"arxivId":"2502.16488","arxivUrl":"https://arxiv.org/abs/2502.16488"},{"key":"journals/corr/abs-2504-17732","title":"DPMambaIR:All-in-One Image Restoration via Degradation-Aware Prompt State Space Model.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2504.17732","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2504-17732","documentUrl":"https://doi.org/10.48550/ARXIV.2504.17732","pages":null,"arxivId":"2504.17732","arxivUrl":"https://arxiv.org/abs/2504.17732"},{"key":"journals/corr/abs-2504-21302","title":"CMD: Constraining Multimodal Distribution for Domain Adaptation in Stereo Matching.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2504.21302","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2504-21302","documentUrl":"https://doi.org/10.48550/ARXIV.2504.21302","pages":null,"arxivId":"2504.21302","arxivUrl":"https://arxiv.org/abs/2504.21302"},{"key":"journals/corr/abs-2505-18129","title":"One RL to See Them All: Visual Triple Unified Reinforcement Learning.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2505.18129","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-18129","documentUrl":"https://doi.org/10.48550/ARXIV.2505.18129","pages":null,"arxivId":"2505.18129","arxivUrl":"https://arxiv.org/abs/2505.18129"},{"key":"journals/corr/abs-2505-22499","title":"The Meeseeks Mesh: Spatially Consistent 3D Adversarial Objects for BEV Detector.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2505.22499","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-22499","documentUrl":"https://doi.org/10.48550/ARXIV.2505.22499","pages":null,"arxivId":"2505.22499","arxivUrl":"https://arxiv.org/abs/2505.22499"},{"key":"journals/corr/abs-2507-01652","title":"Autoregressive Image Generation with Linear Complexity: A Spatial-Aware Decay Perspective.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2507.01652","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2507-01652","documentUrl":"https://doi.org/10.48550/ARXIV.2507.01652","pages":null,"arxivId":"2507.01652","arxivUrl":"https://arxiv.org/abs/2507.01652"},{"key":"journals/corr/abs-2507-21960","title":"PanoSplatt3R: Leveraging Perspective Pretraining for Generalized Unposed Wide-Baseline Panorama Reconstruction.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2507.21960","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2507-21960","documentUrl":"https://doi.org/10.48550/ARXIV.2507.21960","pages":null,"arxivId":"2507.21960","arxivUrl":"https://arxiv.org/abs/2507.21960"},{"key":"journals/corr/abs-2508-09525","title":"Learning Spatial Decay for Vision Transformers.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2508.09525","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-09525","documentUrl":"https://doi.org/10.48550/ARXIV.2508.09525","pages":null,"arxivId":"2508.09525","arxivUrl":"https://arxiv.org/abs/2508.09525"},{"key":"journals/corr/abs-2509-03872","title":"Focus Through Motion: RGB-Event Collaborative Token Sparsification for Efficient Object Detection.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2509.03872","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-03872","documentUrl":"https://doi.org/10.48550/ARXIV.2509.03872","pages":null,"arxivId":"2509.03872","arxivUrl":"https://arxiv.org/abs/2509.03872"}],"excludedFormal":[],"labName":null,"labUrl":null,"labEvidence":"本轮个人主页及团队检索没有确认当前具名 Lab；检索中的 ANU 访学时期关联属于历史信息，不据此填当前实验室。","labSourceUrl":"https://sites.google.com/site/daiyuchao/","affiliationZh":"西北工业大学","sourceWarning":false,"excludedOther":[],"excludedHomonyms":[],"unassignedCandidates":[],"knownPreprintMinimum2025":null,"excludedMisattributed":[],"displayNotes":"身份已经机构或个人主页核对。2025 年正式记录 18 条（会议 11、期刊 7），所有作者位置均计入，不表示主导或贡献份额；预印本 10 条单列，不加总。","labDisplayNotes":"本人主页与本轮检索都未确认当前具名的实验室；ANU 时期的关联属于历史信息，不采用。图中以「姓名及合作者」单列。"},{"index":36,"name":"Hao Dong","nameZh":"董豪","role":"Tenured Associate Professor","affiliation":"Peking University","source":"DBLP official SPARQL","profileUrl":"https://dblp.org/pid/14/1525-3","identifier":"14/1525-3","identityEvidence":[{"url":"https://dblp.org/pid/14/1525-3","evidence":"DBLP 档案名 Hao Dong 0003；机构/履历：Imperial College London, Department of Computing, UK；Peking University, PKU-Agibot Lab, Center on Frontiers of Computing Studies, School of Computer Science, Beijing, China"}],"count2025":27,"conference2025":27,"journal2025":0,"preprint2025":32,"status":"verified","notes":"身份已通过机构/个人主页或 DBLP 机构信息核对；篇数为数据库记录统计，不表示每篇均由本人主导。","retrievedAt":"2026-10-19","yearPolicy":"DBLP yearOfPublication = 2025","queryUrl":"https://sparql.dblp.org/sparql?query=PREFIX%20dblp%3A%20%3Chttps%3A//dblp.org/rdf/schema%23%3E%20PREFIX%20xsd%3A%20%3Chttp%3A//www.w3.org/2001/XMLSchema%23%3E%20SELECT%20%3Fpub%20%3Ftitle%20%3Ftype%20%3Fvenue%20WHERE%20%7B%20%3Fpub%20dblp%3AauthoredBy%20%3Chttps%3A//dblp.org/pid/14/1525-3%3E%3B%20dblp%3AyearOfPublication%20%222025%22%5E%5Exsd%3AgYear%3B%20dblp%3Atitle%20%3Ftitle%3B%20a%20%3Ftype%20.%20OPTIONAL%20%7B%20%3Fpub%20dblp%3ApublishedIn%20%3Fvenue%20%7D%20%7D&format=json","papers":[{"key":"conf/cvpr/0009XZ00PXH0Z025","title":"Object-Centric Prompt-Driven Vision-Language-Action Model for Robotic Manipulation.","type":"Inproceedings","venue":"CVPR","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/CVPR52734.2025.02574","sourceUrl":"https://dblp.org/rec/conf/cvpr/0009XZ00PXH0Z025","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Li_Object-Centric_Prompt-Driven_Vision-Language-Action_Model_for_Robotic_Manipulation_CVPR_2025_paper.html","pages":"27638-27648"},{"key":"conf/cvpr/GaoPGZLDT0025","title":"PartRM: Modeling Part-Level Dynamics with Large Cross-State Reconstruction Model.","type":"Inproceedings","venue":"CVPR","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/CVPR52734.2025.00657","sourceUrl":"https://dblp.org/rec/conf/cvpr/GaoPGZLDT0025","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Gao_PartRM_Modeling_Part-Level_Dynamics_with_Large_Cross-State_Reconstruction_Model_CVPR_2025_paper.html","pages":"7004-7014"},{"key":"conf/cvpr/LongZPWKD25","title":"CheckManual: A New Challenge and Benchmark for Manual-based Appliance Manipulation.","type":"Inproceedings","venue":"CVPR","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/CVPR52734.2025.02104","sourceUrl":"https://dblp.org/rec/conf/cvpr/LongZPWKD25","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Long_CheckManual_A_New_Challenge_and_Benchmark_for_Manual-based_Appliance_Manipulation_CVPR_2025_paper.html","pages":"22595-22604"},{"key":"conf/cvpr/PanZWZGD25","title":"OmniManip: Towards General Robotic Manipulation via Object-Centric Interaction Primitives as Spatial Constraints.","type":"Inproceedings","venue":"CVPR","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/CVPR52734.2025.01618","sourceUrl":"https://dblp.org/rec/conf/cvpr/PanZWZGD25","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Pan_OmniManip_Towards_General_Robotic_Manipulation_via_Object-Centric_Interaction_Primitives_as_CVPR_2025_paper.html","pages":"17359-17369"},{"key":"conf/cvpr/WuZWCW025","title":"GarmentPile: Point-Level Visual Affordance Guided Retrieval and Adaptation for Cluttered Garments Manipulation.","type":"Inproceedings","venue":"CVPR","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/CVPR52734.2025.00652","sourceUrl":"https://dblp.org/rec/conf/cvpr/WuZWCW025","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Wu_GarmentPile_Point-Level_Visual_Affordance_Guided_Retrieval_and_Adaptation_for_Cluttered_CVPR_2025_paper.html","pages":"6950-6959"},{"key":"conf/cvpr/ZhouHCZX0LYL025","title":"SplatMesh: Interactive 3D Segmentation and Editing Using Mesh-Based Gaussian Splatting.","type":"Inproceedings","venue":"CVPR Workshops","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":null,"sourceUrl":"https://dblp.org/rec/conf/cvpr/ZhouHCZX0LYL025","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025W/CV4Metaverse/html/Zhou_SplatMesh_Interactive_3D_Segmentation_and_Editing_Using_Mesh-Based_Gaussian_Splatting_CVPRW_2025_paper.html","pages":"305-316"},{"key":"conf/eccv/MaDM24","title":"Local Occupancy-Enhanced Object Grasping with Multiple Triplanar Projection.","type":"Inproceedings","venue":"ECCV (74)","year":2025,"yearOfPublication":2025,"yearOfEvent":2024,"doi":"https://doi.org/10.1007/978-3-031-72904-1_1","sourceUrl":"https://dblp.org/rec/conf/eccv/MaDM24","documentUrl":"https://doi.org/10.1007/978-3-031-72904-1_1","pages":"1-18"},{"key":"conf/eccv/ZhangHPWHCZD24","title":"Omni6DPose: A Benchmark and Model for Universal 6D Object Pose Estimation and Tracking.","type":"Inproceedings","venue":"ECCV (75)","year":2025,"yearOfPublication":2025,"yearOfEvent":2024,"doi":"https://doi.org/10.1007/978-3-031-73226-3_12","sourceUrl":"https://dblp.org/rec/conf/eccv/ZhangHPWHCZD24","documentUrl":"https://doi.org/10.1007/978-3-031-73226-3_12","pages":"199-216"},{"key":"conf/iccv/XueLLWDZHC25","title":"GFPack++: Attention-Driven Gradient Fields for Optimizing 2D Irregular Packing.","type":"Inproceedings","venue":"ICCV","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/ICCV51701.2025.01674","sourceUrl":"https://dblp.org/rec/conf/iccv/XueLLWDZHC25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.01674","pages":"18014-18023"},{"key":"conf/iccv/ZhangWWXLXDH25","title":"Adaptive Articulated Object Manipulation on the Fly with Foundation Model Reasoning and Part Grounding.","type":"Inproceedings","venue":"ICCV","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/ICCV51701.2025.01211","sourceUrl":"https://dblp.org/rec/conf/iccv/ZhangWWXLXDH25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.01211","pages":"13032-13042"},{"key":"conf/iclr/TianYZWL0P25","title":"Predictive Inverse Dynamics Models are Scalable Learners for Robotic Manipulation.","type":"Inproceedings","venue":"ICLR","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":null,"sourceUrl":"https://dblp.org/rec/conf/iclr/TianYZWL0P25","documentUrl":"https://openreview.net/forum?id=meRCKuUpmc","pages":null},{"key":"conf/iclr/TieCWDLG025","title":"Et-Seed: Efficient trajectory-Level SE(3) equivariant diffusion Policy.","type":"Inproceedings","venue":"ICLR","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":null,"sourceUrl":"https://dblp.org/rec/conf/iclr/TieCWDLG025","documentUrl":"https://openreview.net/forum?id=OheAR2xrtb","pages":null},{"key":"conf/iclr/WangZWLSWH0025","title":"AdaManip: Adaptive Articulated Object Manipulation Environments and Policy Learning.","type":"Inproceedings","venue":"ICLR","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":null,"sourceUrl":"https://dblp.org/rec/conf/iclr/WangZWLSWH0025","documentUrl":"https://openreview.net/forum?id=Luss2sa0vc","pages":null},{"key":"conf/icml/0035WKSL0FL025","title":"BiAssemble: Learning Collaborative Affordance for Bimanual Geometric Assembly.","type":"Inproceedings","venue":"ICML","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":null,"sourceUrl":"https://dblp.org/rec/conf/icml/0035WKSL0FL025","documentUrl":"https://proceedings.mlr.press/v267/shen25i.html","pages":null},{"key":"conf/icra/CaiPYLYDZ25","title":"SpatialBot: Precise Spatial Understanding with Vision Language Models.","type":"Inproceedings","venue":"ICRA","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/ICRA55743.2025.11128671","sourceUrl":"https://dblp.org/rec/conf/icra/CaiPYLYDZ25","documentUrl":"https://doi.org/10.1109/ICRA55743.2025.11128671","pages":"9490-9498"},{"key":"conf/icra/LiLHHGDL25","title":"3DWG: 3D Weakly Supervised Visual Grounding via Category and Instance-Level Alignment.","type":"Inproceedings","venue":"ICRA","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/ICRA55743.2025.11127295","sourceUrl":"https://dblp.org/rec/conf/icra/LiLHHGDL25","documentUrl":"https://doi.org/10.1109/ICRA55743.2025.11127295","pages":"12766-12773"},{"key":"conf/icra/WangZGFWSXZD25","title":"TransDiff: Diffusion-Based Method for Manipulating Transparent Objects Using a Single RGB-D Image.","type":"Inproceedings","venue":"ICRA","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/ICRA55743.2025.11128239","sourceUrl":"https://dblp.org/rec/conf/icra/WangZGFWSXZD25","documentUrl":"https://doi.org/10.1109/ICRA55743.2025.11128239","pages":"7277-7283"},{"key":"conf/icra/WuLZWD25","title":"Canonical Representation and Force-Based Pretraining of 3D Tactile for Dexterous Visuo-Tactile Policy Learning.","type":"Inproceedings","venue":"ICRA","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/ICRA55743.2025.11128094","sourceUrl":"https://dblp.org/rec/conf/icra/WuLZWD25","documentUrl":"https://doi.org/10.1109/ICRA55743.2025.11128094","pages":"6786-6792"},{"key":"conf/icra/WuZLHD25","title":"Foundation Feature-Driven Online End-Effector Pose Estimation: A Marker-Free and Learning-Free Approach.","type":"Inproceedings","venue":"ICRA","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/ICRA55743.2025.11128327","sourceUrl":"https://dblp.org/rec/conf/icra/WuZLHD25","documentUrl":"https://doi.org/10.1109/ICRA55743.2025.11128327","pages":"1921-1928"},{"key":"conf/iros/HengLMLLWWJGZZD25","title":"RwoR: Generating Robot Demonstrations from Human Hand Collection for Policy Learning without Robot.","type":"Inproceedings","venue":"IROS","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/IROS60139.2025.11246192","sourceUrl":"https://dblp.org/rec/conf/iros/HengLMLLWWJGZZD25","documentUrl":"https://doi.org/10.1109/IROS60139.2025.11246192","pages":"13544-13551"},{"key":"conf/iros/KimBLLPWD25","title":"ManipGPT: Is Affordance Segmentation by Large Vision Models Enough for Articulated Object Manipulation?","type":"Inproceedings","venue":"IROS","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/IROS60139.2025.11246374","sourceUrl":"https://dblp.org/rec/conf/iros/KimBLLPWD25","documentUrl":"https://doi.org/10.1109/IROS60139.2025.11246374","pages":"20974-20981"},{"key":"conf/iros/LiWZCJWSYD25","title":"Adaptive Visuo-Tactile Fusion with Predictive Force Attention for Dexterous Manipulation.","type":"Inproceedings","venue":"IROS","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/IROS60139.2025.11246476","sourceUrl":"https://dblp.org/rec/conf/iros/LiWZCJWSYD25","documentUrl":"https://doi.org/10.1109/IROS60139.2025.11246476","pages":"3232-3239"},{"key":"conf/iros/WuWWHFHGLYYCD25","title":"SimLauncher: Launching Sample-Efficient Real-World Robotic Reinforcement Learning via Simulation Pre-Training.","type":"Inproceedings","venue":"IROS","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/IROS60139.2025.11246668","sourceUrl":"https://dblp.org/rec/conf/iros/WuWWHFHGLYYCD25","documentUrl":"https://doi.org/10.1109/IROS60139.2025.11246668","pages":"7933-7940"},{"key":"conf/iros/ZhangLXZBSXD25","title":"SR3D: Unleashing Single-view 3D Reconstruction for Transparent and Specular Object Grasping.","type":"Inproceedings","venue":"IROS","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/IROS60139.2025.11247370","sourceUrl":"https://dblp.org/rec/conf/iros/ZhangLXZBSXD25","documentUrl":"https://doi.org/10.1109/IROS60139.2025.11247370","pages":"15816-15823"},{"key":"conf/nips/WangWCWLZGMAD25","title":"DexGarmentLab: Dexterous Garment Manipulation Environment with Generalizable Policy.","type":"Inproceedings","venue":"NeurIPS","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":null,"sourceUrl":"https://dblp.org/rec/conf/nips/WangWCWLZGMAD25","documentUrl":"http://papers.nips.cc/paper_files/paper/2025/hash/c20ac0df6c213db6d3a930fe9c7296c8-Abstract-Conference.html","pages":null},{"key":"conf/nips/ZhangMWCD25","title":"CADGrasp: Learning Contact and Collision Aware General Dexterous Grasping in Cluttered Scenes.","type":"Inproceedings","venue":"NeurIPS","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":null,"sourceUrl":"https://dblp.org/rec/conf/nips/ZhangMWCD25","documentUrl":"http://papers.nips.cc/paper_files/paper/2025/hash/2aff7a9ba2c654ad96e24f994c3f11bc-Abstract-Conference.html","pages":null},{"key":"conf/nips/ZhuBXCCLWDYFC25","title":"DexFlyWheel: A Scalable and Self-improving Data Generation Framework for Dexterous Manipulation.","type":"Inproceedings","venue":"NeurIPS","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":null,"sourceUrl":"https://dblp.org/rec/conf/nips/ZhuBXCCLWDYFC25","documentUrl":"http://papers.nips.cc/paper_files/paper/2025/hash/066c5542795287822f4f076cf330e5a2-Abstract-Conference.html","pages":null}],"preprints":[{"key":"journals/corr/abs-2501-03841","title":"OmniManip: Towards General Robotic Manipulation via Object-Centric Interaction Primitives as Spatial Constraints.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2501.03841","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2501-03841","documentUrl":"https://doi.org/10.48550/ARXIV.2501.03841","pages":null,"arxivId":"2501.03841","arxivUrl":"https://arxiv.org/abs/2501.03841"},{"key":"journals/corr/abs-2502-08449","title":"CordViP: Correspondence-based Visuomotor Policy for Dexterous Manipulation in Real-World.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2502.08449","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2502-08449","documentUrl":"https://doi.org/10.48550/ARXIV.2502.08449","pages":null,"arxivId":"2502.08449","arxivUrl":"https://arxiv.org/abs/2502.08449"},{"key":"journals/corr/abs-2502-11124","title":"AdaManip: Adaptive Articulated Object Manipulation Environments and Policy Learning.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2502.11124","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2502-11124","documentUrl":"https://doi.org/10.48550/ARXIV.2502.11124","pages":null,"arxivId":"2502.11124","arxivUrl":"https://arxiv.org/abs/2502.11124"},{"key":"journals/corr/abs-2503-09243","title":"GarmentPile: Point-Level Visual Affordance Guided Retrieval and Adaptation for Cluttered Garments Manipulation.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2503.09243","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-09243","documentUrl":"https://doi.org/10.48550/ARXIV.2503.09243","pages":null,"arxivId":"2503.09243","arxivUrl":"https://arxiv.org/abs/2503.09243"},{"key":"journals/corr/abs-2503-12779","title":"TransDiff: Diffusion-Based Method for Manipulating Transparent Objects Using a Single RGB-D Image.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2503.12779","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-12779","documentUrl":"https://doi.org/10.48550/ARXIV.2503.12779","pages":null,"arxivId":"2503.12779","arxivUrl":"https://arxiv.org/abs/2503.12779"},{"key":"journals/corr/abs-2503-14051","title":"Foundation Feature-Driven Online End-Effector Pose Estimation: A Marker-Free and Learning-Free Approach.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2503.14051","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-14051","documentUrl":"https://doi.org/10.48550/ARXIV.2503.14051","pages":null,"arxivId":"2503.14051","arxivUrl":"https://arxiv.org/abs/2503.14051"},{"key":"journals/corr/abs-2503-19913","title":"PartRM: Modeling Part-Level Dynamics with Large Cross-State Reconstruction Model.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2503.19913","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-19913","documentUrl":"https://doi.org/10.48550/ARXIV.2503.19913","pages":null,"arxivId":"2503.19913","arxivUrl":"https://arxiv.org/abs/2503.19913"},{"key":"journals/corr/abs-2504-07596","title":"Boosting Universal LLM Reward Design through Heuristic Reward Observation Space Evolution.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2504.07596","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2504-07596","documentUrl":"https://doi.org/10.48550/ARXIV.2504.07596","pages":null,"arxivId":"2504.07596","arxivUrl":"https://arxiv.org/abs/2504.07596"},{"key":"journals/corr/abs-2504-18904","title":"RoboVerse: Towards a Unified Platform, Dataset and Benchmark for Scalable and Generalizable Robot Learning.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2504.18904","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2504-18904","documentUrl":"https://doi.org/10.48550/ARXIV.2504.18904","pages":null,"arxivId":"2504.18904","arxivUrl":"https://arxiv.org/abs/2504.18904"},{"key":"journals/corr/abs-2505-01809","title":"3DWG: 3D Weakly Supervised Visual Grounding via Category and Instance-Level Alignment.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2505.01809","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-01809","documentUrl":"https://doi.org/10.48550/ARXIV.2505.01809","pages":null,"arxivId":"2505.01809","arxivUrl":"https://arxiv.org/abs/2505.01809"},{"key":"journals/corr/abs-2505-02166","title":"CrayonRobo: Object-Centric Prompt-Driven Vision-Language-Action Model for Robotic Manipulation.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2505.02166","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-02166","documentUrl":"https://doi.org/10.48550/ARXIV.2505.02166","pages":null,"arxivId":"2505.02166","arxivUrl":"https://arxiv.org/abs/2505.02166"},{"key":"journals/corr/abs-2505-11032","title":"DexGarmentLab: Dexterous Garment Manipulation Environment with Generalizable Policy.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2505.11032","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-11032","documentUrl":"https://doi.org/10.48550/ARXIV.2505.11032","pages":null,"arxivId":"2505.11032","arxivUrl":"https://arxiv.org/abs/2505.11032"},{"key":"journals/corr/abs-2505-13982","title":"Adaptive Visuo-Tactile Fusion with Predictive Force Attention for Dexterous Manipulation.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2505.13982","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-13982","documentUrl":"https://doi.org/10.48550/ARXIV.2505.13982","pages":null,"arxivId":"2505.13982","arxivUrl":"https://arxiv.org/abs/2505.13982"},{"key":"journals/corr/abs-2505-19487","title":"SpikeStereoNet: A Brain-Inspired Framework for Stereo Depth Estimation from Spike Streams.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2505.19487","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-19487","documentUrl":"https://doi.org/10.48550/ARXIV.2505.19487","pages":null,"arxivId":"2505.19487","arxivUrl":"https://arxiv.org/abs/2505.19487"},{"key":"journals/corr/abs-2505-22503","title":"From Strangers to Assistants: Fast Desire Alignment for Embodied Agent-User Adaptation.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2505.22503","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-22503","documentUrl":"https://doi.org/10.48550/ARXIV.2505.22503","pages":null,"arxivId":"2505.22503","arxivUrl":"https://arxiv.org/abs/2505.22503"},{"key":"journals/corr/abs-2505-24305","title":"SR3D: Unleashing Single-view 3D Reconstruction for Transparent and Specular Object Grasping.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2505.24305","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-24305","documentUrl":"https://doi.org/10.48550/ARXIV.2505.24305","pages":null,"arxivId":"2505.24305","arxivUrl":"https://arxiv.org/abs/2505.24305"},{"key":"journals/corr/abs-2506-06221","title":"BiAssemble: Learning Collaborative Affordance for Bimanual Geometric Assembly.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2506.06221","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-06221","documentUrl":"https://doi.org/10.48550/ARXIV.2506.06221","pages":null,"arxivId":"2506.06221","arxivUrl":"https://arxiv.org/abs/2506.06221"},{"key":"journals/corr/abs-2506-09343","title":"CheckManual: A New Challenge and Benchmark for Manual-based Appliance Manipulation.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2506.09343","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-09343","documentUrl":"https://doi.org/10.48550/ARXIV.2506.09343","pages":null,"arxivId":"2506.09343","arxivUrl":"https://arxiv.org/abs/2506.09343"},{"key":"journals/corr/abs-2506-14317","title":"ClutterDexGrasp: A Sim-to-Real System for General Dexterous Grasping in Cluttered Scenes.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2506.14317","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-14317","documentUrl":"https://doi.org/10.48550/ARXIV.2506.14317","pages":null,"arxivId":"2506.14317","arxivUrl":"https://arxiv.org/abs/2506.14317"},{"key":"journals/corr/abs-2507-03930","title":"RwoR: Generating Robot Demonstrations from Human Hand Collection for Policy Learning without Robot.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2507.03930","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2507-03930","documentUrl":"https://doi.org/10.48550/ARXIV.2507.03930","pages":null,"arxivId":"2507.03930","arxivUrl":"https://arxiv.org/abs/2507.03930"},{"key":"journals/corr/abs-2507-04452","title":"SimLauncher: Launching Sample-Efficient Real-world Robotic Reinforcement Learning via Simulation Pre-training.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2507.04452","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2507-04452","documentUrl":"https://doi.org/10.48550/ARXIV.2507.04452","pages":null,"arxivId":"2507.04452","arxivUrl":"https://arxiv.org/abs/2507.04452"},{"key":"journals/corr/abs-2507-18276","title":"Adaptive Articulated Object Manipulation On The Fly with Foundation Model Reasoning and Part Grounding.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2507.18276","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2507-18276","documentUrl":"https://doi.org/10.48550/ARXIV.2507.18276","pages":null,"arxivId":"2507.18276","arxivUrl":"https://arxiv.org/abs/2507.18276"},{"key":"journals/corr/abs-2508-10416","title":"CorrectNav: Self-Correction Flywheel Empowers Vision-Language-Action Navigation Model.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2508.10416","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-10416","documentUrl":"https://doi.org/10.48550/ARXIV.2508.10416","pages":null,"arxivId":"2508.10416","arxivUrl":"https://arxiv.org/abs/2508.10416"},{"key":"journals/corr/abs-2509-17125","title":"Imagine2Act: Leveraging Object-Action Motion Consistency from Imagined Goals for Robotic Manipulation.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2509.17125","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-17125","documentUrl":"https://doi.org/10.48550/ARXIV.2509.17125","pages":null,"arxivId":"2509.17125","arxivUrl":"https://arxiv.org/abs/2509.17125"},{"key":"journals/corr/abs-2509-23829","title":"DexFlyWheel: A Scalable and Self-improving Data Generation Framework for Dexterous Manipulation.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2509.23829","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-23829","documentUrl":"https://doi.org/10.48550/ARXIV.2509.23829","pages":null,"arxivId":"2509.23829","arxivUrl":"https://arxiv.org/abs/2509.23829"},{"key":"journals/corr/abs-2509-24494","title":"GRPO-MA: Multi-Answer Generation in GRPO for Stable and Efficient Chain-of-Thought Training.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2509.24494","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-24494","documentUrl":"https://doi.org/10.48550/ARXIV.2509.24494","pages":null,"arxivId":"2509.24494","arxivUrl":"https://arxiv.org/abs/2509.24494"},{"key":"journals/corr/abs-2509-24797","title":"Fidelity-Aware Data Composition for Robust Robot Generalization.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2509.24797","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-24797","documentUrl":"https://doi.org/10.48550/ARXIV.2509.24797","pages":null,"arxivId":"2509.24797","arxivUrl":"https://arxiv.org/abs/2509.24797"},{"key":"journals/corr/abs-2511-16651","title":"InternData-A1: Pioneering High-Fidelity Synthetic Data for Pre-training Generalist Policy.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2511.16651","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2511-16651","documentUrl":"https://doi.org/10.48550/ARXIV.2511.16651","pages":null,"arxivId":"2511.16651","arxivUrl":"https://arxiv.org/abs/2511.16651"},{"key":"journals/corr/abs-2511-17441","title":"RoboCOIN: An Open-Sourced Bimanual Robotic Data COllection for INtegrated Manipulation.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2511.17441","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2511-17441","documentUrl":"https://doi.org/10.48550/ARXIV.2511.17441","pages":null,"arxivId":"2511.17441","arxivUrl":"https://arxiv.org/abs/2511.17441"},{"key":"journals/corr/abs-2512-00287","title":"RealAppliance: Let High-fidelity Appliance Assets Controllable and Workable as Aligned Real Manuals.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2512.00287","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-00287","documentUrl":"https://doi.org/10.48550/ARXIV.2512.00287","pages":null,"arxivId":"2512.00287","arxivUrl":"https://arxiv.org/abs/2512.00287"},{"key":"journals/corr/abs-2512-19390","title":"TwinAligner: Visual-Dynamic Alignment Empowers Physics-aware Real2Sim2Real for Robotic Manipulation.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2512.19390","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-19390","documentUrl":"https://doi.org/10.48550/ARXIV.2512.19390","pages":null,"arxivId":"2512.19390","arxivUrl":"https://arxiv.org/abs/2512.19390"},{"key":"journals/corr/abs-2512-19402","title":"Real2Edit2Real: Generating Robotic Demonstrations via a 3D Control Interface.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2512.19402","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-19402","documentUrl":"https://doi.org/10.48550/ARXIV.2512.19402","pages":null,"arxivId":"2512.19402","arxivUrl":"https://arxiv.org/abs/2512.19402"}],"excludedFormal":[],"labName":"PKU-Agibot Lab","labUrl":null,"labEvidence":"PKU CFCS 当前公开英文教师页明确 Hao Dong leads PKU-Agibot Lab。本人较新主页另列 PrimeBot 职位但未命名学术组；本条保留院系官方列示关联，不推定 2025 年全年团队组成。","labSourceUrl":"https://cfcs.pku.edu.cn/english/people/faculty/haodong/index.htm","affiliationZh":"北京大学","sourceWarning":false,"excludedOther":[],"excludedHomonyms":[],"unassignedCandidates":[],"knownPreprintMinimum2025":null,"excludedMisattributed":[],"displayNotes":"身份已经机构或个人主页核对。2025 年正式记录 27 条，均为会议论文，所有作者位置均计入，不表示主导或贡献份额；预印本 32 条单列，不加总。","labDisplayNotes":"北大前沿计算研究中心的英文教师页写明其领导 PKU-Agibot Lab，据此归组。本人较新的主页另列 PrimeBot 职务，未写学术组名；这里只表示院系公开的关联，不还原 2025 年的团队组成。"},{"index":37,"name":"Qi Dou","nameZh":"窦琪","role":"Associate Professor","affiliation":"The Chinese University of Hong Kong","source":"DBLP official SPARQL","profileUrl":"https://dblp.org/pid/165/7846","identifier":"165/7846","identityEvidence":[{"url":"https://dblp.org/pid/165/7846","evidence":"DBLP 档案名 Qi Dou 0001；机构/履历：Chinese University of Hong Kong；Imperial College London, UK"}],"count2025":29,"conference2025":14,"journal2025":15,"preprint2025":25,"status":"verified","notes":"身份已通过机构/个人主页或 DBLP 机构信息核对；篇数为数据库记录统计，不表示每篇均由本人主导。","retrievedAt":"2026-10-19","yearPolicy":"DBLP yearOfPublication = 2025","queryUrl":"https://sparql.dblp.org/sparql?query=PREFIX%20dblp%3A%20%3Chttps%3A//dblp.org/rdf/schema%23%3E%20PREFIX%20xsd%3A%20%3Chttp%3A//www.w3.org/2001/XMLSchema%23%3E%20SELECT%20%3Fpub%20%3Ftitle%20%3Ftype%20%3Fvenue%20WHERE%20%7B%20%3Fpub%20dblp%3AauthoredBy%20%3Chttps%3A//dblp.org/pid/165/7846%3E%3B%20dblp%3AyearOfPublication%20%222025%22%5E%5Exsd%3AgYear%3B%20dblp%3Atitle%20%3Ftitle%3B%20a%20%3Ftype%20.%20OPTIONAL%20%7B%20%3Fpub%20dblp%3ApublishedIn%20%3Fvenue%20%7D%20%7D&format=json","papers":[{"key":"conf/acl/WuGG025","title":"DDxTutor: Clinical Reasoning Tutoring System with Differential Diagnosis-Based Structured Reasoning.","type":"Inproceedings","venue":"ACL (1)","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.18653/V1/2025.ACL-LONG.1495","sourceUrl":"https://dblp.org/rec/conf/acl/WuGG025","documentUrl":"https://doi.org/10.18653/V1/2025.ACL-LONG.1495","pages":"30934-30957"},{"key":"conf/cvpr/FuZC025","title":"Hybrid Reciprocal Transformer with Triplet Feature Alignment for Scene Graph Generation.","type":"Inproceedings","venue":"CVPR","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/CVPR52734.2025.00837","sourceUrl":"https://dblp.org/rec/conf/cvpr/FuZC025","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Fu_Hybrid_Reciprocal_Transformer_with_Triplet_Feature_Alignment_for_Scene_Graph_CVPR_2025_paper.html","pages":"8953-8963"},{"key":"conf/eccv/MaCTWNKD24","title":"Shape-Guided Configuration-Aware Learning for Endoscopic-Image-Based Pose Estimation of Flexible Robotic Instruments.","type":"Inproceedings","venue":"ECCV (22)","year":2025,"yearOfPublication":2025,"yearOfEvent":2024,"doi":"https://doi.org/10.1007/978-3-031-72670-5_15","sourceUrl":"https://dblp.org/rec/conf/eccv/MaCTWNKD24","documentUrl":"https://doi.org/10.1007/978-3-031-72670-5_15","pages":"259-276"},{"key":"conf/eccv/XuWYFDH24","title":"Towards Real-World Adverse Weather Image Restoration: Enhancing Clearness and Semantics with Vision-Language Models.","type":"Inproceedings","venue":"ECCV (18)","year":2025,"yearOfPublication":2025,"yearOfEvent":2024,"doi":"https://doi.org/10.1007/978-3-031-72649-1_9","sourceUrl":"https://dblp.org/rec/conf/eccv/XuWYFDH24","documentUrl":"https://doi.org/10.1007/978-3-031-72649-1_9","pages":"147-164"},{"key":"conf/emnlp/HuLWZSZDLZL25","title":"LM-Searcher: Cross-domain Neural Architecture Search with LLMs via Unified Numerical Encoding.","type":"Inproceedings","venue":"EMNLP","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.18653/V1/2025.EMNLP-MAIN.478","sourceUrl":"https://dblp.org/rec/conf/emnlp/HuLWZSZDLZL25","documentUrl":"https://doi.org/10.18653/V1/2025.EMNLP-MAIN.478","pages":"9408-9421"},{"key":"conf/emnlp/WuGGHLD25","title":"HealthCards: Exploring Text-to-Image Generation as Visual Aids for Healthcare Knowledge Democratizing and Education.","type":"Inproceedings","venue":"EMNLP","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.18653/V1/2025.EMNLP-MAIN.1401","sourceUrl":"https://dblp.org/rec/conf/emnlp/WuGGHLD25","documentUrl":"https://doi.org/10.18653/V1/2025.EMNLP-MAIN.1401","pages":"27536-27558"},{"key":"conf/iccv/FanCYYQDYS25","title":"Test-Time Retrieval-Augmented Adaptation for Vision-Language Models.","type":"Inproceedings","venue":"ICCV","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/ICCV51701.2025.00824","sourceUrl":"https://dblp.org/rec/conf/iccv/FanCYYQDYS25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.00824","pages":"8810-8819"},{"key":"conf/iclr/GongL0F25","title":"Boosting the visual interpretability of CLIP via adversarial fine-tuning.","type":"Inproceedings","venue":"ICLR","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":null,"sourceUrl":"https://dblp.org/rec/conf/iclr/GongL0F25","documentUrl":"https://openreview.net/forum?id=khuIvzxPRp","pages":null},{"key":"conf/icml/Gong00F25","title":"Kernel-based Unsupervised Embedding Alignment for Enhanced Visual Representation in Vision-language Models.","type":"Inproceedings","venue":"ICML","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":null,"sourceUrl":"https://dblp.org/rec/conf/icml/Gong00F25","documentUrl":"https://proceedings.mlr.press/v267/gong25b.html","pages":null},{"key":"conf/iros/LiCQCD25","title":"Gaussian Splatting with Reflectance Regularization for Endoscopic Scene Reconstruction.","type":"Inproceedings","venue":"IROS","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/IROS60139.2025.11247248","sourceUrl":"https://dblp.org/rec/conf/iros/LiCQCD25","documentUrl":"https://doi.org/10.1109/IROS60139.2025.11247248","pages":"543-550"},{"key":"conf/iros/MaCXZXXD25","title":"ColaDex: Contact-guided Optimization and VLM-assisted Selection for Task-oriented Dexterous Grasp Generation.","type":"Inproceedings","venue":"IROS","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/IROS60139.2025.11246998","sourceUrl":"https://dblp.org/rec/conf/iros/MaCXZXXD25","documentUrl":"https://doi.org/10.1109/IROS60139.2025.11246998","pages":"19562-19569"},{"key":"conf/isbi/ChenH025","title":"LLAMA-VG: A Video Vision LLaMA-Based Model for Endoscopy Video Generation.","type":"Inproceedings","venue":"ISBI","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/ISBI60581.2025.10981310","sourceUrl":"https://dblp.org/rec/conf/isbi/ChenH025","documentUrl":"https://doi.org/10.1109/ISBI60581.2025.10981310","pages":"1-5"},{"key":"conf/miccai/ZhangZCDW24","title":"Holistic Consistency for Subject-Level Segmentation Quality Assessment in Medical Image Segmentation.","type":"Inproceedings","venue":"UNSURE@MICCAI","year":2025,"yearOfPublication":2025,"yearOfEvent":2024,"doi":"https://doi.org/10.1007/978-3-031-73158-7_9","sourceUrl":"https://dblp.org/rec/conf/miccai/ZhangZCDW24","documentUrl":"https://doi.org/10.1007/978-3-031-73158-7_9","pages":"92-102"},{"key":"conf/nips/MaCZD25","title":"Contact Map Transfer with Conditional Diffusion Model for Generalizable Dexterous Grasp Generation.","type":"Inproceedings","venue":"NeurIPS","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":null,"sourceUrl":"https://dblp.org/rec/conf/nips/MaCZD25","documentUrl":"http://papers.nips.cc/paper_files/paper/2025/hash/728a3f18902026dc60b7f7a84c7d2ce4-Abstract-Conference.html","pages":null},{"key":"journals/aisy/LiuNLHDXW25","title":"Small but Strong: Lightweight Architecture Improves Lung Nodule Detection and Segmentation.","type":"Article","venue":"Adv. Intell. Syst.","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.1002/AISY.202401093","sourceUrl":"https://dblp.org/rec/journals/aisy/LiuNLHDXW25","documentUrl":"https://doi.org/10.1002/AISY.202401093","pages":null},{"key":"journals/automatica/XinSDCS25","title":"Learning linearized models from nonlinear systems under initialization constraints with finite data.","type":"Article","venue":"Autom.","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.1016/J.AUTOMATICA.2025.112478","sourceUrl":"https://dblp.org/rec/journals/automatica/XinSDCS25","documentUrl":"https://doi.org/10.1016/J.AUTOMATICA.2025.112478","pages":"112478"},{"key":"journals/mia/WangLCYSCYMD25","title":"Learning dissection trajectories from expert surgical videos via imitation learning with equivariant diffusion.","type":"Article","venue":"Medical Image Anal.","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.1016/J.MEDIA.2025.103599","sourceUrl":"https://dblp.org/rec/journals/mia/WangLCYSCYMD25","documentUrl":"https://doi.org/10.1016/J.MEDIA.2025.103599","pages":"103599"},{"key":"journals/mia/WangZLDCCDH25","title":"Illuminating the unseen: Advancing MRI domain generalization through causality.","type":"Article","venue":"Medical Image Anal.","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.1016/J.MEDIA.2025.103459","sourceUrl":"https://dblp.org/rec/journals/mia/WangZLDCCDH25","documentUrl":"https://doi.org/10.1016/J.MEDIA.2025.103459","pages":"103459"},{"key":"journals/npjdm/ChenGFDCCQZNHDYL25","title":"Artificial intelligence assisted real-time recognition of intra-abdominal metastasis during laparoscopic gastric cancer surgery.","type":"Article","venue":"npj Digit. Medicine","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.1038/S41746-024-01372-6","sourceUrl":"https://dblp.org/rec/journals/npjdm/ChenGFDCCQZNHDYL25","documentUrl":"https://doi.org/10.1038/S41746-024-01372-6","pages":null},{"key":"journals/scirobotics/LongLKZYSSFLWCCHYCKTLCW25","title":"Surgical embodied intelligence for generalized task autonomy in laparoscopic robot-assisted surgery.","type":"Article","venue":"Sci. Robotics","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.1126/SCIROBOTICS.ADT3093","sourceUrl":"https://dblp.org/rec/journals/scirobotics/LongLKZYSSFLWCCHYCKTLCW25","documentUrl":"https://doi.org/10.1126/SCIROBOTICS.ADT3093","pages":null},{"key":"journals/tase/WeiLZMDLS25","title":"Absolute Monocular Depth Estimation on Robotic Visual and Kinematics Data via Self-Supervised Learning.","type":"Article","venue":"IEEE Trans Autom. Sci. Eng.","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.1109/TASE.2024.3409392","sourceUrl":"https://dblp.org/rec/journals/tase/WeiLZMDLS25","documentUrl":"https://doi.org/10.1109/TASE.2024.3409392","pages":"4269-4282"},{"key":"journals/tcsv/ZhouCWZDQ25","title":"Canonical Shape Reconstruction With SE(3) Equivariance Learning for Weakly-Supervised Object Pose Estimation.","type":"Article","venue":"IEEE Trans. Circuits Syst. Video Technol.","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.1109/TCSVT.2025.3542089","sourceUrl":"https://dblp.org/rec/journals/tcsv/ZhouCWZDQ25","documentUrl":"https://doi.org/10.1109/TCSVT.2025.3542089","pages":"6895-6909"},{"key":"journals/titb/ChenDZCCDCHC25","title":"Multi-Organ Segmentation From Partially Labeled and Unaligned Multi-Modal MRI in Thyroid-Associated Orbitopathy.","type":"Article","venue":"IEEE J. Biomed. Health Informatics","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.1109/JBHI.2025.3545138","sourceUrl":"https://dblp.org/rec/journals/titb/ChenDZCCDCHC25","documentUrl":"https://doi.org/10.1109/JBHI.2025.3545138","pages":"4161-4172"},{"key":"journals/titb/WangLZWZD25","title":"Improving Foundation Model for Endoscopy Video Analysis via Representation Learning on Long Sequences.","type":"Article","venue":"IEEE J. Biomed. Health Informatics","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.1109/JBHI.2025.3532311","sourceUrl":"https://dblp.org/rec/journals/titb/WangLZWZD25","documentUrl":"https://doi.org/10.1109/JBHI.2025.3532311","pages":"3526-3536"},{"key":"journals/tmi/FuCDGHZLWG25","title":"IPNet: An Interpretable Network With Progressive Loss for Whole-Stage Colorectal Disease Diagnosis.","type":"Article","venue":"IEEE Trans. Medical Imaging","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.1109/TMI.2024.3459910","sourceUrl":"https://dblp.org/rec/journals/tmi/FuCDGHZLWG25","documentUrl":"https://doi.org/10.1109/TMI.2024.3459910","pages":"789-800"},{"key":"journals/tmi/GuoWWKDL25","title":"UC-NeRF: Uncertainty-Aware Conditional Neural Radiance Fields From Endoscopic Sparse Views.","type":"Article","venue":"IEEE Trans. Medical Imaging","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.1109/TMI.2024.3496558","sourceUrl":"https://dblp.org/rec/journals/tmi/GuoWWKDL25","documentUrl":"https://doi.org/10.1109/TMI.2024.3496558","pages":"1284-1296"},{"key":"journals/tmi/HanZPQFD25","title":"Toward Reliable AR-Guided Surgical Navigation: Interactive Deformation Modeling With Data-Driven Biomechanics and Prompts.","type":"Article","venue":"IEEE Trans. Medical Imaging","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.1109/TMI.2025.3577759","sourceUrl":"https://dblp.org/rec/journals/tmi/HanZPQFD25","documentUrl":"https://doi.org/10.1109/TMI.2025.3577759","pages":"4417-4431"},{"key":"journals/tmi/HuangZXWDZ25","title":"On-the-Fly Improving Segment Anything for Medical Image Segmentation Using Auxiliary Online Learning.","type":"Article","venue":"IEEE Trans. Medical Imaging","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.1109/TMI.2025.3548985","sourceUrl":"https://dblp.org/rec/journals/tmi/HuangZXWDZ25","documentUrl":"https://doi.org/10.1109/TMI.2025.3548985","pages":"3938-3949"},{"key":"journals/trob/ZhouHDAL25","title":"A Dexterous and Compliant (DexCo) Hand Based on Soft Hydraulic Actuation for Human-Inspired Fine In-Hand Manipulation.","type":"Article","venue":"IEEE Trans. Robotics","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.1109/TRO.2024.3508932","sourceUrl":"https://dblp.org/rec/journals/trob/ZhouHDAL25","documentUrl":"https://doi.org/10.1109/TRO.2024.3508932","pages":"666-686"}],"preprints":[{"key":"journals/corr/abs-2501-00525","title":"Is Segment Anything Model 2 All You Need for Surgery Video Segmentation? A Systematic Evaluation.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2501.00525","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2501-00525","documentUrl":"https://doi.org/10.48550/ARXIV.2501.00525","pages":null,"arxivId":"2501.00525","arxivUrl":"https://arxiv.org/abs/2501.00525"},{"key":"journals/corr/abs-2502-08189","title":"AnyCharV: Bootstrap Controllable Character Video Generation with Fine-to-Coarse Guidance.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2502.08189","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2502-08189","documentUrl":"https://doi.org/10.48550/ARXIV.2502.08189","pages":null,"arxivId":"2502.08189","arxivUrl":"https://arxiv.org/abs/2502.08189"},{"key":"journals/corr/abs-2503-01252","title":"Diffusion Stabilizer Policy for Automated Surgical Robot Manipulations.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2503.01252","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-01252","documentUrl":"https://doi.org/10.48550/ARXIV.2503.01252","pages":null,"arxivId":"2503.01252","arxivUrl":"https://arxiv.org/abs/2503.01252"},{"key":"journals/corr/abs-2503-09160","title":"WonderVerse: Extendable 3D Scene Generation with Video Generative Models.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2503.09160","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-09160","documentUrl":"https://doi.org/10.48550/ARXIV.2503.09160","pages":null,"arxivId":"2503.09160","arxivUrl":"https://arxiv.org/abs/2503.09160"},{"key":"journals/corr/abs-2503-14925","title":"pFedFair: Towards Optimal Group Fairness-Accuracy Trade-off in Heterogeneous Federated Learning.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2503.14925","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-14925","documentUrl":"https://doi.org/10.48550/ARXIV.2503.14925","pages":null,"arxivId":"2503.14925","arxivUrl":"https://arxiv.org/abs/2503.14925"},{"key":"journals/corr/abs-2503-18296","title":"Surgical Action Planning with Large Language Models.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2503.18296","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-18296","documentUrl":"https://doi.org/10.48550/ARXIV.2503.18296","pages":null,"arxivId":"2503.18296","arxivUrl":"https://arxiv.org/abs/2503.18296"},{"key":"journals/corr/abs-2504-03198","title":"Endo3R: Unified Online Reconstruction from Dynamic Monocular Endoscopic Video.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2504.03198","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2504-03198","documentUrl":"https://doi.org/10.48550/ARXIV.2504.03198","pages":null,"arxivId":"2504.03198","arxivUrl":"https://arxiv.org/abs/2504.03198"},{"key":"journals/corr/abs-2505-04954","title":"Learning Linearized Models from Nonlinear Systems under Initialization Constraints with Finite Data.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2505.04954","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-04954","documentUrl":"https://doi.org/10.48550/ARXIV.2505.04954","pages":null,"arxivId":"2505.04954","arxivUrl":"https://arxiv.org/abs/2505.04954"},{"key":"journals/corr/abs-2505-19031","title":"Medical Large Vision Language Models with Multi-Image Visual Ability.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2505.19031","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-19031","documentUrl":"https://doi.org/10.48550/ARXIV.2505.19031","pages":null,"arxivId":"2505.19031","arxivUrl":"https://arxiv.org/abs/2505.19031"},{"key":"journals/corr/abs-2506-02555","title":"SurgVLM: A Large Vision-Language Model and Systematic Evaluation Benchmark for Surgical Intelligence.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2506.02555","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-02555","documentUrl":"https://doi.org/10.48550/ARXIV.2506.02555","pages":null,"arxivId":"2506.02555","arxivUrl":"https://arxiv.org/abs/2506.02555"},{"key":"journals/corr/abs-2506-02557","title":"Kernel-based Unsupervised Embedding Alignment for Enhanced Visual Representation in Vision-language Models.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2506.02557","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-02557","documentUrl":"https://doi.org/10.48550/ARXIV.2506.02557","pages":null,"arxivId":"2506.02557","arxivUrl":"https://arxiv.org/abs/2506.02557"},{"key":"journals/corr/abs-2506-04716","title":"Learning dissection trajectories from expert surgical videos via imitation learning with equivariant diffusion.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2506.04716","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-04716","documentUrl":"https://doi.org/10.48550/ARXIV.2506.04716","pages":null,"arxivId":"2506.04716","arxivUrl":"https://arxiv.org/abs/2506.04716"},{"key":"journals/corr/abs-2506-08048","title":"Toward Reliable AR-Guided Surgical Navigation: Interactive Deformation Modeling with Data-Driven Biomechanics and Prompts.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2506.08048","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-08048","documentUrl":"https://doi.org/10.48550/ARXIV.2506.08048","pages":null,"arxivId":"2506.08048","arxivUrl":"https://arxiv.org/abs/2506.08048"},{"key":"journals/corr/abs-2506-17337","title":"Can Common VLMs Rival Medical VLMs? Evaluation and Strategic Insights.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2506.17337","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-17337","documentUrl":"https://doi.org/10.48550/ARXIV.2506.17337","pages":null,"arxivId":"2506.17337","arxivUrl":"https://arxiv.org/abs/2506.17337"},{"key":"journals/corr/abs-2507-06647","title":"ClipGS: Clippable Gaussian Splatting for Interactive Cinematic Visualization of Volumetric Medical Data.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2507.06647","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2507-06647","documentUrl":"https://doi.org/10.48550/ARXIV.2507.06647","pages":null,"arxivId":"2507.06647","arxivUrl":"https://arxiv.org/abs/2507.06647"},{"key":"journals/corr/abs-2507-19165","title":"Extreme Cardiac MRI Analysis under Respiratory Motion: Results of the CMRxMotion Challenge.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2507.19165","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2507-19165","documentUrl":"https://doi.org/10.48550/ARXIV.2507.19165","pages":null,"arxivId":"2507.19165","arxivUrl":"https://arxiv.org/abs/2507.19165"},{"key":"journals/corr/abs-2508-10881","title":"ToonComposer: Streamlining Cartoon Production with Generative Post-Keyframing.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2508.10881","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-10881","documentUrl":"https://doi.org/10.48550/ARXIV.2508.10881","pages":null,"arxivId":"2508.10881","arxivUrl":"https://arxiv.org/abs/2508.10881"},{"key":"journals/corr/abs-2508-18886","title":"Toward Robust Medical Fairness: Debiased Dual-Modal Alignment via Text-Guided Attribute-Disentangled Prompt Learning for Vision-Language Models.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2508.18886","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-18886","documentUrl":"https://doi.org/10.48550/ARXIV.2508.18886","pages":null,"arxivId":"2508.18886","arxivUrl":"https://arxiv.org/abs/2508.18886"},{"key":"journals/corr/abs-2509-05657","title":"LM-Searcher: Cross-domain Neural Architecture Search with LLMs via Unified Numerical Encoding.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2509.05657","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-05657","documentUrl":"https://doi.org/10.48550/ARXIV.2509.05657","pages":null,"arxivId":"2509.05657","arxivUrl":"https://arxiv.org/abs/2509.05657"},{"key":"journals/corr/abs-2509-15103","title":"Vulnerable Agent Identification in Large-Scale Multi-Agent Reinforcement Learning.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2509.15103","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-15103","documentUrl":"https://doi.org/10.48550/ARXIV.2509.15103","pages":null,"arxivId":"2509.15103","arxivUrl":"https://arxiv.org/abs/2509.15103"},{"key":"journals/corr/abs-2510-00037","title":"On Robustness of Vision-Language-Action Model against Multi-Modal Perturbations.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2510.00037","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-00037","documentUrl":"https://doi.org/10.48550/ARXIV.2510.00037","pages":null,"arxivId":"2510.00037","arxivUrl":"https://arxiv.org/abs/2510.00037"},{"key":"journals/corr/abs-2511-01276","title":"Contact Map Transfer with Conditional Diffusion Model for Generalizable Dexterous Grasp Generation.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2511.01276","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2511-01276","documentUrl":"https://doi.org/10.48550/ARXIV.2511.01276","pages":null,"arxivId":"2511.01276","arxivUrl":"https://arxiv.org/abs/2511.01276"},{"key":"journals/corr/abs-2512-02485","title":"UCAgents: Unidirectional Convergence for Visual Evidence Anchored Multi-Agent Medical Decision-Making.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2512.02485","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-02485","documentUrl":"https://doi.org/10.48550/ARXIV.2512.02485","pages":null,"arxivId":"2512.02485","arxivUrl":"https://arxiv.org/abs/2512.02485"},{"key":"journals/corr/abs-2512-10206","title":"CP-Env: Evaluating Large Language Models on Clinical Pathways in a Controllable Hospital Environment.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2512.10206","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-10206","documentUrl":"https://doi.org/10.48550/ARXIV.2512.10206","pages":null,"arxivId":"2512.10206","arxivUrl":"https://arxiv.org/abs/2512.10206"},{"key":"journals/corr/abs-2512-19387","title":"DSTED: Decoupling Temporal Stabilization and Discriminative Enhancement for Surgical Workflow Recognition.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2512.19387","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-19387","documentUrl":"https://doi.org/10.48550/ARXIV.2512.19387","pages":null,"arxivId":"2512.19387","arxivUrl":"https://arxiv.org/abs/2512.19387"}],"excludedFormal":[],"labName":null,"labUrl":null,"labEvidence":"本人及 CUHK 官方页列多个研究所/中心成员关系和当前团队，但未发现明确的当前 Lab 名称；BioMedIA Lab 明确是过去 Imperial 博后经历，不能作为当前组。","labSourceUrl":"https://www.cse.cuhk.edu.hk/~qdou/","affiliationZh":"香港中文大学","sourceWarning":false,"excludedOther":[],"excludedHomonyms":[],"unassignedCandidates":[],"knownPreprintMinimum2025":null,"excludedMisattributed":[],"displayNotes":"身份已经机构或个人主页核对。2025 年正式记录 29 条（会议 14、期刊 15），所有作者位置均计入，不表示主导或贡献份额；预印本 25 条单列，不加总。","labDisplayNotes":"本人主页列有多个研究所与中心的职务，但未见当前实验室名称；BioMedIA 是其在帝国理工做博士后时的团队，不采用。图中以「姓名及合作者」单列。"},{"index":38,"name":"Dong Du","nameZh":"杜冬","role":"Associate Professor","affiliation":"Nanjing University of Science and Technology","source":"DBLP official SPARQL","profileUrl":"https://dblp.org/pid/48/331-2","identifier":"48/331-2","identityEvidence":[{"url":"https://dblp.org/pid/48/331-2","evidence":"DBLP 档案名 Dong Du 0002；机构/履历：City University of Hong Kong, School of Creative Media, Hong Kong；University of Science and Technology of China, Hefei, China"},{"url":"https://dongdu3.github.io/","evidence":"作者主页说明任职 Nanjing University of Science and Technology，博士就读 USTC、曾访问 City University of Hong Kong，与 DBLP Dong Du 0002 的履历一致；两篇 2025 正式记录均见其个人发表列表。"},{"url":"https://dongdu3.github.io/publications","evidence":"作者/机构页面与该 DBLP 档案交叉匹配的题名示例：VIPNet: A Fast and Accurate Single-View Volumetric Reconstruction by Learning Sparse Implicit Point Guidance.；PIFu for the Real World: A Self-supervised Framework to Reconstruct Dressed Human from Single-View Images.","matchedPaperKeys":["conf/3dim/DuZHCL20","conf/cvm/XiongDWDKBH24"]}],"count2025":2,"conference2025":1,"journal2025":1,"preprint2025":1,"status":"verified","notes":"身份已通过机构/个人主页或 DBLP 机构信息核对；篇数为数据库记录统计，不表示每篇均由本人主导。","retrievedAt":"2026-10-19","yearPolicy":"DBLP yearOfPublication = 2025","queryUrl":"https://sparql.dblp.org/sparql?query=PREFIX%20dblp%3A%20%3Chttps%3A//dblp.org/rdf/schema%23%3E%20PREFIX%20xsd%3A%20%3Chttp%3A//www.w3.org/2001/XMLSchema%23%3E%20SELECT%20%3Fpub%20%3Ftitle%20%3Ftype%20%3Fvenue%20WHERE%20%7B%20%3Fpub%20dblp%3AauthoredBy%20%3Chttps%3A//dblp.org/pid/48/331-2%3E%3B%20dblp%3AyearOfPublication%20%222025%22%5E%5Exsd%3AgYear%3B%20dblp%3Atitle%20%3Ftitle%3B%20a%20%3Ftype%20.%20OPTIONAL%20%7B%20%3Fpub%20dblp%3ApublishedIn%20%3Fvenue%20%7D%20%7D&format=json","papers":[{"key":"conf/cvpr/ZhangLDCSZDXZ025","title":"Robust-MVTON: Learning Cross-Pose Feature Alignment and Fusion for Robust Multi-View Virtual Try-On.","type":"Inproceedings","venue":"CVPR","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/CVPR52734.2025.01494","sourceUrl":"https://dblp.org/rec/conf/cvpr/ZhangLDCSZDXZ025","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Zhang_Robust-MVTON_Learning_Cross-Pose_Feature_Alignment_and_Fusion_for_Robust_Multi-View_CVPR_2025_paper.html","pages":"16029-16039"},{"key":"journals/cmig/LiuDLTYHSL25","title":"Subtraction-free artifact-aware digital subtraction angiography image generation for head and neck vessels from motion data.","type":"Article","venue":"Comput. Medical Imaging Graph.","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.1016/J.COMPMEDIMAG.2025.102512","sourceUrl":"https://dblp.org/rec/journals/cmig/LiuDLTYHSL25","documentUrl":"https://doi.org/10.1016/J.COMPMEDIMAG.2025.102512","pages":"102512"}],"preprints":[{"key":"journals/corr/abs-2512-09435","title":"UniPart: Part-Level 3D Generation with Unified 3D Geom-Seg Latents.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2512.09435","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-09435","documentUrl":"https://doi.org/10.48550/ARXIV.2512.09435","pages":null,"arxivId":"2512.09435","arxivUrl":"https://arxiv.org/abs/2512.09435"}],"excludedFormal":[],"labName":null,"labUrl":null,"labEvidence":"本人主页提供 Group 导航，但本轮未确认具名实验室；不以 Dong Du 加 Lab 自行构造。","labSourceUrl":"https://dongdu3.github.io/","affiliationZh":"南京理工大学","sourceWarning":false,"excludedOther":[],"excludedHomonyms":[],"unassignedCandidates":[],"knownPreprintMinimum2025":null,"excludedMisattributed":[],"displayNotes":"身份已经机构或个人主页核对。2025 年正式记录 2 条（会议 1、期刊 1），所有作者位置均计入；预印本 1 条单列，不加总。","labDisplayNotes":"本人主页有 Group 栏目，但未写正式组名，不自行构造；图中以「姓名及合作者」单列。"},{"index":39,"name":"Hongbo Fu","nameZh":"傅红波","role":"Professor","affiliation":"The Hong Kong University of Science and Technology","source":"DBLP official SPARQL","profileUrl":"https://dblp.org/pid/19/5752-1","identifier":"19/5752-1","identityEvidence":[{"url":"https://dblp.org/pid/19/5752-1","evidence":"DBLP 档案名 Hongbo Fu 0001；机构/履历：City University of Hong Kong (CityUHK), School of Creative Media, Kowloon, Hong Kong；Hong Kong University of Science and Technology (HKUST), Division of Arts and Machine Creativity, Sai Kung, Hong Kong"}],"count2025":20,"conference2025":7,"journal2025":13,"preprint2025":8,"status":"verified","notes":"身份已通过机构/个人主页或 DBLP 机构信息核对；篇数为数据库记录统计，不表示每篇均由本人主导。","retrievedAt":"2026-10-19","yearPolicy":"DBLP yearOfPublication = 2025","queryUrl":"https://sparql.dblp.org/sparql?query=PREFIX%20dblp%3A%20%3Chttps%3A//dblp.org/rdf/schema%23%3E%20PREFIX%20xsd%3A%20%3Chttp%3A//www.w3.org/2001/XMLSchema%23%3E%20SELECT%20%3Fpub%20%3Ftitle%20%3Ftype%20%3Fvenue%20WHERE%20%7B%20%3Fpub%20dblp%3AauthoredBy%20%3Chttps%3A//dblp.org/pid/19/5752-1%3E%3B%20dblp%3AyearOfPublication%20%222025%22%5E%5Exsd%3AgYear%3B%20dblp%3Atitle%20%3Ftitle%3B%20a%20%3Ftype%20.%20OPTIONAL%20%7B%20%3Fpub%20dblp%3ApublishedIn%20%3Fvenue%20%7D%20%7D&format=json","papers":[{"key":"conf/cvpr/Liang00K0L25","title":"VODiff: Controlling Object Visibility Order in Text-to-Image Generation.","type":"Inproceedings","venue":"CVPR","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/CVPR52734.2025.01713","sourceUrl":"https://dblp.org/rec/conf/cvpr/Liang00K0L25","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Liang_VODiff_Controlling_Object_Visibility_Order_in_Text-to-Image_Generation_CVPR_2025_paper.html","pages":"18379-18389"},{"key":"conf/cvpr/Liu0WY0Z025","title":"SketchVideo: Sketch-based Video Generation and Editing.","type":"Inproceedings","venue":"CVPR","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/CVPR52734.2025.02177","sourceUrl":"https://dblp.org/rec/conf/cvpr/Liu0WY0Z025","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Liu_SketchVideo_Sketch-based_Video_Generation_and_Editing_CVPR_2025_paper.html","pages":"23379-23390"},{"key":"conf/iccv/ChenZLJCHFH25","title":"GCRayDiffusion: Pose-Free Surface Reconstruction via Geometric Consistent Ray Diffusion.","type":"Inproceedings","venue":"ICCV","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/ICCV51701.2025.02350","sourceUrl":"https://dblp.org/rec/conf/iccv/ChenZLJCHFH25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.02350","pages":"25335-25345"},{"key":"conf/icmcs/QiuLFZCLG25","title":"Audio-Driven Emotion-Aware 3D Talking Face Generation from Single Image.","type":"Inproceedings","venue":"ICME","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/ICME59968.2025.11209335","sourceUrl":"https://dblp.org/rec/conf/icmcs/QiuLFZCLG25","documentUrl":"https://doi.org/10.1109/ICME59968.2025.11209335","pages":"1-6"},{"key":"conf/ismar/YangZXFH25","title":"MRpilot: A Mixed-Reality System for Responsive Navigation of General Procedural Tasks.","type":"Inproceedings","venue":"ISMAR","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1109/ISMAR67309.2025.00031","sourceUrl":"https://dblp.org/rec/conf/ismar/YangZXFH25","documentUrl":"https://doi.org/10.1109/ISMAR67309.2025.00031","pages":"186-196"},{"key":"conf/siggraph/LiuLC0025","title":"Sketch3DVE: Sketch-based 3D-Aware Scene Video Editing.","type":"Inproceedings","venue":"SIGGRAPH (Conference Paper Track)","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1145/3721238.3730623","sourceUrl":"https://dblp.org/rec/conf/siggraph/LiuLC0025","documentUrl":"https://doi.org/10.1145/3721238.3730623","pages":"152:1-152:12"},{"key":"conf/siggrapha/0038ZL0L025","title":"Single-Image 3D Human Reconstruction with 3D-Aware Diffusion Priors and Facial Enhancement.","type":"Inproceedings","venue":"SIGGRAPH Asia","year":2025,"yearOfPublication":2025,"yearOfEvent":2025,"doi":"https://doi.org/10.1145/3757377.3763839","sourceUrl":"https://dblp.org/rec/conf/siggrapha/0038ZL0L025","documentUrl":"https://doi.org/10.1145/3757377.3763839","pages":"33:1-33:13"},{"key":"journals/cga/ZengFZC25","title":"Human-AI Interaction for Visualization and Visual Analytics.","type":"Article","venue":"IEEE Computer Graphics and Applications","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.1109/MCG.2025.3606311","sourceUrl":"https://dblp.org/rec/journals/cga/ZengFZC25","documentUrl":"https://doi.org/10.1109/MCG.2025.3606311","pages":"11-13"},{"key":"journals/pami/HuBSZDWSFT25","title":"Voxel-Mesh Network for Geodesic-Aware 3D Semantic Segmentation of Indoor Scenes.","type":"Article","venue":"IEEE Trans. Pattern Anal. Mach. Intell.","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.1109/TPAMI.2022.3194555","sourceUrl":"https://dblp.org/rec/journals/pami/HuBSZDWSFT25","documentUrl":"https://doi.org/10.1109/TPAMI.2022.3194555","pages":"3244-3256"},{"key":"journals/pami/JiangCLFG25","title":"Towards High-Quality and Disentangled Face Editing in a 3D GAN.","type":"Article","venue":"IEEE Trans. Pattern Anal. Mach. Intell.","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.1109/TPAMI.2024.3523422","sourceUrl":"https://dblp.org/rec/journals/pami/JiangCLFG25","documentUrl":"https://doi.org/10.1109/TPAMI.2024.3523422","pages":"2533-2544"},{"key":"journals/tcsv/WuXTSFJ25","title":"3DPortraitGAN: Learning One-Quarter Headshot 3D GANs From a Single-View Portrait Dataset With Diverse Body Poses.","type":"Article","venue":"IEEE Trans. Circuits Syst. Video Technol.","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.1109/TCSVT.2025.3586442","sourceUrl":"https://dblp.org/rec/journals/tcsv/WuXTSFJ25","documentUrl":"https://doi.org/10.1109/TCSVT.2025.3586442","pages":"12760-12771"},{"key":"journals/tog/ZhouQLF25","title":"From Rigging to Waving: 3D-Guided Diffusion for Natural Animation of Hand-Drawn Characters.","type":"Article","venue":"ACM Trans. Graph.","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.1145/3763280","sourceUrl":"https://dblp.org/rec/journals/tog/ZhouQLF25","documentUrl":"https://doi.org/10.1145/3763280","pages":"255:1-255:11"},{"key":"journals/tvcg/HuXZFH25","title":"StructLayoutFormer: Conditional Structured Layout Generation via Structure Serialization and Disentanglement.","type":"Article","venue":"IEEE Trans. Vis. Comput. Graph.","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.1109/TVCG.2025.3574311","sourceUrl":"https://dblp.org/rec/journals/tvcg/HuXZFH25","documentUrl":"https://doi.org/10.1109/TVCG.2025.3574311","pages":"8623-8636"},{"key":"journals/tvcg/JiangLCWZLFG25","title":"NeRFFaceShop: Learning a Photo-Realistic 3D-Aware Generative Model of Animatable and Relightable Heads From Large-Scale in-the-Wild Videos.","type":"Article","venue":"IEEE Trans. Vis. Comput. Graph.","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.1109/TVCG.2025.3560869","sourceUrl":"https://dblp.org/rec/journals/tvcg/JiangLCWZLFG25","documentUrl":"https://doi.org/10.1109/TVCG.2025.3560869","pages":"7938-7950"},{"key":"journals/tvcg/JiangXZFLW25","title":"Region-Aware Color Smudging.","type":"Article","venue":"IEEE Trans. Vis. Comput. Graph.","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.1109/TVCG.2024.3374210","sourceUrl":"https://dblp.org/rec/journals/tvcg/JiangXZFLW25","documentUrl":"https://doi.org/10.1109/TVCG.2024.3374210","pages":"1999-2011"},{"key":"journals/tvcg/QuSLF25","title":"Controllable Human Video Generation From Sparse Sketches.","type":"Article","venue":"IEEE Trans. Vis. Comput. Graph.","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.1109/TVCG.2025.3543687","sourceUrl":"https://dblp.org/rec/journals/tvcg/QuSLF25","documentUrl":"https://doi.org/10.1109/TVCG.2025.3543687","pages":"7243-7253"},{"key":"journals/tvcg/QuSYHF25","title":"Sketch2Human: Deep Human Generation With Disentangled Geometry and Appearance Constraints.","type":"Article","venue":"IEEE Trans. Vis. Comput. Graph.","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.1109/TVCG.2024.3403160","sourceUrl":"https://dblp.org/rec/journals/tvcg/QuSYHF25","documentUrl":"https://doi.org/10.1109/TVCG.2024.3403160","pages":"4480-4492"},{"key":"journals/tvcg/SuWLHFL25","title":"StyleRetoucher: Generalized Portrait Image Retouching With GAN Priors.","type":"Article","venue":"IEEE Trans. Vis. Comput. Graph.","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.1109/TVCG.2024.3432910","sourceUrl":"https://dblp.org/rec/journals/tvcg/SuWLHFL25","documentUrl":"https://doi.org/10.1109/TVCG.2024.3432910","pages":"5089-5100"},{"key":"journals/tvcg/WangZSF25","title":"Real-and-Present: Investigating the Use of Life-Size 2D Video Avatars in HMD-Based AR Teleconferencing.","type":"Article","venue":"IEEE Trans. Vis. Comput. Graph.","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.1109/TVCG.2024.3466554","sourceUrl":"https://dblp.org/rec/journals/tvcg/WangZSF25","documentUrl":"https://doi.org/10.1109/TVCG.2024.3466554","pages":"5626-5641"},{"key":"journals/tvcg/ZouHCMSFZ25","title":"GP-Recon: Online Monocular Neural 3D Reconstruction With Geometric Prior.","type":"Article","venue":"IEEE Trans. Vis. Comput. Graph.","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.1109/TVCG.2024.3413860","sourceUrl":"https://dblp.org/rec/journals/tvcg/ZouHCMSFZ25","documentUrl":"https://doi.org/10.1109/TVCG.2024.3413860","pages":"4790-4804"}],"preprints":[{"key":"journals/corr/abs-2502-04983","title":"MoGraphGPT: Creating Interactive Scenes Using Modular LLM and Graphical Control.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2502.04983","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2502-04983","documentUrl":"https://doi.org/10.48550/ARXIV.2502.04983","pages":null,"arxivId":"2502.04983","arxivUrl":"https://arxiv.org/abs/2502.04983"},{"key":"journals/corr/abs-2503-22349","title":"GCRayDiffusion: Pose-Free Surface Reconstruction via Geometric Consistent Ray Diffusion.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2503.22349","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-22349","documentUrl":"https://doi.org/10.48550/ARXIV.2503.22349","pages":null,"arxivId":"2503.22349","arxivUrl":"https://arxiv.org/abs/2503.22349"},{"key":"journals/corr/abs-2503-23284","title":"SketchVideo: Sketch-based Video Generation and Editing.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2503.23284","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-23284","documentUrl":"https://doi.org/10.48550/ARXIV.2503.23284","pages":null,"arxivId":"2503.23284","arxivUrl":"https://arxiv.org/abs/2503.23284"},{"key":"journals/corr/abs-2504-20599","title":"PartHOI: Part-based Hand-Object Interaction Transfer via Generalized Cylinders.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2504.20599","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2504-20599","documentUrl":"https://doi.org/10.48550/ARXIV.2504.20599","pages":null,"arxivId":"2504.20599","arxivUrl":"https://arxiv.org/abs/2504.20599"},{"key":"journals/corr/abs-2508-13797","title":"Sketch3DVE: Sketch-based 3D-Aware Scene Video Editing.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2508.13797","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-13797","documentUrl":"https://doi.org/10.48550/ARXIV.2508.13797","pages":null,"arxivId":"2508.13797","arxivUrl":"https://arxiv.org/abs/2508.13797"},{"key":"journals/corr/abs-2509-06573","title":"From Rigging to Waving: 3D-Guided Diffusion for Natural Animation of Hand-Drawn Characters.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2509.06573","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-06573","documentUrl":"https://doi.org/10.48550/ARXIV.2509.06573","pages":null,"arxivId":"2509.06573","arxivUrl":"https://arxiv.org/abs/2509.06573"},{"key":"journals/corr/abs-2509-21291","title":"VC-Agent: An Interactive Agent for Customized Video Dataset Collection.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2509.21291","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-21291","documentUrl":"https://doi.org/10.48550/ARXIV.2509.21291","pages":null,"arxivId":"2509.21291","arxivUrl":"https://arxiv.org/abs/2509.21291"},{"key":"journals/corr/abs-2510-26141","title":"StructLayoutFormer:Conditional Structured Layout Generation via Structure Serialization and Disentanglement.","type":"Informal","venue":"CoRR","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.48550/ARXIV.2510.26141","sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-26141","documentUrl":"https://doi.org/10.48550/ARXIV.2510.26141","pages":null,"arxivId":"2510.26141","arxivUrl":"https://arxiv.org/abs/2510.26141"}],"excludedFormal":[{"key":"journals/ijcv/HeGFJJY25","title":"Guest Editorial: Special Issue on Large-Scale Generative Models for Content Creation and Manipulation.","type":"Article","venue":"Int. J. Comput. Vis.","year":2025,"yearOfPublication":2025,"yearOfEvent":null,"doi":"https://doi.org/10.1007/S11263-025-02414-6","sourceUrl":"https://dblp.org/rec/journals/ijcv/HeGFJJY25","documentUrl":"https://doi.org/10.1007/S11263-025-02414-6","pages":"4962-4965","exclusionReason":"明确为社论、勘误、修正或序言，非研究论文"}],"labName":null,"labUrl":null,"labEvidence":"本人及 HKUST 官方资料确认 AMC/EMIA 等院系职位，未确认当前具名 Lab；Imager Lab 为历史博后经历，VisGraph 论文合作/致谢也不足以作为其当前团队名。","labSourceUrl":"https://hongbofu.people.ust.hk/","affiliationZh":"香港科技大学","sourceWarning":false,"excludedOther":[],"excludedHomonyms":[],"unassignedCandidates":[],"knownPreprintMinimum2025":null,"excludedMisattributed":[],"displayNotes":"身份已经机构或个人主页核对。2025 年正式记录 20 条（会议 7、期刊 13），所有作者位置均计入，不表示主导或贡献份额；预印本 8 条单列，不加总。","labDisplayNotes":"本人与港科大资料只写明所属学部；Imager Lab 是早年经历，论文合作也不足以说明其当前团队。图中以「姓名及合作者」单列。"},{"index":40,"name":"Yanwei Fu","nameZh":"付彦伟","role":"Professor","affiliation":"Fudan University","affiliationZh":"复旦大学","source":"DBLP RDF via official SPARQL; primary-source identity checks","sourceUrl":"https://sparql.dblp.org/","profileUrl":"https://dblp.org/pid/63/9065.html","identifier":"63/9065","retrievedAt":"2026-10-19","count2025":44,"conference2025":39,"journal2025":5,"preprint2025":55,"status":"confirmed","notes":"","identityEvidence":[{"url":"https://dblp.org/pid/63/9065.html","evidence":"DBLP RDF 类型为 Person，消歧后名字为 Yanwei Fu 0001。机构元数据含：Nanjing University, National Key Laboratory for Novel Software Technology, China；Fudan University, School of Data Science, Shanghai, China；Disney Research, Pittsburgh, PA, USA；Queen Mary University of London, UK；Zhejiang Normal University, Fudan ISTBI-ZJNU Algorithm Centre for Brain-inspired Intelligence, Jinhua, China"}],"papers":[{"key":"conf/aaai/Zheng025","url":"https://dblp.org/rec/conf/aaai/Zheng025","title":"ContextualStory: Consistent Visual Storytelling with Spatially-Enhanced and Storyline Context.","year":2025,"types":["Inproceedings"],"venue":"AAAI","doi":"https://doi.org/10.1609/AAAI.V39I10.33153","eventYear":2025,"numberOfCreators":2,"category":"conference","sources":["https://dblp.org/rec/conf/aaai/Zheng025","https://doi.org/10.1609/AAAI.V39I10.33153"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/aaai/Zheng025","documentUrl":null,"type":"Inproceedings"},{"key":"conf/cvpr/0002CYFX025","url":"https://dblp.org/rec/conf/cvpr/0002CYFX025","title":"Towards Enhanced Image Inpainting: Mitigating Unwanted Object Insertion and Preserving Color Consistency.","year":2025,"types":["Inproceedings"],"venue":"CVPR","doi":"https://doi.org/10.1109/CVPR52734.2025.02164","eventYear":2025,"numberOfCreators":6,"category":"conference","sources":["https://dblp.org/rec/conf/cvpr/0002CYFX025","https://doi.org/10.1109/CVPR52734.2025.02164"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/0002CYFX025","documentUrl":null,"type":"Inproceedings"},{"key":"conf/cvpr/CaoYL0X025","url":"https://dblp.org/rec/conf/cvpr/CaoYL0X025","title":"MVGenMaster: Scaling Multi-View Generation from Any Image via 3D Priors Enhanced Diffusion Model.","year":2025,"types":["Inproceedings"],"venue":"CVPR","doi":"https://doi.org/10.1109/CVPR52734.2025.00567","eventYear":2025,"numberOfCreators":6,"category":"conference","sources":["https://dblp.org/rec/conf/cvpr/CaoYL0X025","https://doi.org/10.1109/CVPR52734.2025.00567"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/CaoYL0X025","documentUrl":null,"type":"Inproceedings"},{"key":"conf/cvpr/ChengWSZ025","url":"https://dblp.org/rec/conf/cvpr/ChengWSZ025","title":"HOP: Heterogeneous Topology-based Multimodal Entanglement for Co-Speech Gesture Generation.","year":2025,"types":["Inproceedings"],"venue":"CVPR","doi":"https://doi.org/10.1109/CVPR52734.2025.00093","eventYear":2025,"numberOfCreators":5,"category":"conference","sources":["https://dblp.org/rec/conf/cvpr/ChengWSZ025","https://doi.org/10.1109/CVPR52734.2025.00093"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/ChengWSZ025","documentUrl":null,"type":"Inproceedings"},{"key":"conf/cvpr/FuQR0TS0GZNDGZP25","url":"https://dblp.org/rec/conf/cvpr/FuQR0TS0GZNDGZP25","title":"NTIRE 2025 Challenge on Cross-Domain Few-Shot Object Detection: Methods and Results.","year":2025,"types":["Inproceedings"],"venue":"CVPR Workshops","doi":null,"eventYear":2025,"numberOfCreators":62,"category":"conference","sources":["https://dblp.org/rec/conf/cvpr/FuQR0TS0GZNDGZP25"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/FuQR0TS0GZNDGZP25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/cvpr/HuangLW00025","url":"https://dblp.org/rec/conf/cvpr/HuangLW00025","title":"CAP-Net: A Unified Network for 6D Pose and Size Estimation of Categorical Articulated Parts from a Single RGB-D Image.","year":2025,"types":["Inproceedings"],"venue":"CVPR","doi":"https://doi.org/10.1109/CVPR52734.2025.01088","eventYear":2025,"numberOfCreators":6,"category":"conference","sources":["https://dblp.org/rec/conf/cvpr/HuangLW00025","https://doi.org/10.1109/CVPR52734.2025.01088"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/HuangLW00025","documentUrl":null,"type":"Inproceedings"},{"key":"conf/cvpr/KongW0HHP0LZW025","url":"https://dblp.org/rec/conf/cvpr/KongW0HHP0LZW025","title":"CustAny: Customizing Anything from A Single Example.","year":2025,"types":["Inproceedings"],"venue":"CVPR","doi":"https://doi.org/10.1109/CVPR52734.2025.01948","eventYear":2025,"numberOfCreators":11,"category":"conference","sources":["https://dblp.org/rec/conf/cvpr/KongW0HHP0LZW025","https://doi.org/10.1109/CVPR52734.2025.01948"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/KongW0HHP0LZW025","documentUrl":null,"type":"Inproceedings"},{"key":"conf/cvpr/Liu0ZPL0025","url":"https://dblp.org/rec/conf/cvpr/Liu0ZPL0025","title":"ReasonGrounder: LVLM-Guided Hierarchical Feature Splatting for Open-Vocabulary 3D Visual Grounding and Reasoning.","year":2025,"types":["Inproceedings"],"venue":"CVPR","doi":"https://doi.org/10.1109/CVPR52734.2025.00352","eventYear":2025,"numberOfCreators":7,"category":"conference","sources":["https://dblp.org/rec/conf/cvpr/Liu0ZPL0025","https://doi.org/10.1109/CVPR52734.2025.00352"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/Liu0ZPL0025","documentUrl":null,"type":"Inproceedings"},{"key":"conf/cvpr/ZhangCZL00W25","url":"https://dblp.org/rec/conf/cvpr/ZhangCZL00W25","title":"EDEN: Enhanced Diffusion for High-quality Large-motion Video Frame Interpolation.","year":2025,"types":["Inproceedings"],"venue":"CVPR","doi":"https://doi.org/10.1109/CVPR52734.2025.00202","eventYear":2025,"numberOfCreators":7,"category":"conference","sources":["https://dblp.org/rec/conf/cvpr/ZhangCZL00W25","https://doi.org/10.1109/CVPR52734.2025.00202"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/ZhangCZL00W25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/cvpr/ZhangX0C25","url":"https://dblp.org/rec/conf/cvpr/ZhangX0C25","title":"Concept Replacer: Replacing Sensitive Concepts in Diffusion Models via Precision Localization.","year":2025,"types":["Inproceedings"],"venue":"CVPR","doi":"https://doi.org/10.1109/CVPR52734.2025.00765","eventYear":2025,"numberOfCreators":4,"category":"conference","sources":["https://dblp.org/rec/conf/cvpr/ZhangX0C25","https://doi.org/10.1109/CVPR52734.2025.00765"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/ZhangX0C25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/eccv/FuWPHQSLFGJ24","url":"https://dblp.org/rec/conf/eccv/FuWPHQSLFGJ24","title":"Cross-Domain Few-Shot Object Detection via Enhanced Open-Set Object Detector.","year":2025,"types":["Inproceedings"],"venue":"ECCV (58)","doi":"https://doi.org/10.1007/978-3-031-73636-0_15","eventYear":2024,"numberOfCreators":10,"category":"conference","sources":["https://dblp.org/rec/conf/eccv/FuWPHQSLFGJ24","https://doi.org/10.1007/978-3-031-73636-0_15"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2024,"sourceUrl":"https://dblp.org/rec/conf/eccv/FuWPHQSLFGJ24","documentUrl":null,"type":"Inproceedings"},{"key":"conf/eccv/GaoFWQFF24","url":"https://dblp.org/rec/conf/eccv/GaoFWQFF24","title":"MinD-3D: Reconstruct High-Quality 3D Objects in Human Brain.","year":2025,"types":["Inproceedings"],"venue":"ECCV (47)","doi":"https://doi.org/10.1007/978-3-031-72970-6_18","eventYear":2024,"numberOfCreators":6,"category":"conference","sources":["https://dblp.org/rec/conf/eccv/GaoFWQFF24","https://doi.org/10.1007/978-3-031-72970-6_18"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2024,"sourceUrl":"https://dblp.org/rec/conf/eccv/GaoFWQFF24","documentUrl":null,"type":"Inproceedings"},{"key":"conf/eccv/HuoWWQLFF24","url":"https://dblp.org/rec/conf/eccv/HuoWWQLFF24","title":"NeuroPictor: Refining fMRI-to-Image Reconstruction via Multi-individual Pretraining and Multi-level Modulation.","year":2025,"types":["Inproceedings"],"venue":"ECCV (51)","doi":"https://doi.org/10.1007/978-3-031-72983-6_4","eventYear":2024,"numberOfCreators":7,"category":"conference","sources":["https://dblp.org/rec/conf/eccv/HuoWWQLFF24","https://doi.org/10.1007/978-3-031-72983-6_4"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2024,"sourceUrl":"https://dblp.org/rec/conf/eccv/HuoWWQLFF24","documentUrl":null,"type":"Inproceedings"},{"key":"conf/eccv/LiQWHXFM24","url":"https://dblp.org/rec/conf/eccv/LiQWHXFM24","title":"Enhancing Cross-Subject fMRI-to-Video Decoding with Global-Local Functional Alignment.","year":2025,"types":["Inproceedings"],"venue":"ECCV (83)","doi":"https://doi.org/10.1007/978-3-031-73010-8_21","eventYear":2024,"numberOfCreators":7,"category":"conference","sources":["https://dblp.org/rec/conf/eccv/LiQWHXFM24","https://doi.org/10.1007/978-3-031-73010-8_21"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2024,"sourceUrl":"https://dblp.org/rec/conf/eccv/LiQWHXFM24","documentUrl":null,"type":"Inproceedings"},{"key":"conf/eccv/RenCFX24","url":"https://dblp.org/rec/conf/eccv/RenCFX24","title":"Improving Neural Surface Reconstruction with Feature Priors from Multi-view Images.","year":2025,"types":["Inproceedings"],"venue":"ECCV (58)","doi":"https://doi.org/10.1007/978-3-031-73636-0_26","eventYear":2024,"numberOfCreators":4,"category":"conference","sources":["https://dblp.org/rec/conf/eccv/RenCFX24","https://doi.org/10.1007/978-3-031-73636-0_26"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2024,"sourceUrl":"https://dblp.org/rec/conf/eccv/RenCFX24","documentUrl":null,"type":"Inproceedings"},{"key":"conf/icassp/WangQLC0025","url":"https://dblp.org/rec/conf/icassp/WangQLC0025","title":"Content and Salient Semantics Collaboration for Cloth-Changing Person Re-Identification.","year":2025,"types":["Inproceedings"],"venue":"ICASSP","doi":"https://doi.org/10.1109/ICASSP49660.2025.10890451","eventYear":2025,"numberOfCreators":6,"category":"conference","sources":["https://dblp.org/rec/conf/icassp/WangQLC0025","https://doi.org/10.1109/ICASSP49660.2025.10890451"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/icassp/WangQLC0025","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iccv/DongF25","url":"https://dblp.org/rec/conf/iccv/DongF25","title":"Online Dense Point Tracking with Streaming Memory.","year":2025,"types":["Inproceedings"],"venue":"ICCV","doi":"https://doi.org/10.1109/ICCV51701.2025.00815","eventYear":2025,"numberOfCreators":2,"category":"conference","sources":["https://dblp.org/rec/conf/iccv/DongF25","https://doi.org/10.1109/ICCV51701.2025.00815"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/DongF25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iccv/FuWRSGFPHG25","url":"https://dblp.org/rec/conf/iccv/FuWRSGFPHG25","title":"ObjectRelator: Enabling Cross-View Object Relation Understanding Across Ego-Centric and Exo-Centric Perspectives.","year":2025,"types":["Inproceedings"],"venue":"ICCV","doi":"https://doi.org/10.1109/ICCV51701.2025.00616","eventYear":2025,"numberOfCreators":9,"category":"conference","sources":["https://dblp.org/rec/conf/iccv/FuWRSGFPHG25","https://doi.org/10.1109/ICCV51701.2025.00616"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/FuWRSGFPHG25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iccv/LiuWWLXF25","url":"https://dblp.org/rec/conf/iccv/LiuWWLXF25","title":"Spatial-Temporal Aware Visuomotor Diffusion Policy Learning.","year":2025,"types":["Inproceedings"],"venue":"ICCV","doi":"https://doi.org/10.1109/ICCV51701.2025.00669","eventYear":2025,"numberOfCreators":6,"category":"conference","sources":["https://dblp.org/rec/conf/iccv/LiuWWLXF25","https://doi.org/10.1109/ICCV51701.2025.00669"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/LiuWWLXF25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iccv/XuDXWCMFGXE25","url":"https://dblp.org/rec/conf/iccv/XuDXWCMFGXE25","title":"Diffusion-Based Imaginative Coordination for Bimanual Manipulation.","year":2025,"types":["Inproceedings"],"venue":"ICCV","doi":"https://doi.org/10.1109/ICCV51701.2025.01067","eventYear":2025,"numberOfCreators":10,"category":"conference","sources":["https://dblp.org/rec/conf/iccv/XuDXWCMFGXE25","https://doi.org/10.1109/ICCV51701.2025.01067"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/XuDXWCMFGXE25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iclr/DingF00025","url":"https://dblp.org/rec/conf/iclr/DingF00025","title":"Adaptive Pruning of Pretrained Transformer via Differential Inclusions.","year":2025,"types":["Inproceedings"],"venue":"ICLR","doi":null,"eventYear":2025,"numberOfCreators":5,"category":"conference","sources":["https://dblp.org/rec/conf/iclr/DingF00025"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iclr/DingF00025","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iclr/Xu0Z0G25","url":"https://dblp.org/rec/conf/iclr/Xu0Z0G25","title":"3D StreetUnveiler with Semantic-aware 2DGS - a simple baseline.","year":2025,"types":["Inproceedings"],"venue":"ICLR","doi":null,"eventYear":2025,"numberOfCreators":5,"category":"conference","sources":["https://dblp.org/rec/conf/iclr/Xu0Z0G25"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iclr/Xu0Z0G25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/icmcs/WangJXZWZCCWWF25","url":"https://dblp.org/rec/conf/icmcs/WangJXZWZCCWWF25","title":"VividPose: Vividly 3D-driven Stable Pose Diffusion of High Facial Fidelity.","year":2025,"types":["Inproceedings"],"venue":"ICME","doi":"https://doi.org/10.1109/ICME59968.2025.11209876","eventYear":2025,"numberOfCreators":11,"category":"conference","sources":["https://dblp.org/rec/conf/icmcs/WangJXZWZCCWWF25","https://doi.org/10.1109/ICME59968.2025.11209876"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/icmcs/WangJXZWZCCWWF25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/icml/Wu0W025","url":"https://dblp.org/rec/conf/icml/Wu0W025","title":"Bivariate Causal Discovery with Proxy Variables: Integral Solving and Beyond.","year":2025,"types":["Inproceedings"],"venue":"ICML","doi":null,"eventYear":2025,"numberOfCreators":4,"category":"conference","sources":["https://dblp.org/rec/conf/icml/Wu0W025"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/icml/Wu0W025","documentUrl":null,"type":"Inproceedings"},{"key":"conf/icml/ZhuPM0YW025","url":"https://dblp.org/rec/conf/icml/ZhuPM0YW025","title":"UniDB: A Unified Diffusion Bridge Framework via Stochastic Optimal Control.","year":2025,"types":["Inproceedings"],"venue":"ICML","doi":null,"eventYear":2025,"numberOfCreators":7,"category":"conference","sources":["https://dblp.org/rec/conf/icml/ZhuPM0YW025"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/icml/ZhuPM0YW025","documentUrl":null,"type":"Inproceedings"},{"key":"conf/icra/HuangLWFJX25","url":"https://dblp.org/rec/conf/icra/HuangLWFJX25","title":"You Only Estimate Once: Unified, One-stage, Real-Time Category-Level Articulated Object 6D Pose Estimation for Robotic Grasping.","year":2025,"types":["Inproceedings"],"venue":"ICRA","doi":"https://doi.org/10.1109/ICRA55743.2025.11128513","eventYear":2025,"numberOfCreators":6,"category":"conference","sources":["https://dblp.org/rec/conf/icra/HuangLWFJX25","https://doi.org/10.1109/ICRA55743.2025.11128513"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/icra/HuangLWFJX25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/ijcai/0001LPHJ0JW025","url":"https://dblp.org/rec/conf/ijcai/0001LPHJ0JW025","title":"CrossVTON: Mimicking the Logic Reasoning on Cross-Category Virtual Try-On Guided by Tri-Zone Priors.","year":2025,"types":["Inproceedings"],"venue":"IJCAI","doi":"https://doi.org/10.24963/IJCAI.2025/191","eventYear":2025,"numberOfCreators":9,"category":"conference","sources":["https://dblp.org/rec/conf/ijcai/0001LPHJ0JW025","https://doi.org/10.24963/IJCAI.2025/191"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/ijcai/0001LPHJ0JW025","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iros/GuLF25","url":"https://dblp.org/rec/conf/iros/GuLF25","title":"TransSoft: The Low-Cost, Adaptable, and Radial Reconfigurable Soft Hand for Diverse Object Grasping.","year":2025,"types":["Inproceedings"],"venue":"IROS","doi":"https://doi.org/10.1109/IROS60139.2025.11247145","eventYear":2025,"numberOfCreators":3,"category":"conference","sources":["https://dblp.org/rec/conf/iros/GuLF25","https://doi.org/10.1109/IROS60139.2025.11247145"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iros/GuLF25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iros/HeSWGFFS25","url":"https://dblp.org/rec/conf/iros/HeSWGFFS25","title":"Sequential Multi-Object Grasping with One Dexterous Hand.","year":2025,"types":["Inproceedings"],"venue":"IROS","doi":"https://doi.org/10.1109/IROS60139.2025.11246620","eventYear":2025,"numberOfCreators":7,"category":"conference","sources":["https://dblp.org/rec/conf/iros/HeSWGFFS25","https://doi.org/10.1109/IROS60139.2025.11246620"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iros/HeSWGFFS25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iros/WangFWFLJX25","url":"https://dblp.org/rec/conf/iros/WangFWFLJX25","title":"RAG-6DPose: Retrieval-Augmented 6D Pose Estimation via Leveraging CAD as Knowledge Base.","year":2025,"types":["Inproceedings"],"venue":"IROS","doi":"https://doi.org/10.1109/IROS60139.2025.11246449","eventYear":2025,"numberOfCreators":7,"category":"conference","sources":["https://dblp.org/rec/conf/iros/WangFWFLJX25","https://doi.org/10.1109/IROS60139.2025.11246449"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iros/WangFWFLJX25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/mm/LiHH0025","url":"https://dblp.org/rec/conf/mm/LiHH0025","title":"Ali-UI: Enhancing Complex Vision-Language Navigation with Alignment of Unified Map and Instruction Parsing.","year":2025,"types":["Inproceedings"],"venue":"ACM Multimedia","doi":"https://doi.org/10.1145/3746027.3755232","eventYear":2025,"numberOfCreators":5,"category":"conference","sources":["https://dblp.org/rec/conf/mm/LiHH0025","https://doi.org/10.1145/3746027.3755232"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/mm/LiHH0025","documentUrl":null,"type":"Inproceedings"},{"key":"conf/mm/LiuZCZL0025","url":"https://dblp.org/rec/conf/mm/LiuZCZL0025","title":"A Neural Representation Framework with LLM-Driven Spatial Reasoning for Open-Vocabulary 3D Visual Grounding.","year":2025,"types":["Inproceedings"],"venue":"ACM Multimedia","doi":"https://doi.org/10.1145/3746027.3754918","eventYear":2025,"numberOfCreators":7,"category":"conference","sources":["https://dblp.org/rec/conf/mm/LiuZCZL0025","https://doi.org/10.1145/3746027.3754918"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/mm/LiuZCZL0025","documentUrl":null,"type":"Inproceedings"},{"key":"conf/mm/TanL0XHJZW025","url":"https://dblp.org/rec/conf/mm/TanL0XHJZW025","title":"Disentangle Identity, Cooperate Emotion: Correlation-Aware Emotional Talking Portrait Generation.","year":2025,"types":["Inproceedings"],"venue":"ACM Multimedia","doi":"https://doi.org/10.1145/3746027.3755286","eventYear":2025,"numberOfCreators":9,"category":"conference","sources":["https://dblp.org/rec/conf/mm/TanL0XHJZW025","https://doi.org/10.1145/3746027.3755286"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/mm/TanL0XHJZW025","documentUrl":null,"type":"Inproceedings"},{"key":"conf/mm/ZhangL0FHZCW025","url":"https://dblp.org/rec/conf/mm/ZhangL0FHZCW025","title":"StrandDesigner: Towards Practical Strand Generation with Sketch Guidance.","year":2025,"types":["Inproceedings"],"venue":"ACM Multimedia","doi":"https://doi.org/10.1145/3746027.3755529","eventYear":2025,"numberOfCreators":9,"category":"conference","sources":["https://dblp.org/rec/conf/mm/ZhangL0FHZCW025","https://doi.org/10.1145/3746027.3755529"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/mm/ZhangL0FHZCW025","documentUrl":null,"type":"Inproceedings"},{"key":"conf/nips/LiHHFJX25","url":"https://dblp.org/rec/conf/nips/LiHHFJX25","title":"TP-MDDN: Task-Preferenced Multi-Demand-Driven Navigation with Autonomous Decision-Making.","year":2025,"types":["Inproceedings"],"venue":"NeurIPS","doi":null,"eventYear":2025,"numberOfCreators":6,"category":"conference","sources":["https://dblp.org/rec/conf/nips/LiHHFJX25"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/nips/LiHHFJX25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/nips/LiQFCQZPFHGJ25","url":"https://dblp.org/rec/conf/nips/LiQFCQZPFHGJ25","title":"Domain-RAG: Retrieval-Guided Compositional Image Generation for Cross-Domain Few-Shot Object Detection.","year":2025,"types":["Inproceedings"],"venue":"NeurIPS","doi":null,"eventYear":2025,"numberOfCreators":11,"category":"conference","sources":["https://dblp.org/rec/conf/nips/LiQFCQZPFHGJ25"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/nips/LiQFCQZPFHGJ25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/nips/WangHDZFLW25","url":"https://dblp.org/rec/conf/nips/WangHDZFLW25","title":"PPMStereo: Pick-and-Play Memory Construction for Consistent Dynamic Stereo Matching.","year":2025,"types":["Inproceedings"],"venue":"NeurIPS","doi":null,"eventYear":2025,"numberOfCreators":7,"category":"conference","sources":["https://dblp.org/rec/conf/nips/WangHDZFLW25"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/nips/WangHDZFLW25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/nips/WuXXLSGSF25","url":"https://dblp.org/rec/conf/nips/WuXXLSGSF25","title":"Towards Reliable and Holistic Visual In-Context Learning Prompt Selection.","year":2025,"types":["Inproceedings"],"venue":"NeurIPS","doi":null,"eventYear":2025,"numberOfCreators":8,"category":"conference","sources":["https://dblp.org/rec/conf/nips/WuXXLSGSF25"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/nips/WuXXLSGSF25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/siggrapha/CaoZLLYW0F25","url":"https://dblp.org/rec/conf/siggrapha/CaoZLLYW0F25","title":"Uni3C: Unifying Precisely 3D-Enhanced Camera and Human Motion Controls for Video Generation.","year":2025,"types":["Inproceedings"],"venue":"SIGGRAPH Asia","doi":"https://doi.org/10.1145/3757377.3763842","eventYear":2025,"numberOfCreators":8,"category":"conference","sources":["https://dblp.org/rec/conf/siggrapha/CaoZLLYW0F25","https://doi.org/10.1145/3757377.3763842"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/siggrapha/CaoZLLYW0F25","documentUrl":null,"type":"Inproceedings"},{"key":"journals/ml/WanFSFLJZ25","url":"https://dblp.org/rec/journals/ml/WanFSFLJZ25","title":"A new formulation of Lipschitz constrained with functional gradient learning for GANs.","year":2025,"types":["Article"],"venue":"Mach. Learn.","doi":"https://doi.org/10.1007/S10994-024-06633-9","numberOfCreators":7,"category":"journal","sources":["https://dblp.org/rec/journals/ml/WanFSFLJZ25","https://doi.org/10.1007/S10994-024-06633-9"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/ml/WanFSFLJZ25","documentUrl":null,"type":"Article"},{"key":"journals/pami/GaoFFWQF25","url":"https://dblp.org/rec/journals/pami/GaoFFWQF25","title":"MinD-3D++: Advancing fMRI-Based 3D Reconstruction With High-Quality Textured Mesh Generation and a Comprehensive Dataset.","year":2025,"types":["Article"],"venue":"IEEE Trans. Pattern Anal. Mach. Intell.","doi":"https://doi.org/10.1109/TPAMI.2025.3599860","numberOfCreators":6,"category":"journal","sources":["https://dblp.org/rec/journals/pami/GaoFFWQF25","https://doi.org/10.1109/TPAMI.2025.3599860"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/pami/GaoFFWQF25","documentUrl":null,"type":"Article"},{"key":"journals/pami/QianWJXF25","url":"https://dblp.org/rec/journals/pami/QianWJXF25","title":"Dynamic Routing and Knowledge Re-Learning for Data-Free Black-Box Attack.","year":2025,"types":["Article"],"venue":"IEEE Trans. Pattern Anal. Mach. Intell.","doi":"https://doi.org/10.1109/TPAMI.2024.3469952","numberOfCreators":5,"category":"journal","sources":["https://dblp.org/rec/journals/pami/QianWJXF25","https://doi.org/10.1109/TPAMI.2024.3469952"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/pami/QianWJXF25","documentUrl":null,"type":"Article"},{"key":"journals/spl/WangZXCF25","url":"https://dblp.org/rec/journals/spl/WangZXCF25","title":"MagicFace: Slot-Driven High-Fidelity One-Shot Facial Appearance Editing.","year":2025,"types":["Article"],"venue":"IEEE Signal Process. Lett.","doi":"https://doi.org/10.1109/LSP.2025.3563128","numberOfCreators":5,"category":"journal","sources":["https://dblp.org/rec/journals/spl/WangZXCF25","https://doi.org/10.1109/LSP.2025.3563128"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/spl/WangZXCF25","documentUrl":null,"type":"Article"},{"key":"journals/tip/WangQLFX25","url":"https://dblp.org/rec/journals/tip/WangQLFX25","title":"Image-Text-Image Knowledge Transfer for Lifelong Person Re-Identification With Hybrid Clothing States.","year":2025,"types":["Article"],"venue":"IEEE Trans. Image Process.","doi":"https://doi.org/10.1109/TIP.2025.3602745","numberOfCreators":5,"category":"journal","sources":["https://dblp.org/rec/journals/tip/WangQLFX25","https://doi.org/10.1109/TIP.2025.3602745"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/tip/WangQLFX25","documentUrl":null,"type":"Article"}],"preprints":[{"key":"journals/corr/abs-2501-03289","url":"https://dblp.org/rec/journals/corr/abs-2501-03289","title":"Adaptive Pruning of Pretrained Transformer via Differential Inclusions.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2501.03289","numberOfCreators":5,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2501-03289","https://doi.org/10.48550/ARXIV.2501.03289"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2501-03289","documentUrl":null,"type":"Informal","arxivId":"2501.03289","arxivUrl":"https://arxiv.org/abs/2501.03289"},{"key":"journals/corr/abs-2501-09350","url":"https://dblp.org/rec/journals/corr/abs-2501-09350","title":"Making Your Dreams A Reality: Decoding the Dreams into a Coherent Video Story from fMRI Signals.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2501.09350","numberOfCreators":4,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2501-09350","https://doi.org/10.48550/ARXIV.2501.09350"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2501-09350","documentUrl":null,"type":"Informal","arxivId":"2501.09350","arxivUrl":"https://arxiv.org/abs/2501.09350"},{"key":"journals/corr/abs-2501-11236","url":"https://dblp.org/rec/journals/corr/abs-2501-11236","title":"A New Formulation of Lipschitz Constrained With Functional Gradient Learning for GANs.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2501.11236","numberOfCreators":7,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2501-11236","https://doi.org/10.48550/ARXIV.2501.11236"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2501-11236","documentUrl":null,"type":"Informal","arxivId":"2501.11236","arxivUrl":"https://arxiv.org/abs/2501.11236"},{"key":"journals/corr/abs-2502-05749","url":"https://dblp.org/rec/journals/corr/abs-2502-05749","title":"UniDB: A Unified Diffusion Bridge Framework via Stochastic Optimal Control.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2502.05749","numberOfCreators":7,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2502-05749","https://doi.org/10.48550/ARXIV.2502.05749"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2502-05749","documentUrl":null,"type":"Informal","arxivId":"2502.05749","arxivUrl":"https://arxiv.org/abs/2502.05749"},{"key":"journals/corr/abs-2502-07531","url":"https://dblp.org/rec/journals/corr/abs-2502-07531","title":"VidCRAFT3: Camera, Object, and Lighting Control for Image-to-Video Generation.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2502.07531","numberOfCreators":7,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2502-07531","https://doi.org/10.48550/ARXIV.2502.07531"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2502-07531","documentUrl":null,"type":"Informal","arxivId":"2502.07531","arxivUrl":"https://arxiv.org/abs/2502.07531"},{"key":"journals/corr/abs-2502-11158","url":"https://dblp.org/rec/journals/corr/abs-2502-11158","title":"AnyRefill: A Unified, Data-Efficient Framework for Left-Prompt-Guided Vision Tasks.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2502.11158","numberOfCreators":6,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2502-11158","https://doi.org/10.48550/ARXIV.2502.11158"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2502-11158","documentUrl":null,"type":"Informal","arxivId":"2502.11158","arxivUrl":"https://arxiv.org/abs/2502.11158"},{"key":"journals/corr/abs-2502-14373","url":"https://dblp.org/rec/journals/corr/abs-2502-14373","title":"CrossVTON: Mimicking the Logic Reasoning on Cross-category Virtual Try-on guided by Tri-zone Priors.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2502.14373","numberOfCreators":9,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2502-14373","https://doi.org/10.48550/ARXIV.2502.14373"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2502-14373","documentUrl":null,"type":"Informal","arxivId":"2502.14373","arxivUrl":"https://arxiv.org/abs/2502.14373"},{"key":"journals/corr/abs-2502-16587","url":"https://dblp.org/rec/journals/corr/abs-2502-16587","title":"Human2Robot: Learning Robot Actions from Paired Human-Robot Videos.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2502.16587","numberOfCreators":10,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2502-16587","https://doi.org/10.48550/ARXIV.2502.16587"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2502-16587","documentUrl":null,"type":"Informal","arxivId":"2502.16587","arxivUrl":"https://arxiv.org/abs/2502.16587"},{"key":"journals/corr/abs-2503-01175","url":"https://dblp.org/rec/journals/corr/abs-2503-01175","title":"HOP: Heterogeneous Topology-based Multimodal Entanglement for Co-Speech Gesture Generation.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2503.01175","numberOfCreators":5,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2503-01175","https://doi.org/10.48550/ARXIV.2503.01175"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-01175","documentUrl":null,"type":"Informal","arxivId":"2503.01175","arxivUrl":"https://arxiv.org/abs/2503.01175"},{"key":"journals/corr/abs-2503-01542","url":"https://dblp.org/rec/journals/corr/abs-2503-01542","title":"Revisiting Large Language Model Pruning using Neuron Semantic Attribution.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2503.01542","numberOfCreators":4,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2503-01542","https://doi.org/10.48550/ARXIV.2503.01542"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-01542","documentUrl":null,"type":"Informal","arxivId":"2503.01542","arxivUrl":"https://arxiv.org/abs/2503.01542"},{"key":"journals/corr/abs-2503-06471","url":"https://dblp.org/rec/journals/corr/abs-2503-06471","title":"Online Dense Point Tracking with Streaming Memory.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2503.06471","numberOfCreators":2,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2503-06471","https://doi.org/10.48550/ARXIV.2503.06471"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-06471","documentUrl":null,"type":"Informal","arxivId":"2503.06471","arxivUrl":"https://arxiv.org/abs/2503.06471"},{"key":"journals/corr/abs-2503-06940","url":"https://dblp.org/rec/journals/corr/abs-2503-06940","title":"CineBrain: A Large-Scale Multi-Modal Brain Dataset During Naturalistic Audiovisual Narrative Processing.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2503.06940","numberOfCreators":5,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2503-06940","https://doi.org/10.48550/ARXIV.2503.06940"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-06940","documentUrl":null,"type":"Informal","arxivId":"2503.06940","arxivUrl":"https://arxiv.org/abs/2503.06940"},{"key":"journals/corr/abs-2503-09078","url":"https://dblp.org/rec/journals/corr/abs-2503-09078","title":"Sequential Multi-Object Grasping with One Dexterous Hand.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2503.09078","numberOfCreators":7,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2503-09078","https://doi.org/10.48550/ARXIV.2503.09078"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-09078","documentUrl":null,"type":"Informal","arxivId":"2503.09078","arxivUrl":"https://arxiv.org/abs/2503.09078"},{"key":"journals/corr/abs-2503-15831","url":"https://dblp.org/rec/journals/corr/abs-2503-15831","title":"EDEN: Enhanced Diffusion for High-quality Large-motion Video Frame Interpolation.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2503.15831","numberOfCreators":7,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2503-15831","https://doi.org/10.48550/ARXIV.2503.15831"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-15831","documentUrl":null,"type":"Informal","arxivId":"2503.15831","arxivUrl":"https://arxiv.org/abs/2503.15831"},{"key":"journals/corr/abs-2503-16921","url":"https://dblp.org/rec/journals/corr/abs-2503-16921","title":"When Preferences Diverge: Aligning Diffusion Models with Minority-Aware Adaptive DPO.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2503.16921","numberOfCreators":8,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2503-16921","https://doi.org/10.48550/ARXIV.2503.16921"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-16921","documentUrl":null,"type":"Informal","arxivId":"2503.16921","arxivUrl":"https://arxiv.org/abs/2503.16921"},{"key":"journals/corr/abs-2503-23297","url":"https://dblp.org/rec/journals/corr/abs-2503-23297","title":"ReasonGrounder: LVLM-Guided Hierarchical Feature Splatting for Open-Vocabulary 3D Visual Grounding and Reasoning.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2503.23297","numberOfCreators":7,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2503-23297","https://doi.org/10.48550/ARXIV.2503.23297"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-23297","documentUrl":null,"type":"Informal","arxivId":"2503.23297","arxivUrl":"https://arxiv.org/abs/2503.23297"},{"key":"journals/corr/abs-2504-00432","url":"https://dblp.org/rec/journals/corr/abs-2504-00432","title":"DecoFuse: Decomposing and Fusing the \"What\", \"Where\", and \"How\" for Brain-Inspired fMRI-to-Video Decoding.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2504.00432","numberOfCreators":6,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2504-00432","https://doi.org/10.48550/ARXIV.2504.00432"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2504-00432","documentUrl":null,"type":"Informal","arxivId":"2504.00432","arxivUrl":"https://arxiv.org/abs/2504.00432"},{"key":"journals/corr/abs-2504-10685","url":"https://dblp.org/rec/journals/corr/abs-2504-10685","title":"NTIRE 2025 Challenge on Cross-Domain Few-Shot Object Detection: Methods and Results.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2504.10685","numberOfCreators":62,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2504-10685","https://doi.org/10.48550/ARXIV.2504.10685"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2504-10685","documentUrl":null,"type":"Informal","arxivId":"2504.10685","arxivUrl":"https://arxiv.org/abs/2504.10685"},{"key":"journals/corr/abs-2504-11230","url":"https://dblp.org/rec/journals/corr/abs-2504-11230","title":"CAP-Net: A Unified Network for 6D Pose and Size Estimation of Categorical Articulated Parts from a Single RGB-D Image.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2504.11230","numberOfCreators":6,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2504-11230","https://doi.org/10.48550/ARXIV.2504.11230"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2504-11230","documentUrl":null,"type":"Informal","arxivId":"2504.11230","arxivUrl":"https://arxiv.org/abs/2504.11230"},{"key":"journals/corr/abs-2504-14899","url":"https://dblp.org/rec/journals/corr/abs-2504-14899","title":"Uni3C: Unifying Precisely 3D-Enhanced Camera and Human Motion Controls for Video Generation.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2504.14899","numberOfCreators":8,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2504-14899","https://doi.org/10.48550/ARXIV.2504.14899"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2504-14899","documentUrl":null,"type":"Informal","arxivId":"2504.14899","arxivUrl":"https://arxiv.org/abs/2504.14899"},{"key":"journals/corr/abs-2504-18087","url":"https://dblp.org/rec/journals/corr/abs-2504-18087","title":"Disentangle Identity, Cooperate Emotion: Correlation-Aware Emotional Talking Portrait Generation.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2504.18087","numberOfCreators":9,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2504-18087","https://doi.org/10.48550/ARXIV.2504.18087"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2504-18087","documentUrl":null,"type":"Informal","arxivId":"2504.18087","arxivUrl":"https://arxiv.org/abs/2504.18087"},{"key":"journals/corr/abs-2505-19571","url":"https://dblp.org/rec/journals/corr/abs-2505-19571","title":"VTBench: Comprehensive Benchmark Suite Towards Real-World Virtual Try-on Models.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2505.19571","numberOfCreators":8,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2505-19571","https://doi.org/10.48550/ARXIV.2505.19571"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-19571","documentUrl":null,"type":"Informal","arxivId":"2505.19571","arxivUrl":"https://arxiv.org/abs/2505.19571"},{"key":"journals/corr/abs-2505-21528","url":"https://dblp.org/rec/journals/corr/abs-2505-21528","title":"UniDB++: Fast Sampling of Unified Diffusion Bridge.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2505.21528","numberOfCreators":7,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2505-21528","https://doi.org/10.48550/ARXIV.2505.21528"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-21528","documentUrl":null,"type":"Informal","arxivId":"2505.21528","arxivUrl":"https://arxiv.org/abs/2505.21528"},{"key":"journals/corr/abs-2506-05719","url":"https://dblp.org/rec/journals/corr/abs-2506-05719","title":"You Only Estimate Once: Unified, One-stage, Real-Time Category-level Articulated Object 6D Pose Estimation for Robotic Grasping.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2506.05719","numberOfCreators":6,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2506-05719","https://doi.org/10.48550/ARXIV.2506.05719"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-05719","documentUrl":null,"type":"Informal","arxivId":"2506.05719","arxivUrl":"https://arxiv.org/abs/2506.05719"},{"key":"journals/corr/abs-2506-05856","url":"https://dblp.org/rec/journals/corr/abs-2506-05856","title":"Cross-View Multi-Modal Segmentation @ Ego-Exo4D Challenges 2025.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2506.05856","numberOfCreators":5,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2506-05856","https://doi.org/10.48550/ARXIV.2506.05856"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-05856","documentUrl":null,"type":"Informal","arxivId":"2506.05856","arxivUrl":"https://arxiv.org/abs/2506.05856"},{"key":"journals/corr/abs-2506-05872","url":"https://dblp.org/rec/journals/corr/abs-2506-05872","title":"Domain-RAG: Retrieval-Guided Compositional Image Generation for Cross-Domain Few-Shot Object Detection.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2506.05872","numberOfCreators":11,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2506-05872","https://doi.org/10.48550/ARXIV.2506.05872"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-05872","documentUrl":null,"type":"Informal","arxivId":"2506.05872","arxivUrl":"https://arxiv.org/abs/2506.05872"},{"key":"journals/corr/abs-2506-18325","url":"https://dblp.org/rec/journals/corr/abs-2506-18325","title":"NSFW-Classifier Guided Prompt Sanitization for Safe Text-to-Image Generation.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2506.18325","numberOfCreators":4,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2506-18325","https://doi.org/10.48550/ARXIV.2506.18325"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-18325","documentUrl":null,"type":"Informal","arxivId":"2506.18325","arxivUrl":"https://arxiv.org/abs/2506.18325"},{"key":"journals/corr/abs-2506-18856","url":"https://dblp.org/rec/journals/corr/abs-2506-18856","title":"RAG-6DPose: Retrieval-Augmented 6D Pose Estimation via Leveraging CAD as Knowledge Base.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2506.18856","numberOfCreators":7,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2506-18856","https://doi.org/10.48550/ARXIV.2506.18856"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-18856","documentUrl":null,"type":"Informal","arxivId":"2506.18856","arxivUrl":"https://arxiv.org/abs/2506.18856"},{"key":"journals/corr/abs-2506-23508","url":"https://dblp.org/rec/journals/corr/abs-2506-23508","title":"Reinforcement Fine-Tuning Enables MLLMs Learning Novel Tasks Stably.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2506.23508","numberOfCreators":13,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2506-23508","https://doi.org/10.48550/ARXIV.2506.23508"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-23508","documentUrl":null,"type":"Informal","arxivId":"2506.23508","arxivUrl":"https://arxiv.org/abs/2506.23508"},{"key":"journals/corr/abs-2507-01424","url":"https://dblp.org/rec/journals/corr/abs-2507-01424","title":"TriVLA: A Triple-System-Based Unified Vision-Language-Action Model for General Robot Control.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2507.01424","numberOfCreators":5,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2507-01424","https://doi.org/10.48550/ARXIV.2507.01424"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2507-01424","documentUrl":null,"type":"Informal","arxivId":"2507.01424","arxivUrl":"https://arxiv.org/abs/2507.01424"},{"key":"journals/corr/abs-2507-06710","url":"https://dblp.org/rec/journals/corr/abs-2507-06710","title":"Spatial-Temporal Aware Visuomotor Diffusion Policy Learning.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2507.06710","numberOfCreators":6,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2507-06710","https://doi.org/10.48550/ARXIV.2507.06710"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2507-06710","documentUrl":null,"type":"Informal","arxivId":"2507.06710","arxivUrl":"https://arxiv.org/abs/2507.06710"},{"key":"journals/corr/abs-2507-06719","url":"https://dblp.org/rec/journals/corr/abs-2507-06719","title":"A Neural Representation Framework with LLM-Driven Spatial Reasoning for Open-Vocabulary 3D Visual Grounding.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2507.06719","numberOfCreators":7,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2507-06719","https://doi.org/10.48550/ARXIV.2507.06719"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2507-06719","documentUrl":null,"type":"Informal","arxivId":"2507.06719","arxivUrl":"https://arxiv.org/abs/2507.06719"},{"key":"journals/corr/abs-2507-10532","url":"https://dblp.org/rec/journals/corr/abs-2507-10532","title":"Reasoning or Memorization? Unreliable Results of Reinforcement Learning Due to Data Contamination.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2507.10532","numberOfCreators":12,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2507-10532","https://doi.org/10.48550/ARXIV.2507.10532"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2507-10532","documentUrl":null,"type":"Informal","arxivId":"2507.10532","arxivUrl":"https://arxiv.org/abs/2507.10532"},{"key":"journals/corr/abs-2507-11296","url":"https://dblp.org/rec/journals/corr/abs-2507-11296","title":"Diffusion-Based Imaginative Coordination for Bimanual Manipulation.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2507.11296","numberOfCreators":10,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2507-11296","https://doi.org/10.48550/ARXIV.2507.11296"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2507-11296","documentUrl":null,"type":"Informal","arxivId":"2507.11296","arxivUrl":"https://arxiv.org/abs/2507.11296"},{"key":"journals/corr/abs-2508-01650","url":"https://dblp.org/rec/journals/corr/abs-2508-01650","title":"StrandDesigner: Towards Practical Strand Generation with Sketch Guidance.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2508.01650","numberOfCreators":9,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2508-01650","https://doi.org/10.48550/ARXIV.2508.01650"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-01650","documentUrl":null,"type":"Informal","arxivId":"2508.01650","arxivUrl":"https://arxiv.org/abs/2508.01650"},{"key":"journals/corr/abs-2508-03404","url":"https://dblp.org/rec/journals/corr/abs-2508-03404","title":"Visual Document Understanding and Question Answering: A Multi-Agent Collaboration Framework with Test-Time Scaling.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2508.03404","numberOfCreators":9,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2508-03404","https://doi.org/10.48550/ARXIV.2508.03404"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-03404","documentUrl":null,"type":"Informal","arxivId":"2508.03404","arxivUrl":"https://arxiv.org/abs/2508.03404"},{"key":"journals/corr/abs-2508-03694","url":"https://dblp.org/rec/journals/corr/abs-2508-03694","title":"LongVie: Multimodal-Guided Controllable Ultra-Long Video Generation.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2508.03694","numberOfCreators":8,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2508-03694","https://doi.org/10.48550/ARXIV.2508.03694"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-03694","documentUrl":null,"type":"Informal","arxivId":"2508.03694","arxivUrl":"https://arxiv.org/abs/2508.03694"},{"key":"journals/corr/abs-2508-06082","url":"https://dblp.org/rec/journals/corr/abs-2508-06082","title":"SwiftVideo: A Unified Framework for Few-Step Video Generation through Trajectory-Distribution Alignment.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2508.06082","numberOfCreators":9,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2508-06082","https://doi.org/10.48550/ARXIV.2508.06082"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-06082","documentUrl":null,"type":"Informal","arxivId":"2508.06082","arxivUrl":"https://arxiv.org/abs/2508.06082"},{"key":"journals/corr/abs-2508-11904","url":"https://dblp.org/rec/journals/corr/abs-2508-11904","title":"SafeCtrl: Region-Based Safety Control for Text-to-Image Diffusion via Detect-Then-Suppress.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2508.11904","numberOfCreators":4,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2508-11904","https://doi.org/10.48550/ARXIV.2508.11904"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-11904","documentUrl":null,"type":"Informal","arxivId":"2508.11904","arxivUrl":"https://arxiv.org/abs/2508.11904"},{"key":"journals/corr/abs-2509-24776","url":"https://dblp.org/rec/journals/corr/abs-2509-24776","title":"VTPerception-R1: Enhancing Multimodal Reasoning via Explicit Visual and Textual Perceptual Grounding.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2509.24776","numberOfCreators":7,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2509-24776","https://doi.org/10.48550/ARXIV.2509.24776"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-24776","documentUrl":null,"type":"Informal","arxivId":"2509.24776","arxivUrl":"https://arxiv.org/abs/2509.24776"},{"key":"journals/corr/abs-2509-25989","url":"https://dblp.org/rec/journals/corr/abs-2509-25989","title":"Towards Reliable and Holistic Visual In-Context Learning Prompt Selection.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2509.25989","numberOfCreators":8,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2509-25989","https://doi.org/10.48550/ARXIV.2509.25989"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-25989","documentUrl":null,"type":"Informal","arxivId":"2509.25989","arxivUrl":"https://arxiv.org/abs/2509.25989"},{"key":"journals/corr/abs-2510-03291","url":"https://dblp.org/rec/journals/corr/abs-2510-03291","title":"UniPruning: Unifying Local Metric and Global Feedback for Scalable Sparse LLMs.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2510.03291","numberOfCreators":5,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2510-03291","https://doi.org/10.48550/ARXIV.2510.03291"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-03291","documentUrl":null,"type":"Informal","arxivId":"2510.03291","arxivUrl":"https://arxiv.org/abs/2510.03291"},{"key":"journals/corr/abs-2510-04196","url":"https://dblp.org/rec/journals/corr/abs-2510-04196","title":"COSMO-RL: Towards Trustworthy LMRMs via Joint Safety and Stability.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2510.04196","numberOfCreators":10,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2510-04196","https://doi.org/10.48550/ARXIV.2510.04196"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-04196","documentUrl":null,"type":"Informal","arxivId":"2510.04196","arxivUrl":"https://arxiv.org/abs/2510.04196"},{"key":"journals/corr/abs-2510-11566","url":"https://dblp.org/rec/journals/corr/abs-2510-11566","title":"SCOOP'D: Learning Mixed-Liquid-Solid Scooping via Sim2Real Generative Policy.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2510.11566","numberOfCreators":8,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2510-11566","https://doi.org/10.48550/ARXIV.2510.11566"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-11566","documentUrl":null,"type":"Informal","arxivId":"2510.11566","arxivUrl":"https://arxiv.org/abs/2510.11566"},{"key":"journals/corr/abs-2510-11687","url":"https://dblp.org/rec/journals/corr/abs-2510-11687","title":"Beyond 'Templates': Category-Agnostic Object Pose, Size, and Shape Estimation from a Single View.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2510.11687","numberOfCreators":5,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2510-11687","https://doi.org/10.48550/ARXIV.2510.11687"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-11687","documentUrl":null,"type":"Informal","arxivId":"2510.11687","arxivUrl":"https://arxiv.org/abs/2510.11687"},{"key":"journals/corr/abs-2510-13778","url":"https://dblp.org/rec/journals/corr/abs-2510-13778","title":"InternVLA-M1: A Spatially Guided Vision-Language-Action Framework for Generalist Robot Policy.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2510.13778","numberOfCreators":29,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2510-13778","https://doi.org/10.48550/ARXIV.2510.13778"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-13778","documentUrl":null,"type":"Informal","arxivId":"2510.13778","arxivUrl":"https://arxiv.org/abs/2510.13778"},{"key":"journals/corr/abs-2510-20178","url":"https://dblp.org/rec/journals/corr/abs-2510-20178","title":"PPMStereo: Pick-and-Play Memory Construction for Consistent Dynamic Stereo Matching.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2510.20178","numberOfCreators":7,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2510-20178","https://doi.org/10.48550/ARXIV.2510.20178"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-20178","documentUrl":null,"type":"Informal","arxivId":"2510.20178","arxivUrl":"https://arxiv.org/abs/2510.20178"},{"key":"journals/corr/abs-2510-21461","url":"https://dblp.org/rec/journals/corr/abs-2510-21461","title":"VidSplice: Towards Coherent Video Inpainting via Explicit Spaced Frame Guidance.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2510.21461","numberOfCreators":5,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2510-21461","https://doi.org/10.48550/ARXIV.2510.21461"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-21461","documentUrl":null,"type":"Informal","arxivId":"2510.21461","arxivUrl":"https://arxiv.org/abs/2510.21461"},{"key":"journals/corr/abs-2511-13035","url":"https://dblp.org/rec/journals/corr/abs-2511-13035","title":"One-Step Generative Policies with Q-Learning: A Reformulation of MeanFlow.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2511.13035","numberOfCreators":7,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2511-13035","https://doi.org/10.48550/ARXIV.2511.13035"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2511-13035","documentUrl":null,"type":"Informal","arxivId":"2511.13035","arxivUrl":"https://arxiv.org/abs/2511.13035"},{"key":"journals/corr/abs-2511-17225","url":"https://dblp.org/rec/journals/corr/abs-2511-17225","title":"TP-MDDN: Task-Preferenced Multi-Demand-Driven Navigation with Autonomous Decision-Making.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2511.17225","numberOfCreators":6,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2511-17225","https://doi.org/10.48550/ARXIV.2511.17225"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2511-17225","documentUrl":null,"type":"Informal","arxivId":"2511.17225","arxivUrl":"https://arxiv.org/abs/2511.17225"},{"key":"journals/corr/abs-2511-18765","url":"https://dblp.org/rec/journals/corr/abs-2511-18765","title":"NI-Tex: Non-isometric Image-based Garment Texture Generation.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2511.18765","numberOfCreators":7,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2511-18765","https://doi.org/10.48550/ARXIV.2511.18765"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2511-18765","documentUrl":null,"type":"Informal","arxivId":"2511.18765","arxivUrl":"https://arxiv.org/abs/2511.18765"},{"key":"journals/corr/abs-2511-20886","url":"https://dblp.org/rec/journals/corr/abs-2511-20886","title":"V2-SAM: Marrying SAM2 with Multi-Prompt Experts for Cross-View Object Correspondence.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2511.20886","numberOfCreators":10,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2511-20886","https://doi.org/10.48550/ARXIV.2511.20886"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2511-20886","documentUrl":null,"type":"Informal","arxivId":"2511.20886","arxivUrl":"https://arxiv.org/abs/2511.20886"},{"key":"journals/corr/abs-2512-02835","url":"https://dblp.org/rec/journals/corr/abs-2512-02835","title":"ReVSeg: Incentivizing the Reasoning Chain for Video Segmentation with Reinforcement Learning.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2512.02835","numberOfCreators":7,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2512-02835","https://doi.org/10.48550/ARXIV.2512.02835"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-02835","documentUrl":null,"type":"Informal","arxivId":"2512.02835","arxivUrl":"https://arxiv.org/abs/2512.02835"},{"key":"journals/corr/abs-2512-13604","url":"https://dblp.org/rec/journals/corr/abs-2512-13604","title":"LongVie 2: Multimodal Controllable Ultra-Long Video World Model.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2512.13604","numberOfCreators":10,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2512-13604","https://doi.org/10.48550/ARXIV.2512.13604"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-13604","documentUrl":null,"type":"Informal","arxivId":"2512.13604","arxivUrl":"https://arxiv.org/abs/2512.13604"},{"key":"journals/corr/abs-2512-21201","url":"https://dblp.org/rec/journals/corr/abs-2512-21201","title":"Schrödinger's Navigator: Imagining an Ensemble of Futures for Zero-Shot Object Navigation.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2512.21201","numberOfCreators":7,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2512-21201","https://doi.org/10.48550/ARXIV.2512.21201"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-21201","documentUrl":null,"type":"Informal","arxivId":"2512.21201","arxivUrl":"https://arxiv.org/abs/2512.21201"}],"excludedFormal":[],"otherRecords":[],"matchedName":"Yanwei Fu","databaseLabel":"Yanwei Fu 0001","databaseMetadata":{"type":["https://dblp.org/rdf/schema#Person","https://dblp.org/rdf/schema#Creator"],"label":["Yanwei Fu 0001"],"affiliation":["Nanjing University, National Key Laboratory for Novel Software Technology, China","Fudan University, School of Data Science, Shanghai, China","Disney Research, Pittsburgh, PA, USA","Queen Mary University of London, UK","Zhejiang Normal University, Fudan ISTBI-ZJNU Algorithm Centre for Brain-inspired Intelligence, Jinhua, China"],"homepage":["https://openreview.net/profile?id=~Yanwei_Fu2"],"orcid":["https://orcid.org/0000-0002-6595-6893"],"primaryAffiliation":["Fudan University, School of Data Science, Shanghai, China"],"primaryHomepage":["https://openreview.net/profile?id=~Yanwei_Fu2"]},"rawFormalRecordCount2025":44,"signatureAudit":{"completedAt":"2026-10-19","frozen":true,"scope":"对 B 组 39 个数值档案的全部 1074 条原始 2025 正式记录扫描 DBLP author-signature ORCID 和机构；复用既有 59 条 Crossref 核验，补查 6 条新触发记录。重点核查不同 ORCID，以及只有预期机构之外机构的条目。本轮不扩展为所有作者逐篇全文审计。","formalRecordCoverage":44,"orcidCounts":{"https://orcid.org/0000-0002-6595-6893":10},"institutionCounts":{"Fudan University":34,"Ministry of Education of the People's Republic of China (MOE)":1,"Shanghai Center for Brain Science and Brain-Inspired Technology":2,"Sofia University":3,"Zhejiang Normal University (ZJNU)":3},"caveat":"机构名称可能由 DBLP 自动映射而失真；多 ORCID 也不自动等于异人。只有有原始资料支撑的错归才作确认排除，未解决分支则暂停总数。"},"labName":null,"labUrl":null,"labEvidence":"本轮补查本人当前主页，只明确复旦大学、上海创智学院任职及学生，未找到公开明确命名的当前实验室；不采用第三方反推的实验室名称。","labSourceUrl":"https://yanweifu.github.io/index.html","sourceWarning":false,"excludedOther":[],"excludedHomonyms":[],"unassignedCandidates":[],"knownPreprintMinimum2025":null,"excludedMisattributed":[],"displayNotes":"身份已与原名单机构及公开资料核对确认。2025 年正式记录 44 条（会议 39、期刊 5），所有作者位置均计入，不表示主导或贡献份额；预印本 55 条单列，不加总。","labDisplayNotes":"本人当前主页写明在复旦大学与上海创智学院的任职及所带学生，但未见具名实验室；不采用第三方反推的名称，图中以「姓名及合作者」单列。"},{"index":41,"name":"Yulan Guo","nameZh":"郭裕兰","role":"Professor","affiliation":"Sun Yat-sen University","affiliationZh":"中山大学","source":"DBLP RDF via official SPARQL; primary-source identity checks","sourceUrl":"https://sparql.dblp.org/","profileUrl":"https://dblp.org/pid/127/0477.html","identifier":"127/0477","retrievedAt":"2026-10-19","count2025":48,"conference2025":21,"journal2025":27,"preprint2025":18,"status":"matched_with_source_warning","notes":"DBLP HTML 页面提示 ID conflict found in this bibliography（ORCID 冲突）；作者身份与学校/个人来源相符，但应与普通已确认记录分开展示。","identityEvidence":[{"url":"https://dblp.org/pid/127/0477.html","evidence":"DBLP RDF 类型为 Person，消歧后名字为 Yulan Guo。此档案未提供可用机构元数据，以下以本人/机构/出版商来源补证。"},{"url":"https://www.yulanguo.cn/","evidence":"个人主页列明 Yulan Guo、Sun Yat-sen University 和 guoyulan@sysu.edu.cn；其个人论文列表与所选 DBLP 记录交叉匹配。"},{"url":"https://www.yulanguo.cn/","evidence":"此本人或机构页面的正文与所选档案中 1 条 2025 记录标题匹配，其中 1 条为当前计入的正式记录（忽略空格、标点、大小写）。","matchedPaperKeys":["journals/pami/WangGWDXYA25"],"matchedFormalPaperKeys":["journals/pami/WangGWDXYA25"]}],"papers":[{"key":"conf/aaai/JiangZWYG25","url":"https://dblp.org/rec/conf/aaai/JiangZWYG25","title":"AIQViT: Architecture-Informed Post-Training Quantization for Vision Transformers.","year":2025,"types":["Inproceedings"],"venue":"AAAI","doi":"https://doi.org/10.1609/AAAI.V39I17.33939","eventYear":2025,"numberOfCreators":5,"category":"conference","sources":["https://dblp.org/rec/conf/aaai/JiangZWYG25","https://doi.org/10.1609/AAAI.V39I17.33939"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/aaai/JiangZWYG25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/accv/LiuWGZG24","url":"https://dblp.org/rec/conf/accv/LiuWGZG24","title":"Pluggable Style Representation Learning for Multi-style Transfer.","year":2025,"types":["Inproceedings"],"venue":"ACCV (6)","doi":"https://doi.org/10.1007/978-981-96-0960-4_18","eventYear":2024,"numberOfCreators":5,"category":"conference","sources":["https://dblp.org/rec/conf/accv/LiuWGZG24","https://doi.org/10.1007/978-981-96-0960-4_18"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2024,"sourceUrl":"https://dblp.org/rec/conf/accv/LiuWGZG24","documentUrl":null,"type":"Inproceedings"},{"key":"conf/cvpr/LiuWZYG25","url":"https://dblp.org/rec/conf/cvpr/LiuWZYG25","title":"SaMam: Style-aware State Space Model for Arbitrary Image Style Transfer.","year":2025,"types":["Inproceedings"],"venue":"CVPR","doi":"https://doi.org/10.1109/CVPR52734.2025.02651","eventYear":2025,"numberOfCreators":5,"category":"conference","sources":["https://dblp.org/rec/conf/cvpr/LiuWZYG25","https://doi.org/10.1109/CVPR52734.2025.02651"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/LiuWZYG25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/cvpr/TangZLGD0X25","url":"https://dblp.org/rec/conf/cvpr/TangZLGD0X25","title":"OnlineAnySeg: Online Zero-Shot 3D Segmentation by Visual Foundation Model Guided 2D Mask Merging.","year":2025,"types":["Inproceedings"],"venue":"CVPR","doi":"https://doi.org/10.1109/CVPR52734.2025.00348","eventYear":2025,"numberOfCreators":7,"category":"conference","sources":["https://dblp.org/rec/conf/cvpr/TangZLGD0X25","https://doi.org/10.1109/CVPR52734.2025.00348"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/TangZLGD0X25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/cvpr/WangLZTW00TGJWY25","url":"https://dblp.org/rec/conf/cvpr/WangLZTW00TGJWY25","title":"NTIRE 2025 Challenge on Light Field Image Super-Resolution: Methods and Results.","year":2025,"types":["Inproceedings"],"venue":"CVPR Workshops","doi":null,"eventYear":2025,"numberOfCreators":74,"category":"conference","sources":["https://dblp.org/rec/conf/cvpr/WangLZTW00TGJWY25"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/WangLZTW00TGJWY25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/cvpr/WangWMHXG25","url":"https://dblp.org/rec/conf/cvpr/WangWMHXG25","title":"VideoDirector: Precise Video Editing via Text-to-Video Models.","year":2025,"types":["Inproceedings"],"venue":"CVPR","doi":"https://doi.org/10.1109/CVPR52734.2025.00247","eventYear":2025,"numberOfCreators":6,"category":"conference","sources":["https://dblp.org/rec/conf/cvpr/WangWMHXG25","https://doi.org/10.1109/CVPR52734.2025.00247"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/WangWMHXG25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/cvpr/WangZLLXWGW25","url":"https://dblp.org/rec/conf/cvpr/WangZLLXWGW25","title":"TopNet: Transformer-Efficient Occupancy Prediction Network for Octree-Structured Point Cloud Geometry Compression.","year":2025,"types":["Inproceedings"],"venue":"CVPR","doi":"https://doi.org/10.1109/CVPR52734.2025.02543","eventYear":2025,"numberOfCreators":8,"category":"conference","sources":["https://dblp.org/rec/conf/cvpr/WangZLLXWGW25","https://doi.org/10.1109/CVPR52734.2025.02543"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/WangZLLXWGW25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/cvpr/XuWCA0G25","url":"https://dblp.org/rec/conf/cvpr/XuWCA0G25","title":"DropoutGS: Dropping Out Gaussians for Better Sparse-view Rendering.","year":2025,"types":["Inproceedings"],"venue":"CVPR","doi":"https://doi.org/10.1109/CVPR52734.2025.00074","eventYear":2025,"numberOfCreators":6,"category":"conference","sources":["https://dblp.org/rec/conf/cvpr/XuWCA0G25","https://doi.org/10.1109/CVPR52734.2025.00074"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/XuWCA0G25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/cvpr/ZhaoAZXG25","url":"https://dblp.org/rec/conf/cvpr/ZhaoAZXG25","title":"Progressive Correspondence Regenerator for Robust 3D Registration.","year":2025,"types":["Inproceedings"],"venue":"CVPR","doi":"https://doi.org/10.1109/CVPR52734.2025.00121","eventYear":2025,"numberOfCreators":5,"category":"conference","sources":["https://dblp.org/rec/conf/cvpr/ZhaoAZXG25","https://doi.org/10.1109/CVPR52734.2025.00121"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/ZhaoAZXG25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/eccv/FuWXWLGBB24","url":"https://dblp.org/rec/conf/eccv/FuWXWLGBB24","title":"AEDNet: Adaptive Embedding and Multiview-Aware Disentanglement for Point Cloud Completion.","year":2025,"types":["Inproceedings"],"venue":"ECCV (11)","doi":"https://doi.org/10.1007/978-3-031-73247-8_8","eventYear":2024,"numberOfCreators":8,"category":"conference","sources":["https://dblp.org/rec/conf/eccv/FuWXWLGBB24","https://doi.org/10.1007/978-3-031-73247-8_8"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2024,"sourceUrl":"https://dblp.org/rec/conf/eccv/FuWXWLGBB24","documentUrl":null,"type":"Inproceedings"},{"key":"conf/eccv/MaLPG24","url":"https://dblp.org/rec/conf/eccv/MaLPG24","title":"Heterogeneous Graph Learning for Scene Graph Prediction in 3D Point Clouds.","year":2025,"types":["Inproceedings"],"venue":"ECCV (26)","doi":"https://doi.org/10.1007/978-3-031-73347-5_16","eventYear":2024,"numberOfCreators":4,"category":"conference","sources":["https://dblp.org/rec/conf/eccv/MaLPG24","https://doi.org/10.1007/978-3-031-73347-5_16"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2024,"sourceUrl":"https://dblp.org/rec/conf/eccv/MaLPG24","documentUrl":null,"type":"Inproceedings"},{"key":"conf/eccv/WangLCWZXG24","url":"https://dblp.org/rec/conf/eccv/WangLCWZXG24","title":"Distractor-Free Novel View Synthesis via Exploiting Memorization Effect in Optimization.","year":2025,"types":["Inproceedings"],"venue":"ECCV (54)","doi":"https://doi.org/10.1007/978-3-031-72949-2_27","eventYear":2024,"numberOfCreators":7,"category":"conference","sources":["https://dblp.org/rec/conf/eccv/WangLCWZXG24","https://doi.org/10.1007/978-3-031-72949-2_27"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2024,"sourceUrl":"https://dblp.org/rec/conf/eccv/WangLCWZXG24","documentUrl":null,"type":"Inproceedings"},{"key":"conf/eccv/ZhangWLWG24","url":"https://dblp.org/rec/conf/eccv/ZhangWLWG24","title":"Learning Representations from Foundation Models for Domain Generalized Stereo Matching.","year":2025,"types":["Inproceedings"],"venue":"ECCV (42)","doi":"https://doi.org/10.1007/978-3-031-72946-1_9","eventYear":2024,"numberOfCreators":5,"category":"conference","sources":["https://dblp.org/rec/conf/eccv/ZhangWLWG24","https://doi.org/10.1007/978-3-031-72946-1_9"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2024,"sourceUrl":"https://dblp.org/rec/conf/eccv/ZhangWLWG24","documentUrl":null,"type":"Inproceedings"},{"key":"conf/globecom/YeDDG25","url":"https://dblp.org/rec/conf/globecom/YeDDG25","title":"User-Intent-Driven Semantic Communication via Adaptive Deep Understanding.","year":2025,"types":["Inproceedings"],"venue":"GLOBECOM","doi":"https://doi.org/10.1109/GLOBECOM59602.2025.11432290","eventYear":2025,"numberOfCreators":4,"category":"conference","sources":["https://dblp.org/rec/conf/globecom/YeDDG25","https://doi.org/10.1109/GLOBECOM59602.2025.11432290"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/globecom/YeDDG25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iccv/ZhouGWX25","url":"https://dblp.org/rec/conf/iccv/ZhouGWX25","title":"Monomobility: Zero-Shot 3D Mobility Analysis From Monocular Videos.","year":2025,"types":["Inproceedings"],"venue":"ICCV","doi":"https://doi.org/10.1109/ICCV51701.2025.00823","eventYear":2025,"numberOfCreators":4,"category":"conference","sources":["https://dblp.org/rec/conf/iccv/ZhouGWX25","https://doi.org/10.1109/ICCV51701.2025.00823"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/ZhouGWX25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/icpr/YinGHZXZCWWCYLLHJDWLWTP24","url":"https://dblp.org/rec/conf/icpr/YinGHZXZCWWCYLLHJDWLWTP24","title":"ICPR 2024 Competition on Moving Object Detection and Tracking in Satellite Videos: Methods and Results.","year":2025,"types":["Inproceedings"],"venue":"ICPR (34)","doi":"https://doi.org/10.1007/978-3-031-80139-6_6","eventYear":2024,"numberOfCreators":27,"category":"conference","sources":["https://dblp.org/rec/conf/icpr/YinGHZXZCWWCYLLHJDWLWTP24","https://doi.org/10.1007/978-3-031-80139-6_6"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2024,"sourceUrl":"https://dblp.org/rec/conf/icpr/YinGHZXZCWWCYLLHJDWLWTP24","documentUrl":null,"type":"Inproceedings"},{"key":"conf/icra/LiuZZLG25","url":"https://dblp.org/rec/conf/icra/LiuZZLG25","title":"Multi-Modality Test-Time Adaptation for Semantic Segmentation in Robotic Perception.","year":2025,"types":["Inproceedings"],"venue":"ICRA","doi":"https://doi.org/10.1109/ICRA55743.2025.11127565","eventYear":2025,"numberOfCreators":5,"category":"conference","sources":["https://dblp.org/rec/conf/icra/LiuZZLG25","https://doi.org/10.1109/ICRA55743.2025.11127565"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/icra/LiuZZLG25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/icra/ZhangAZSHCG25","url":"https://dblp.org/rec/conf/icra/ZhangAZSHCG25","title":"$U^2$ Frame: A Unified and Unsupervised Learning Framework for LiDAR-Based Loop Closing.","year":2025,"types":["Inproceedings"],"venue":"ICRA","doi":"https://doi.org/10.1109/ICRA55743.2025.11127309","eventYear":2025,"numberOfCreators":7,"category":"conference","sources":["https://dblp.org/rec/conf/icra/ZhangAZSHCG25","https://doi.org/10.1109/ICRA55743.2025.11127309"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/icra/ZhangAZSHCG25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/icra/ZhangGLZCG25","url":"https://dblp.org/rec/conf/icra/ZhangGLZCG25","title":"3D Whole-Body Pose Estimation Using Graph High-Resolution Network for Humanoid Robot Teleoperation.","year":2025,"types":["Inproceedings"],"venue":"ICRA","doi":"https://doi.org/10.1109/ICRA55743.2025.11128446","eventYear":2025,"numberOfCreators":6,"category":"conference","sources":["https://dblp.org/rec/conf/icra/ZhangGLZCG25","https://doi.org/10.1109/ICRA55743.2025.11128446"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/icra/ZhangGLZCG25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iros/ChenYHXZG25","url":"https://dblp.org/rec/conf/iros/ChenYHXZG25","title":"Graph2Scene: Versatile 3D Indoor Scene Generation with Interaction-aware Scene Graph.","year":2025,"types":["Inproceedings"],"venue":"IROS","doi":"https://doi.org/10.1109/IROS60139.2025.11246595","eventYear":2025,"numberOfCreators":6,"category":"conference","sources":["https://dblp.org/rec/conf/iros/ChenYHXZG25","https://doi.org/10.1109/IROS60139.2025.11246595"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iros/ChenYHXZG25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iros/ZhangLZSJZG25","url":"https://dblp.org/rec/conf/iros/ZhangLZSJZG25","title":"Self-Distilled Stereo Matching: Real-Time Domain Generalization for Robotic Depth Perception.","year":2025,"types":["Inproceedings"],"venue":"IROS","doi":"https://doi.org/10.1109/IROS60139.2025.11246574","eventYear":2025,"numberOfCreators":7,"category":"conference","sources":["https://dblp.org/rec/conf/iros/ZhangLZSJZG25","https://doi.org/10.1109/IROS60139.2025.11246574"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iros/ZhangLZSJZG25","documentUrl":null,"type":"Inproceedings"},{"key":"journals/aeog/WangLFJDZCGW25","url":"https://dblp.org/rec/journals/aeog/WangLFJDZCGW25","title":"PhaseVSRnet: Deep complex network for phase-based satellite video super-resolution.","year":2025,"types":["Article"],"venue":"Int. J. Appl. Earth Obs. Geoinformation","doi":"https://doi.org/10.1016/J.JAG.2025.104418","numberOfCreators":9,"category":"journal","sources":["https://dblp.org/rec/journals/aeog/WangLFJDZCGW25","https://doi.org/10.1016/J.JAG.2025.104418"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/aeog/WangLFJDZCGW25","documentUrl":null,"type":"Article"},{"key":"journals/cn/TengXGGXHC25","url":"https://dblp.org/rec/journals/cn/TengXGGXHC25","title":"ARPDR++: Exploiting local-global temporal modeling for smartphone-based indoor pedestrian localization.","year":2025,"types":["Article"],"venue":"Comput. Networks","doi":"https://doi.org/10.1016/J.COMNET.2025.111710","numberOfCreators":7,"category":"journal","sources":["https://dblp.org/rec/journals/cn/TengXGGXHC25","https://doi.org/10.1016/J.COMNET.2025.111710"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/cn/TengXGGXHC25","documentUrl":null,"type":"Article"},{"key":"journals/pami/HuFOGGL25","url":"https://dblp.org/rec/journals/pami/HuFOGGL25","title":"Robust Depth Estimation Under Sensor Degradations: A Multi-Sensor Fusion Perspective.","year":2025,"types":["Article"],"venue":"IEEE Trans. Pattern Anal. Mach. Intell.","doi":"https://doi.org/10.1109/TPAMI.2025.3581311","numberOfCreators":6,"category":"journal","sources":["https://dblp.org/rec/journals/pami/HuFOGGL25","https://doi.org/10.1109/TPAMI.2025.3581311"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/pami/HuFOGGL25","documentUrl":null,"type":"Article"},{"key":"journals/pami/WangGWDXYA25","url":"https://dblp.org/rec/journals/pami/WangGWDXYA25","title":"Unsupervised Degradation Representation Learning for Unpaired Restoration of Images and Point Clouds.","year":2025,"types":["Article"],"venue":"IEEE Trans. Pattern Anal. Mach. Intell.","doi":"https://doi.org/10.1109/TPAMI.2024.3471571","numberOfCreators":7,"category":"journal","sources":["https://dblp.org/rec/journals/pami/WangGWDXYA25","https://doi.org/10.1109/TPAMI.2024.3471571"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/pami/WangGWDXYA25","documentUrl":null,"type":"Article"},{"key":"journals/spl/WangXDGW25","url":"https://dblp.org/rec/journals/spl/WangXDGW25","title":"ASRL: Adaptive Sparse Representation Learning for LiDAR Point Cloud Geometry Compression.","year":2025,"types":["Article"],"venue":"IEEE Signal Process. Lett.","doi":"https://doi.org/10.1109/LSP.2025.3616643","numberOfCreators":5,"category":"journal","sources":["https://dblp.org/rec/journals/spl/WangXDGW25","https://doi.org/10.1109/LSP.2025.3616643"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/spl/WangXDGW25","documentUrl":null,"type":"Article"},{"key":"journals/tcss/ZhangGHDLG25","url":"https://dblp.org/rec/journals/tcss/ZhangGHDLG25","title":"Differentiable Prior-Driven Data Augmentation for Sensor-Based Human Activity Recognition.","year":2025,"types":["Article"],"venue":"IEEE Trans. Comput. Soc. Syst.","doi":"https://doi.org/10.1109/TCSS.2025.3565414","numberOfCreators":6,"category":"journal","sources":["https://dblp.org/rec/journals/tcss/ZhangGHDLG25","https://doi.org/10.1109/TCSS.2025.3565414"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/tcss/ZhangGHDLG25","documentUrl":null,"type":"Article"},{"key":"journals/tcsv/YanFWGDWM25","url":"https://dblp.org/rec/journals/tcsv/YanFWGDWM25","title":"Discriminative Correspondence Estimation for Unsupervised RGB-D Point Cloud Registration.","year":2025,"types":["Article"],"venue":"IEEE Trans. Circuits Syst. Video Technol.","doi":"https://doi.org/10.1109/TCSVT.2024.3480268","numberOfCreators":7,"category":"journal","sources":["https://dblp.org/rec/journals/tcsv/YanFWGDWM25","https://doi.org/10.1109/TCSVT.2024.3480268"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/tcsv/YanFWGDWM25","documentUrl":null,"type":"Article"},{"key":"journals/tgrs/YinALSLGW25","url":"https://dblp.org/rec/journals/tgrs/YinALSLGW25","title":"Satellite Video Object Detection Based on Enhanced 3DTV Regularization and Gaussian Prior.","year":2025,"types":["Article"],"venue":"IEEE Trans. Geosci. Remote. Sens.","doi":"https://doi.org/10.1109/TGRS.2025.3554845","numberOfCreators":7,"category":"journal","sources":["https://dblp.org/rec/journals/tgrs/YinALSLGW25","https://doi.org/10.1109/TGRS.2025.3554845"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/tgrs/YinALSLGW25","documentUrl":null,"type":"Article"},{"key":"journals/tip/ChenLWYWZGLA25","url":"https://dblp.org/rec/journals/tip/ChenLWYWZGLA25","title":"Motion and Appearance Decoupling Representation for Event Cameras.","year":2025,"types":["Article"],"venue":"IEEE Trans. Image Process.","doi":"https://doi.org/10.1109/TIP.2025.3607632","numberOfCreators":9,"category":"journal","sources":["https://dblp.org/rec/journals/tip/ChenLWYWZGLA25","https://doi.org/10.1109/TIP.2025.3607632"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/tip/ChenLWYWZGLA25","documentUrl":null,"type":"Article"},{"key":"journals/tip/FuGCHLBB25","url":"https://dblp.org/rec/journals/tip/FuGCHLBB25","title":"WSSIC-Net: Weakly-Supervised Semantic Instance Completion of 3D Point Cloud Scenes.","year":2025,"types":["Article"],"venue":"IEEE Trans. Image Process.","doi":"https://doi.org/10.1109/TIP.2024.3520013","numberOfCreators":7,"category":"journal","sources":["https://dblp.org/rec/journals/tip/FuGCHLBB25","https://doi.org/10.1109/TIP.2024.3520013"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/tip/FuGCHLBB25","documentUrl":null,"type":"Article"},{"key":"journals/tip/FuZWXLGBB25","url":"https://dblp.org/rec/journals/tip/FuZWXLGBB25","title":"CompletionMamba: Taming State Space Model for Point Cloud Completion.","year":2025,"types":["Article"],"venue":"IEEE Trans. Image Process.","doi":"https://doi.org/10.1109/TIP.2025.3597041","numberOfCreators":8,"category":"journal","sources":["https://dblp.org/rec/journals/tip/FuZWXLGBB25","https://doi.org/10.1109/TIP.2025.3597041"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/tip/FuZWXLGBB25","documentUrl":null,"type":"Article"},{"key":"journals/tip/WangLWHWG25","url":"https://dblp.org/rec/journals/tip/WangLWHWG25","title":"ADStereo: Efficient Stereo Matching With Adaptive Downsampling and Disparity Alignment.","year":2025,"types":["Article"],"venue":"IEEE Trans. Image Process.","doi":"https://doi.org/10.1109/TIP.2025.3540282","numberOfCreators":6,"category":"journal","sources":["https://dblp.org/rec/journals/tip/WangLWHWG25","https://doi.org/10.1109/TIP.2025.3540282"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/tip/WangLWHWG25","documentUrl":null,"type":"Article"},{"key":"journals/tmc/WangZLXWGW25","url":"https://dblp.org/rec/journals/tmc/WangZLXWGW25","title":"GCFI-Net: Global-Local Cross-Spatial-Channel Feature Interaction Network for Point Cloud Geometry Compression.","year":2025,"types":["Article"],"venue":"IEEE Trans. Mob. Comput.","doi":"https://doi.org/10.1109/TMC.2025.3590775","numberOfCreators":7,"category":"journal","sources":["https://dblp.org/rec/journals/tmc/WangZLXWGW25","https://doi.org/10.1109/TMC.2025.3590775"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/tmc/WangZLXWGW25","documentUrl":null,"type":"Article"},{"key":"journals/tmc/XiangLZWZG25","url":"https://dblp.org/rec/journals/tmc/XiangLZWZG25","title":"EagleEye: Balancing Latency, Accuracy, and Power on Edge-Assisted UAVs for Urban Crowd Surveillance.","year":2025,"types":["Article"],"venue":"IEEE Trans. Mob. Comput.","doi":"https://doi.org/10.1109/TMC.2025.3586860","numberOfCreators":6,"category":"journal","sources":["https://dblp.org/rec/journals/tmc/XiangLZWZG25","https://doi.org/10.1109/TMC.2025.3586860"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/tmc/XiangLZWZG25","documentUrl":null,"type":"Article"},{"key":"journals/tmm/ChaoDGW25","url":"https://dblp.org/rec/journals/tmm/ChaoDGW25","title":"MaskBlur: Spatial and Angular Data Augmentation for Light Field Image Super-Resolution.","year":2025,"types":["Article"],"venue":"IEEE Trans. Multim.","doi":"https://doi.org/10.1109/TMM.2024.3521781","numberOfCreators":4,"category":"journal","sources":["https://dblp.org/rec/journals/tmm/ChaoDGW25","https://doi.org/10.1109/TMM.2024.3521781"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/tmm/ChaoDGW25","documentUrl":null,"type":"Article"},{"key":"journals/tmm/FengHZGYWM25","url":"https://dblp.org/rec/journals/tmm/FengHZGYWM25","title":"Exploring Hierarchical Spatial Layout Cues for 3D Point Cloud Based Scene Graph Prediction.","year":2025,"types":["Article"],"venue":"IEEE Trans. Multim.","doi":"https://doi.org/10.1109/TMM.2023.3277736","numberOfCreators":7,"category":"journal","sources":["https://dblp.org/rec/journals/tmm/FengHZGYWM25","https://doi.org/10.1109/TMM.2023.3277736"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/tmm/FengHZGYWM25","documentUrl":null,"type":"Article"},{"key":"journals/tmm/GaoWAZG25","url":"https://dblp.org/rec/journals/tmm/GaoWAZG25","title":"Enhancing Event-Based Video Reconstruction With Bidirectional Temporal Information.","year":2025,"types":["Article"],"venue":"IEEE Trans. Multim.","doi":"https://doi.org/10.1109/TMM.2025.3543010","numberOfCreators":5,"category":"journal","sources":["https://dblp.org/rec/journals/tmm/GaoWAZG25","https://doi.org/10.1109/TMM.2025.3543010"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/tmm/GaoWAZG25","documentUrl":null,"type":"Article"},{"key":"journals/tmm/LiGYYR25","url":"https://dblp.org/rec/journals/tmm/LiGYYR25","title":"Graph Proxy Fusion: Consensus Graph Intermediated Multi-View Local Information Fusion Clustering.","year":2025,"types":["Article"],"venue":"IEEE Trans. Multim.","doi":"https://doi.org/10.1109/TMM.2024.3521803","numberOfCreators":5,"category":"journal","sources":["https://dblp.org/rec/journals/tmm/LiGYYR25","https://doi.org/10.1109/TMM.2024.3521803"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/tmm/LiGYYR25","documentUrl":null,"type":"Article"},{"key":"journals/tmm/LiuHWXWG25","url":"https://dblp.org/rec/journals/tmm/LiuHWXWG25","title":"DuInNet: Dual-Modality Feature Interaction for Point Cloud Completion.","year":2025,"types":["Article"],"venue":"IEEE Trans. Multim.","doi":"https://doi.org/10.1109/TMM.2025.3607739","numberOfCreators":6,"category":"journal","sources":["https://dblp.org/rec/journals/tmm/LiuHWXWG25","https://doi.org/10.1109/TMM.2025.3607739"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/tmm/LiuHWXWG25","documentUrl":null,"type":"Article"},{"key":"journals/tmm/LiuZLLPG25","url":"https://dblp.org/rec/journals/tmm/LiuZLLPG25","title":"SF-City: A Source-Free Domain Adaptation Method for City-Scale Point Cloud Semantic Segmentation.","year":2025,"types":["Article"],"venue":"IEEE Trans. Multim.","doi":"https://doi.org/10.1109/TMM.2025.3590934","numberOfCreators":6,"category":"journal","sources":["https://dblp.org/rec/journals/tmm/LiuZLLPG25","https://doi.org/10.1109/TMM.2025.3590934"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/tmm/LiuZLLPG25","documentUrl":null,"type":"Article"},{"key":"journals/tmm/YuZLLG25","url":"https://dblp.org/rec/journals/tmm/YuZLLG25","title":"Hierarchical Distortion Learning for Fast Lossy Compression of Point Clouds.","year":2025,"types":["Article"],"venue":"IEEE Trans. Multim.","doi":"https://doi.org/10.1109/TMM.2025.3565958","numberOfCreators":5,"category":"journal","sources":["https://dblp.org/rec/journals/tmm/YuZLLG25","https://doi.org/10.1109/TMM.2025.3565958"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/tmm/YuZLLG25","documentUrl":null,"type":"Article"},{"key":"journals/tnn/DangZXWHG25","url":"https://dblp.org/rec/journals/tnn/DangZXWHG25","title":"Adaptive Sparse Memory Networks for Efficient and Robust Video Object Segmentation.","year":2025,"types":["Article"],"venue":"IEEE Trans. Neural Networks Learn. Syst.","doi":"https://doi.org/10.1109/TNNLS.2024.3357118","numberOfCreators":6,"category":"journal","sources":["https://dblp.org/rec/journals/tnn/DangZXWHG25","https://doi.org/10.1109/TNNLS.2024.3357118"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/tnn/DangZXWHG25","documentUrl":null,"type":"Article"},{"key":"journals/tnn/LiAXLWLG25","url":"https://dblp.org/rec/journals/tnn/LiAXLWLG25","title":"Direction-Coded Temporal U-Shape Module for Multiframe Infrared Small Target Detection.","year":2025,"types":["Article"],"venue":"IEEE Trans. Neural Networks Learn. Syst.","doi":"https://doi.org/10.1109/TNNLS.2023.3331004","numberOfCreators":7,"category":"journal","sources":["https://dblp.org/rec/journals/tnn/LiAXLWLG25","https://doi.org/10.1109/TNNLS.2023.3331004"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/tnn/LiAXLWLG25","documentUrl":null,"type":"Article"},{"key":"journals/tnn/LiRGYY25","url":"https://dblp.org/rec/journals/tnn/LiRGYY25","title":"LSVC: A Lifelong Learning Approach for Stream-View Clustering.","year":2025,"types":["Article"],"venue":"IEEE Trans. Neural Networks Learn. Syst.","doi":"https://doi.org/10.1109/TNNLS.2024.3439394","numberOfCreators":5,"category":"journal","sources":["https://dblp.org/rec/journals/tnn/LiRGYY25","https://doi.org/10.1109/TNNLS.2024.3439394"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/tnn/LiRGYY25","documentUrl":null,"type":"Article"},{"key":"journals/tnn/WangLSGWY25","url":"https://dblp.org/rec/journals/tnn/WangLSGWY25","title":"Satellite Pose Set Estimation by Uncertainty-Guided Conformal Keypoint Detection.","year":2025,"types":["Article"],"venue":"IEEE Trans. Neural Networks Learn. Syst.","doi":"https://doi.org/10.1109/TNNLS.2025.3598481","numberOfCreators":6,"category":"journal","sources":["https://dblp.org/rec/journals/tnn/WangLSGWY25","https://doi.org/10.1109/TNNLS.2025.3598481"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/tnn/WangLSGWY25","documentUrl":null,"type":"Article"},{"key":"journals/tnn/WangLWYAG25","url":"https://dblp.org/rec/journals/tnn/WangLWYAG25","title":"Real-World Light Field Image Super-Resolution Via Degradation Modulation.","year":2025,"types":["Article"],"venue":"IEEE Trans. Neural Networks Learn. Syst.","doi":"https://doi.org/10.1109/TNNLS.2024.3378420","numberOfCreators":6,"category":"journal","sources":["https://dblp.org/rec/journals/tnn/WangLWYAG25","https://doi.org/10.1109/TNNLS.2024.3378420"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/tnn/WangLWYAG25","documentUrl":null,"type":"Article"},{"key":"journals/vc/PeiLJZYLG25","url":"https://dblp.org/rec/journals/vc/PeiLJZYLG25","title":"Energy-guided test-time adaptation for data shifts in multi-modal perception.","year":2025,"types":["Article"],"venue":"Vis. Comput.","doi":"https://doi.org/10.1007/S00371-025-03952-3","numberOfCreators":7,"category":"journal","sources":["https://dblp.org/rec/journals/vc/PeiLJZYLG25","https://doi.org/10.1007/S00371-025-03952-3"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/vc/PeiLJZYLG25","documentUrl":null,"type":"Article"}],"preprints":[{"key":"journals/corr/abs-2501-02519","url":"https://dblp.org/rec/journals/corr/abs-2501-02519","title":"Layout2Scene: 3D Semantic Layout Guided Scene Generation via Geometry and Appearance Diffusion Priors.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2501.02519","numberOfCreators":6,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2501-02519","https://doi.org/10.48550/ARXIV.2501.02519"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2501-02519","documentUrl":null,"type":"Informal","arxivId":"2501.02519","arxivUrl":"https://arxiv.org/abs/2501.02519"},{"key":"journals/corr/abs-2502-02163","url":"https://dblp.org/rec/journals/corr/abs-2502-02163","title":"Progressive Correspondence Regenerator for Robust 3D Registration.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2502.02163","numberOfCreators":5,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2502-02163","https://doi.org/10.48550/ARXIV.2502.02163"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2502-02163","documentUrl":null,"type":"Informal","arxivId":"2502.02163","arxivUrl":"https://arxiv.org/abs/2502.02163"},{"key":"journals/corr/abs-2502-04628","url":"https://dblp.org/rec/journals/corr/abs-2502-04628","title":"AIQViT: Architecture-Informed Post-Training Quantization for Vision Transformers.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2502.04628","numberOfCreators":5,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2502-04628","https://doi.org/10.48550/ARXIV.2502.04628"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2502-04628","documentUrl":null,"type":"Informal","arxivId":"2502.04628","arxivUrl":"https://arxiv.org/abs/2502.04628"},{"key":"journals/corr/abs-2503-01309","url":"https://dblp.org/rec/journals/corr/abs-2503-01309","title":"OnlineAnySeg: Online Zero-Shot 3D Segmentation by Visual Foundation Model Guided 2D Mask Merging.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2503.01309","numberOfCreators":7,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2503-01309","https://doi.org/10.48550/ARXIV.2503.01309"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-01309","documentUrl":null,"type":"Informal","arxivId":"2503.01309","arxivUrl":"https://arxiv.org/abs/2503.01309"},{"key":"journals/corr/abs-2503-15934","url":"https://dblp.org/rec/journals/corr/abs-2503-15934","title":"SaMam: Style-aware State Space Model for Arbitrary Image Style Transfer.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2503.15934","numberOfCreators":5,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2503-15934","https://doi.org/10.48550/ARXIV.2503.15934"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-15934","documentUrl":null,"type":"Informal","arxivId":"2503.15934","arxivUrl":"https://arxiv.org/abs/2503.15934"},{"key":"journals/corr/abs-2503-20368","url":"https://dblp.org/rec/journals/corr/abs-2503-20368","title":"Pluggable Style Representation Learning for Multi-Style Transfer.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2503.20368","numberOfCreators":5,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2503-20368","https://doi.org/10.48550/ARXIV.2503.20368"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-20368","documentUrl":null,"type":"Informal","arxivId":"2503.20368","arxivUrl":"https://arxiv.org/abs/2503.20368"},{"key":"journals/corr/abs-2504-09491","url":"https://dblp.org/rec/journals/corr/abs-2504-09491","title":"DropoutGS: Dropping Out Gaussians for Better Sparse-view Rendering.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2504.09491","numberOfCreators":6,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2504-09491","https://doi.org/10.48550/ARXIV.2504.09491"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2504-09491","documentUrl":null,"type":"Informal","arxivId":"2504.09491","arxivUrl":"https://arxiv.org/abs/2504.09491"},{"key":"journals/corr/abs-2505-00259","url":"https://dblp.org/rec/journals/corr/abs-2505-00259","title":"Pack-PTQ: Advancing Post-training Quantization of Neural Networks by Pack-wise Reconstruction.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2505.00259","numberOfCreators":6,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2505-00259","https://doi.org/10.48550/ARXIV.2505.00259"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-00259","documentUrl":null,"type":"Informal","arxivId":"2505.00259","arxivUrl":"https://arxiv.org/abs/2505.00259"},{"key":"journals/corr/abs-2505-07622","url":"https://dblp.org/rec/journals/corr/abs-2505-07622","title":"A Unified Hierarchical Framework for Fine-grained Cross-view Geo-localization over Large-scale Scenarios.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2505.07622","numberOfCreators":5,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2505-07622","https://doi.org/10.48550/ARXIV.2505.07622"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-07622","documentUrl":null,"type":"Informal","arxivId":"2505.07622","arxivUrl":"https://arxiv.org/abs/2505.07622"},{"key":"journals/corr/abs-2505-11868","url":"https://dblp.org/rec/journals/corr/abs-2505-11868","title":"MonoMobility: Zero-Shot 3D Mobility Analysis from Monocular Videos.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2505.11868","numberOfCreators":4,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2505-11868","https://doi.org/10.48550/ARXIV.2505.11868"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-11868","documentUrl":null,"type":"Informal","arxivId":"2505.11868","arxivUrl":"https://arxiv.org/abs/2505.11868"},{"key":"journals/corr/abs-2506-00835","url":"https://dblp.org/rec/journals/corr/abs-2506-00835","title":"SynPO: Synergizing Descriptiveness and Preference Optimization for Video Detailed Captioning.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2506.00835","numberOfCreators":9,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2506-00835","https://doi.org/10.48550/ARXIV.2506.00835"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-00835","documentUrl":null,"type":"Informal","arxivId":"2506.00835","arxivUrl":"https://arxiv.org/abs/2506.00835"},{"key":"journals/corr/abs-2506-12766","url":"https://dblp.org/rec/journals/corr/abs-2506-12766","title":"Probing Deep into Temporal Profile Makes the Infrared Small Target Detector Much Better.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2506.12766","numberOfCreators":9,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2506-12766","https://doi.org/10.48550/ARXIV.2506.12766"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-12766","documentUrl":null,"type":"Informal","arxivId":"2506.12766","arxivUrl":"https://arxiv.org/abs/2506.12766"},{"key":"journals/corr/abs-2506-14769","url":"https://dblp.org/rec/journals/corr/abs-2506-14769","title":"CDP: Towards Robust Autoregressive Visuomotor Policy Learning via Causal Diffusion.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2506.14769","numberOfCreators":6,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2506-14769","https://doi.org/10.48550/ARXIV.2506.14769"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-14769","documentUrl":null,"type":"Informal","arxivId":"2506.14769","arxivUrl":"https://arxiv.org/abs/2506.14769"},{"key":"journals/corr/abs-2507-08400","url":"https://dblp.org/rec/journals/corr/abs-2507-08400","title":"PanMatch: Unleashing the Potential of Large Vision Models for Unified Matching Models.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2507.08400","numberOfCreators":7,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2507-08400","https://doi.org/10.48550/ARXIV.2507.08400"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2507-08400","documentUrl":null,"type":"Informal","arxivId":"2507.08400","arxivUrl":"https://arxiv.org/abs/2507.08400"},{"key":"journals/corr/abs-2508-05884","url":"https://dblp.org/rec/journals/corr/abs-2508-05884","title":"User-Intent-Driven Semantic Communication via Adaptive Deep Understanding.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2508.05884","numberOfCreators":4,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2508-05884","https://doi.org/10.48550/ARXIV.2508.05884"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-05884","documentUrl":null,"type":"Informal","arxivId":"2508.05884","arxivUrl":"https://arxiv.org/abs/2508.05884"},{"key":"journals/corr/abs-2508-20466","url":"https://dblp.org/rec/journals/corr/abs-2508-20466","title":"Re-Densification Meets Cross-Scale Propagation: Real-Time Compression of LiDAR Point Clouds.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2508.20466","numberOfCreators":7,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2508-20466","https://doi.org/10.48550/ARXIV.2508.20466"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-20466","documentUrl":null,"type":"Informal","arxivId":"2508.20466","arxivUrl":"https://arxiv.org/abs/2508.20466"},{"key":"journals/corr/abs-2509-13662","url":"https://dblp.org/rec/journals/corr/abs-2509-13662","title":"Deep Lookup Network.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2509.13662","numberOfCreators":7,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2509-13662","https://doi.org/10.48550/ARXIV.2509.13662"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-13662","documentUrl":null,"type":"Informal","arxivId":"2509.13662","arxivUrl":"https://arxiv.org/abs/2509.13662"},{"key":"journals/corr/abs-2511-15288","url":"https://dblp.org/rec/journals/corr/abs-2511-15288","title":"Edge-Centric Relational Reasoning for 3D Scene Graph Prediction.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2511.15288","numberOfCreators":5,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2511-15288","https://doi.org/10.48550/ARXIV.2511.15288"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2511-15288","documentUrl":null,"type":"Informal","arxivId":"2511.15288","arxivUrl":"https://arxiv.org/abs/2511.15288"}],"excludedFormal":[],"otherRecords":[],"matchedName":"Yulan Guo","databaseLabel":"Yulan Guo","databaseMetadata":{"type":["https://dblp.org/rdf/schema#Creator","https://dblp.org/rdf/schema#Person"],"label":["Yulan Guo"],"orcid":["https://orcid.org/0000-0001-7051-841X"]},"rawFormalRecordCount2025":48,"sourceWarning":true,"crossrefIdentityChecks":[{"pid":"127/0477","key":"conf/aaai/JiangZWYG25","title":"AIQViT: Architecture-Informed Post-Training Quantization for Vision Transformers.","crossrefUrl":"https://api.crossref.org/works/10.1609/AAAI.V39I17.33939","authors":[{"given":"Yulan","family":"Guo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}]},{"pid":"127/0477","key":"conf/accv/LiuWGZG24","title":"Pluggable Style Representation Learning for Multi-style Transfer.","crossrefUrl":"https://api.crossref.org/works/10.1007/978-981-96-0960-4_18","authors":[{"given":"Yulan","family":"Guo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}]},{"pid":"127/0477","key":"conf/cvpr/LiuWZYG25","title":"SaMam: Style-aware State Space Model for Arbitrary Image Style Transfer.","crossrefUrl":"https://api.crossref.org/works/10.1109/CVPR52734.2025.02651","authors":[{"given":"Yulan","family":"Guo","sequence":"additional","affiliation":[{"name":"The Shenzhen Campus of Sun Yat-Sen University, Sun Yat-Sen University"}],"role":[{"vocabulary":"crossref","role":"author"}]}]},{"pid":"127/0477","key":"conf/cvpr/TangZLGD0X25","title":"OnlineAnySeg: Online Zero-Shot 3D Segmentation by Visual Foundation Model Guided 2D Mask Merging.","crossrefUrl":"https://api.crossref.org/works/10.1109/CVPR52734.2025.00348","authors":[{"given":"Yulan","family":"Guo","sequence":"additional","affiliation":[{"name":"Sun Yat-Sen University"}],"role":[{"vocabulary":"crossref","role":"author"}]}]},{"pid":"127/0477","key":"conf/cvpr/WangWMHXG25","title":"VideoDirector: Precise Video Editing via Text-to-Video Models.","crossrefUrl":"https://api.crossref.org/works/10.1109/CVPR52734.2025.00247","authors":[{"given":"Yulan","family":"Guo","sequence":"additional","affiliation":[{"name":"Shenzhen Campus of Sun Yat-sen University, Sun Yat-sen University"}],"role":[{"vocabulary":"crossref","role":"author"}]}]},{"pid":"127/0477","key":"conf/cvpr/WangZLLXWGW25","title":"TopNet: Transformer-Efficient Occupancy Prediction Network for Octree-Structured Point Cloud Geometry Compression.","crossrefUrl":"https://api.crossref.org/works/10.1109/CVPR52734.2025.02543","authors":[{"given":"Yulan","family":"Guo","sequence":"additional","affiliation":[{"name":"Sun Yat-sen University"}],"role":[{"vocabulary":"crossref","role":"author"}]}]},{"pid":"127/0477","key":"conf/cvpr/XuWCA0G25","title":"DropoutGS: Dropping Out Gaussians for Better Sparse-view Rendering.","crossrefUrl":"https://api.crossref.org/works/10.1109/CVPR52734.2025.00074","authors":[{"given":"Yulan","family":"Guo","sequence":"additional","affiliation":[{"name":"Sun Yat-Sen University,The Shenzhen Campus"}],"role":[{"vocabulary":"crossref","role":"author"}]}]},{"pid":"127/0477","key":"conf/cvpr/ZhaoAZXG25","title":"Progressive Correspondence Regenerator for Robust 3D Registration.","crossrefUrl":"https://api.crossref.org/works/10.1109/CVPR52734.2025.00121","authors":[{"given":"Yulan","family":"Guo","sequence":"additional","affiliation":[{"name":"Sun Yat-sen University"}],"role":[{"vocabulary":"crossref","role":"author"}]}]},{"pid":"127/0477","key":"conf/eccv/FuWXWLGBB24","title":"AEDNet: Adaptive Embedding and Multiview-Aware Disentanglement for Point Cloud Completion.","crossrefUrl":"https://api.crossref.org/works/10.1007/978-3-031-73247-8_8","authors":[{"given":"Yulan","family":"Guo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}]},{"pid":"127/0477","key":"conf/eccv/MaLPG24","title":"Heterogeneous Graph Learning for Scene Graph Prediction in 3D Point Clouds.","crossrefUrl":"https://api.crossref.org/works/10.1007/978-3-031-73347-5_16","authors":[{"ORCID":"https://orcid.org/0000-0001-7051-841X","authenticated-orcid":false,"given":"Yulan","family":"Guo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}]},{"pid":"127/0477","key":"conf/eccv/WangLCWZXG24","title":"Distractor-Free Novel View Synthesis via Exploiting Memorization Effect in Optimization.","crossrefUrl":"https://api.crossref.org/works/10.1007/978-3-031-72949-2_27","authors":[{"ORCID":"https://orcid.org/0000-0001-7051-841X","authenticated-orcid":false,"given":"Yulan","family":"Guo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}]},{"pid":"127/0477","key":"conf/eccv/ZhangWLWG24","title":"Learning Representations from Foundation Models for Domain Generalized Stereo Matching.","crossrefUrl":"https://api.crossref.org/works/10.1007/978-3-031-72946-1_9","authors":[{"ORCID":"https://orcid.org/0000-0001-7051-841X","authenticated-orcid":false,"given":"Yulan","family":"Guo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}]},{"pid":"127/0477","key":"conf/globecom/YeDDG25","title":"User-Intent-Driven Semantic Communication via Adaptive Deep Understanding.","crossrefUrl":"https://api.crossref.org/works/10.1109/GLOBECOM59602.2025.11432290","authors":[{"given":"Yulan","family":"Guo","sequence":"additional","affiliation":[{"name":"Sun Yat-sen University,School of Electronics and Communication Engineering,Shenzhen,China,518107"}],"role":[{"role":"author","vocabulary":"crossref"}]}]},{"pid":"127/0477","key":"conf/iccv/ZhouGWX25","title":"Monomobility: Zero-Shot 3D Mobility Analysis From Monocular Videos.","crossrefUrl":"https://api.crossref.org/works/10.1109/ICCV51701.2025.00823","authors":[{"given":"Yulan","family":"Guo","sequence":"additional","affiliation":[{"name":"Sun Yat-sen University"}],"role":[{"vocabulary":"crossref","role":"author"}]}]},{"pid":"127/0477","key":"conf/icpr/YinGHZXZCWWCYLLHJDWLWTP24","title":"ICPR 2024 Competition on Moving Object Detection and Tracking in Satellite Videos: Methods and Results.","crossrefUrl":"https://api.crossref.org/works/10.1007/978-3-031-80139-6_6","authors":[{"given":"Yulan","family":"Guo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}]},{"pid":"127/0477","key":"conf/icra/LiuZZLG25","title":"Multi-Modality Test-Time Adaptation for Semantic Segmentation in Robotic Perception.","crossrefUrl":"https://api.crossref.org/works/10.1109/ICRA55743.2025.11127565","authors":[{"given":"Yulan","family":"Guo","sequence":"additional","affiliation":[{"name":"School of Electronics and Communication Engineering, the Shenzhen Campus of Sun Yat-sen University, Sun Yat-sen University,China"}],"role":[{"vocabulary":"crossref","role":"author"}]}]},{"pid":"127/0477","key":"conf/icra/ZhangAZSHCG25","title":"$U^2$ Frame: A Unified and Unsupervised Learning Framework for LiDAR-Based Loop Closing.","crossrefUrl":"https://api.crossref.org/works/10.1109/ICRA55743.2025.11127309","authors":[{"given":"Yulan","family":"Guo","sequence":"additional","affiliation":[{"name":"School of Electronics and Communication Engineering, the Shenzhen Campus of Sun Yat-sen University,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}]},{"pid":"127/0477","key":"conf/icra/ZhangGLZCG25","title":"3D Whole-Body Pose Estimation Using Graph High-Resolution Network for Humanoid Robot Teleoperation.","crossrefUrl":"https://api.crossref.org/works/10.1109/ICRA55743.2025.11128446","authors":[{"given":"Yulan","family":"Guo","sequence":"additional","affiliation":[{"name":"School of Electronics and Communication Engineering, Sun Yat-sen University,Shenzhen,China,518107"}],"role":[{"role":"author","vocabulary":"crossref"}]}]},{"pid":"127/0477","key":"conf/iros/ChenYHXZG25","title":"Graph2Scene: Versatile 3D Indoor Scene Generation with Interaction-aware Scene Graph.","crossrefUrl":"https://api.crossref.org/works/10.1109/IROS60139.2025.11246595","authors":[{"given":"Yulan","family":"Guo","sequence":"additional","affiliation":[{"name":"the Shenzhen Campus of Sun Yat-sen University, Sun Yat-sen University,School of Electronics and Communication Engineering,China"}],"role":[{"vocabulary":"crossref","role":"author"}]}]},{"pid":"127/0477","key":"conf/iros/ZhangLZSJZG25","title":"Self-Distilled Stereo Matching: Real-Time Domain Generalization for Robotic Depth Perception.","crossrefUrl":"https://api.crossref.org/works/10.1109/IROS60139.2025.11246574","authors":[{"given":"Yulan","family":"Guo","sequence":"additional","affiliation":[{"name":"Shenzhen Campus of Sun Yat-sen University, Sun Yat-sen University,School of Electronics and Communication Engineering,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}]},{"pid":"127/0477","key":"journals/aeog/WangLFJDZCGW25","title":"PhaseVSRnet: Deep complex network for phase-based satellite video super-resolution.","crossrefUrl":"https://api.crossref.org/works/10.1016/J.JAG.2025.104418","authors":[{"given":"Yulan","family":"Guo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}]},{"pid":"127/0477","key":"journals/cn/TengXGGXHC25","title":"ARPDR++: Exploiting local-global temporal modeling for smartphone-based indoor pedestrian localization.","crossrefUrl":"https://api.crossref.org/works/10.1016/J.COMNET.2025.111710","authors":[{"given":"Yulan","family":"Guo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}]},{"pid":"127/0477","key":"journals/pami/HuFOGGL25","title":"Robust Depth Estimation Under Sensor Degradations: A Multi-Sensor Fusion Perspective.","crossrefUrl":"https://api.crossref.org/works/10.1109/TPAMI.2025.3581311","authors":[{"ORCID":"https://orcid.org/0000-0003-0952-476X","authenticated-orcid":false,"given":"Yulan","family":"Guo","sequence":"additional","affiliation":[{"name":"School of Electronics and Communication Engineering, Sun Yat-sen University, Shenzhen, Guangdong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}]},{"pid":"127/0477","key":"journals/pami/WangGWDXYA25","title":"Unsupervised Degradation Representation Learning for Unpaired Restoration of Images and Point Clouds.","crossrefUrl":"https://api.crossref.org/works/10.1109/TPAMI.2024.3471571","authors":[{"ORCID":"https://orcid.org/0000-0003-0952-476X","authenticated-orcid":false,"given":"Yulan","family":"Guo","sequence":"additional","affiliation":[{"name":"School of Electronics and Communication Engineering, The Shenzhen Campus of Sun Yat-sen University, Sun Yat-sen University, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}]},{"pid":"127/0477","key":"journals/spl/WangXDGW25","title":"ASRL: Adaptive Sparse Representation Learning for LiDAR Point Cloud Geometry Compression.","crossrefUrl":"https://api.crossref.org/works/10.1109/LSP.2025.3616643","authors":[{"ORCID":"https://orcid.org/0000-0003-0952-476X","authenticated-orcid":false,"given":"Yulan","family":"Guo","sequence":"additional","affiliation":[{"name":"School of Electronics and Communication Engineering, Shenzhen Campus, Sun Yat-sen University, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}]},{"pid":"127/0477","key":"journals/tcss/ZhangGHDLG25","title":"Differentiable Prior-Driven Data Augmentation for Sensor-Based Human Activity Recognition.","crossrefUrl":"https://api.crossref.org/works/10.1109/TCSS.2025.3565414","authors":[{"ORCID":"https://orcid.org/0000-0001-7051-841X","authenticated-orcid":false,"given":"Yulan","family":"Guo","sequence":"additional","affiliation":[{"name":"School of Electronics and Communication Engineering, Shenzhen Campus of Sun Yat-sen University, Sun Yat-sen University, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}]},{"pid":"127/0477","key":"journals/tcsv/YanFWGDWM25","title":"Discriminative Correspondence Estimation for Unsupervised RGB-D Point Cloud Registration.","crossrefUrl":"https://api.crossref.org/works/10.1109/TCSVT.2024.3480268","authors":[{"ORCID":"https://orcid.org/0000-0003-0952-476X","authenticated-orcid":false,"given":"Yulan","family":"Guo","sequence":"additional","affiliation":[{"name":"School of Electronics and Communication Engineering, Sun Yat-sen University, Shenzhen Campus, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}]},{"pid":"127/0477","key":"journals/tgrs/YinALSLGW25","title":"Satellite Video Object Detection Based on Enhanced 3DTV Regularization and Gaussian Prior.","crossrefUrl":"https://api.crossref.org/works/10.1109/TGRS.2025.3554845","authors":[{"ORCID":"https://orcid.org/0000-0003-0952-476X","authenticated-orcid":false,"given":"Yulan","family":"Guo","sequence":"additional","affiliation":[{"name":"School of Electronics and Communication Engineering, Shenzhen Campus, Sun Yat-sen University, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}]},{"pid":"127/0477","key":"journals/tip/ChenLWYWZGLA25","title":"Motion and Appearance Decoupling Representation for Event Cameras.","crossrefUrl":"https://api.crossref.org/works/10.1109/TIP.2025.3607632","authors":[{"ORCID":"https://orcid.org/0000-0003-0952-476X","authenticated-orcid":false,"given":"Yulan","family":"Guo","sequence":"additional","affiliation":[{"name":"School of Electronics and Communication Engineering, Sun Yat-sen University, Shenzhen Campus, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}]},{"pid":"127/0477","key":"journals/tip/FuGCHLBB25","title":"WSSIC-Net: Weakly-Supervised Semantic Instance Completion of 3D Point Cloud Scenes.","crossrefUrl":"https://api.crossref.org/works/10.1109/TIP.2024.3520013","authors":[{"ORCID":"https://orcid.org/0000-0003-0952-476X","authenticated-orcid":false,"given":"Yulan","family":"Guo","sequence":"additional","affiliation":[{"name":"School of Electronics and Communication Engineering, Sun Yat-sen University, Shenzhen Campus, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}]},{"pid":"127/0477","key":"journals/tip/FuZWXLGBB25","title":"CompletionMamba: Taming State Space Model for Point Cloud Completion.","crossrefUrl":"https://api.crossref.org/works/10.1109/TIP.2025.3597041","authors":[{"ORCID":"https://orcid.org/0000-0003-0952-476X","authenticated-orcid":false,"given":"Yulan","family":"Guo","sequence":"additional","affiliation":[{"name":"School of Electronics and Communication Engineering, Sun Yat-sen University (SYSU), Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}]},{"pid":"127/0477","key":"journals/tip/WangLWHWG25","title":"ADStereo: Efficient Stereo Matching With Adaptive Downsampling and Disparity Alignment.","crossrefUrl":"https://api.crossref.org/works/10.1109/TIP.2025.3540282","authors":[{"ORCID":"https://orcid.org/0000-0003-0952-476X","authenticated-orcid":false,"given":"Yulan","family":"Guo","sequence":"additional","affiliation":[{"name":"School of Electronics and Communication Engineering, Sun Yat-sen University, Shenzhen Campus, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}]},{"pid":"127/0477","key":"journals/tmc/WangZLXWGW25","title":"GCFI-Net: Global-Local Cross-Spatial-Channel Feature Interaction Network for Point Cloud Geometry Compression.","crossrefUrl":"https://api.crossref.org/works/10.1109/TMC.2025.3590775","authors":[{"ORCID":"https://orcid.org/0000-0003-0952-476X","authenticated-orcid":false,"given":"Yulan","family":"Guo","sequence":"additional","affiliation":[{"name":"School of Electronics and Communication Engineering, Sun Yat-sen University, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}]},{"pid":"127/0477","key":"journals/tmc/XiangLZWZG25","title":"EagleEye: Balancing Latency, Accuracy, and Power on Edge-Assisted UAVs for Urban Crowd Surveillance.","crossrefUrl":"https://api.crossref.org/works/10.1109/TMC.2025.3586860","authors":[{"ORCID":"https://orcid.org/0000-0003-0952-476X","authenticated-orcid":false,"given":"Yulan","family":"Guo","sequence":"additional","affiliation":[{"name":"School of Electronics and Communication Engineering, Shenzhen Campus of Sun Yat-sen University, Sun Yat-sen University, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}]},{"pid":"127/0477","key":"journals/tmm/ChaoDGW25","title":"MaskBlur: Spatial and Angular Data Augmentation for Light Field Image Super-Resolution.","crossrefUrl":"https://api.crossref.org/works/10.1109/TMM.2024.3521781","authors":[{"ORCID":"https://orcid.org/0000-0003-0952-476X","authenticated-orcid":false,"given":"Yulan","family":"Guo","sequence":"additional","affiliation":[{"name":"School of Electronics and Communication Engineering, Sun Yat-sen University, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}]},{"pid":"127/0477","key":"journals/tmm/FengHZGYWM25","title":"Exploring Hierarchical Spatial Layout Cues for 3D Point Cloud Based Scene Graph Prediction.","crossrefUrl":"https://api.crossref.org/works/10.1109/TMM.2023.3277736","authors":[{"ORCID":"https://orcid.org/0000-0003-0952-476X","authenticated-orcid":false,"given":"Yulan","family":"Guo","sequence":"additional","affiliation":[{"name":"School of Electronics and Communication Engineering, Sun Yat-sen University, Shenzhen Campus, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}]},{"pid":"127/0477","key":"journals/tmm/GaoWAZG25","title":"Enhancing Event-Based Video Reconstruction With Bidirectional Temporal Information.","crossrefUrl":"https://api.crossref.org/works/10.1109/TMM.2025.3543010","authors":[{"ORCID":"https://orcid.org/0000-0003-0952-476X","authenticated-orcid":false,"given":"Yulan","family":"Guo","sequence":"additional","affiliation":[{"name":"School of Electronics and Communication Engineering, Shenzhen Campus of Sun Yat-sen University, Sun Yat-sen University, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}]},{"pid":"127/0477","key":"journals/tmm/LiGYYR25","title":"Graph Proxy Fusion: Consensus Graph Intermediated Multi-View Local Information Fusion Clustering.","crossrefUrl":"https://api.crossref.org/works/10.1109/TMM.2024.3521803","authors":[{"ORCID":"https://orcid.org/0000-0003-0952-476X","authenticated-orcid":false,"given":"Yulan","family":"Guo","sequence":"additional","affiliation":[{"name":"School of Electronics and Communication Engineering, Shenzhen Campus of Sun Yat-sen University, Sun Yat-sen University, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}]},{"pid":"127/0477","key":"journals/tmm/LiuHWXWG25","title":"DuInNet: Dual-Modality Feature Interaction for Point Cloud Completion.","crossrefUrl":"https://api.crossref.org/works/10.1109/TMM.2025.3607739","authors":[{"ORCID":"https://orcid.org/0000-0003-0952-476X","authenticated-orcid":false,"given":"Yulan","family":"Guo","sequence":"additional","affiliation":[{"name":"School of Electronics and Communication Engineering, Shenzhen Campus, Sun Yat-sen University, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}]},{"pid":"127/0477","key":"journals/tmm/LiuZLLPG25","title":"SF-City: A Source-Free Domain Adaptation Method for City-Scale Point Cloud Semantic Segmentation.","crossrefUrl":"https://api.crossref.org/works/10.1109/TMM.2025.3590934","authors":[{"ORCID":"https://orcid.org/0000-0003-0952-476X","authenticated-orcid":false,"given":"Yulan","family":"Guo","sequence":"additional","affiliation":[{"name":"School of Electronics and Communication Engineering, the Shenzhen Campus of Sun Yat-Sen University, Sun Yat-Sen University, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}]},{"pid":"127/0477","key":"journals/tmm/YuZLLG25","title":"Hierarchical Distortion Learning for Fast Lossy Compression of Point Clouds.","crossrefUrl":"https://api.crossref.org/works/10.1109/TMM.2025.3565958","authors":[{"ORCID":"https://orcid.org/0000-0003-0952-476X","authenticated-orcid":false,"given":"Yulan","family":"Guo","sequence":"additional","affiliation":[{"name":"School of Electronics and Communication Engineering, Sun Yat-sen University, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}]},{"pid":"127/0477","key":"journals/tnn/DangZXWHG25","title":"Adaptive Sparse Memory Networks for Efficient and Robust Video Object Segmentation.","crossrefUrl":"https://api.crossref.org/works/10.1109/TNNLS.2024.3357118","authors":[{"ORCID":"https://orcid.org/0000-0003-0952-476X","authenticated-orcid":false,"given":"Yulan","family":"Guo","sequence":"additional","affiliation":[{"name":"School of Electronics and Communication Engineering, Sun Yat-sen University, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}]},{"pid":"127/0477","key":"journals/tnn/LiAXLWLG25","title":"Direction-Coded Temporal U-Shape Module for Multiframe Infrared Small Target Detection.","crossrefUrl":"https://api.crossref.org/works/10.1109/TNNLS.2023.3331004","authors":[{"ORCID":"https://orcid.org/0000-0003-0952-476X","authenticated-orcid":false,"given":"Yulan","family":"Guo","sequence":"additional","affiliation":[{"name":"College of Electronic Science and Technology, National University of Defense Technology (NUDT), Changsha, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}]},{"pid":"127/0477","key":"journals/tnn/LiRGYY25","title":"LSVC: A Lifelong Learning Approach for Stream-View Clustering.","crossrefUrl":"https://api.crossref.org/works/10.1109/TNNLS.2024.3439394","authors":[{"ORCID":"https://orcid.org/0000-0003-0952-476X","authenticated-orcid":false,"given":"Yulan","family":"Guo","sequence":"additional","affiliation":[{"name":"School of Electronics and Communication Engineering, Shenzhen Campus of Sun Yat-sen University, Sun Yat-sen University, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}]},{"pid":"127/0477","key":"journals/tnn/WangLSGWY25","title":"Satellite Pose Set Estimation by Uncertainty-Guided Conformal Keypoint Detection.","crossrefUrl":"https://api.crossref.org/works/10.1109/TNNLS.2025.3598481","authors":[{"ORCID":"https://orcid.org/0000-0003-0952-476X","authenticated-orcid":false,"given":"Yulan","family":"Guo","sequence":"additional","affiliation":[{"name":"College of Electronic Science and Technology, National University of Defense Technology, Changsha, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}]},{"pid":"127/0477","key":"journals/tnn/WangLWYAG25","title":"Real-World Light Field Image Super-Resolution Via Degradation Modulation.","crossrefUrl":"https://api.crossref.org/works/10.1109/TNNLS.2024.3378420","authors":[{"ORCID":"https://orcid.org/0000-0003-0952-476X","authenticated-orcid":false,"given":"Yulan","family":"Guo","sequence":"additional","affiliation":[{"name":"College of Electronic Science and Technology, National University of Defense Technology, Changsha, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}]},{"pid":"127/0477","key":"journals/vc/PeiLJZYLG25","title":"Energy-guided test-time adaptation for data shifts in multi-modal perception.","crossrefUrl":"https://api.crossref.org/works/10.1007/S00371-025-03952-3","authors":[{"given":"Yulan","family":"Guo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}]}],"identityReview":{"formalTitlesScreened":48,"crossrefRecordsChecked":47,"scope":"已筛查全部 2025 正式标题及以下 Crossref/原始来源；这不是逐篇全文审计，也不保证数据库不存在未发现的错归。","findings":["48 条正式记录全部筛查标题；47 条有 DOI 的记录全部查出版商提交的 Crossref 作者信息。","数据库 ORCID 0000-0001-7051-841X 与大量出版商元数据中的 0000-0003-0952-476X 不同；两种编号的记录均有中山大学机构证据。国防科技大学为其早期任职背景；未发现可证实的异人条目，暂保留 48。","无 DOI 的 NTIRE CVPR 2025 Challenge Light Field 记录仅按 DBLP 已消歧作者关联计入。"]},"signatureAudit":{"completedAt":"2026-10-19","frozen":true,"scope":"对 B 组 39 个数值档案的全部 1074 条原始 2025 正式记录扫描 DBLP author-signature ORCID 和机构；复用既有 59 条 Crossref 核验，补查 6 条新触发记录。重点核查不同 ORCID，以及只有预期机构之外机构的条目。本轮不扩展为所有作者逐篇全文审计。","formalRecordCoverage":48,"orcidCounts":{"https://orcid.org/0000-0001-7051-841X":4,"https://orcid.org/0000-0003-0952-476X":23},"institutionCounts":{"National University of Defense Technology (NUDT)":5,"Peng Cheng Laboratory":3,"Shenzhen University (SZU)":1,"Sun Yat-sen University":41},"caveat":"机构名称可能由 DBLP 自动映射而失真；多 ORCID 也不自动等于异人。只有有原始资料支撑的错归才作确认排除，未解决分支则暂停总数。"},"labName":"中山大学空间智能实验室（Spatial Artificial Intelligence Lab, SAIL）","labUrl":"https://sysu-sail.net/","labEvidence":"中山大学官方郭裕兰教师页明确将 sysu-sail.net 列作团队主页；该网站公开页面脚本明确写中山大学空间智能实验室（Spatial Artificial Intelligence Lab，SAIL），并列郭裕兰带领课题组的活动。","labSourceUrl":"https://sece.sysu.edu.cn/szll/js/zngz/1417219.htm","excludedOther":[],"excludedHomonyms":[],"unassignedCandidates":[],"knownPreprintMinimum2025":null,"excludedMisattributed":[],"displayNotes":"DBLP 页面提示 ORCID 冲突。作者身份与学校及个人来源相符，但与普通确认档案分开标记。计入 48 条（会议 21、期刊 27），所有作者位置均计入；预印本 18 条单列，不加总。","labDisplayNotes":"中山大学官方教师页将 sysu-sail.net 列为其团队主页；该站写明中山大学空间智能实验室（SAIL），并记录其带领的课题组活动，据此归组。它与港大赵恒爽的 SAIL 是不同实验室，不合并。"},{"index":42,"name":"Xiaoguang Han","nameZh":"韩晓光","role":"Associate Professor","affiliation":"The Chinese University of Hong Kong, Shenzhen","affiliationZh":"香港中文大学（深圳）","source":"DBLP RDF via official SPARQL; primary-source identity checks","sourceUrl":"https://sparql.dblp.org/","profileUrl":"https://dblp.org/pid/60/8294.html","identifier":"60/8294","retrievedAt":"2026-10-19","count2025":20,"conference2025":15,"journal2025":5,"preprint2025":20,"status":"confirmed","notes":"","identityEvidence":[{"url":"https://dblp.org/pid/60/8294.html","evidence":"DBLP RDF 类型为 Person，消歧后名字为 Xiaoguang Han 0001。机构元数据含：Chinese University of Hong Kong-Shenzhen (CUHK-SZ), Shenzhen, China；Hong Kong University；Zhejiang University, Hangzhou, China"}],"papers":[{"key":"conf/3dim/XuYQLTH25","url":"https://dblp.org/rec/conf/3dim/XuYQLTH25","title":"SAMPro3D: Locating SAM Prompts in 3D for Zero-Shot Instance Segmentation.","year":2025,"types":["Inproceedings"],"venue":"3DV","doi":"https://doi.org/10.1109/3DV66043.2025.00116","eventYear":2025,"numberOfCreators":6,"category":"conference","sources":["https://dblp.org/rec/conf/3dim/XuYQLTH25","https://doi.org/10.1109/3DV66043.2025.00116"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/3dim/XuYQLTH25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/cvpr/GaoYG0Y025","url":"https://dblp.org/rec/conf/cvpr/GaoYG0Y025","title":"Towards Realistic Example-based Modeling via 3D Gaussian Stitching.","year":2025,"types":["Inproceedings"],"venue":"CVPR","doi":"https://doi.org/10.1109/CVPR52734.2025.02477","eventYear":2025,"numberOfCreators":6,"category":"conference","sources":["https://dblp.org/rec/conf/cvpr/GaoYG0Y025","https://doi.org/10.1109/CVPR52734.2025.02477"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/GaoYG0Y025","documentUrl":null,"type":"Inproceedings"},{"key":"conf/cvpr/LiuF0LL0QWD025","url":"https://dblp.org/rec/conf/cvpr/LiuF0LL0QWD025","title":"Motions as Queries: One-Stage Multi-Person Holistic Human Motion Capture.","year":2025,"types":["Inproceedings"],"venue":"CVPR","doi":"https://doi.org/10.1109/CVPR52734.2025.01633","eventYear":2025,"numberOfCreators":10,"category":"conference","sources":["https://dblp.org/rec/conf/cvpr/LiuF0LL0QWD025","https://doi.org/10.1109/CVPR52734.2025.01633"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/LiuF0LL0QWD025","documentUrl":null,"type":"Inproceedings"},{"key":"conf/cvpr/LiuZYLW025","url":"https://dblp.org/rec/conf/cvpr/LiuZYLW025","title":"Stable-SCore: A Stable Registration-based Framework for 3D Shape Correspondence.","year":2025,"types":["Inproceedings"],"venue":"CVPR","doi":"https://doi.org/10.1109/CVPR52734.2025.00094","eventYear":2025,"numberOfCreators":6,"category":"conference","sources":["https://dblp.org/rec/conf/cvpr/LiuZYLW025","https://doi.org/10.1109/CVPR52734.2025.00094"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/LiuZYLW025","documentUrl":null,"type":"Inproceedings"},{"key":"conf/cvpr/ZhangLDCSZDXZ025","url":"https://dblp.org/rec/conf/cvpr/ZhangLDCSZDXZ025","title":"Robust-MVTON: Learning Cross-Pose Feature Alignment and Fusion for Robust Multi-View Virtual Try-On.","year":2025,"types":["Inproceedings"],"venue":"CVPR","doi":"https://doi.org/10.1109/CVPR52734.2025.01494","eventYear":2025,"numberOfCreators":10,"category":"conference","sources":["https://dblp.org/rec/conf/cvpr/ZhangLDCSZDXZ025","https://doi.org/10.1109/CVPR52734.2025.01494"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/ZhangLDCSZDXZ025","documentUrl":null,"type":"Inproceedings"},{"key":"conf/cvpr/ZhaoLXH0025","url":"https://dblp.org/rec/conf/cvpr/ZhaoLXH0025","title":"TASTE-Rob: Advancing Video Generation of Task-Oriented Hand-Object Interaction for Generalizable Robotic Manipulation.","year":2025,"types":["Inproceedings"],"venue":"CVPR","doi":"https://doi.org/10.1109/CVPR52734.2025.02578","eventYear":2025,"numberOfCreators":6,"category":"conference","sources":["https://dblp.org/rec/conf/cvpr/ZhaoLXH0025","https://doi.org/10.1109/CVPR52734.2025.02578"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/ZhaoLXH0025","documentUrl":null,"type":"Inproceedings"},{"key":"conf/eccv/ChangXLCFH24","url":"https://dblp.org/rec/conf/eccv/ChangXLCFH24","title":"GaussReg: Fast 3D Registration with Gaussian Splatting.","year":2025,"types":["Inproceedings"],"venue":"ECCV (15)","doi":"https://doi.org/10.1007/978-3-031-72633-0_23","eventYear":2024,"numberOfCreators":6,"category":"conference","sources":["https://dblp.org/rec/conf/eccv/ChangXLCFH24","https://doi.org/10.1007/978-3-031-72633-0_23"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2024,"sourceUrl":"https://dblp.org/rec/conf/eccv/ChangXLCFH24","documentUrl":null,"type":"Inproceedings"},{"key":"conf/eccv/LiCSQACH24","url":"https://dblp.org/rec/conf/eccv/LiCSQACH24","title":"SphereHead: Stable 3D Full-Head Synthesis with Spherical Tri-Plane Representation.","year":2025,"types":["Inproceedings"],"venue":"ECCV (75)","doi":"https://doi.org/10.1007/978-3-031-73226-3_19","eventYear":2024,"numberOfCreators":7,"category":"conference","sources":["https://dblp.org/rec/conf/eccv/LiCSQACH24","https://doi.org/10.1007/978-3-031-73226-3_19"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2024,"sourceUrl":"https://dblp.org/rec/conf/eccv/LiCSQACH24","documentUrl":null,"type":"Inproceedings"},{"key":"conf/eccv/YanZMWQYCCH24","url":"https://dblp.org/rec/conf/eccv/YanZMWQYCCH24","title":"DreamDissector: Learning Disentangled Text-to-3D Generation from 2D Diffusion Priors.","year":2025,"types":["Inproceedings"],"venue":"ECCV (12)","doi":"https://doi.org/10.1007/978-3-031-73254-6_8","eventYear":2024,"numberOfCreators":9,"category":"conference","sources":["https://dblp.org/rec/conf/eccv/YanZMWQYCCH24","https://doi.org/10.1007/978-3-031-73254-6_8"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2024,"sourceUrl":"https://dblp.org/rec/conf/eccv/YanZMWQYCCH24","documentUrl":null,"type":"Inproceedings"},{"key":"conf/eccv/ZhangXWXZHBS24","url":"https://dblp.org/rec/conf/eccv/ZhangXWXZHBS24","title":"Free-ATM: Harnessing Free Attention Masks for Representation Learning on Diffusion-Generated Images.","year":2025,"types":["Inproceedings"],"venue":"ECCV (40)","doi":"https://doi.org/10.1007/978-3-031-73661-2_26","eventYear":2024,"numberOfCreators":8,"category":"conference","sources":["https://dblp.org/rec/conf/eccv/ZhangXWXZHBS24","https://doi.org/10.1007/978-3-031-73661-2_26"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2024,"sourceUrl":"https://dblp.org/rec/conf/eccv/ZhangXWXZHBS24","documentUrl":null,"type":"Inproceedings"},{"key":"conf/eccv/ZhouLLXCLHL24","url":"https://dblp.org/rec/conf/eccv/ZhouLLXCLHL24","title":"Unveiling Advanced Frequency Disentanglement Paradigm for Low-Light Image Enhancement.","year":2025,"types":["Inproceedings"],"venue":"ECCV (7)","doi":"https://doi.org/10.1007/978-3-031-72667-5_12","eventYear":2024,"numberOfCreators":8,"category":"conference","sources":["https://dblp.org/rec/conf/eccv/ZhouLLXCLHL24","https://doi.org/10.1007/978-3-031-72667-5_12"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2024,"sourceUrl":"https://dblp.org/rec/conf/eccv/ZhouLLXCLHL24","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iccv/XuYLWCH25","url":"https://dblp.org/rec/conf/iccv/XuYLWCH25","title":"Stable-Sim2Real: Exploring Simulation of Real-Captured 3D Data with Two-Stage Depth Diffusion.","year":2025,"types":["Inproceedings"],"venue":"ICCV","doi":"https://doi.org/10.1109/ICCV51701.2025.00251","eventYear":2025,"numberOfCreators":6,"category":"conference","sources":["https://dblp.org/rec/conf/iccv/XuYLWCH25","https://doi.org/10.1109/ICCV51701.2025.00251"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/XuYLWCH25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iccv/YeWLCGZZH25","url":"https://dblp.org/rec/conf/iccv/YeWLCGZZH25","title":"Hi3dgen: High-Fidelity 3D Geometry Generation From Images Via Normal Bridging.","year":2025,"types":["Inproceedings"],"venue":"ICCV","doi":"https://doi.org/10.1109/ICCV51701.2025.02323","eventYear":2025,"numberOfCreators":8,"category":"conference","sources":["https://dblp.org/rec/conf/iccv/YeWLCGZZH25","https://doi.org/10.1109/ICCV51701.2025.02323"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/YeWLCGZZH25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/nips/LiLQZZDH25","url":"https://dblp.org/rec/conf/nips/LiLQZZDH25","title":"HyPlaneHead: Rethinking Tri-plane-like Representations in Full-Head Image Synthesis.","year":2025,"types":["Inproceedings"],"venue":"NeurIPS","doi":null,"eventYear":2025,"numberOfCreators":7,"category":"conference","sources":["https://dblp.org/rec/conf/nips/LiLQZZDH25"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/nips/LiLQZZDH25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/siggrapha/ZhiLLYSCCF025","url":"https://dblp.org/rec/conf/siggrapha/ZhiLLYSCCF025","title":"MV-Performer: Taming Video Diffusion Model for Faithful and Synchronized Multi-view Performer Synthesis.","year":2025,"types":["Inproceedings"],"venue":"SIGGRAPH Asia","doi":"https://doi.org/10.1145/3757377.3763935","eventYear":2025,"numberOfCreators":9,"category":"conference","sources":["https://dblp.org/rec/conf/siggrapha/ZhiLLYSCCF025","https://doi.org/10.1145/3757377.3763935"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/siggrapha/ZhiLLYSCCF025","documentUrl":null,"type":"Inproceedings"},{"key":"journals/cmig/LiuDLTYHSL25","url":"https://dblp.org/rec/journals/cmig/LiuDLTYHSL25","title":"Subtraction-free artifact-aware digital subtraction angiography image generation for head and neck vessels from motion data.","year":2025,"types":["Article"],"venue":"Comput. Medical Imaging Graph.","doi":"https://doi.org/10.1016/J.COMPMEDIMAG.2025.102512","numberOfCreators":8,"category":"journal","sources":["https://dblp.org/rec/journals/cmig/LiuDLTYHSL25","https://doi.org/10.1016/J.COMPMEDIMAG.2025.102512"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/cmig/LiuDLTYHSL25","documentUrl":null,"type":"Article"},{"key":"journals/tvcg/QuSYHF25","url":"https://dblp.org/rec/journals/tvcg/QuSYHF25","title":"Sketch2Human: Deep Human Generation With Disentangled Geometry and Appearance Constraints.","year":2025,"types":["Article"],"venue":"IEEE Trans. Vis. Comput. Graph.","doi":"https://doi.org/10.1109/TVCG.2024.3403160","numberOfCreators":5,"category":"journal","sources":["https://dblp.org/rec/journals/tvcg/QuSYHF25","https://doi.org/10.1109/TVCG.2024.3403160"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/tvcg/QuSYHF25","documentUrl":null,"type":"Article"},{"key":"journals/tvcg/ShuSC0X25","url":"https://dblp.org/rec/journals/tvcg/ShuSC0X25","title":"StrucADT: Generating Structure-Controlled 3D Point Clouds With Adjacency Diffusion Transformer.","year":2025,"types":["Article"],"venue":"IEEE Trans. Vis. Comput. Graph.","doi":"https://doi.org/10.1109/TVCG.2025.3600392","numberOfCreators":5,"category":"journal","sources":["https://dblp.org/rec/journals/tvcg/ShuSC0X25","https://doi.org/10.1109/TVCG.2025.3600392"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/tvcg/ShuSC0X25","documentUrl":null,"type":"Article"},{"key":"journals/tvcg/ZhangXSZJXHW25","url":"https://dblp.org/rec/journals/tvcg/ZhangXSZJXHW25","title":"ViTon-GUN: Person-to-Person Virtual Try-on via Garment Unwrapping.","year":2025,"types":["Article"],"venue":"IEEE Trans. Vis. Comput. Graph.","doi":"https://doi.org/10.1109/TVCG.2025.3550776","numberOfCreators":8,"category":"journal","sources":["https://dblp.org/rec/journals/tvcg/ZhangXSZJXHW25","https://doi.org/10.1109/TVCG.2025.3550776"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/tvcg/ZhangXSZJXHW25","documentUrl":null,"type":"Article"},{"key":"journals/tvcg/ZhiSCYFH25","url":"https://dblp.org/rec/journals/tvcg/ZhiSCYFH25","title":"StruGauAvatar: Learning Structured 3D Gaussians for Animatable Avatars From Monocular Videos.","year":2025,"types":["Article"],"venue":"IEEE Trans. Vis. Comput. Graph.","doi":"https://doi.org/10.1109/TVCG.2025.3557457","numberOfCreators":6,"category":"journal","sources":["https://dblp.org/rec/journals/tvcg/ZhiSCYFH25","https://doi.org/10.1109/TVCG.2025.3557457"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/tvcg/ZhiSCYFH25","documentUrl":null,"type":"Article"}],"preprints":[{"key":"journals/corr/abs-2501-05369","url":"https://dblp.org/rec/journals/corr/abs-2501-05369","title":"1-2-1: Renaissance of Single-Network Paradigm for Virtual Try-On.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2501.05369","numberOfCreators":3,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2501-05369","https://doi.org/10.48550/ARXIV.2501.05369"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2501-05369","documentUrl":null,"type":"Informal","arxivId":"2501.05369","arxivUrl":"https://arxiv.org/abs/2501.05369"},{"key":"journals/corr/abs-2501-16177","url":"https://dblp.org/rec/journals/corr/abs-2501-16177","title":"BAG: Body-Aligned 3D Wearable Asset Generation.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2501.16177","numberOfCreators":11,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2501-16177","https://doi.org/10.48550/ARXIV.2501.16177"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2501-16177","documentUrl":null,"type":"Informal","arxivId":"2501.16177","arxivUrl":"https://arxiv.org/abs/2501.16177"},{"key":"journals/corr/abs-2503-11423","url":"https://dblp.org/rec/journals/corr/abs-2503-11423","title":"TASTE-Rob: Advancing Video Generation of Task-Oriented Hand-Object Interaction for Generalizable Robotic Manipulation.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2503.11423","numberOfCreators":6,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2503-11423","https://doi.org/10.48550/ARXIV.2503.11423"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-11423","documentUrl":null,"type":"Informal","arxivId":"2503.11423","arxivUrl":"https://arxiv.org/abs/2503.11423"},{"key":"journals/corr/abs-2503-21766","url":"https://dblp.org/rec/journals/corr/abs-2503-21766","title":"Stable-SCore: A Stable Registration-based Framework for 3D Shape Correspondence.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2503.21766","numberOfCreators":6,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2503-21766","https://doi.org/10.48550/ARXIV.2503.21766"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-21766","documentUrl":null,"type":"Informal","arxivId":"2503.21766","arxivUrl":"https://arxiv.org/abs/2503.21766"},{"key":"journals/corr/abs-2503-22236","url":"https://dblp.org/rec/journals/corr/abs-2503-22236","title":"Hi3DGen: High-fidelity 3D Geometry Generation from Images via Normal Bridging.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2503.22236","numberOfCreators":8,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2503-22236","https://doi.org/10.48550/ARXIV.2503.22236"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-22236","documentUrl":null,"type":"Informal","arxivId":"2503.22236","arxivUrl":"https://arxiv.org/abs/2503.22236"},{"key":"journals/corr/abs-2505-01838","url":"https://dblp.org/rec/journals/corr/abs-2505-01838","title":"MVHumanNet++: A Large-scale Dataset of Multi-view Daily Dressing Human Captures with Richer Annotations for 3D Human Digitization.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2505.01838","numberOfCreators":8,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2505-01838","https://doi.org/10.48550/ARXIV.2505.01838"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-01838","documentUrl":null,"type":"Informal","arxivId":"2505.01838","arxivUrl":"https://arxiv.org/abs/2505.01838"},{"key":"journals/corr/abs-2506-13766","url":"https://dblp.org/rec/journals/corr/abs-2506-13766","title":"PF-LHM: 3D Animatable Avatar Reconstruction from Pose-free Articulated Human Images.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2506.13766","numberOfCreators":10,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2506-13766","https://doi.org/10.48550/ARXIV.2506.13766"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-13766","documentUrl":null,"type":"Informal","arxivId":"2506.13766","arxivUrl":"https://arxiv.org/abs/2506.13766"},{"key":"journals/corr/abs-2507-23483","url":"https://dblp.org/rec/journals/corr/abs-2507-23483","title":"Stable-Sim2Real: Exploring Simulation of Real-Captured 3D Data with Two-Stage Depth Diffusion.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2507.23483","numberOfCreators":6,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2507-23483","https://doi.org/10.48550/ARXIV.2507.23483"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2507-23483","documentUrl":null,"type":"Informal","arxivId":"2507.23483","arxivUrl":"https://arxiv.org/abs/2507.23483"},{"key":"journals/corr/abs-2509-00777","url":"https://dblp.org/rec/journals/corr/abs-2509-00777","title":"IntrinsicReal: Adapting IntrinsicAnything from Synthetic to Real Objects.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2509.00777","numberOfCreators":6,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2509-00777","https://doi.org/10.48550/ARXIV.2509.00777"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-00777","documentUrl":null,"type":"Informal","arxivId":"2509.00777","arxivUrl":"https://arxiv.org/abs/2509.00777"},{"key":"journals/corr/abs-2509-16748","url":"https://dblp.org/rec/journals/corr/abs-2509-16748","title":"HyPlaneHead: Rethinking Tri-plane-like Representations in Full-Head Image Synthesis.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2509.16748","numberOfCreators":7,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2509-16748","https://doi.org/10.48550/ARXIV.2509.16748"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-16748","documentUrl":null,"type":"Informal","arxivId":"2509.16748","arxivUrl":"https://arxiv.org/abs/2509.16748"},{"key":"journals/corr/abs-2509-21291","url":"https://dblp.org/rec/journals/corr/abs-2509-21291","title":"VC-Agent: An Interactive Agent for Customized Video Dataset Collection.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2509.21291","numberOfCreators":9,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2509-21291","https://doi.org/10.48550/ARXIV.2509.21291"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-21291","documentUrl":null,"type":"Informal","arxivId":"2509.21291","arxivUrl":"https://arxiv.org/abs/2509.21291"},{"key":"journals/corr/abs-2509-23709","url":"https://dblp.org/rec/journals/corr/abs-2509-23709","title":"StrucADT: Generating Structure-controlled 3D Point Clouds with Adjacency Diffusion Transformer.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2509.23709","numberOfCreators":5,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2509-23709","https://doi.org/10.48550/ARXIV.2509.23709"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-23709","documentUrl":null,"type":"Informal","arxivId":"2509.23709","arxivUrl":"https://arxiv.org/abs/2509.23709"},{"key":"journals/corr/abs-2510-07190","url":"https://dblp.org/rec/journals/corr/abs-2510-07190","title":"MV-Performer: Taming Video Diffusion Model for Faithful and Synchronized Multi-view Performer Synthesis.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2510.07190","numberOfCreators":9,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2510-07190","https://doi.org/10.48550/ARXIV.2510.07190"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-07190","documentUrl":null,"type":"Informal","arxivId":"2510.07190","arxivUrl":"https://arxiv.org/abs/2510.07190"},{"key":"journals/corr/abs-2510-23306","url":"https://dblp.org/rec/journals/corr/abs-2510-23306","title":"ReconViaGen: Towards Accurate Multi-view 3D Object Reconstruction via Generation.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2510.23306","numberOfCreators":9,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2510-23306","https://doi.org/10.48550/ARXIV.2510.23306"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-23306","documentUrl":null,"type":"Informal","arxivId":"2510.23306","arxivUrl":"https://arxiv.org/abs/2510.23306"},{"key":"journals/corr/abs-2511-06721","url":"https://dblp.org/rec/journals/corr/abs-2511-06721","title":"AvatarTex: High-Fidelity Facial Texture Reconstruction from Single-Image Stylized Avatars.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2511.06721","numberOfCreators":6,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2511-06721","https://doi.org/10.48550/ARXIV.2511.06721"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2511-06721","documentUrl":null,"type":"Informal","arxivId":"2511.06721","arxivUrl":"https://arxiv.org/abs/2511.06721"},{"key":"journals/corr/abs-2511-18600","url":"https://dblp.org/rec/journals/corr/abs-2511-18600","title":"NeAR: Coupled Neural Asset-Renderer Stack.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2511.18600","numberOfCreators":15,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2511-18600","https://doi.org/10.48550/ARXIV.2511.18600"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2511-18600","documentUrl":null,"type":"Informal","arxivId":"2511.18600","arxivUrl":"https://arxiv.org/abs/2511.18600"},{"key":"journals/corr/abs-2511-19437","url":"https://dblp.org/rec/journals/corr/abs-2511-19437","title":"LumiTex: Towards High-Fidelity PBR Texture Generation with Illumination Context.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2511.19437","numberOfCreators":13,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2511-19437","https://doi.org/10.48550/ARXIV.2511.19437"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2511-19437","documentUrl":null,"type":"Informal","arxivId":"2511.19437","arxivUrl":"https://arxiv.org/abs/2511.19437"},{"key":"journals/corr/abs-2512-07720","url":"https://dblp.org/rec/journals/corr/abs-2512-07720","title":"ViSA: 3D-Aware Video Shading for Real-Time Upper-Body Avatar Creation.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2512.07720","numberOfCreators":12,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2512-07720","https://doi.org/10.48550/ARXIV.2512.07720"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-07720","documentUrl":null,"type":"Informal","arxivId":"2512.07720","arxivUrl":"https://arxiv.org/abs/2512.07720"},{"key":"journals/corr/abs-2512-08785","url":"https://dblp.org/rec/journals/corr/abs-2512-08785","title":"LoFA: Learning to Predict Personalized Priors for Fast Adaptation of Visual Generative Models.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2512.08785","numberOfCreators":7,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2512-08785","https://doi.org/10.48550/ARXIV.2512.08785"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-08785","documentUrl":null,"type":"Informal","arxivId":"2512.08785","arxivUrl":"https://arxiv.org/abs/2512.08785"},{"key":"journals/corr/abs-2512-09435","url":"https://dblp.org/rec/journals/corr/abs-2512-09435","title":"UniPart: Part-Level 3D Generation with Unified 3D Geom-Seg Latents.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2512.09435","numberOfCreators":8,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2512-09435","https://doi.org/10.48550/ARXIV.2512.09435"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-09435","documentUrl":null,"type":"Informal","arxivId":"2512.09435","arxivUrl":"https://arxiv.org/abs/2512.09435"}],"excludedFormal":[],"otherRecords":[],"matchedName":"Xiaoguang Han","databaseLabel":"Xiaoguang Han 0001","databaseMetadata":{"type":["https://dblp.org/rdf/schema#Person","https://dblp.org/rdf/schema#Creator"],"label":["Xiaoguang Han 0001"],"affiliation":["Chinese University of Hong Kong-Shenzhen (CUHK-SZ), Shenzhen, China","Hong Kong University","Zhejiang University, Hangzhou, China"],"homepage":["https://mypage.cuhk.edu.cn/academics/hanxiaoguang/"],"orcid":["https://orcid.org/0000-0003-0162-3296"],"primaryAffiliation":["Chinese University of Hong Kong-Shenzhen (CUHK-SZ), Shenzhen, China"],"primaryHomepage":["https://mypage.cuhk.edu.cn/academics/hanxiaoguang/"]},"rawFormalRecordCount2025":20,"signatureAudit":{"completedAt":"2026-10-19","frozen":true,"scope":"对 B 组 39 个数值档案的全部 1074 条原始 2025 正式记录扫描 DBLP author-signature ORCID 和机构；复用既有 59 条 Crossref 核验，补查 6 条新触发记录。重点核查不同 ORCID，以及只有预期机构之外机构的条目。本轮不扩展为所有作者逐篇全文审计。","formalRecordCoverage":20,"orcidCounts":{"https://orcid.org/0000-0003-0162-3296":7},"institutionCounts":{"Chinese University of Hong Kong (CUHK)":5,"Shenzhen Research Institute of Big Data (SRIBD)":2,"Stockholm School of Economics (HHS)":7,"The Chinese University of Hong Kong, Shenzhen (CUHK-SZ)":15},"caveat":"机构名称可能由 DBLP 自动映射而失真；多 ORCID 也不自动等于异人。只有有原始资料支撑的错归才作确认排除，未解决分支则暂停总数。"},"labName":"GAP Lab","labUrl":"https://gaplab.cuhk.edu.cn/","labEvidence":"实验室官方 About 明确写 led by Dr. Xiaoguang Han；香港中文大学（深圳）官方韩晓光教师页也将此实验室域名列为 Personal Website。","labSourceUrl":"https://gaplab.cuhk.edu.cn/","sourceWarning":false,"excludedOther":[],"excludedHomonyms":[],"unassignedCandidates":[],"knownPreprintMinimum2025":null,"excludedMisattributed":[],"displayNotes":"身份已与原名单机构及公开资料核对确认。2025 年正式记录 20 条（会议 15、期刊 5），所有作者位置均计入，不表示主导或贡献份额；预印本 20 条单列，不加总。","labDisplayNotes":"GAP Lab 官网写明由其领导，港中文（深圳）官方教师页也把该网站列为其个人网站，据此归组。原倡议即托管在这个站点。"},{"index":43,"name":"Junhui Hou","nameZh":"侯军辉","role":"Professor","affiliation":"City University of Hong Kong","affiliationZh":"香港城市大学","source":"DBLP RDF via official SPARQL; primary-source identity checks","sourceUrl":"https://sparql.dblp.org/","profileUrl":"https://dblp.org/pid/122/2673.html","identifier":"122/2673","retrievedAt":"2026-10-19","count2025":49,"conference2025":21,"journal2025":28,"preprint2025":26,"status":"confirmed","notes":"排除 1 条数据库形式上属于期刊/会议的记录，逐条原因见 excludedFormal。","identityEvidence":[{"url":"https://dblp.org/pid/122/2673.html","evidence":"DBLP RDF 类型为 Person，消歧后名字为 Junhui Hou。机构元数据含：City University of Hong Kong, Department of Computer Science, Hong Kong"}],"papers":[{"key":"conf/cvpr/HuLHHZWL025","url":"https://dblp.org/rec/conf/cvpr/HuLHHZWL025","title":"A Lightweight UDF Learning Framework for 3D Reconstruction Based on Local Shape Functions.","year":2025,"types":["Inproceedings"],"venue":"CVPR","doi":"https://doi.org/10.1109/CVPR52734.2025.00129","eventYear":2025,"numberOfCreators":8,"category":"conference","sources":["https://dblp.org/rec/conf/cvpr/HuLHHZWL025","https://doi.org/10.1109/CVPR52734.2025.00129"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/HuLHHZWL025","documentUrl":null,"type":"Inproceedings"},{"key":"conf/cvpr/LiuZ0H25","url":"https://dblp.org/rec/conf/cvpr/LiuZ0H25","title":"Acc3D: Accelerating Single Image to 3D Diffusion Models via Edge Consistency Guided Score Distillation.","year":2025,"types":["Inproceedings"],"venue":"CVPR","doi":"https://doi.org/10.1109/CVPR52734.2025.01680","eventYear":2025,"numberOfCreators":4,"category":"conference","sources":["https://dblp.org/rec/conf/cvpr/LiuZ0H25","https://doi.org/10.1109/CVPR52734.2025.01680"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/LiuZ0H25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/cvpr/LiuZZZS0H25","url":"https://dblp.org/rec/conf/cvpr/LiuZZZS0H25","title":"LFTramba: Comprehensive Information Learning for Light Field Image Super-Resolution via A Hybrid Transformer-Mamba Framework.","year":2025,"types":["Inproceedings"],"venue":"CVPR Workshops","doi":null,"eventYear":2025,"numberOfCreators":7,"category":"conference","sources":["https://dblp.org/rec/conf/cvpr/LiuZZZS0H25"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/LiuZZZS0H25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/cvpr/WangLZTW00TGJWY25","url":"https://dblp.org/rec/conf/cvpr/WangLZTW00TGJWY25","title":"NTIRE 2025 Challenge on Light Field Image Super-Resolution: Methods and Results.","year":2025,"types":["Inproceedings"],"venue":"CVPR Workshops","doi":null,"eventYear":2025,"numberOfCreators":74,"category":"conference","sources":["https://dblp.org/rec/conf/cvpr/WangLZTW00TGJWY25"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/WangLZTW00TGJWY25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/cvpr/YaoDH25","url":"https://dblp.org/rec/conf/cvpr/YaoDH25","title":"RigGS: Rigging of 3D Gaussians for Modeling Articulated Objects in Videos.","year":2025,"types":["Inproceedings"],"venue":"CVPR","doi":"https://doi.org/10.1109/CVPR52734.2025.00525","eventYear":2025,"numberOfCreators":3,"category":"conference","sources":["https://dblp.org/rec/conf/cvpr/YaoDH25","https://doi.org/10.1109/CVPR52734.2025.00525"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/YaoDH25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/eccv/YaoRHDZW24","url":"https://dblp.org/rec/conf/eccv/YaoRHDZW24","title":"DynoSurf: Neural Deformation-Based Temporally Consistent Dynamic Surface Reconstruction.","year":2025,"types":["Inproceedings"],"venue":"ECCV (33)","doi":"https://doi.org/10.1007/978-3-031-73414-4_16","eventYear":2024,"numberOfCreators":6,"category":"conference","sources":["https://dblp.org/rec/conf/eccv/YaoRHDZW24","https://doi.org/10.1007/978-3-031-73414-4_16"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2024,"sourceUrl":"https://dblp.org/rec/conf/eccv/YaoRHDZW24","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iccv/KristanMTLFZTVBNCFADFFG25","url":"https://dblp.org/rec/conf/iccv/KristanMTLFZTVBNCFADFFG25","title":"The Third Visual Object Tracking Segmentation VOTS2025 Challenge Results.","year":2025,"types":["Inproceedings"],"venue":"ICCVW","doi":"https://doi.org/10.1109/ICCVW69036.2025.00771","eventYear":2025,"numberOfCreators":70,"category":"conference","sources":["https://dblp.org/rec/conf/iccv/KristanMTLFZTVBNCFADFFG25","https://doi.org/10.1109/ICCVW69036.2025.00771"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/KristanMTLFZTVBNCFADFFG25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iccv/QianHHSF25","url":"https://dblp.org/rec/conf/iccv/QianHHSF25","title":"VOVTrack: Exploring the Potentiality in Raw Videos for Open-Vocabulary Multi-Object Tracking.","year":2025,"types":["Inproceedings"],"venue":"ICCV","doi":"https://doi.org/10.1109/ICCV51701.2025.00701","eventYear":2025,"numberOfCreators":5,"category":"conference","sources":["https://dblp.org/rec/conf/iccv/QianHHSF25","https://doi.org/10.1109/ICCV51701.2025.00701"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/QianHHSF25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iccv/QianHWHF25","url":"https://dblp.org/rec/conf/iccv/QianHWHF25","title":"COVTrack: Continuous Open-Vocabulary Tracking via Adaptive Multi-Cue Fusion.","year":2025,"types":["Inproceedings"],"venue":"ICCV","doi":"https://doi.org/10.1109/ICCV51701.2025.00937","eventYear":2025,"numberOfCreators":5,"category":"conference","sources":["https://dblp.org/rec/conf/iccv/QianHWHF25","https://doi.org/10.1109/ICCV51701.2025.00937"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/QianHWHF25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iccv/RenHLW25","url":"https://dblp.org/rec/conf/iccv/RenHLW25","title":"Neural Compression for 3D Geometry Sets.","year":2025,"types":["Inproceedings"],"venue":"ICCV","doi":"https://doi.org/10.1109/ICCV51701.2025.02346","eventYear":2025,"numberOfCreators":4,"category":"conference","sources":["https://dblp.org/rec/conf/iccv/RenHLW25","https://doi.org/10.1109/ICCV51701.2025.02346"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/RenHLW25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iclr/JiaC0H25","url":"https://dblp.org/rec/conf/iclr/JiaC0H25","title":"Towards Calibrated Deep Clustering Network.","year":2025,"types":["Inproceedings"],"venue":"ICLR","doi":null,"eventYear":2025,"numberOfCreators":4,"category":"conference","sources":["https://dblp.org/rec/conf/iclr/JiaC0H25"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iclr/JiaC0H25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iclr/Liu00L0WH25","url":"https://dblp.org/rec/conf/iclr/Liu00L0WH25","title":"MoDGS: Dynamic Gaussian Splatting from Casually-captured Monocular Videos with Depth Priors.","year":2025,"types":["Inproceedings"],"venue":"ICLR","doi":null,"eventYear":2025,"numberOfCreators":7,"category":"conference","sources":["https://dblp.org/rec/conf/iclr/Liu00L0WH25"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iclr/Liu00L0WH25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iclr/LuZH25","url":"https://dblp.org/rec/conf/iclr/LuZH25","title":"ParaSolver: A Hierarchical Parallel Integral Solver for Diffusion Models.","year":2025,"types":["Inproceedings"],"venue":"ICLR","doi":null,"eventYear":2025,"numberOfCreators":3,"category":"conference","sources":["https://dblp.org/rec/conf/iclr/LuZH25"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iclr/LuZH25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iclr/RenH25","url":"https://dblp.org/rec/conf/iclr/RenH25","title":"Shape as Line Segments: Accurate and Flexible Implicit Surface Representation.","year":2025,"types":["Inproceedings"],"venue":"ICLR","doi":null,"eventYear":2025,"numberOfCreators":2,"category":"conference","sources":["https://dblp.org/rec/conf/iclr/RenH25"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iclr/RenH25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iclr/YouZ0H25","url":"https://dblp.org/rec/conf/iclr/YouZ0H25","title":"NVS-Solver: Video Diffusion Model as Zero-Shot Novel View Synthesizer.","year":2025,"types":["Inproceedings"],"venue":"ICLR","doi":null,"eventYear":2025,"numberOfCreators":4,"category":"conference","sources":["https://dblp.org/rec/conf/iclr/YouZ0H25"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iclr/YouZ0H25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/icml/LiJ0H25","url":"https://dblp.org/rec/conf/icml/LiJ0H25","title":"Learning from Sample Stability for Deep Clustering.","year":2025,"types":["Inproceedings"],"venue":"ICML","doi":null,"eventYear":2025,"numberOfCreators":4,"category":"conference","sources":["https://dblp.org/rec/conf/icml/LiJ0H25"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/icml/LiJ0H25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/icml/ZhangQL0HJ25","url":"https://dblp.org/rec/conf/icml/ZhangQL0HJ25","title":"Generalization Performance of Ensemble Clustering: From Theory to Algorithm.","year":2025,"types":["Inproceedings"],"venue":"ICML","doi":null,"eventYear":2025,"numberOfCreators":6,"category":"conference","sources":["https://dblp.org/rec/conf/icml/ZhangQL0HJ25"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/icml/ZhangQL0HJ25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/kdd/YangC0DJH25","url":"https://dblp.org/rec/conf/kdd/YangC0DJH25","title":"Mixed Blessing: Class-Wise Embedding guided Instance-Dependent Partial Label Learning.","year":2025,"types":["Inproceedings"],"venue":"KDD (1)","doi":"https://doi.org/10.1145/3690624.3709276","eventYear":2025,"numberOfCreators":6,"category":"conference","sources":["https://dblp.org/rec/conf/kdd/YangC0DJH25","https://doi.org/10.1145/3690624.3709276"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/kdd/YangC0DJH25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/nips/HouHJLH25","url":"https://dblp.org/rec/conf/nips/HouHJLH25","title":"Keep It on a Leash: Controllable Pseudo-label Generation Towards Realistic Long-Tailed Semi-Supervised Learning.","year":2025,"types":["Inproceedings"],"venue":"NeurIPS","doi":null,"eventYear":2025,"numberOfCreators":5,"category":"conference","sources":["https://dblp.org/rec/conf/nips/HouHJLH25"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/nips/HouHJLH25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/nips/LiJLH25","url":"https://dblp.org/rec/conf/nips/LiJLH25","title":"You Can Trust Your Clustering Model: A Parameter-free Self-Boosting Plug-in for Deep Clustering.","year":2025,"types":["Inproceedings"],"venue":"NeurIPS","doi":null,"eventYear":2025,"numberOfCreators":4,"category":"conference","sources":["https://dblp.org/rec/conf/nips/LiJLH25"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/nips/LiJLH25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/nips/QianHWHF25","url":"https://dblp.org/rec/conf/nips/QianHWHF25","title":"DOVTrack: Data-Efficient Open-Vocabulary Tracking.","year":2025,"types":["Inproceedings"],"venue":"NeurIPS","doi":null,"eventYear":2025,"numberOfCreators":5,"category":"conference","sources":["https://dblp.org/rec/conf/nips/QianHWHF25"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/nips/QianHWHF25","documentUrl":null,"type":"Inproceedings"},{"key":"journals/caaitrit/ChengWHHWX25","url":"https://dblp.org/rec/journals/caaitrit/ChengWHHWX25","title":"Arbitrary-Scale Point Cloud Upsampling via Enhanced Geometric Spatial Consistency.","year":2025,"types":["Article"],"venue":"CAAI Trans. Intell. Technol.","doi":"https://doi.org/10.1049/CIT2.70052","numberOfCreators":6,"category":"journal","sources":["https://dblp.org/rec/journals/caaitrit/ChengWHHWX25","https://doi.org/10.1049/CIT2.70052"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/caaitrit/ChengWHHWX25","documentUrl":null,"type":"Article"},{"key":"journals/cvm/DidykH25","url":"https://dblp.org/rec/journals/cvm/DidykH25","title":"Message from Guest Editors of the CVM 2025 Special Issue.","year":2025,"types":["Article"],"venue":"Comput. Vis. Media","doi":"https://doi.org/10.26599/CVM.2025.9450515","numberOfCreators":2,"category":"journal","sources":["https://dblp.org/rec/journals/cvm/DidykH25","https://doi.org/10.26599/CVM.2025.9450515"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/cvm/DidykH25","documentUrl":null,"type":"Article"},{"key":"journals/jstsp/LinHLZM25","url":"https://dblp.org/rec/journals/jstsp/LinHLZM25","title":"Enhancing Underwater Imaging With 4-D Light Fields: Dataset and Method.","year":2025,"types":["Article"],"venue":"IEEE J. Sel. Top. Signal Process.","doi":"https://doi.org/10.1109/JSTSP.2025.3589758","numberOfCreators":5,"category":"journal","sources":["https://dblp.org/rec/journals/jstsp/LinHLZM25","https://doi.org/10.1109/JSTSP.2025.3589758"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/jstsp/LinHLZM25","documentUrl":null,"type":"Article"},{"key":"journals/pami/FengWHGQHW25","url":"https://dblp.org/rec/journals/pami/FengWHGQHW25","title":"Unveiling the Power of Self-Supervision for Multi-View Multi-Human Association and Tracking.","year":2025,"types":["Article"],"venue":"IEEE Trans. Pattern Anal. Mach. Intell.","doi":"https://doi.org/10.1109/TPAMI.2024.3463966","numberOfCreators":7,"category":"journal","sources":["https://dblp.org/rec/journals/pami/FengWHGQHW25","https://doi.org/10.1109/TPAMI.2024.3463966"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/pami/FengWHGQHW25","documentUrl":null,"type":"Article"},{"key":"journals/pami/RenHCXW25","url":"https://dblp.org/rec/journals/pami/RenHCXW25","title":"DDM: A Metric for Comparing 3D Shapes Using Directional Distance Fields.","year":2025,"types":["Article"],"venue":"IEEE Trans. Pattern Anal. Mach. Intell.","doi":"https://doi.org/10.1109/TPAMI.2025.3560297","numberOfCreators":5,"category":"journal","sources":["https://dblp.org/rec/journals/pami/RenHCXW25","https://doi.org/10.1109/TPAMI.2025.3560297"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/pami/RenHCXW25","documentUrl":null,"type":"Article"},{"key":"journals/pami/TangZLH25","url":"https://dblp.org/rec/journals/pami/TangZLH25","title":"Human as Points: Explicit Point-Based 3D Human Reconstruction From Single-View RGB Images.","year":2025,"types":["Article"],"venue":"IEEE Trans. Pattern Anal. Mach. Intell.","doi":"https://doi.org/10.1109/TPAMI.2025.3552408","numberOfCreators":4,"category":"journal","sources":["https://dblp.org/rec/journals/pami/TangZLH25","https://doi.org/10.1109/TPAMI.2025.3552408"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/pami/TangZLH25","documentUrl":null,"type":"Article"},{"key":"journals/pami/YangZWMHLW25","url":"https://dblp.org/rec/journals/pami/YangZWMHLW25","title":"Monge-Ampere Regularization for Learning Arbitrary Shapes From Point Clouds.","year":2025,"types":["Article"],"venue":"IEEE Trans. Pattern Anal. Mach. Intell.","doi":"https://doi.org/10.1109/TPAMI.2025.3563601","numberOfCreators":7,"category":"journal","sources":["https://dblp.org/rec/journals/pami/YangZWMHLW25","https://doi.org/10.1109/TPAMI.2025.3563601"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/pami/YangZWMHLW25","documentUrl":null,"type":"Article"},{"key":"journals/pami/YaoDHZ25","url":"https://dblp.org/rec/journals/pami/YaoDHZ25","title":"SPARE: Symmetrized Point-to-Plane Distance for Robust Non-Rigid 3D Registration.","year":2025,"types":["Article"],"venue":"IEEE Trans. Pattern Anal. Mach. Intell.","doi":"https://doi.org/10.1109/TPAMI.2025.3598630","numberOfCreators":4,"category":"journal","sources":["https://dblp.org/rec/journals/pami/YaoDHZ25","https://doi.org/10.1109/TPAMI.2025.3598630"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/pami/YaoDHZ25","documentUrl":null,"type":"Article"},{"key":"journals/pami/ZhangHRWYS25","url":"https://dblp.org/rec/journals/pami/ZhangHRWYS25","title":"Self-Supervised Learning of LiDAR 3D Point Clouds via 2D-3D Neural Calibration.","year":2025,"types":["Article"],"venue":"IEEE Trans. Pattern Anal. Mach. Intell.","doi":"https://doi.org/10.1109/TPAMI.2025.3584625","numberOfCreators":6,"category":"journal","sources":["https://dblp.org/rec/journals/pami/ZhangHRWYS25","https://doi.org/10.1109/TPAMI.2025.3584625"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/pami/ZhangHRWYS25","documentUrl":null,"type":"Article"},{"key":"journals/pami/ZhuHLZH25","url":"https://dblp.org/rec/journals/pami/ZhuHLZH25","title":"Learning Efficient and Effective Trajectories for Differential Equation-Based Image Restoration.","year":2025,"types":["Article"],"venue":"IEEE Trans. Pattern Anal. Mach. Intell.","doi":"https://doi.org/10.1109/TPAMI.2025.3584921","numberOfCreators":5,"category":"journal","sources":["https://dblp.org/rec/journals/pami/ZhuHLZH25","https://doi.org/10.1109/TPAMI.2025.3584921"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/pami/ZhuHLZH25","documentUrl":null,"type":"Article"},{"key":"journals/tcsv/ChenLLSGHL25","url":"https://dblp.org/rec/journals/tcsv/ChenLLSGHL25","title":"CSTA: Spatial-Temporal Causal Adaptive Learning for Exemplar-Free Video Class-Incremental Learning.","year":2025,"types":["Article"],"venue":"IEEE Trans. Circuits Syst. Video Technol.","doi":"https://doi.org/10.1109/TCSVT.2025.3579477","numberOfCreators":7,"category":"journal","sources":["https://dblp.org/rec/journals/tcsv/ChenLLSGHL25","https://doi.org/10.1109/TCSVT.2025.3579477"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/tcsv/ChenLLSGHL25","documentUrl":null,"type":"Article"},{"key":"journals/tcsv/HuoHWY25","url":"https://dblp.org/rec/journals/tcsv/HuoHWY25","title":"Rendering-Oriented 3D Point Cloud Attribute Compression Using Sparse Tensor-Based Transformer.","year":2025,"types":["Article"],"venue":"IEEE Trans. Circuits Syst. Video Technol.","doi":"https://doi.org/10.1109/TCSVT.2025.3546626","numberOfCreators":4,"category":"journal","sources":["https://dblp.org/rec/journals/tcsv/HuoHWY25","https://doi.org/10.1109/TCSVT.2025.3546626"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/tcsv/HuoHWY25","documentUrl":null,"type":"Article"},{"key":"journals/tcsv/JingWZYBZZH25","url":"https://dblp.org/rec/journals/tcsv/JingWZYBZZH25","title":"Boosting 3D Object Detection With Semantic-Aware Multi-Branch Framework.","year":2025,"types":["Article"],"venue":"IEEE Trans. Circuits Syst. Video Technol.","doi":"https://doi.org/10.1109/TCSVT.2025.3527997","numberOfCreators":8,"category":"journal","sources":["https://dblp.org/rec/journals/tcsv/JingWZYBZZH25","https://doi.org/10.1109/TCSVT.2025.3527997"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/tcsv/JingWZYBZZH25","documentUrl":null,"type":"Article"},{"key":"journals/tcsv/LiuZCDSH25","url":"https://dblp.org/rec/journals/tcsv/LiuZCDSH25","title":"A No-Reference Quality Assessment Model for Screen Content Videos via Hierarchical Spatiotemporal Perception.","year":2025,"types":["Article"],"venue":"IEEE Trans. Circuits Syst. Video Technol.","doi":"https://doi.org/10.1109/TCSVT.2024.3469180","numberOfCreators":6,"category":"journal","sources":["https://dblp.org/rec/journals/tcsv/LiuZCDSH25","https://doi.org/10.1109/TCSVT.2024.3469180"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/tcsv/LiuZCDSH25","documentUrl":null,"type":"Article"},{"key":"journals/tifs/ZhangHWSHF25","url":"https://dblp.org/rec/journals/tifs/ZhangHWSHF25","title":"Synthetic-to-Real Video Person Re-ID.","year":2025,"types":["Article"],"venue":"IEEE Trans. Inf. Forensics Secur.","doi":"https://doi.org/10.1109/TIFS.2025.3574972","numberOfCreators":6,"category":"journal","sources":["https://dblp.org/rec/journals/tifs/ZhangHWSHF25","https://doi.org/10.1109/TIFS.2025.3574972"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/tifs/ZhangHWSHF25","documentUrl":null,"type":"Article"},{"key":"journals/tip/ChenWHZL25","url":"https://dblp.org/rec/journals/tip/ChenWHZL25","title":"HOPE: Enhanced Position Image Priors via High-Order Implicit Representations.","year":2025,"types":["Article"],"venue":"IEEE Trans. Image Process.","doi":"https://doi.org/10.1109/TIP.2025.3607582","numberOfCreators":5,"category":"journal","sources":["https://dblp.org/rec/journals/tip/ChenWHZL25","https://doi.org/10.1109/TIP.2025.3607582"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/tip/ChenWHZL25","documentUrl":null,"type":"Article"},{"key":"journals/tip/ChengWWHWX25","url":"https://dblp.org/rec/journals/tip/ChengWWHWX25","title":"PVNet: Point-Voxel Interaction LiDAR Scene Upsampling via Diffusion Models.","year":2025,"types":["Article"],"venue":"IEEE Trans. Image Process.","doi":"https://doi.org/10.1109/TIP.2025.3620666","numberOfCreators":6,"category":"journal","sources":["https://dblp.org/rec/journals/tip/ChengWWHWX25","https://doi.org/10.1109/TIP.2025.3620666"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/tip/ChengWWHWX25","documentUrl":null,"type":"Article"},{"key":"journals/tip/HanJLH25","url":"https://dblp.org/rec/journals/tip/HanJLH25","title":"Irregular Tensor Low-Rank Representation for Hyperspectral Image Representation.","year":2025,"types":["Article"],"venue":"IEEE Trans. Image Process.","doi":"https://doi.org/10.1109/TIP.2025.3571669","numberOfCreators":4,"category":"journal","sources":["https://dblp.org/rec/journals/tip/HanJLH25","https://doi.org/10.1109/TIP.2025.3571669"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/tip/HanJLH25","documentUrl":null,"type":"Article"},{"key":"journals/tip/QiJLH25","url":"https://dblp.org/rec/journals/tip/QiJLH25","title":"Structural-Spectral Graph Convolution With Evidential Edge Learning for Hyperspectral Image Clustering.","year":2025,"types":["Article"],"venue":"IEEE Trans. Image Process.","doi":"https://doi.org/10.1109/TIP.2025.3636098","numberOfCreators":4,"category":"journal","sources":["https://dblp.org/rec/journals/tip/QiJLH25","https://doi.org/10.1109/TIP.2025.3636098"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/tip/QiJLH25","documentUrl":null,"type":"Article"},{"key":"journals/tmc/ZhuHLWH25","url":"https://dblp.org/rec/journals/tmc/ZhuHLWH25","title":"Modeling State Shifting via Local-Global Distillation for Event-Frame Gaze Tracking.","year":2025,"types":["Article"],"venue":"IEEE Trans. Mob. Comput.","doi":"https://doi.org/10.1109/TMC.2025.3581317","numberOfCreators":5,"category":"journal","sources":["https://dblp.org/rec/journals/tmc/ZhuHLWH25","https://doi.org/10.1109/TMC.2025.3581317"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/tmc/ZhuHLWH25","documentUrl":null,"type":"Article"},{"key":"journals/tmm/ChenWRYYH25","url":"https://dblp.org/rec/journals/tmm/ChenWRYYH25","title":"RBFIM: Perceptual Quality Assessment for Compressed Point Clouds Using Radial Basis Function Interpolation.","year":2025,"types":["Article"],"venue":"IEEE Trans. Multim.","doi":"https://doi.org/10.1109/TMM.2025.3607782","numberOfCreators":6,"category":"journal","sources":["https://dblp.org/rec/journals/tmm/ChenWRYYH25","https://doi.org/10.1109/TMM.2025.3607782"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/tmm/ChenWRYYH25","documentUrl":null,"type":"Article"},{"key":"journals/tmm/WuZHX25","url":"https://dblp.org/rec/journals/tmm/WuZHX25","title":"Leveraging Single-View Images for Unsupervised 3D Point Cloud Completion.","year":2025,"types":["Article"],"venue":"IEEE Trans. Multim.","doi":"https://doi.org/10.1109/TMM.2023.3340892","numberOfCreators":4,"category":"journal","sources":["https://dblp.org/rec/journals/tmm/WuZHX25","https://doi.org/10.1109/TMM.2023.3340892"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/tmm/WuZHX25","documentUrl":null,"type":"Article"},{"key":"journals/tmm/ZhangHQ25","url":"https://dblp.org/rec/journals/tmm/ZhangHQ25","title":"PointMCD: Boosting Deep Point Cloud Encoders via Multi-View Cross-Modal Distillation for 3D Shape Recognition.","year":2025,"types":["Article"],"venue":"IEEE Trans. Multim.","doi":"https://doi.org/10.1109/TMM.2023.3286981","numberOfCreators":3,"category":"journal","sources":["https://dblp.org/rec/journals/tmm/ZhangHQ25","https://doi.org/10.1109/TMM.2023.3286981"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/tmm/ZhangHQ25","documentUrl":null,"type":"Article"},{"key":"journals/tvcg/GuoCYMHH25","url":"https://dblp.org/rec/journals/tvcg/GuoCYMHH25","title":"CS-Net: Contribution-Based Sampling Network for Point Cloud Simplification.","year":2025,"types":["Article"],"venue":"IEEE Trans. Vis. Comput. Graph.","doi":"https://doi.org/10.1109/TVCG.2025.3591189","numberOfCreators":6,"category":"journal","sources":["https://dblp.org/rec/journals/tvcg/GuoCYMHH25","https://doi.org/10.1109/TVCG.2025.3591189"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/tvcg/GuoCYMHH25","documentUrl":null,"type":"Article"},{"key":"journals/tvcg/LinYLZHJKKW25","url":"https://dblp.org/rec/journals/tvcg/LinYLZHJKKW25","title":"On Optimal Sampling for Learning SDF Using MLPs Equipped With Positional Encoding.","year":2025,"types":["Article"],"venue":"IEEE Trans. Vis. Comput. Graph.","doi":"https://doi.org/10.1109/TVCG.2024.3522082","numberOfCreators":9,"category":"journal","sources":["https://dblp.org/rec/journals/tvcg/LinYLZHJKKW25","https://doi.org/10.1109/TVCG.2024.3522082"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/tvcg/LinYLZHJKKW25","documentUrl":null,"type":"Article"},{"key":"journals/tvcg/WuCXZH25","url":"https://dblp.org/rec/journals/tvcg/WuCXZH25","title":"Unsupervised 3D Point Cloud Completion via Multi-View Adversarial Learning.","year":2025,"types":["Article"],"venue":"IEEE Trans. Vis. Comput. Graph.","doi":"https://doi.org/10.1109/TVCG.2025.3559340","numberOfCreators":5,"category":"journal","sources":["https://dblp.org/rec/journals/tvcg/WuCXZH25","https://doi.org/10.1109/TVCG.2025.3559340"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/tvcg/WuCXZH25","documentUrl":null,"type":"Article"},{"key":"journals/tvcg/WuHSX25","url":"https://dblp.org/rec/journals/tvcg/WuHSX25","title":"3D Shape Completion on Unseen Categories: A Weakly-Supervised Approach.","year":2025,"types":["Article"],"venue":"IEEE Trans. Vis. Comput. Graph.","doi":"https://doi.org/10.1109/TVCG.2024.3459018","numberOfCreators":4,"category":"journal","sources":["https://dblp.org/rec/journals/tvcg/WuHSX25","https://doi.org/10.1109/TVCG.2024.3459018"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/tvcg/WuHSX25","documentUrl":null,"type":"Article"},{"key":"journals/tvcg/YouH25","url":"https://dblp.org/rec/journals/tvcg/YouH25","title":"Decoupling Dynamic Monocular Videos for Dynamic View Synthesis.","year":2025,"types":["Article"],"venue":"IEEE Trans. Vis. Comput. Graph.","doi":"https://doi.org/10.1109/TVCG.2024.3434361","numberOfCreators":2,"category":"journal","sources":["https://dblp.org/rec/journals/tvcg/YouH25","https://doi.org/10.1109/TVCG.2024.3434361"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/tvcg/YouH25","documentUrl":null,"type":"Article"}],"preprints":[{"key":"journals/corr/abs-2501-00838","url":"https://dblp.org/rec/journals/corr/abs-2501-00838","title":"Spatially-guided Temporal Aggregation for Robust Event-RGB Optical Flow Estimation.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2501.00838","numberOfCreators":6,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2501-00838","https://doi.org/10.48550/ARXIV.2501.00838"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2501-00838","documentUrl":null,"type":"Informal","arxivId":"2501.00838","arxivUrl":"https://arxiv.org/abs/2501.00838"},{"key":"journals/corr/abs-2501-07236","url":"https://dblp.org/rec/journals/corr/abs-2501-07236","title":"CSTA: Spatial-Temporal Causal Adaptive Learning for Exemplar-Free Video Class-Incremental Learning.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2501.07236","numberOfCreators":7,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2501-07236","https://doi.org/10.48550/ARXIV.2501.07236"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2501-07236","documentUrl":null,"type":"Informal","arxivId":"2501.07236","arxivUrl":"https://arxiv.org/abs/2501.07236"},{"key":"journals/corr/abs-2501-10789","url":"https://dblp.org/rec/journals/corr/abs-2501-10789","title":"CS-Net:Contribution-based Sampling Network for Point Cloud Simplification.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2501.10789","numberOfCreators":6,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2501-10789","https://doi.org/10.48550/ARXIV.2501.10789"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2501-10789","documentUrl":null,"type":"Informal","arxivId":"2501.10789","arxivUrl":"https://arxiv.org/abs/2501.10789"},{"key":"journals/corr/abs-2501-15008","url":"https://dblp.org/rec/journals/corr/abs-2501-15008","title":"HuGDiffusion: Generalizable Single-Image Human Rendering via 3D Gaussian Diffusion.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2501.15008","numberOfCreators":3,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2501-15008","https://doi.org/10.48550/ARXIV.2501.15008"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2501-15008","documentUrl":null,"type":"Informal","arxivId":"2501.15008","arxivUrl":"https://arxiv.org/abs/2501.15008"},{"key":"journals/corr/abs-2503-09439","url":"https://dblp.org/rec/journals/corr/abs-2503-09439","title":"SuperCarver: Texture-Consistent 3D Geometry Super-Resolution for High-Fidelity Surface Detail Generation.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2503.09439","numberOfCreators":5,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2503-09439","https://doi.org/10.48550/ARXIV.2503.09439"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-09439","documentUrl":null,"type":"Informal","arxivId":"2503.09439","arxivUrl":"https://arxiv.org/abs/2503.09439"},{"key":"journals/corr/abs-2503-14154","url":"https://dblp.org/rec/journals/corr/abs-2503-14154","title":"RBFIM: Perceptual Quality Assessment for Compressed Point Clouds Using Radial Basis Function Interpolation.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2503.14154","numberOfCreators":6,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2503-14154","https://doi.org/10.48550/ARXIV.2503.14154"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-14154","documentUrl":null,"type":"Informal","arxivId":"2503.14154","arxivUrl":"https://arxiv.org/abs/2503.14154"},{"key":"journals/corr/abs-2503-15975","url":"https://dblp.org/rec/journals/corr/abs-2503-15975","title":"Acc3D: Accelerating Single Image to 3D Diffusion Models via Edge Consistency Guided Score Distillation.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2503.15975","numberOfCreators":4,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2503-15975","https://doi.org/10.48550/ARXIV.2503.15975"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-15975","documentUrl":null,"type":"Informal","arxivId":"2503.15975","arxivUrl":"https://arxiv.org/abs/2503.15975"},{"key":"journals/corr/abs-2503-16822","url":"https://dblp.org/rec/journals/corr/abs-2503-16822","title":"RigGS: Rigging of 3D Gaussians for Modeling Articulated Objects in Videos.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2503.16822","numberOfCreators":3,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2503-16822","https://doi.org/10.48550/ARXIV.2503.16822"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-16822","documentUrl":null,"type":"Informal","arxivId":"2503.16822","arxivUrl":"https://arxiv.org/abs/2503.16822"},{"key":"journals/corr/abs-2504-19210","url":"https://dblp.org/rec/journals/corr/abs-2504-19210","title":"FlexPara: Flexible Neural Surface Parameterization.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2504.19210","numberOfCreators":6,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2504-19210","https://doi.org/10.48550/ARXIV.2504.19210"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2504-19210","documentUrl":null,"type":"Informal","arxivId":"2504.19210","arxivUrl":"https://arxiv.org/abs/2504.19210"},{"key":"journals/corr/abs-2505-17442","url":"https://dblp.org/rec/journals/corr/abs-2505-17442","title":"Reflectance Prediction-based Knowledge Distillation for Robust 3D Object Detection in Compressed Point Clouds.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2505.17442","numberOfCreators":5,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2505-17442","https://doi.org/10.48550/ARXIV.2505.17442"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-17442","documentUrl":null,"type":"Informal","arxivId":"2505.17442","arxivUrl":"https://arxiv.org/abs/2505.17442"},{"key":"journals/corr/abs-2506-02053","url":"https://dblp.org/rec/journals/corr/abs-2506-02053","title":"Generalization Performance of Ensemble Clustering: From Theory to Algorithm.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2506.02053","numberOfCreators":6,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2506-02053","https://doi.org/10.48550/ARXIV.2506.02053"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-02053","documentUrl":null,"type":"Informal","arxivId":"2506.02053","arxivUrl":"https://arxiv.org/abs/2506.02053"},{"key":"journals/corr/abs-2506-09920","url":"https://dblp.org/rec/journals/corr/abs-2506-09920","title":"Structural-Spectral Graph Convolution with Evidential Edge Learning for Hyperspectral Image Clustering.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2506.09920","numberOfCreators":4,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2506-09920","https://doi.org/10.48550/ARXIV.2506.09920"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-09920","documentUrl":null,"type":"Informal","arxivId":"2506.09920","arxivUrl":"https://arxiv.org/abs/2506.09920"},{"key":"journals/corr/abs-2506-15228","url":"https://dblp.org/rec/journals/corr/abs-2506-15228","title":"ABC: Adaptive BayesNet Structure Learning for Computational Scalable Multi-task Image Compression.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2506.15228","numberOfCreators":7,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2506-15228","https://doi.org/10.48550/ARXIV.2506.15228"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-15228","documentUrl":null,"type":"Informal","arxivId":"2506.15228","arxivUrl":"https://arxiv.org/abs/2506.15228"},{"key":"journals/corr/abs-2508-17050","url":"https://dblp.org/rec/journals/corr/abs-2508-17050","title":"PVNet: Point-Voxel Interaction LiDAR Scene Upsampling Via Diffusion Models.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2508.17050","numberOfCreators":6,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2508-17050","https://doi.org/10.48550/ARXIV.2508.17050"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-17050","documentUrl":null,"type":"Informal","arxivId":"2508.17050","arxivUrl":"https://arxiv.org/abs/2508.17050"},{"key":"journals/corr/abs-2508-17488","url":"https://dblp.org/rec/journals/corr/abs-2508-17488","title":"Optimizing Multi-Modal Trackers via Sensitivity-aware Regularized Tuning.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2508.17488","numberOfCreators":6,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2508-17488","https://doi.org/10.48550/ARXIV.2508.17488"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-17488","documentUrl":null,"type":"Informal","arxivId":"2508.17488","arxivUrl":"https://arxiv.org/abs/2508.17488"},{"key":"journals/corr/abs-2509-00066","url":"https://dblp.org/rec/journals/corr/abs-2509-00066","title":"T-MLP: Tailed Multi-Layer Perceptron for Level-of-Detail Signal Representation.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2509.00066","numberOfCreators":7,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2509-00066","https://doi.org/10.48550/ARXIV.2509.00066"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-00066","documentUrl":null,"type":"Informal","arxivId":"2509.00066","arxivUrl":"https://arxiv.org/abs/2509.00066"},{"key":"journals/corr/abs-2509-04824","url":"https://dblp.org/rec/journals/corr/abs-2509-04824","title":"Exploring Non-Local Spatial-Angular Correlations with a Hybrid Mamba-Transformer Framework for Light Field Super-Resolution.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2509.04824","numberOfCreators":6,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2509-04824","https://doi.org/10.48550/ARXIV.2509.04824"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-04824","documentUrl":null,"type":"Informal","arxivId":"2509.04824","arxivUrl":"https://arxiv.org/abs/2509.04824"},{"key":"journals/corr/abs-2509-18826","url":"https://dblp.org/rec/journals/corr/abs-2509-18826","title":"Graph-based Clustering Revisited: A Relaxation of Kernel k-Means Perspective.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2509.18826","numberOfCreators":4,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2509-18826","https://doi.org/10.48550/ARXIV.2509.18826"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-18826","documentUrl":null,"type":"Informal","arxivId":"2509.18826","arxivUrl":"https://arxiv.org/abs/2509.18826"},{"key":"journals/corr/abs-2509-19165","url":"https://dblp.org/rec/journals/corr/abs-2509-19165","title":"RoSe: Robust Self-supervised Stereo Matching under Adverse Weather Conditions.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2509.19165","numberOfCreators":6,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2509-19165","https://doi.org/10.48550/ARXIV.2509.19165"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-19165","documentUrl":null,"type":"Informal","arxivId":"2509.19165","arxivUrl":"https://arxiv.org/abs/2509.19165"},{"key":"journals/corr/abs-2509-23194","url":"https://dblp.org/rec/journals/corr/abs-2509-23194","title":"Unsupervised Online 3D Instance Segmentation with Synthetic Sequences and Dynamic Loss.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2509.23194","numberOfCreators":5,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2509-23194","https://doi.org/10.48550/ARXIV.2509.23194"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-23194","documentUrl":null,"type":"Informal","arxivId":"2509.23194","arxivUrl":"https://arxiv.org/abs/2509.23194"},{"key":"journals/corr/abs-2510-03993","url":"https://dblp.org/rec/journals/corr/abs-2510-03993","title":"Keep It on a Leash: Controllable Pseudo-label Generation Towards Realistic Long-Tailed Semi-Supervised Learning.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2510.03993","numberOfCreators":5,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2510-03993","https://doi.org/10.48550/ARXIV.2510.03993"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-03993","documentUrl":null,"type":"Informal","arxivId":"2510.03993","arxivUrl":"https://arxiv.org/abs/2510.03993"},{"key":"journals/corr/abs-2510-12524","url":"https://dblp.org/rec/journals/corr/abs-2510-12524","title":"Voronoi-Assisted Diffusion for Computing Unsigned Distance Fields from Unoriented Points.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2510.12524","numberOfCreators":9,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2510-12524","https://doi.org/10.48550/ARXIV.2510.12524"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-12524","documentUrl":null,"type":"Informal","arxivId":"2510.12524","arxivUrl":"https://arxiv.org/abs/2510.12524"},{"key":"journals/corr/abs-2511-12494","url":"https://dblp.org/rec/journals/corr/abs-2511-12494","title":"Towards Better IncomLDL: We Are Unaware of Hidden Labels in Advance.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2511.12494","numberOfCreators":6,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2511-12494","https://doi.org/10.48550/ARXIV.2511.12494"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2511-12494","documentUrl":null,"type":"Informal","arxivId":"2511.12494","arxivUrl":"https://arxiv.org/abs/2511.12494"},{"key":"journals/corr/abs-2511-20225","url":"https://dblp.org/rec/journals/corr/abs-2511-20225","title":"DiCaP: Distribution-Calibrated Pseudo-labeling for Semi-Supervised Multi-Label Learning.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2511.20225","numberOfCreators":7,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2511-20225","https://doi.org/10.48550/ARXIV.2511.20225"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2511-20225","documentUrl":null,"type":"Informal","arxivId":"2511.20225","arxivUrl":"https://arxiv.org/abs/2511.20225"},{"key":"journals/corr/abs-2511-21193","url":"https://dblp.org/rec/journals/corr/abs-2511-21193","title":"You Can Trust Your Clustering Model: A Parameter-free Self-Boosting Plug-in for Deep Clustering.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2511.21193","numberOfCreators":4,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2511-21193","https://doi.org/10.48550/ARXIV.2511.21193"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2511-21193","documentUrl":null,"type":"Informal","arxivId":"2511.21193","arxivUrl":"https://arxiv.org/abs/2511.21193"},{"key":"journals/corr/abs-2512-00725","url":"https://dblp.org/rec/journals/corr/abs-2512-00725","title":"ESMC: MLLM-Based Embedding Selection for Explainable Multiple Clustering.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2512.00725","numberOfCreators":4,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2512-00725","https://doi.org/10.48550/ARXIV.2512.00725"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-00725","documentUrl":null,"type":"Informal","arxivId":"2512.00725","arxivUrl":"https://arxiv.org/abs/2512.00725"}],"excludedFormal":[{"key":"journals/jcst/HuDH25","url":"https://dblp.org/rec/journals/jcst/HuDH25","title":"Preface.","year":2025,"types":["Article"],"venue":"J. Comput. Sci. Technol.","doi":"https://doi.org/10.1007/S11390-025-0006-5","numberOfCreators":3,"category":"journal","sources":["https://dblp.org/rec/journals/jcst/HuDH25","https://doi.org/10.1007/S11390-025-0006-5"],"publicationYear":2025,"eventYear":null,"exclusionReason":"标题为 Preface；不计研究论文。","exclusionReasonCode":"non_research_front_matter","exclusionSources":["https://dblp.org/rec/journals/jcst/HuDH25"],"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/jcst/HuDH25","documentUrl":null,"type":"Article"}],"otherRecords":[],"matchedName":"Junhui Hou","databaseLabel":"Junhui Hou","databaseMetadata":{"type":["https://dblp.org/rdf/schema#Creator","https://dblp.org/rdf/schema#Person"],"label":["Junhui Hou"],"affiliation":["City University of Hong Kong, Department of Computer Science, Hong Kong"],"homepage":["http://www6.cityu.edu.hk/stfprofile/csjhhou.htm","https://openreview.net/profile?id=~Junhui_Hou2"],"orcid":["https://orcid.org/0000-0003-3431-2021"],"primaryAffiliation":["City University of Hong Kong, Department of Computer Science, Hong Kong"],"primaryHomepage":["http://www6.cityu.edu.hk/stfprofile/csjhhou.htm"]},"rawFormalRecordCount2025":50,"signatureAudit":{"completedAt":"2026-10-19","frozen":true,"scope":"对 B 组 39 个数值档案的全部 1074 条原始 2025 正式记录扫描 DBLP author-signature ORCID 和机构；复用既有 59 条 Crossref 核验，补查 6 条新触发记录。重点核查不同 ORCID，以及只有预期机构之外机构的条目。本轮不扩展为所有作者逐篇全文审计。","formalRecordCoverage":50,"orcidCounts":{"https://orcid.org/0000-0003-3431-2021":36},"institutionCounts":{"City University of Hong Kong":38,"Clark University":1},"caveat":"机构名称可能由 DBLP 自动映射而失真；多 ORCID 也不自动等于异人。只有有原始资料支撑的错归才作确认排除，未解决分支则暂停总数。"},"labName":null,"labUrl":null,"labEvidence":"本轮补查本人主页及 People 页面，未找到公开明确命名的当前实验室。","labSourceUrl":"https://sites.google.com/site/junhuihoushomepage/","sourceWarning":false,"excludedOther":[],"excludedHomonyms":[],"unassignedCandidates":[],"knownPreprintMinimum2025":null,"excludedMisattributed":[],"displayNotes":"身份已确认。另排除 1 条形式上属于期刊或会议的记录，逐条原因见排除记录。计入 49 条（会议 21、期刊 28），所有作者位置均计入；预印本 26 条单列，不加总。","labDisplayNotes":"本人主页与 People 页都未见具名的实验室；图中以「姓名及合作者」单列。"},{"index":44,"name":"Di Hu","nameZh":"胡迪","role":"Tenure-Track Associate Professor","affiliation":"Renmin University of China","affiliationZh":"中国人民大学","source":"DBLP RDF via official SPARQL; primary-source identity checks","sourceUrl":"https://sparql.dblp.org/","profileUrl":"https://dblp.org/pid/49/8496-1.html","identifier":"49/8496-1","retrievedAt":"2026-10-19","count2025":17,"conference2025":16,"journal2025":1,"preprint2025":14,"status":"confirmed","notes":"DBLP 的 primaryAffiliation 含历史机构；以原签名名单机构和本人履历交叉核对，未据旧机构另选同名者。","identityEvidence":[{"url":"https://dblp.org/pid/49/8496-1.html","evidence":"DBLP RDF 类型为 Person，消歧后名字为 Di Hu 0001。机构元数据含：Renmin University of China, Gaoling School of Artificial Intelligence, Beijing, China；Northwestern Polytechnical University, School of Computer Science and Engineering, OPTIMAL, Xi'an, China；Baidu Research, Big Data Laboratory, Beijing, China"}],"papers":[{"key":"conf/acl/Chen0W00JMZDMLS25","url":"https://dblp.org/rec/conf/acl/Chen0W00JMZDMLS25","title":"Towards Effective and Efficient Continual Pre-training of Large Language Models.","year":2025,"types":["Inproceedings"],"venue":"ACL (1)","doi":"https://doi.org/10.18653/V1/2025.ACL-LONG.289","eventYear":2025,"numberOfCreators":19,"category":"conference","sources":["https://dblp.org/rec/conf/acl/Chen0W00JMZDMLS25","https://doi.org/10.18653/V1/2025.ACL-LONG.289"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/acl/Chen0W00JMZDMLS25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/cvpr/DuLZZZ025","url":"https://dblp.org/rec/conf/cvpr/DuLZZZ025","title":"Crab: A Unified Audio-Visual Scene Understanding Model with Explicit Cooperation.","year":2025,"types":["Inproceedings"],"venue":"CVPR","doi":"https://doi.org/10.1109/CVPR52734.2025.01752","eventYear":2025,"numberOfCreators":6,"category":"conference","sources":["https://dblp.org/rec/conf/cvpr/DuLZZZ025","https://doi.org/10.1109/CVPR52734.2025.01752"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/DuLZZZ025","documentUrl":null,"type":"Inproceedings"},{"key":"conf/cvpr/HuangWY025","url":"https://dblp.org/rec/conf/cvpr/HuangWY025","title":"Adaptive Unimodal Regulation for Balanced Multimodal Information Acquisition.","year":2025,"types":["Inproceedings"],"venue":"CVPR","doi":"https://doi.org/10.1109/CVPR52734.2025.02408","eventYear":2025,"numberOfCreators":4,"category":"conference","sources":["https://dblp.org/rec/conf/cvpr/HuangWY025","https://doi.org/10.1109/CVPR52734.2025.02408"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/HuangWY025","documentUrl":null,"type":"Inproceedings"},{"key":"conf/cvpr/PengHWWH25","url":"https://dblp.org/rec/conf/cvpr/PengHWWH25","title":"Patch Matters: Training-free Fine-grained Image Caption Enhancement via Local Perception.","year":2025,"types":["Inproceedings"],"venue":"CVPR","doi":"https://doi.org/10.1109/CVPR52734.2025.00375","eventYear":2025,"numberOfCreators":5,"category":"conference","sources":["https://dblp.org/rec/conf/cvpr/PengHWWH25","https://doi.org/10.1109/CVPR52734.2025.00375"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/PengHWWH25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/cvpr/XiaF0025","url":"https://dblp.org/rec/conf/cvpr/XiaF0025","title":"Phoenix: A Motion-based Self-Reflection Framework for Fine-grained Robotic Action Correction.","year":2025,"types":["Inproceedings"],"venue":"CVPR","doi":"https://doi.org/10.1109/CVPR52734.2025.00655","eventYear":2025,"numberOfCreators":4,"category":"conference","sources":["https://dblp.org/rec/conf/cvpr/XiaF0025","https://doi.org/10.1109/CVPR52734.2025.00655"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/XiaF0025","documentUrl":null,"type":"Inproceedings"},{"key":"conf/eccv/MaSWH24","url":"https://dblp.org/rec/conf/eccv/MaSWH24","title":"Stepping Stones: A Progressive Training Strategy for Audio-Visual Semantic Segmentation.","year":2025,"types":["Inproceedings"],"venue":"ECCV (73)","doi":"https://doi.org/10.1007/978-3-031-73464-9_19","eventYear":2024,"numberOfCreators":4,"category":"conference","sources":["https://dblp.org/rec/conf/eccv/MaSWH24","https://doi.org/10.1007/978-3-031-73464-9_19"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2024,"sourceUrl":"https://dblp.org/rec/conf/eccv/MaSWH24","documentUrl":null,"type":"Inproceedings"},{"key":"conf/eccv/WangSLZH24","url":"https://dblp.org/rec/conf/eccv/WangSLZH24","title":"Can Textual Semantics Mitigate Sounding Object Segmentation Preference?","year":2025,"types":["Inproceedings"],"venue":"ECCV (74)","doi":"https://doi.org/10.1007/978-3-031-72904-1_20","eventYear":2024,"numberOfCreators":5,"category":"conference","sources":["https://dblp.org/rec/conf/eccv/WangSLZH24","https://doi.org/10.1007/978-3-031-72904-1_20"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2024,"sourceUrl":"https://dblp.org/rec/conf/eccv/WangSLZH24","documentUrl":null,"type":"Inproceedings"},{"key":"conf/eccv/WangSZLZH24","url":"https://dblp.org/rec/conf/eccv/WangSZLZH24","title":"Ref-AVS: Refer and Segment Objects in Audio-Visual Scenes.","year":2025,"types":["Inproceedings"],"venue":"ECCV (74)","doi":"https://doi.org/10.1007/978-3-031-72904-1_12","eventYear":2024,"numberOfCreators":6,"category":"conference","sources":["https://dblp.org/rec/conf/eccv/WangSZLZH24","https://doi.org/10.1007/978-3-031-72904-1_12"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2024,"sourceUrl":"https://dblp.org/rec/conf/eccv/WangSZLZH24","documentUrl":null,"type":"Inproceedings"},{"key":"conf/eccv/WeiLFH24","url":"https://dblp.org/rec/conf/eccv/WeiLFH24","title":"Diagnosing and Re-learning for Balanced Multimodal Learning.","year":2025,"types":["Inproceedings"],"venue":"ECCV (64)","doi":"https://doi.org/10.1007/978-3-031-73039-9_5","eventYear":2024,"numberOfCreators":4,"category":"conference","sources":["https://dblp.org/rec/conf/eccv/WeiLFH24","https://doi.org/10.1007/978-3-031-73039-9_5"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2024,"sourceUrl":"https://dblp.org/rec/conf/eccv/WeiLFH24","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iclr/FengHXGSSF025","url":"https://dblp.org/rec/conf/iclr/FengHXGSSF025","title":"AnyTouch: Learning Unified Static-Dynamic Representation across Multiple Visuo-tactile Sensors.","year":2025,"types":["Inproceedings"],"venue":"ICLR","doi":null,"eventYear":2025,"numberOfCreators":8,"category":"conference","sources":["https://dblp.org/rec/conf/iclr/FengHXGSSF025"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iclr/FengHXGSSF025","documentUrl":null,"type":"Inproceedings"},{"key":"conf/icml/NiWLCPL025","url":"https://dblp.org/rec/conf/icml/NiWLCPL025","title":"RollingQ: Reviving the Cooperation Dynamics in Multimodal Transformer.","year":2025,"types":["Inproceedings"],"venue":"ICML","doi":null,"eventYear":2025,"numberOfCreators":7,"category":"conference","sources":["https://dblp.org/rec/conf/icml/NiWLCPL025"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/icml/NiWLCPL025","documentUrl":null,"type":"Inproceedings"},{"key":"conf/icml/YangW025","url":"https://dblp.org/rec/conf/icml/YangW025","title":"Efficient Quantification of Multimodal Interaction at Sample Level.","year":2025,"types":["Inproceedings"],"venue":"ICML","doi":null,"eventYear":2025,"numberOfCreators":3,"category":"conference","sources":["https://dblp.org/rec/conf/icml/YangW025"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/icml/YangW025","documentUrl":null,"type":"Inproceedings"},{"key":"conf/mir/HouY025","url":"https://dblp.org/rec/conf/mir/HouY025","title":"Learning to Predict Advertisement Expansion Moments in Short-Form Video Platforms.","year":2025,"types":["Inproceedings"],"venue":"ICMR","doi":"https://doi.org/10.1145/3731715.3733372","eventYear":2025,"numberOfCreators":3,"category":"conference","sources":["https://dblp.org/rec/conf/mir/HouY025","https://doi.org/10.1145/3731715.3733372"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/mir/HouY025","documentUrl":null,"type":"Inproceedings"},{"key":"conf/nips/WeiMZH25","url":"https://dblp.org/rec/conf/nips/WeiMZH25","title":"MokA: Multimodal Low-Rank Adaptation for MLLMs.","year":2025,"types":["Inproceedings"],"venue":"NeurIPS","doi":null,"eventYear":2025,"numberOfCreators":4,"category":"conference","sources":["https://dblp.org/rec/conf/nips/WeiMZH25"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/nips/WeiMZH25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/nips/XiaYWMKH25","url":"https://dblp.org/rec/conf/nips/XiaYWMKH25","title":"Human-assisted Robotic Policy Refinement via Action Preference Optimization.","year":2025,"types":["Inproceedings"],"venue":"NeurIPS","doi":null,"eventYear":2025,"numberOfCreators":6,"category":"conference","sources":["https://dblp.org/rec/conf/nips/XiaYWMKH25"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/nips/XiaYWMKH25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/sigir/Feng0PMZ0Z25","url":"https://dblp.org/rec/conf/sigir/Feng0PMZ0Z25","title":"MGIPF: Multi-Granularity Interest Prediction Framework for Personalized Recommendation.","year":2025,"types":["Inproceedings"],"venue":"SIGIR","doi":"https://doi.org/10.1145/3726302.3730033","eventYear":2025,"numberOfCreators":7,"category":"conference","sources":["https://dblp.org/rec/conf/sigir/Feng0PMZ0Z25","https://doi.org/10.1145/3726302.3730033"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/sigir/Feng0PMZ0Z25","documentUrl":null,"type":"Inproceedings"},{"key":"journals/pami/WeiHDW25","url":"https://dblp.org/rec/journals/pami/WeiHDW25","title":"On-the-Fly Modulation for Balanced Multimodal Learning.","year":2025,"types":["Article"],"venue":"IEEE Trans. Pattern Anal. Mach. Intell.","doi":"https://doi.org/10.1109/TPAMI.2024.3468315","numberOfCreators":4,"category":"journal","sources":["https://dblp.org/rec/journals/pami/WeiHDW25","https://doi.org/10.1109/TPAMI.2024.3468315"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/pami/WeiHDW25","documentUrl":null,"type":"Article"}],"preprints":[{"key":"journals/corr/abs-2502-10816","url":"https://dblp.org/rec/journals/corr/abs-2502-10816","title":"BalanceBenchmark: A Survey for Multimodal Imbalance Learning.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2502.10816","numberOfCreators":5,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2502-10816","https://doi.org/10.48550/ARXIV.2502.10816"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2502-10816","documentUrl":null,"type":"Informal","arxivId":"2502.10816","arxivUrl":"https://arxiv.org/abs/2502.10816"},{"key":"journals/corr/abs-2502-12191","url":"https://dblp.org/rec/journals/corr/abs-2502-12191","title":"AnyTouch: Learning Unified Static-Dynamic Representation across Multiple Visuo-tactile Sensors.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2502.12191","numberOfCreators":8,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2502-12191","https://doi.org/10.48550/ARXIV.2502.12191"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2502-12191","documentUrl":null,"type":"Informal","arxivId":"2502.12191","arxivUrl":"https://arxiv.org/abs/2502.12191"},{"key":"journals/corr/abs-2503-13068","url":"https://dblp.org/rec/journals/corr/abs-2503-13068","title":"Crab: A Unified Audio-Visual Scene Understanding Model with Explicit Cooperation.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2503.13068","numberOfCreators":6,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2503-13068","https://doi.org/10.48550/ARXIV.2503.13068"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-13068","documentUrl":null,"type":"Informal","arxivId":"2503.13068","arxivUrl":"https://arxiv.org/abs/2503.13068"},{"key":"journals/corr/abs-2503-18595","url":"https://dblp.org/rec/journals/corr/abs-2503-18595","title":"Adaptive Unimodal Regulation for Balanced Multimodal Information Acquisition.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2503.18595","numberOfCreators":4,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2503-18595","https://doi.org/10.48550/ARXIV.2503.18595"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-18595","documentUrl":null,"type":"Informal","arxivId":"2503.18595","arxivUrl":"https://arxiv.org/abs/2503.18595"},{"key":"journals/corr/abs-2504-06666","url":"https://dblp.org/rec/journals/corr/abs-2504-06666","title":"Patch Matters: Training-free Fine-grained Image Caption Enhancement via Local Perception.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2504.06666","numberOfCreators":5,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2504-06666","https://doi.org/10.48550/ARXIV.2504.06666"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2504-06666","documentUrl":null,"type":"Informal","arxivId":"2504.06666","arxivUrl":"https://arxiv.org/abs/2504.06666"},{"key":"journals/corr/abs-2504-14588","url":"https://dblp.org/rec/journals/corr/abs-2504-14588","title":"Phoenix: A Motion-based Self-Reflection Framework for Fine-grained Robotic Action Correction.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2504.14588","numberOfCreators":4,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2504-14588","https://doi.org/10.48550/ARXIV.2504.14588"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2504-14588","documentUrl":null,"type":"Informal","arxivId":"2504.14588","arxivUrl":"https://arxiv.org/abs/2504.14588"},{"key":"journals/corr/abs-2506-05191","url":"https://dblp.org/rec/journals/corr/abs-2506-05191","title":"MokA: Multimodal Low-Rank Adaptation for MLLMs.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2506.05191","numberOfCreators":4,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2506-05191","https://doi.org/10.48550/ARXIV.2506.05191"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-05191","documentUrl":null,"type":"Informal","arxivId":"2506.05191","arxivUrl":"https://arxiv.org/abs/2506.05191"},{"key":"journals/corr/abs-2506-07127","url":"https://dblp.org/rec/journals/corr/abs-2506-07127","title":"Robotic Policy Learning via Human-assisted Action Preference Optimization.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2506.07127","numberOfCreators":6,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2506-07127","https://doi.org/10.48550/ARXIV.2506.07127"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-07127","documentUrl":null,"type":"Informal","arxivId":"2506.07127","arxivUrl":"https://arxiv.org/abs/2506.07127"},{"key":"journals/corr/abs-2506-11465","url":"https://dblp.org/rec/journals/corr/abs-2506-11465","title":"RollingQ: Reviving the Cooperation Dynamics in Multimodal Transformer.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2506.11465","numberOfCreators":7,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2506-11465","https://doi.org/10.48550/ARXIV.2506.11465"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-11465","documentUrl":null,"type":"Informal","arxivId":"2506.11465","arxivUrl":"https://arxiv.org/abs/2506.11465"},{"key":"journals/corr/abs-2506-17248","url":"https://dblp.org/rec/journals/corr/abs-2506-17248","title":"Efficient Quantification of Multimodal Interaction at Sample Level.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2506.17248","numberOfCreators":3,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2506-17248","https://doi.org/10.48550/ARXIV.2506.17248"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-17248","documentUrl":null,"type":"Informal","arxivId":"2506.17248","arxivUrl":"https://arxiv.org/abs/2506.17248"},{"key":"journals/corr/abs-2506-19613","url":"https://dblp.org/rec/journals/corr/abs-2506-19613","title":"Position: Intelligent Science Laboratory Requires the Integration of Cognitive and Embodied AI.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2506.19613","numberOfCreators":21,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2506-19613","https://doi.org/10.48550/ARXIV.2506.19613"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-19613","documentUrl":null,"type":"Informal","arxivId":"2506.19613","arxivUrl":"https://arxiv.org/abs/2506.19613"},{"key":"journals/corr/abs-2510-00050","url":"https://dblp.org/rec/journals/corr/abs-2510-00050","title":"Object-AVEdit: An Object-level Audio-Visual Editing Model.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2510.00050","numberOfCreators":9,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2510-00050","https://doi.org/10.48550/ARXIV.2510.00050"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-00050","documentUrl":null,"type":"Informal","arxivId":"2510.00050","arxivUrl":"https://arxiv.org/abs/2510.00050"},{"key":"journals/corr/abs-2511-17441","url":"https://dblp.org/rec/journals/corr/abs-2511-17441","title":"RoboCOIN: An Open-Sourced Bimanual Robotic Data COllection for INtegrated Manipulation.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2511.17441","numberOfCreators":84,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2511-17441","https://doi.org/10.48550/ARXIV.2511.17441"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2511-17441","documentUrl":null,"type":"Informal","arxivId":"2511.17441","arxivUrl":"https://arxiv.org/abs/2511.17441"},{"key":"journals/corr/abs-2512-17229","url":"https://dblp.org/rec/journals/corr/abs-2512-17229","title":"Video Detective: Seek Critical Clues Recurrently to Answer Question from Long Videos.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2512.17229","numberOfCreators":5,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2512-17229","https://doi.org/10.48550/ARXIV.2512.17229"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-17229","documentUrl":null,"type":"Informal","arxivId":"2512.17229","arxivUrl":"https://arxiv.org/abs/2512.17229"}],"excludedFormal":[],"otherRecords":[],"matchedName":"Di Hu","databaseLabel":"Di Hu 0001","databaseMetadata":{"type":["https://dblp.org/rdf/schema#Person","https://dblp.org/rdf/schema#Creator"],"label":["Di Hu 0001"],"affiliation":["Renmin University of China, Gaoling School of Artificial Intelligence, Beijing, China","Northwestern Polytechnical University, School of Computer Science and Engineering, OPTIMAL, Xi'an, China","Baidu Research, Big Data Laboratory, Beijing, China"],"homepage":["https://openreview.net/profile?id=~Di_Hu1"],"orcid":["https://orcid.org/0000-0002-7118-6733"],"primaryAffiliation":["Baidu Research, Big Data Laboratory, Beijing, China"],"primaryHomepage":["https://openreview.net/profile?id=~Di_Hu1"]},"rawFormalRecordCount2025":17,"signatureAudit":{"completedAt":"2026-10-19","frozen":true,"scope":"对 B 组 39 个数值档案的全部 1074 条原始 2025 正式记录扫描 DBLP author-signature ORCID 和机构；复用既有 59 条 Crossref 核验，补查 6 条新触发记录。重点核查不同 ORCID，以及只有预期机构之外机构的条目。本轮不扩展为所有作者逐篇全文审计。","formalRecordCoverage":17,"orcidCounts":{"https://orcid.org/0000-0002-7118-6733":6},"institutionCounts":{"Beijing Academy of Artificial Intelligence (BAAI)":2,"Georgian State University of Subtropical Agriculture (GSAI)":1,"Renmin University of China (RUC)":11},"caveat":"机构名称可能由 DBLP 自动映射而失真；多 ORCID 也不自动等于异人。只有有原始资料支撑的错归才作确认排除，未解决分支则暂停总数。"},"labName":"GeWu Lab","labUrl":"https://gewu-lab.github.io/","labEvidence":"实验室官方成员页明确写 Currently, Di Hu is leading the GeWu Lab，本人主页也直接链接该组。","labSourceUrl":"https://gewu-lab.github.io/member/","sourceWarning":false,"excludedOther":[],"excludedHomonyms":[],"unassignedCandidates":[],"knownPreprintMinimum2025":null,"excludedMisattributed":[],"displayNotes":"DBLP 的机构字段含历史机构，已按原名单机构与本人履历交叉核对，未依据旧机构另选同名者。计入 17 条（会议 16、期刊 1）；预印本 14 条单列，不加总。","labDisplayNotes":"GeWu Lab 官方成员页写明目前由胡迪带领，本人主页也链接该组，据此归组。"},{"index":45,"name":"Ruizhen Hu","nameZh":"胡瑞珍","role":"Professor","affiliation":"Shenzhen University","affiliationZh":"深圳大学","source":"DBLP RDF via official SPARQL; primary-source identity checks","sourceUrl":"https://sparql.dblp.org/","profileUrl":"https://dblp.org/pid/14/11270.html","identifier":"14/11270","retrievedAt":"2026-10-19","count2025":18,"conference2025":16,"journal2025":2,"preprint2025":16,"status":"confirmed","notes":"","identityEvidence":[{"url":"https://dblp.org/pid/14/11270.html","evidence":"DBLP RDF 类型为 Person，消歧后名字为 Ruizhen Hu。此档案未提供可用机构元数据，以下以本人/机构/出版商来源补证。"},{"url":"https://sa2025.conference-schedule.org/contributor/?uid=922143","evidence":"SIGGRAPH Asia 官方议程将 Ruizhen Hu 标为 Shenzhen University 教授。"},{"url":"https://sa2025.conference-schedule.org/presentation/?id=papers_2228&sess=sess111","evidence":"官方议程 Neural Octahedral Field 的作者 Ruizhen Hu 为深圳大学；与 DBLP journals/tog/ZhengYH25 对应。"},{"url":"https://sa2025.conference-schedule.org/presentation/?id=papers_1810&sess=sess110","evidence":"官方议程 S3Imagery 作者及机构同样与所选个人记录吻合。"}],"papers":[{"key":"conf/cvm/SuPKHH25","url":"https://dblp.org/rec/conf/cvm/SuPKHH25","title":"MTScan: Material Transfer from Partial Scans to CAD Models.","year":2025,"types":["Inproceedings"],"venue":"CVM (2)","doi":"https://doi.org/10.1007/978-981-96-5812-1_8","eventYear":2025,"numberOfCreators":5,"category":"conference","sources":["https://dblp.org/rec/conf/cvm/SuPKHH25","https://doi.org/10.1007/978-981-96-5812-1_8"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/cvm/SuPKHH25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/cvpr/ChenMLCPCXH00025","url":"https://dblp.org/rec/conf/cvpr/ChenMLCPCXH00025","title":"G3Flow: Generative 3D Semantic Flow for Pose-aware and Generalizable Object Manipulation.","year":2025,"types":["Inproceedings"],"venue":"CVPR","doi":"https://doi.org/10.1109/CVPR52734.2025.00169","eventYear":2025,"numberOfCreators":11,"category":"conference","sources":["https://dblp.org/rec/conf/cvpr/ChenMLCPCXH00025","https://doi.org/10.1109/CVPR52734.2025.00169"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/ChenMLCPCXH00025","documentUrl":null,"type":"Inproceedings"},{"key":"conf/cvpr/GuoXL0LH25","url":"https://dblp.org/rec/conf/cvpr/GuoXL0LH25","title":"ArticulatedGS: Self-supervised Digital Twin Modeling of Articulated Objects using 3D Gaussian Splatting.","year":2025,"types":["Inproceedings"],"venue":"CVPR","doi":"https://doi.org/10.1109/CVPR52734.2025.02528","eventYear":2025,"numberOfCreators":6,"category":"conference","sources":["https://dblp.org/rec/conf/cvpr/GuoXL0LH25","https://doi.org/10.1109/CVPR52734.2025.02528"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/GuoXL0LH25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/cvpr/Wu0H025","url":"https://dblp.org/rec/conf/cvpr/Wu0H025","title":"Glossy Object Reconstruction with Cost-effective Polarized Acquisition.","year":2025,"types":["Inproceedings"],"venue":"CVPR","doi":"https://doi.org/10.1109/CVPR52734.2025.00048","eventYear":2025,"numberOfCreators":4,"category":"conference","sources":["https://dblp.org/rec/conf/cvpr/Wu0H025","https://doi.org/10.1109/CVPR52734.2025.00048"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/Wu0H025","documentUrl":null,"type":"Inproceedings"},{"key":"conf/eccv/DaiLSHMHXH24","url":"https://dblp.org/rec/conf/eccv/DaiLSHMHXH24","title":"InterFusion: Text-Driven Generation of 3D Human-Object Interaction.","year":2025,"types":["Inproceedings"],"venue":"ECCV (48)","doi":"https://doi.org/10.1007/978-3-031-73195-2_2","eventYear":2024,"numberOfCreators":8,"category":"conference","sources":["https://dblp.org/rec/conf/eccv/DaiLSHMHXH24","https://doi.org/10.1007/978-3-031-73195-2_2"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2024,"sourceUrl":"https://dblp.org/rec/conf/eccv/DaiLSHMHXH24","documentUrl":null,"type":"Inproceedings"},{"key":"conf/eccv/GuoZPWSHZ24","url":"https://dblp.org/rec/conf/eccv/GuoZPWSHZ24","title":"SAM-Guided Graph Cut for 3D Instance Segmentation.","year":2025,"types":["Inproceedings"],"venue":"ECCV (48)","doi":"https://doi.org/10.1007/978-3-031-73195-2_14","eventYear":2024,"numberOfCreators":7,"category":"conference","sources":["https://dblp.org/rec/conf/eccv/GuoZPWSHZ24","https://doi.org/10.1007/978-3-031-73195-2_14"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2024,"sourceUrl":"https://dblp.org/rec/conf/eccv/GuoZPWSHZ24","documentUrl":null,"type":"Inproceedings"},{"key":"conf/eccv/SheZYHX24","url":"https://dblp.org/rec/conf/eccv/SheZYHX24","title":"Learning Cross-Hand Policies of High-DOF Reaching and Grasping.","year":2025,"types":["Inproceedings"],"venue":"ECCV (30)","doi":"https://doi.org/10.1007/978-3-031-73404-5_16","eventYear":2024,"numberOfCreators":5,"category":"conference","sources":["https://dblp.org/rec/conf/eccv/SheZYHX24","https://doi.org/10.1007/978-3-031-73404-5_16"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2024,"sourceUrl":"https://dblp.org/rec/conf/eccv/SheZYHX24","documentUrl":null,"type":"Inproceedings"},{"key":"conf/eccv/XuXHXHH24","url":"https://dblp.org/rec/conf/eccv/XuXHXHH24","title":"FRI-Net: Floorplan Reconstruction via Room-Wise Implicit Representation.","year":2025,"types":["Inproceedings"],"venue":"ECCV (32)","doi":"https://doi.org/10.1007/978-3-031-73411-3_1","eventYear":2024,"numberOfCreators":6,"category":"conference","sources":["https://dblp.org/rec/conf/eccv/XuXHXHH24","https://doi.org/10.1007/978-3-031-73411-3_1"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2024,"sourceUrl":"https://dblp.org/rec/conf/eccv/XuXHXHH24","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iccv/GuoPSSHWDHKPZ25","url":"https://dblp.org/rec/conf/iccv/GuoPSSHWDHKPZ25","title":"Motion-2-To-3: Leveraging 2D Motion Data for 3D Motion Generations.","year":2025,"types":["Inproceedings"],"venue":"ICCV","doi":"https://doi.org/10.1109/ICCV51701.2025.01327","eventYear":2025,"numberOfCreators":11,"category":"conference","sources":["https://dblp.org/rec/conf/iccv/GuoPSSHWDHKPZ25","https://doi.org/10.1109/ICCV51701.2025.01327"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/GuoPSSHWDHKPZ25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iccv/JianLCLLH25","url":"https://dblp.org/rec/conf/iccv/JianLCLLH25","title":"G-DexGrasp: Generalizable Dexterous Grasping Synthesis via Part-Aware Prior Retrieval and Prior-Assisted Generation.","year":2025,"types":["Inproceedings"],"venue":"ICCV","doi":"https://doi.org/10.1109/ICCV51701.2025.01065","eventYear":2025,"numberOfCreators":6,"category":"conference","sources":["https://dblp.org/rec/conf/iccv/JianLCLLH25","https://doi.org/10.1109/ICCV51701.2025.01065"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/JianLCLLH25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iccv/TanHPGZSHSBZ25","url":"https://dblp.org/rec/conf/iccv/TanHPGZSHSBZ25","title":"ReTracker: Exploring Image Matching for Robust Online Any Point Tracking.","year":2025,"types":["Inproceedings"],"venue":"ICCV","doi":"https://doi.org/10.1109/ICCV51701.2025.00410","eventYear":2025,"numberOfCreators":10,"category":"conference","sources":["https://dblp.org/rec/conf/iccv/TanHPGZSHSBZ25","https://doi.org/10.1109/ICCV51701.2025.00410"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/TanHPGZSHSBZ25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iccv/WangWGPQBZH25","url":"https://dblp.org/rec/conf/iccv/WangWGPQBZH25","title":"Precise Action-to-Video Generation Through Visual Action Prompts.","year":2025,"types":["Inproceedings"],"venue":"ICCV","doi":"https://doi.org/10.1109/ICCV51701.2025.01181","eventYear":2025,"numberOfCreators":8,"category":"conference","sources":["https://dblp.org/rec/conf/iccv/WangWGPQBZH25","https://doi.org/10.1109/ICCV51701.2025.01181"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/WangWGPQBZH25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iccv/YuHZYYHSZZP25","url":"https://dblp.org/rec/conf/iccv/YuHZYYHSZZP25","title":"BoxDreamer: Dreaming Box Corners for Generalizable Object Pose Estimation.","year":2025,"types":["Inproceedings"],"venue":"ICCV","doi":"https://doi.org/10.1109/ICCV51701.2025.00875","eventYear":2025,"numberOfCreators":10,"category":"conference","sources":["https://dblp.org/rec/conf/iccv/YuHZYYHSZZP25","https://doi.org/10.1109/ICCV51701.2025.00875"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/YuHZYYHSZZP25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iclr/CenPPSSB0H25","url":"https://dblp.org/rec/conf/iclr/CenPPSSB0H25","title":"Ready-to-React: Online Reaction Policy for Two-Character Interaction Generation.","year":2025,"types":["Inproceedings"],"venue":"ICLR","doi":null,"eventYear":2025,"numberOfCreators":8,"category":"conference","sources":["https://dblp.org/rec/conf/iclr/CenPPSSB0H25"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iclr/CenPPSSB0H25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/siggraph/LiX0SZ0H25","url":"https://dblp.org/rec/conf/siggraph/LiX0SZ0H25","title":"MASH: Masked Anchored SpHerical Distances for 3D Shape Representation and Generation.","year":2025,"types":["Inproceedings"],"venue":"SIGGRAPH (Conference Paper Track)","doi":"https://doi.org/10.1145/3721238.3730610","eventYear":2025,"numberOfCreators":7,"category":"conference","sources":["https://dblp.org/rec/conf/siggraph/LiX0SZ0H25","https://doi.org/10.1145/3721238.3730610"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/siggraph/LiX0SZ0H25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/siggrapha/ShenQLH025","url":"https://dblp.org/rec/conf/siggrapha/ShenQLH025","title":"S3 Imagery: Specular Shading from Scratch-Anisotropy.","year":2025,"types":["Inproceedings"],"venue":"SIGGRAPH Asia","doi":"https://doi.org/10.1145/3757377.3763928","eventYear":2025,"numberOfCreators":5,"category":"conference","sources":["https://dblp.org/rec/conf/siggrapha/ShenQLH025","https://doi.org/10.1145/3757377.3763928"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/siggrapha/ShenQLH025","documentUrl":null,"type":"Inproceedings"},{"key":"journals/cg/ZhengMH25","url":"https://dblp.org/rec/journals/cg/ZhengMH25","title":"PhaseTrack: Physics-Based Motion Tracking via Phase-Guided Motion Generation.","year":2025,"types":["Article"],"venue":"Comput. Graph.","doi":"https://doi.org/10.1016/J.CAG.2025.104333","numberOfCreators":3,"category":"journal","sources":["https://dblp.org/rec/journals/cg/ZhengMH25","https://doi.org/10.1016/J.CAG.2025.104333"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/cg/ZhengMH25","documentUrl":null,"type":"Article"},{"key":"journals/tog/ZhengYH25","url":"https://dblp.org/rec/journals/tog/ZhengYH25","title":"Neural Octahedral Field: Octahedral Prior for Simultaneous Smoothing and Sharp Edge Regularization.","year":2025,"types":["Article"],"venue":"ACM Trans. Graph.","doi":"https://doi.org/10.1145/3763362","numberOfCreators":3,"category":"journal","sources":["https://dblp.org/rec/journals/tog/ZhengYH25","https://doi.org/10.1145/3763362"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/tog/ZhengYH25","documentUrl":null,"type":"Article"}],"preprints":[{"key":"journals/corr/abs-2502-05309","url":"https://dblp.org/rec/journals/corr/abs-2502-05309","title":"Learning the Geometric Mechanics of Robot Motion Using Gaussian Mixtures.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2502.05309","numberOfCreators":2,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2502-05309","https://doi.org/10.48550/ARXIV.2502.05309"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2502-05309","documentUrl":null,"type":"Informal","arxivId":"2502.05309","arxivUrl":"https://arxiv.org/abs/2502.05309"},{"key":"journals/corr/abs-2502-20370","url":"https://dblp.org/rec/journals/corr/abs-2502-20370","title":"Ready-to-React: Online Reaction Policy for Two-Character Interaction Generation.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2502.20370","numberOfCreators":8,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2502-20370","https://doi.org/10.48550/ARXIV.2502.20370"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2502-20370","documentUrl":null,"type":"Informal","arxivId":"2502.20370","arxivUrl":"https://arxiv.org/abs/2502.20370"},{"key":"journals/corr/abs-2503-08135","url":"https://dblp.org/rec/journals/corr/abs-2503-08135","title":"ArticulatedGS: Self-supervised Digital Twin Modeling of Articulated Objects using 3D Gaussian Splatting.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2503.08135","numberOfCreators":6,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2503-08135","https://doi.org/10.48550/ARXIV.2503.08135"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-08135","documentUrl":null,"type":"Informal","arxivId":"2503.08135","arxivUrl":"https://arxiv.org/abs/2503.08135"},{"key":"journals/corr/abs-2503-19457","url":"https://dblp.org/rec/journals/corr/abs-2503-19457","title":"G-DexGrasp: Generalizable Dexterous Grasping Synthesis Via Part-Aware Prior Retrieval and Prior-Assisted Generation.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2503.19457","numberOfCreators":6,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2503-19457","https://doi.org/10.48550/ARXIV.2503.19457"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-19457","documentUrl":null,"type":"Informal","arxivId":"2503.19457","arxivUrl":"https://arxiv.org/abs/2503.19457"},{"key":"journals/corr/abs-2504-04421","url":"https://dblp.org/rec/journals/corr/abs-2504-04421","title":"Deliberate Planning of 3D Bin Packing on Packing Configuration Trees.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2504.04421","numberOfCreators":6,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2504-04421","https://doi.org/10.48550/ARXIV.2504.04421"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2504-04421","documentUrl":null,"type":"Informal","arxivId":"2504.04421","arxivUrl":"https://arxiv.org/abs/2504.04421"},{"key":"journals/corr/abs-2504-07025","url":"https://dblp.org/rec/journals/corr/abs-2504-07025","title":"Glossy Object Reconstruction with Cost-effective Polarized Acquisition.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2504.07025","numberOfCreators":4,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2504-07025","https://doi.org/10.48550/ARXIV.2504.07025"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2504-07025","documentUrl":null,"type":"Informal","arxivId":"2504.07025","arxivUrl":"https://arxiv.org/abs/2504.07025"},{"key":"journals/corr/abs-2504-07955","url":"https://dblp.org/rec/journals/corr/abs-2504-07955","title":"BoxDreamer: Dreaming Box Corners for Generalizable Object Pose Estimation.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2504.07955","numberOfCreators":10,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2504-07955","https://doi.org/10.48550/ARXIV.2504.07955"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2504-07955","documentUrl":null,"type":"Informal","arxivId":"2504.07955","arxivUrl":"https://arxiv.org/abs/2504.07955"},{"key":"journals/corr/abs-2504-09149","url":"https://dblp.org/rec/journals/corr/abs-2504-09149","title":"MASH: Masked Anchored SpHerical Distances for 3D Shape Representation and Generation.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2504.09149","numberOfCreators":7,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2504-09149","https://doi.org/10.48550/ARXIV.2504.09149"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2504-09149","documentUrl":null,"type":"Informal","arxivId":"2504.09149","arxivUrl":"https://arxiv.org/abs/2504.09149"},{"key":"journals/corr/abs-2504-16693","url":"https://dblp.org/rec/journals/corr/abs-2504-16693","title":"PIN-WM: Learning Physics-INformed World Models for Non-Prehensile Manipulation.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2504.16693","numberOfCreators":7,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2504-16693","https://doi.org/10.48550/ARXIV.2504.16693"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2504-16693","documentUrl":null,"type":"Informal","arxivId":"2504.16693","arxivUrl":"https://arxiv.org/abs/2504.16693"},{"key":"journals/corr/abs-2505-11528","url":"https://dblp.org/rec/journals/corr/abs-2505-11528","title":"LaDi-WM: A Latent Diffusion-based World Model for Predictive Manipulation.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2505.11528","numberOfCreators":6,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2505-11528","https://doi.org/10.48550/ARXIV.2505.11528"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-11528","documentUrl":null,"type":"Informal","arxivId":"2505.11528","arxivUrl":"https://arxiv.org/abs/2505.11528"},{"key":"journals/corr/abs-2506-24121","url":"https://dblp.org/rec/journals/corr/abs-2506-24121","title":"TextMesh4D: High-Quality Text-to-4D Mesh Generation.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2506.24121","numberOfCreators":5,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2506-24121","https://doi.org/10.48550/ARXIV.2506.24121"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-24121","documentUrl":null,"type":"Informal","arxivId":"2506.24121","arxivUrl":"https://arxiv.org/abs/2506.24121"},{"key":"journals/corr/abs-2507-11540","url":"https://dblp.org/rec/journals/corr/abs-2507-11540","title":"Towards Depth Foundation Model: Recent Trends in Vision-Based Depth Estimation.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2507.11540","numberOfCreators":16,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2507-11540","https://doi.org/10.48550/ARXIV.2507.11540"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2507-11540","documentUrl":null,"type":"Informal","arxivId":"2507.11540","arxivUrl":"https://arxiv.org/abs/2507.11540"},{"key":"journals/corr/abs-2508-13104","url":"https://dblp.org/rec/journals/corr/abs-2508-13104","title":"Precise Action-to-Video Generation Through Visual Action Prompts.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2508.13104","numberOfCreators":8,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2508-13104","https://doi.org/10.48550/ARXIV.2508.13104"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-13104","documentUrl":null,"type":"Informal","arxivId":"2508.13104","arxivUrl":"https://arxiv.org/abs/2508.13104"},{"key":"journals/corr/abs-2511-13327","url":"https://dblp.org/rec/journals/corr/abs-2511-13327","title":"ZeroDexGrasp: Zero-Shot Task-Oriented Dexterous Grasp Synthesis with Prompt-Based Multi-Stage Semantic Reasoning.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2511.13327","numberOfCreators":8,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2511-13327","https://doi.org/10.48550/ARXIV.2511.13327"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2511-13327","documentUrl":null,"type":"Informal","arxivId":"2511.13327","arxivUrl":"https://arxiv.org/abs/2511.13327"},{"key":"journals/corr/abs-2512-03538","url":"https://dblp.org/rec/journals/corr/abs-2512-03538","title":"AdaPower: Specializing World Foundation Models for Predictive Manipulation.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2512.03538","numberOfCreators":6,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2512-03538","https://doi.org/10.48550/ARXIV.2512.03538"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-03538","documentUrl":null,"type":"Informal","arxivId":"2512.03538","arxivUrl":"https://arxiv.org/abs/2512.03538"},{"key":"journals/corr/abs-2512-04415","url":"https://dblp.org/rec/journals/corr/abs-2512-04415","title":"RoboBPP: Benchmarking Robotic Online Bin Packing with Physics-based Simulation.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2512.04415","numberOfCreators":8,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2512-04415","https://doi.org/10.48550/ARXIV.2512.04415"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-04415","documentUrl":null,"type":"Informal","arxivId":"2512.04415","arxivUrl":"https://arxiv.org/abs/2512.04415"}],"excludedFormal":[],"otherRecords":[],"matchedName":"Ruizhen Hu","databaseLabel":"Ruizhen Hu","databaseMetadata":{"type":["https://dblp.org/rdf/schema#Person","https://dblp.org/rdf/schema#Creator"],"label":["Ruizhen Hu"],"orcid":["https://orcid.org/0000-0002-6798-0336"]},"rawFormalRecordCount2025":18,"signatureAudit":{"completedAt":"2026-10-19","frozen":true,"scope":"对 B 组 39 个数值档案的全部 1074 条原始 2025 正式记录扫描 DBLP author-signature ORCID 和机构；复用既有 59 条 Crossref 核验，补查 6 条新触发记录。重点核查不同 ORCID，以及只有预期机构之外机构的条目。本轮不扩展为所有作者逐篇全文审计。","formalRecordCoverage":18,"orcidCounts":{"https://orcid.org/0000-0002-6798-0336":6},"institutionCounts":{"Shenzhen University (SZU)":17},"caveat":"机构名称可能由 DBLP 自动映射而失真；多 ORCID 也不自动等于异人。只有有原始资料支撑的错归才作确认排除，未解决分支则暂停总数。"},"labName":"可视计算研究中心","labUrl":null,"labEvidence":"深圳大学官方胡瑞珍教师页在本人信息中明确列可视计算研究中心。该名称是较大研究中心关联，不应解读为其独立实验室或该中心完整产量；本轮未确认独立中心 URL。","labSourceUrl":"https://csse.szu.edu.cn/pages/user/index?id=531","sourceWarning":false,"excludedOther":[],"excludedHomonyms":[],"unassignedCandidates":[],"knownPreprintMinimum2025":null,"excludedMisattributed":[],"displayNotes":"身份已经官方会议来源确认，与深圳大学对应。2025 年正式记录 18 条（会议 16、期刊 2），所有作者位置均计入；预印本 16 条单列，不加总。","labDisplayNotes":"深圳大学本人教师页列出可视计算研究中心。这是规模较大的研究中心，不是其独立实验室；分组只含本人参与的记录，未确认中心网址。"},{"index":46,"name":"Gao Huang","nameZh":"黄高","role":"Associate Professor","affiliation":"Tsinghua University","affiliationZh":"清华大学","source":"DBLP RDF via official SPARQL; primary-source identity checks","sourceUrl":"https://sparql.dblp.org/","profileUrl":"https://dblp.org/pid/120/2687-1.html","identifier":"120/2687-1","retrievedAt":"2026-10-19","count2025":48,"conference2025":34,"journal2025":14,"preprint2025":35,"status":"confirmed","notes":"","identityEvidence":[{"url":"https://dblp.org/pid/120/2687-1.html","evidence":"DBLP RDF 类型为 Person，消歧后名字为 Gao Huang 0001。机构元数据含：Tsinghua University, Department of Automation, Beijing, China；Cornell University, Ithaca, NY, USA；Tsinghua University, Department of Automation, BNRist, Beijing, China"}],"papers":[{"key":"conf/aaai/ZhaoXLWLZ025","url":"https://dblp.org/rec/conf/aaai/ZhaoXLWLZ025","title":"DiveR-CT: Diversity-enhanced Red Teaming Large Language Model Assistants with Relaxing Constraints.","year":2025,"types":["Inproceedings"],"venue":"AAAI","doi":"https://doi.org/10.1609/AAAI.V39I24.34797","eventYear":2025,"numberOfCreators":7,"category":"conference","sources":["https://dblp.org/rec/conf/aaai/ZhaoXLWLZ025","https://doi.org/10.1609/AAAI.V39I24.34797"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/aaai/ZhaoXLWLZ025","documentUrl":null,"type":"Inproceedings"},{"key":"conf/cvpr/0001ZZSHQ0P25","url":"https://dblp.org/rec/conf/cvpr/0001ZZSHQ0P25","title":"4D LangSplat: 4D Language Gaussian Splatting via Multimodal Large Language Models.","year":2025,"types":["Inproceedings"],"venue":"CVPR","doi":"https://doi.org/10.1109/CVPR52734.2025.02049","eventYear":2025,"numberOfCreators":8,"category":"conference","sources":["https://dblp.org/rec/conf/cvpr/0001ZZSHQ0P25","https://doi.org/10.1109/CVPR52734.2025.02049"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/0001ZZSHQ0P25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/cvpr/GuoZDWGNSSH25","url":"https://dblp.org/rec/conf/cvpr/GuoZDWGNSSH25","title":"Everything to the Synthetic: Diffusion-driven Test-time Adaptation via Synthetic-Domain Alignment.","year":2025,"types":["Inproceedings"],"venue":"CVPR","doi":"https://doi.org/10.1109/CVPR52734.2025.02840","eventYear":2025,"numberOfCreators":9,"category":"conference","sources":["https://dblp.org/rec/conf/cvpr/GuoZDWGNSSH25","https://doi.org/10.1109/CVPR52734.2025.02840"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/GuoZDWGNSSH25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/cvpr/PengZ025","url":"https://dblp.org/rec/conf/cvpr/PengZ025","title":"ProxyTransformation: Preshaping Point Cloud Manifold With Proxy Attention For 3D Visual Grounding.","year":2025,"types":["Inproceedings"],"venue":"CVPR","doi":"https://doi.org/10.1109/CVPR52734.2025.02289","eventYear":2025,"numberOfCreators":3,"category":"conference","sources":["https://dblp.org/rec/conf/cvpr/PengZ025","https://doi.org/10.1109/CVPR52734.2025.02289"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/PengZ025","documentUrl":null,"type":"Inproceedings"},{"key":"conf/cvpr/PuZTYYYCBZWLWLL25","url":"https://dblp.org/rec/conf/cvpr/PuZTYYYCBZWLWLL25","title":"ART: Anonymous Region Transformer for Variable Multi-Layer Transparent Image Generation.","year":2025,"types":["Inproceedings"],"venue":"CVPR","doi":"https://doi.org/10.1109/CVPR52734.2025.00745","eventYear":2025,"numberOfCreators":17,"category":"conference","sources":["https://dblp.org/rec/conf/cvpr/PuZTYYYCBZWLWLL25","https://doi.org/10.1109/CVPR52734.2025.00745"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/PuZTYYYCBZWLWLL25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/cvpr/TaoSZZ0LWL00D25","url":"https://dblp.org/rec/conf/cvpr/TaoSZZ0LWL00D25","title":"HoVLE: Unleashing the Power of Monolithic Vision-Language Models with Holistic Vision-Language Embedding.","year":2025,"types":["Inproceedings"],"venue":"CVPR","doi":"https://doi.org/10.1109/CVPR52734.2025.01357","eventYear":2025,"numberOfCreators":11,"category":"conference","sources":["https://dblp.org/rec/conf/cvpr/TaoSZZ0LWL00D25","https://doi.org/10.1109/CVPR52734.2025.01357"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/TaoSZZ0LWL00D25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/cvpr/TianZ0XH025","url":"https://dblp.org/rec/conf/cvpr/TianZ0XH025","title":"DTOS: Dynamic Time Object Sensing with Large Multimodal Model.","year":2025,"types":["Inproceedings"],"venue":"CVPR","doi":"https://doi.org/10.1109/CVPR52734.2025.01289","eventYear":2025,"numberOfCreators":6,"category":"conference","sources":["https://dblp.org/rec/conf/cvpr/TianZ0XH025","https://doi.org/10.1109/CVPR52734.2025.01289"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/TianZ0XH025","documentUrl":null,"type":"Inproceedings"},{"key":"conf/cvpr/YueWJLS025","url":"https://dblp.org/rec/conf/cvpr/YueWJLS025","title":"EchoWorld: Learning Motion-Aware World Models for Echocardiography Probe Guidance.","year":2025,"types":["Inproceedings"],"venue":"CVPR","doi":"https://doi.org/10.1109/CVPR52734.2025.02421","eventYear":2025,"numberOfCreators":6,"category":"conference","sources":["https://dblp.org/rec/conf/cvpr/YueWJLS025","https://doi.org/10.1109/CVPR52734.2025.02421"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/YueWJLS025","documentUrl":null,"type":"Inproceedings"},{"key":"conf/cvpr/YueWTLS025","url":"https://dblp.org/rec/conf/cvpr/YueWTLS025","title":"CheXWorld: Exploring Image World Modeling for Radiograph Representation Learning.","year":2025,"types":["Inproceedings"],"venue":"CVPR","doi":"https://doi.org/10.1109/CVPR52734.2025.01935","eventYear":2025,"numberOfCreators":6,"category":"conference","sources":["https://dblp.org/rec/conf/cvpr/YueWTLS025","https://doi.org/10.1109/CVPR52734.2025.01935"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/YueWTLS025","documentUrl":null,"type":"Inproceedings"},{"key":"conf/eccv/GuoXYCNGCLH24","url":"https://dblp.org/rec/conf/eccv/GuoXYCNGCLH24","title":"LLaVA-UHD: An LMM Perceiving Any Aspect Ratio and High-Resolution Images.","year":2025,"types":["Inproceedings"],"venue":"ECCV (83)","doi":"https://doi.org/10.1007/978-3-031-73010-8_23","eventYear":2024,"numberOfCreators":9,"category":"conference","sources":["https://dblp.org/rec/conf/eccv/GuoXYCNGCLH24","https://doi.org/10.1007/978-3-031-73010-8_23"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2024,"sourceUrl":"https://dblp.org/rec/conf/eccv/GuoXYCNGCLH24","documentUrl":null,"type":"Inproceedings"},{"key":"conf/eccv/HanYHXPWSH24","url":"https://dblp.org/rec/conf/eccv/HanYHXPWSH24","title":"Agent Attention: On the Integration of Softmax and Linear Attention.","year":2025,"types":["Inproceedings"],"venue":"ECCV (50)","doi":"https://doi.org/10.1007/978-3-031-72973-7_8","eventYear":2024,"numberOfCreators":8,"category":"conference","sources":["https://dblp.org/rec/conf/eccv/HanYHXPWSH24","https://doi.org/10.1007/978-3-031-72973-7_8"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2024,"sourceUrl":"https://dblp.org/rec/conf/eccv/HanYHXPWSH24","documentUrl":null,"type":"Inproceedings"},{"key":"conf/eccv/HuangPTTPSHE24","url":"https://dblp.org/rec/conf/eccv/HuangPTTPSHE24","title":"Segment3D: Learning Fine-Grained Class-Agnostic 3D Segmentation Without Manual Labels.","year":2025,"types":["Inproceedings"],"venue":"ECCV (34)","doi":"https://doi.org/10.1007/978-3-031-72754-2_16","eventYear":2024,"numberOfCreators":8,"category":"conference","sources":["https://dblp.org/rec/conf/eccv/HuangPTTPSHE24","https://doi.org/10.1007/978-3-031-72754-2_16"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2024,"sourceUrl":"https://dblp.org/rec/conf/eccv/HuangPTTPSHE24","documentUrl":null,"type":"Inproceedings"},{"key":"conf/eccv/LiuLLLLHY24","url":"https://dblp.org/rec/conf/eccv/LiuLLLLHY24","title":"Glyph-ByT5: A Customized Text Encoder for Accurate Visual Text Rendering.","year":2025,"types":["Inproceedings"],"venue":"ECCV (75)","doi":"https://doi.org/10.1007/978-3-031-73226-3_21","eventYear":2024,"numberOfCreators":7,"category":"conference","sources":["https://dblp.org/rec/conf/eccv/LiuLLLLHY24","https://doi.org/10.1007/978-3-031-73226-3_21"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2024,"sourceUrl":"https://dblp.org/rec/conf/eccv/LiuLLLLHY24","documentUrl":null,"type":"Inproceedings"},{"key":"conf/eccv/NiWZLGHLYH24","url":"https://dblp.org/rec/conf/eccv/NiWZLGHLYH24","title":"AdaNAT: Exploring Adaptive Policy for Token-Based Image Generation.","year":2025,"types":["Inproceedings"],"venue":"ECCV (16)","doi":"https://doi.org/10.1007/978-3-031-72640-8_17","eventYear":2024,"numberOfCreators":9,"category":"conference","sources":["https://dblp.org/rec/conf/eccv/NiWZLGHLYH24","https://doi.org/10.1007/978-3-031-72640-8_17"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2024,"sourceUrl":"https://dblp.org/rec/conf/eccv/NiWZLGHLYH24","documentUrl":null,"type":"Inproceedings"},{"key":"conf/eccv/PuXGHLLYLHSHX24","url":"https://dblp.org/rec/conf/eccv/PuXGHLLYLHSHX24","title":"Efficient Diffusion Transformer with Step-Wise Dynamic Attention Mediators.","year":2025,"types":["Inproceedings"],"venue":"ECCV (15)","doi":"https://doi.org/10.1007/978-3-031-72633-0_24","eventYear":2024,"numberOfCreators":12,"category":"conference","sources":["https://dblp.org/rec/conf/eccv/PuXGHLLYLHSHX24","https://doi.org/10.1007/978-3-031-72633-0_24"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2024,"sourceUrl":"https://dblp.org/rec/conf/eccv/PuXGHLLYLHSHX24","documentUrl":null,"type":"Inproceedings"},{"key":"conf/eccv/WangPHGWLH24","url":"https://dblp.org/rec/conf/eccv/WangPHGWLH24","title":"GRA: Detecting Oriented Objects Through Group-Wise Rotating and Attention.","year":2025,"types":["Inproceedings"],"venue":"ECCV (17)","doi":"https://doi.org/10.1007/978-3-031-72643-9_18","eventYear":2024,"numberOfCreators":7,"category":"conference","sources":["https://dblp.org/rec/conf/eccv/WangPHGWLH24","https://doi.org/10.1007/978-3-031-72643-9_18"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2024,"sourceUrl":"https://dblp.org/rec/conf/eccv/WangPHGWLH24","documentUrl":null,"type":"Inproceedings"},{"key":"conf/eccv/YangZHCSHL24","url":"https://dblp.org/rec/conf/eccv/YangZHCSHL24","title":"DyFADet: Dynamic Feature Aggregation for Temporal Action Detection.","year":2025,"types":["Inproceedings"],"venue":"ECCV (46)","doi":"https://doi.org/10.1007/978-3-031-72952-2_18","eventYear":2024,"numberOfCreators":7,"category":"conference","sources":["https://dblp.org/rec/conf/eccv/YangZHCSHL24","https://doi.org/10.1007/978-3-031-72952-2_18"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2024,"sourceUrl":"https://dblp.org/rec/conf/eccv/YangZHCSHL24","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iccv/GuoYXWWHS25","url":"https://dblp.org/rec/conf/iccv/GuoYXWWHS25","title":"IMG: Calibrating Diffusion Models via Implicit Multimodal Guidance.","year":2025,"types":["Inproceedings"],"venue":"ICCV","doi":"https://doi.org/10.1109/ICCV51701.2025.01492","eventYear":2025,"numberOfCreators":7,"category":"conference","sources":["https://dblp.org/rec/conf/iccv/GuoYXWWHS25","https://doi.org/10.1109/ICCV51701.2025.01492"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/GuoYXWWHS25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iccv/LiuNHDMZH25","url":"https://dblp.org/rec/conf/iccv/LiuNHDMZH25","title":"CODA: Repurposing Continuous VAEs for Discrete Tokenization.","year":2025,"types":["Inproceedings"],"venue":"ICCV","doi":"https://doi.org/10.1109/ICCV51701.2025.01757","eventYear":2025,"numberOfCreators":7,"category":"conference","sources":["https://dblp.org/rec/conf/iccv/LiuNHDMZH25","https://doi.org/10.1109/ICCV51701.2025.01757"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/LiuNHDMZH25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iclr/LuWLJ0W25","url":"https://dblp.org/rec/conf/iclr/LuWLJ0W25","title":"Towards Understanding Text Hallucination of Diffusion Models via Local Generation Bias.","year":2025,"types":["Inproceedings"],"venue":"ICLR","doi":null,"eventYear":2025,"numberOfCreators":6,"category":"conference","sources":["https://dblp.org/rec/conf/iclr/LuWLJ0W25"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iclr/LuWLJ0W25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iclr/WangS025","url":"https://dblp.org/rec/conf/iclr/WangS025","title":"GridMix: Exploring Spatial Modulation for Neural Fields in PDE Modeling.","year":2025,"types":["Inproceedings"],"venue":"ICLR","doi":null,"eventYear":2025,"numberOfCreators":3,"category":"conference","sources":["https://dblp.org/rec/conf/iclr/WangS025"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iclr/WangS025","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iclr/Ye0XSZ0W25","url":"https://dblp.org/rec/conf/iclr/Ye0XSZ0W25","title":"Differential Transformer.","year":2025,"types":["Inproceedings"],"venue":"ICLR","doi":null,"eventYear":2025,"numberOfCreators":7,"category":"conference","sources":["https://dblp.org/rec/conf/iclr/Ye0XSZ0W25"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iclr/Ye0XSZ0W25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iclr/ZhaoHT0S0W025","url":"https://dblp.org/rec/conf/iclr/ZhaoHT0S0W025","title":"Dynamic Diffusion Transformer.","year":2025,"types":["Inproceedings"],"venue":"ICLR","doi":null,"eventYear":2025,"numberOfCreators":8,"category":"conference","sources":["https://dblp.org/rec/conf/iclr/ZhaoHT0S0W025"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iclr/ZhaoHT0S0W025","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iclr/ZhengSPCHWS025","url":"https://dblp.org/rec/conf/iclr/ZhengSPCHWS025","title":"DenseGrounding: Improving Dense Language-Vision Semantics for Ego-centric 3D Visual Grounding.","year":2025,"types":["Inproceedings"],"venue":"ICLR","doi":null,"eventYear":2025,"numberOfCreators":8,"category":"conference","sources":["https://dblp.org/rec/conf/iclr/ZhengSPCHWS025"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iclr/ZhengSPCHWS025","documentUrl":null,"type":"Inproceedings"},{"key":"conf/icml/KangYL00W0F25","url":"https://dblp.org/rec/conf/icml/KangYL00W0F25","title":"How Far Is Video Generation from World Model: A Physical Law Perspective.","year":2025,"types":["Inproceedings"],"venue":"ICML","doi":null,"eventYear":2025,"numberOfCreators":8,"category":"conference","sources":["https://dblp.org/rec/conf/icml/KangYL00W0F25"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/icml/KangYL00W0F25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iros/ChenYLHLL25","url":"https://dblp.org/rec/conf/iros/ChenYLHLL25","title":"UltraDP: Generalizable Carotid Ultrasound Scanning with Force-Aware Diffusion Policy.","year":2025,"types":["Inproceedings"],"venue":"IROS","doi":"https://doi.org/10.1109/IROS60139.2025.11246769","eventYear":2025,"numberOfCreators":6,"category":"conference","sources":["https://dblp.org/rec/conf/iros/ChenYLHLL25","https://doi.org/10.1109/IROS60139.2025.11246769"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iros/ChenYLHLL25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/miccai/JiangLSJSLSH24","url":"https://dblp.org/rec/conf/miccai/JiangLSJSLSH24","title":"Structure-aware World Model for Probe Guidance via Large-scale Self-supervised Pre-train.","year":2025,"types":["Inproceedings"],"venue":"ASMUS@MICCAI","doi":"https://doi.org/10.1007/978-3-031-73647-6_6","eventYear":2024,"numberOfCreators":8,"category":"conference","sources":["https://dblp.org/rec/conf/miccai/JiangLSJSLSH24","https://doi.org/10.1007/978-3-031-73647-6_6"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2024,"sourceUrl":"https://dblp.org/rec/conf/miccai/JiangLSJSLSH24","documentUrl":null,"type":"Inproceedings"},{"key":"conf/naacl/WangYLSZWSH25","url":"https://dblp.org/rec/conf/naacl/WangYLSZWSH25","title":"Model Surgery: Modulating LLM's Behavior Via Simple Parameter Editing.","year":2025,"types":["Inproceedings"],"venue":"NAACL (Long Papers)","doi":"https://doi.org/10.18653/V1/2025.NAACL-LONG.321","eventYear":2025,"numberOfCreators":8,"category":"conference","sources":["https://dblp.org/rec/conf/naacl/WangYLSZWSH25","https://doi.org/10.18653/V1/2025.NAACL-LONG.321"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/naacl/WangYLSZWSH25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/nips/ChenLZWYSH25","url":"https://dblp.org/rec/conf/nips/ChenLZWYSH25","title":"Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?","year":2025,"types":["Inproceedings"],"venue":"NeurIPS","doi":null,"eventYear":2025,"numberOfCreators":7,"category":"conference","sources":["https://dblp.org/rec/conf/nips/ChenLZWYSH25"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/nips/ChenLZWYSH25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/nips/HuangZBPTGHE25","url":"https://dblp.org/rec/conf/nips/HuangZBPTGHE25","title":"Video Perception Models for 3D Scene Synthesis.","year":2025,"types":["Inproceedings"],"venue":"NeurIPS","doi":null,"eventYear":2025,"numberOfCreators":8,"category":"conference","sources":["https://dblp.org/rec/conf/nips/HuangZBPTGHE25"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/nips/HuangZBPTGHE25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/nips/PuYLYHWWSHL25","url":"https://dblp.org/rec/conf/nips/PuYLYHWWSHL25","title":"Linear Differential Vision Transformer: Learning Visual Contrasts via Pairwise Differentials.","year":2025,"types":["Inproceedings"],"venue":"NeurIPS","doi":null,"eventYear":2025,"numberOfCreators":10,"category":"conference","sources":["https://dblp.org/rec/conf/nips/PuYLYHWWSHL25"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/nips/PuYLYHWWSHL25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/nips/WangYGZLLDCYZLY25","url":"https://dblp.org/rec/conf/nips/WangYGZLLDCYZLY25","title":"Beyond the 80/20 Rule: High-Entropy Minority Tokens Drive Effective Reinforcement Learning for LLM Reasoning.","year":2025,"types":["Inproceedings"],"venue":"NeurIPS","doi":null,"eventYear":2025,"numberOfCreators":18,"category":"conference","sources":["https://dblp.org/rec/conf/nips/WangYGZLLDCYZLY25"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/nips/WangYGZLLDCYZLY25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/nips/ZhangWXZSHCW25","url":"https://dblp.org/rec/conf/nips/ZhangWXZSHCW25","title":"DyMoDreamer: World Modeling with Dynamic Modulation.","year":2025,"types":["Inproceedings"],"venue":"NeurIPS","doi":null,"eventYear":2025,"numberOfCreators":8,"category":"conference","sources":["https://dblp.org/rec/conf/nips/ZhangWXZSHCW25"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/nips/ZhangWXZSHCW25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/nips/ZhaoWWXYLWWZH25","url":"https://dblp.org/rec/conf/nips/ZhaoWWXYLWWZH25","title":"Absolute Zero: Reinforced Self-play Reasoning with Zero Data.","year":2025,"types":["Inproceedings"],"venue":"NeurIPS","doi":null,"eventYear":2025,"numberOfCreators":10,"category":"conference","sources":["https://dblp.org/rec/conf/nips/ZhaoWWXYLWWZH25"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/nips/ZhaoWWXYLWWZH25","documentUrl":null,"type":"Inproceedings"},{"key":"journals/artmed/YangWLWSSFH25","url":"https://dblp.org/rec/journals/artmed/YangWLWSSFH25","title":"Anatomical prior-based vertebral landmark detection for spinal disorder diagnosis.","year":2025,"types":["Article"],"venue":"Artif. Intell. Medicine","doi":"https://doi.org/10.1016/J.ARTMED.2024.103011","numberOfCreators":8,"category":"journal","sources":["https://dblp.org/rec/journals/artmed/YangWLWSSFH25","https://doi.org/10.1016/J.ARTMED.2024.103011"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/artmed/YangWLWSSFH25","documentUrl":null,"type":"Article"},{"key":"journals/eaai/SunWLZHL25","url":"https://dblp.org/rec/journals/eaai/SunWLZHL25","title":"Towards pedestrian head tracking: A benchmark dataset and a multi-source data fusion network.","year":2025,"types":["Article"],"venue":"Eng. Appl. Artif. Intell.","doi":"https://doi.org/10.1016/J.ENGAPPAI.2025.111265","numberOfCreators":6,"category":"journal","sources":["https://dblp.org/rec/journals/eaai/SunWLZHL25","https://doi.org/10.1016/J.ENGAPPAI.2025.111265"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/eaai/SunWLZHL25","documentUrl":null,"type":"Article"},{"key":"journals/ijcv/WangNPZYSH25","url":"https://dblp.org/rec/journals/ijcv/WangNPZYSH25","title":"InfoPro: Locally Supervised Deep Learning by Maximizing Information Propagation.","year":2025,"types":["Article"],"venue":"Int. J. Comput. Vis.","doi":"https://doi.org/10.1007/S11263-024-02296-0","numberOfCreators":7,"category":"journal","sources":["https://dblp.org/rec/journals/ijcv/WangNPZYSH25","https://doi.org/10.1007/S11263-024-02296-0"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/ijcv/WangNPZYSH25","documentUrl":null,"type":"Article"},{"key":"journals/nn/LiCLXMH25","url":"https://dblp.org/rec/journals/nn/LiCLXMH25","title":"From ReLU to GeMU: Activation functions in the lens of cone projection.","year":2025,"types":["Article"],"venue":"Neural Networks","doi":"https://doi.org/10.1016/J.NEUNET.2025.107654","numberOfCreators":6,"category":"journal","sources":["https://dblp.org/rec/journals/nn/LiCLXMH25","https://doi.org/10.1016/J.NEUNET.2025.107654"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/nn/LiCLXMH25","documentUrl":null,"type":"Article"},{"key":"journals/nn/ZhaoZLLLH25","url":"https://dblp.org/rec/journals/nn/ZhaoZLLLH25","title":"Self-Referencing Agents for Unsupervised Reinforcement Learning.","year":2025,"types":["Article"],"venue":"Neural Networks","doi":"https://doi.org/10.1016/J.NEUNET.2025.107448","numberOfCreators":6,"category":"journal","sources":["https://dblp.org/rec/journals/nn/ZhaoZLLLH25","https://doi.org/10.1016/J.NEUNET.2025.107448"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/nn/ZhaoZLLLH25","documentUrl":null,"type":"Article"},{"key":"journals/nn/ZhaoZLLLH25a","url":"https://dblp.org/rec/journals/nn/ZhaoZLLLH25a","title":"Corrigendum to \"Self-Referencing agents for unsupervised reinforcement learning\" [Neural Networks Volume 188, August 2025, 107448].","year":2025,"types":["Article"],"venue":"Neural Networks","doi":"https://doi.org/10.1016/J.NEUNET.2025.107632","numberOfCreators":6,"category":"journal","sources":["https://dblp.org/rec/journals/nn/ZhaoZLLLH25a","https://doi.org/10.1016/J.NEUNET.2025.107632"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/nn/ZhaoZLLLH25a","documentUrl":null,"type":"Article"},{"key":"journals/pami/WangZYSDFH25","url":"https://dblp.org/rec/journals/pami/WangZYSDFH25","title":"Uni-AdaFocus: Spatial-Temporal Dynamic Computation for Video Recognition.","year":2025,"types":["Article"],"venue":"IEEE Trans. Pattern Anal. Mach. Intell.","doi":"https://doi.org/10.1109/TPAMI.2024.3514654","numberOfCreators":7,"category":"journal","sources":["https://dblp.org/rec/journals/pami/WangZYSDFH25","https://doi.org/10.1109/TPAMI.2024.3514654"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/pami/WangZYSDFH25","documentUrl":null,"type":"Article"},{"key":"journals/pr/JiangZHGNSH25","url":"https://dblp.org/rec/journals/pr/JiangZHGNSH25","title":"Cross-modal adapter for vision-language retrieval.","year":2025,"types":["Article"],"venue":"Pattern Recognit.","doi":"https://doi.org/10.1016/J.PATCOG.2024.111144","numberOfCreators":7,"category":"journal","sources":["https://dblp.org/rec/journals/pr/JiangZHGNSH25","https://doi.org/10.1016/J.PATCOG.2024.111144"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/pr/JiangZHGNSH25","documentUrl":null,"type":"Article"},{"key":"journals/tnn/GeHXLSLH25","url":"https://dblp.org/rec/journals/tnn/GeHXLSLH25","title":"Domain Adaptation via Prompt Learning.","year":2025,"types":["Article"],"venue":"IEEE Trans. Neural Networks Learn. Syst.","doi":"https://doi.org/10.1109/TNNLS.2023.3327962","numberOfCreators":7,"category":"journal","sources":["https://dblp.org/rec/journals/tnn/GeHXLSLH25","https://doi.org/10.1109/TNNLS.2023.3327962"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/tnn/GeHXLSLH25","documentUrl":null,"type":"Article"},{"key":"journals/tnn/LiuDZLZWH25","url":"https://dblp.org/rec/journals/tnn/LiuDZLZWH25","title":"Multidimensional Refinement Graph Convolutional Network With Robust Decouple Loss for Fine-Grained Skeleton-Based Action Recognition.","year":2025,"types":["Article"],"venue":"IEEE Trans. Neural Networks Learn. Syst.","doi":"https://doi.org/10.1109/TNNLS.2024.3384770","numberOfCreators":7,"category":"journal","sources":["https://dblp.org/rec/journals/tnn/LiuDZLZWH25","https://doi.org/10.1109/TNNLS.2024.3384770"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/tnn/LiuDZLZWH25","documentUrl":null,"type":"Article"},{"key":"journals/tnn/WangPSH25","url":"https://dblp.org/rec/journals/tnn/WangPSH25","title":"Advancing Generalization in PINNs Through Latent-Space Representations.","year":2025,"types":["Article"],"venue":"IEEE Trans. Neural Networks Learn. Syst.","doi":"https://doi.org/10.1109/TNNLS.2025.3598617","numberOfCreators":4,"category":"journal","sources":["https://dblp.org/rec/journals/tnn/WangPSH25","https://doi.org/10.1109/TNNLS.2025.3598617"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/tnn/WangPSH25","documentUrl":null,"type":"Article"},{"key":"journals/tnn/YueKMYHSY25","url":"https://dblp.org/rec/journals/tnn/YueKMYHSY25","title":"Decoupled Prioritized Resampling for Offline RL.","year":2025,"types":["Article"],"venue":"IEEE Trans. Neural Networks Learn. Syst.","doi":"https://doi.org/10.1109/TNNLS.2024.3488358","numberOfCreators":7,"category":"journal","sources":["https://dblp.org/rec/journals/tnn/YueKMYHSY25","https://doi.org/10.1109/TNNLS.2024.3488358"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/tnn/YueKMYHSY25","documentUrl":null,"type":"Article"},{"key":"journals/tnn/ZhangWLHLLF25","url":"https://dblp.org/rec/journals/tnn/ZhangWLHLLF25","title":"End-to-End Streaming Video Temporal Action Segmentation With Reinforcement Learning.","year":2025,"types":["Article"],"venue":"IEEE Trans. Neural Networks Learn. Syst.","doi":"https://doi.org/10.1109/TNNLS.2025.3550910","numberOfCreators":7,"category":"journal","sources":["https://dblp.org/rec/journals/tnn/ZhangWLHLLF25","https://doi.org/10.1109/TNNLS.2025.3550910"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/tnn/ZhangWLHLLF25","documentUrl":null,"type":"Article"},{"key":"journals/tnn/ZhuWPWZH25","url":"https://dblp.org/rec/journals/tnn/ZhuWPWZH25","title":"A-SDM: Accelerating Stable Diffusion Through Model Assembly and Feature Inheritance Strategies.","year":2025,"types":["Article"],"venue":"IEEE Trans. Neural Networks Learn. Syst.","doi":"https://doi.org/10.1109/TNNLS.2025.3587724","numberOfCreators":6,"category":"journal","sources":["https://dblp.org/rec/journals/tnn/ZhuWPWZH25","https://doi.org/10.1109/TNNLS.2025.3587724"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/tnn/ZhuWPWZH25","documentUrl":null,"type":"Article"}],"preprints":[{"key":"journals/corr/abs-2502-18364","url":"https://dblp.org/rec/journals/corr/abs-2502-18364","title":"ART: Anonymous Region Transformer for Variable Multi-Layer Transparent Image Generation.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2502.18364","numberOfCreators":17,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2502-18364","https://doi.org/10.48550/ARXIV.2502.18364"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2502-18364","documentUrl":null,"type":"Informal","arxivId":"2502.18364","arxivUrl":"https://arxiv.org/abs/2502.18364"},{"key":"journals/corr/abs-2502-19247","url":"https://dblp.org/rec/journals/corr/abs-2502-19247","title":"ProxyTransformation: Preshaping Point Cloud Manifold With Proxy Attention For 3D Visual Grounding.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2502.19247","numberOfCreators":3,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2502-19247","https://doi.org/10.48550/ARXIV.2502.19247"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2502-19247","documentUrl":null,"type":"Informal","arxivId":"2502.19247","arxivUrl":"https://arxiv.org/abs/2502.19247"},{"key":"journals/corr/abs-2503-00345","url":"https://dblp.org/rec/journals/corr/abs-2503-00345","title":"Towards Understanding the Benefit of Multitask Representation Learning in Decision Process.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2503.00345","numberOfCreators":5,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2503-00345","https://doi.org/10.48550/ARXIV.2503.00345"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-00345","documentUrl":null,"type":"Informal","arxivId":"2503.00345","arxivUrl":"https://arxiv.org/abs/2503.00345"},{"key":"journals/corr/abs-2503-03595","url":"https://dblp.org/rec/journals/corr/abs-2503-03595","title":"Towards Understanding Text Hallucination of Diffusion Models via Local Generation Bias.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2503.03595","numberOfCreators":6,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2503-03595","https://doi.org/10.48550/ARXIV.2503.03595"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-03595","documentUrl":null,"type":"Informal","arxivId":"2503.03595","arxivUrl":"https://arxiv.org/abs/2503.03595"},{"key":"journals/corr/abs-2503-10437","url":"https://dblp.org/rec/journals/corr/abs-2503-10437","title":"4D LangSplat: 4D Language Gaussian Splatting via Multimodal Large Language Models.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2503.10437","numberOfCreators":8,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2503-10437","https://doi.org/10.48550/ARXIV.2503.10437"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-10437","documentUrl":null,"type":"Informal","arxivId":"2503.10437","arxivUrl":"https://arxiv.org/abs/2503.10437"},{"key":"journals/corr/abs-2503-17760","url":"https://dblp.org/rec/journals/corr/abs-2503-17760","title":"CODA: Repurposing Continuous VAEs for Discrete Tokenization.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2503.17760","numberOfCreators":7,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2503-17760","https://doi.org/10.48550/ARXIV.2503.17760"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-17760","documentUrl":null,"type":"Informal","arxivId":"2503.17760","arxivUrl":"https://arxiv.org/abs/2503.17760"},{"key":"journals/corr/abs-2504-06803","url":"https://dblp.org/rec/journals/corr/abs-2504-06803","title":"DyDiT++: Dynamic Diffusion Transformers for Efficient Visual Generation.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2504.06803","numberOfCreators":9,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2504-06803","https://doi.org/10.48550/ARXIV.2504.06803"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2504-06803","documentUrl":null,"type":"Informal","arxivId":"2504.06803","arxivUrl":"https://arxiv.org/abs/2504.06803"},{"key":"journals/corr/abs-2504-13065","url":"https://dblp.org/rec/journals/corr/abs-2504-13065","title":"EchoWorld: Learning Motion-Aware World Models for Echocardiography Probe Guidance.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2504.13065","numberOfCreators":6,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2504-13065","https://doi.org/10.48550/ARXIV.2504.13065"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2504-13065","documentUrl":null,"type":"Informal","arxivId":"2504.13065","arxivUrl":"https://arxiv.org/abs/2504.13065"},{"key":"journals/corr/abs-2504-13820","url":"https://dblp.org/rec/journals/corr/abs-2504-13820","title":"CheXWorld: Exploring Image World Modeling for Radiograph Representation Learning.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2504.13820","numberOfCreators":6,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2504-13820","https://doi.org/10.48550/ARXIV.2504.13820"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2504-13820","documentUrl":null,"type":"Informal","arxivId":"2504.13820","arxivUrl":"https://arxiv.org/abs/2504.13820"},{"key":"journals/corr/abs-2504-13837","url":"https://dblp.org/rec/journals/corr/abs-2504-13837","title":"Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2504.13837","numberOfCreators":8,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2504-13837","https://doi.org/10.48550/ARXIV.2504.13837"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2504-13837","documentUrl":null,"type":"Informal","arxivId":"2504.13837","arxivUrl":"https://arxiv.org/abs/2504.13837"},{"key":"journals/corr/abs-2505-03335","url":"https://dblp.org/rec/journals/corr/abs-2505-03335","title":"Absolute Zero: Reinforced Self-play Reasoning with Zero Data.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2505.03335","numberOfCreators":11,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2505-03335","https://doi.org/10.48550/ARXIV.2505.03335"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-03335","documentUrl":null,"type":"Informal","arxivId":"2505.03335","arxivUrl":"https://arxiv.org/abs/2505.03335"},{"key":"journals/corr/abs-2505-04965","url":"https://dblp.org/rec/journals/corr/abs-2505-04965","title":"DenseGrounding: Improving Dense Language-Vision Semantics for Ego-Centric 3D Visual Grounding.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2505.04965","numberOfCreators":8,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2505-04965","https://doi.org/10.48550/ARXIV.2505.04965"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-04965","documentUrl":null,"type":"Informal","arxivId":"2505.04965","arxivUrl":"https://arxiv.org/abs/2505.04965"},{"key":"journals/corr/abs-2506-01939","url":"https://dblp.org/rec/journals/corr/abs-2506-01939","title":"Beyond the 80/20 Rule: High-Entropy Minority Tokens Drive Effective Reinforcement Learning for LLM Reasoning.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2506.01939","numberOfCreators":18,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2506-01939","https://doi.org/10.48550/ARXIV.2506.01939"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-01939","documentUrl":null,"type":"Informal","arxivId":"2506.01939","arxivUrl":"https://arxiv.org/abs/2506.01939"},{"key":"journals/corr/abs-2506-20601","url":"https://dblp.org/rec/journals/corr/abs-2506-20601","title":"Video Perception Models for 3D Scene Synthesis.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2506.20601","numberOfCreators":8,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2506-20601","https://doi.org/10.48550/ARXIV.2506.20601"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-20601","documentUrl":null,"type":"Informal","arxivId":"2506.20601","arxivUrl":"https://arxiv.org/abs/2506.20601"},{"key":"journals/corr/abs-2506-23280","url":"https://dblp.org/rec/journals/corr/abs-2506-23280","title":"BAPE: Learning an Explicit Bayes Classifier for Long-tailed Visual Recognition.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2506.23280","numberOfCreators":4,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2506-23280","https://doi.org/10.48550/ARXIV.2506.23280"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-23280","documentUrl":null,"type":"Informal","arxivId":"2506.23280","arxivUrl":"https://arxiv.org/abs/2506.23280"},{"key":"journals/corr/abs-2508-19236","url":"https://dblp.org/rec/journals/corr/abs-2508-19236","title":"MemoryVLA: Perceptual-Cognitive Memory in Vision-Language-Action Models for Robotic Manipulation.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2508.19236","numberOfCreators":10,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2508-19236","https://doi.org/10.48550/ARXIV.2508.19236"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-19236","documentUrl":null,"type":"Informal","arxivId":"2508.19236","arxivUrl":"https://arxiv.org/abs/2508.19236"},{"key":"journals/corr/abs-2509-13832","url":"https://dblp.org/rec/journals/corr/abs-2509-13832","title":"UltraHiT: A Hierarchical Transformer Architecture for Generalizable Internal Carotid Artery Robotic Ultrasonography.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2509.13832","numberOfCreators":7,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2509-13832","https://doi.org/10.48550/ARXIV.2509.13832"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-13832","documentUrl":null,"type":"Informal","arxivId":"2509.13832","arxivUrl":"https://arxiv.org/abs/2509.13832"},{"key":"journals/corr/abs-2509-15333","url":"https://dblp.org/rec/journals/corr/abs-2509-15333","title":"Emulating Human-like Adaptive Vision for Efficient and Flexible Machine Visual Perception.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2509.15333","numberOfCreators":15,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2509-15333","https://doi.org/10.48550/ARXIV.2509.15333"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-15333","documentUrl":null,"type":"Informal","arxivId":"2509.15333","arxivUrl":"https://arxiv.org/abs/2509.15333"},{"key":"journals/corr/abs-2509-24804","url":"https://dblp.org/rec/journals/corr/abs-2509-24804","title":"DyMoDreamer: World Modeling with Dynamic Modulation.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2509.24804","numberOfCreators":8,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2509-24804","https://doi.org/10.48550/ARXIV.2509.24804"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-24804","documentUrl":null,"type":"Informal","arxivId":"2509.24804","arxivUrl":"https://arxiv.org/abs/2509.24804"},{"key":"journals/corr/abs-2509-26231","url":"https://dblp.org/rec/journals/corr/abs-2509-26231","title":"IMG: Calibrating Diffusion Models via Implicit Multimodal Guidance.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2509.26231","numberOfCreators":7,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2509-26231","https://doi.org/10.48550/ARXIV.2509.26231"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-26231","documentUrl":null,"type":"Informal","arxivId":"2509.26231","arxivUrl":"https://arxiv.org/abs/2509.26231"},{"key":"journals/corr/abs-2510-06809","url":"https://dblp.org/rec/journals/corr/abs-2510-06809","title":"VA-Adapter: Adapting Ultrasound Foundation Model to Echocardiography Probe Guidance.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2510.06809","numberOfCreators":6,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2510-06809","https://doi.org/10.48550/ARXIV.2510.06809"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-06809","documentUrl":null,"type":"Informal","arxivId":"2510.06809","arxivUrl":"https://arxiv.org/abs/2510.06809"},{"key":"journals/corr/abs-2510-14381","url":"https://dblp.org/rec/journals/corr/abs-2510-14381","title":"Are My Optimized Prompts Compromised? Exploring Vulnerabilities of LLM-based Optimizers.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2510.14381","numberOfCreators":7,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2510-14381","https://doi.org/10.48550/ARXIV.2510.14381"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-14381","documentUrl":null,"type":"Informal","arxivId":"2510.14381","arxivUrl":"https://arxiv.org/abs/2510.14381"},{"key":"journals/corr/abs-2511-00833","url":"https://dblp.org/rec/journals/corr/abs-2511-00833","title":"Linear Differential Vision Transformer: Learning Visual Contrasts via Pairwise Differentials.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2511.00833","numberOfCreators":10,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2511-00833","https://doi.org/10.48550/ARXIV.2511.00833"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2511-00833","documentUrl":null,"type":"Informal","arxivId":"2511.00833","arxivUrl":"https://arxiv.org/abs/2511.00833"},{"key":"journals/corr/abs-2511-09555","url":"https://dblp.org/rec/journals/corr/abs-2511-09555","title":"SpatialActor: Exploring Disentangled Spatial Representations for Robust Robotic Manipulation.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2511.09555","numberOfCreators":8,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2511-09555","https://doi.org/10.48550/ARXIV.2511.09555"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2511-09555","documentUrl":null,"type":"Informal","arxivId":"2511.09555","arxivUrl":"https://arxiv.org/abs/2511.09555"},{"key":"journals/corr/abs-2511-14329","url":"https://dblp.org/rec/journals/corr/abs-2511-14329","title":"Step by Step Network.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2511.14329","numberOfCreators":7,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2511-14329","https://doi.org/10.48550/ARXIV.2511.14329"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2511-14329","documentUrl":null,"type":"Informal","arxivId":"2511.14329","arxivUrl":"https://arxiv.org/abs/2511.14329"},{"key":"journals/corr/abs-2511-15550","url":"https://dblp.org/rec/journals/corr/abs-2511-15550","title":"UltraDP: Generalizable Carotid Ultrasound Scanning with Force-Aware Diffusion Policy.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2511.15550","numberOfCreators":6,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2511-15550","https://doi.org/10.48550/ARXIV.2511.15550"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2511-15550","documentUrl":null,"type":"Informal","arxivId":"2511.15550","arxivUrl":"https://arxiv.org/abs/2511.15550"},{"key":"journals/corr/abs-2511-17441","url":"https://dblp.org/rec/journals/corr/abs-2511-17441","title":"RoboCOIN: An Open-Sourced Bimanual Robotic Data COllection for INtegrated Manipulation.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2511.17441","numberOfCreators":84,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2511-17441","https://doi.org/10.48550/ARXIV.2511.17441"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2511-17441","documentUrl":null,"type":"Informal","arxivId":"2511.17441","arxivUrl":"https://arxiv.org/abs/2511.17441"},{"key":"journals/corr/abs-2512-00493","url":"https://dblp.org/rec/journals/corr/abs-2512-00493","title":"CC-FMO: Camera-Conditioned Zero-Shot Single Image to 3D Scene Generation with Foundation Model Orchestration.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2512.00493","numberOfCreators":4,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2512-00493","https://doi.org/10.48550/ARXIV.2512.00493"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-00493","documentUrl":null,"type":"Informal","arxivId":"2512.00493","arxivUrl":"https://arxiv.org/abs/2512.00493"},{"key":"journals/corr/abs-2512-01643","url":"https://dblp.org/rec/journals/corr/abs-2512-01643","title":"ViT3: Unlocking Test-Time Training in Vision.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2512.01643","numberOfCreators":9,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2512-01643","https://doi.org/10.48550/ARXIV.2512.01643"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-01643","documentUrl":null,"type":"Informal","arxivId":"2512.01643","arxivUrl":"https://arxiv.org/abs/2512.01643"},{"key":"journals/corr/abs-2512-04813","url":"https://dblp.org/rec/journals/corr/abs-2512-04813","title":"MOVE: A Simple Motion-Based Data Collection Paradigm for Spatial Generalization in Robotic Manipulation.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2512.04813","numberOfCreators":10,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2512-04813","https://doi.org/10.48550/ARXIV.2512.04813"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-04813","documentUrl":null,"type":"Informal","arxivId":"2512.04813","arxivUrl":"https://arxiv.org/abs/2512.04813"},{"key":"journals/corr/abs-2512-13006","url":"https://dblp.org/rec/journals/corr/abs-2512-13006","title":"Few-Step Distillation for Text-to-Image Generation: A Practical Guide.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2512.13006","numberOfCreators":7,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2512-13006","https://doi.org/10.48550/ARXIV.2512.13006"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-13006","documentUrl":null,"type":"Informal","arxivId":"2512.13006","arxivUrl":"https://arxiv.org/abs/2512.13006"},{"key":"journals/corr/abs-2512-21542","url":"https://dblp.org/rec/journals/corr/abs-2512-21542","title":"Vision Transformers are Circulant Attention Learners.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2512.21542","numberOfCreators":4,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2512-21542","https://doi.org/10.48550/ARXIV.2512.21542"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-21542","documentUrl":null,"type":"Informal","arxivId":"2512.21542","arxivUrl":"https://arxiv.org/abs/2512.21542"},{"key":"journals/corr/abs-2512-22288","url":"https://dblp.org/rec/journals/corr/abs-2512-22288","title":"Co-GRPO: Co-Optimized Group Relative Policy Optimization for Masked Diffusion Model.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2512.22288","numberOfCreators":9,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2512-22288","https://doi.org/10.48550/ARXIV.2512.22288"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-22288","documentUrl":null,"type":"Informal","arxivId":"2512.22288","arxivUrl":"https://arxiv.org/abs/2512.22288"},{"key":"journals/corr/abs-2512-24330","url":"https://dblp.org/rec/journals/corr/abs-2512-24330","title":"SenseNova-MARS: Empowering Multimodal Agentic Reasoning and Search via Reinforcement Learning.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2512.24330","numberOfCreators":13,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2512-24330","https://doi.org/10.48550/ARXIV.2512.24330"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-24330","documentUrl":null,"type":"Informal","arxivId":"2512.24330","arxivUrl":"https://arxiv.org/abs/2512.24330"},{"key":"journals/corr/abs-2512-24603","url":"https://dblp.org/rec/journals/corr/abs-2512-24603","title":"Collaborative Low-Rank Adaptation for Pre-Trained Vision Transformers.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2512.24603","numberOfCreators":3,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2512-24603","https://doi.org/10.48550/ARXIV.2512.24603"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-24603","documentUrl":null,"type":"Informal","arxivId":"2512.24603","arxivUrl":"https://arxiv.org/abs/2512.24603"}],"excludedFormal":[],"otherRecords":[],"matchedName":"Gao Huang","databaseLabel":"Gao Huang 0001","databaseMetadata":{"type":["https://dblp.org/rdf/schema#Creator","https://dblp.org/rdf/schema#Person"],"label":["Gao Huang 0001"],"affiliation":["Tsinghua University, Department of Automation, Beijing, China","Cornell University, Ithaca, NY, USA","Tsinghua University, Department of Automation, BNRist, Beijing, China"],"homepage":["https://openreview.net/profile?id=~Gao_Huang1","https://www.au.tsinghua.edu.cn/en/info/1075/3328.htm","https://www.gaohuang.net/"],"orcid":["https://orcid.org/0000-0002-7251-0988"],"primaryAffiliation":["Tsinghua University, Department of Automation, BNRist, Beijing, China"],"primaryHomepage":["https://www.gaohuang.net/"]},"rawFormalRecordCount2025":48,"signatureAudit":{"completedAt":"2026-10-19","frozen":true,"scope":"对 B 组 39 个数值档案的全部 1074 条原始 2025 正式记录扫描 DBLP author-signature ORCID 和机构；复用既有 59 条 Crossref 核验，补查 6 条新触发记录。重点核查不同 ORCID，以及只有预期机构之外机构的条目。本轮不扩展为所有作者逐篇全文审计。","formalRecordCoverage":48,"orcidCounts":{"https://orcid.org/0000-0002-7251-0988":14},"institutionCounts":{"Beijing Academy of Artificial Intelligence (BAAI)":4,"Dalian University of Technology (DUT)":1,"Microsoft Research Asia":1,"Tsinghua University (THU)":33},"caveat":"机构名称可能由 DBLP 自动映射而失真；多 ORCID 也不自动等于异人。只有有原始资料支撑的错归才作确认排除，未解决分支则暂停总数。"},"labName":"LEarning And Perception (LEAP) Lab","labUrl":"https://www.leaplab.ai","labEvidence":"本人当前主页明确写 where I lead the LEarning And Perception (LEAP) Lab，并直接链接实验室网站。","labSourceUrl":"https://gaohuang-net.github.io/","sourceWarning":false,"excludedOther":[],"excludedHomonyms":[],"unassignedCandidates":[],"knownPreprintMinimum2025":null,"excludedMisattributed":[],"displayNotes":"身份已与原名单机构及公开资料核对确认。2025 年正式记录 48 条（会议 34、期刊 14），所有作者位置均计入，不表示主导或贡献份额；预印本 35 条单列，不加总。","labDisplayNotes":"本人主页写明其领导 LEarning And Perception（LEAP）Lab，并链接实验室网站，据此归组。"},{"index":47,"name":"Haibin Huang","nameZh":"黄海斌","role":"Principal Research Scientist","affiliation":"China Telecom AI Research Institute (TeleAI)","affiliationZh":"中国电信人工智能研究院","source":"DBLP RDF via official SPARQL; primary-source identity checks","sourceUrl":"https://sparql.dblp.org/","profileUrl":null,"identifier":null,"retrievedAt":"2026-10-19","count2025":null,"conference2025":null,"journal2025":null,"preprint2025":null,"status":"unresolved","notes":"Haibin Huang 82/1981 在 DBLP RDF 中明确标为 AmbiguousCreator，并混合图形学、遥感、网络控制等不同作者；无法可靠拆分全部 2025 记录，故总数留空，绝非 0。 本人主页有至少 6 条 2025 正式记录标题可与候选 DBLP 档案匹配，但此部分核验不等于完整计数。","identityEvidence":[{"url":"https://brotherhuang.github.io/","evidence":"本人为 TeleAI Haibin Huang，曾在 ByteDance、Kuaishou、Megvii 任职，UMass Amherst 博士。"},{"url":"https://brotherhuang.github.io/publications.html","evidence":"本人发表清单与候选混合档案中至少 6 个正式标题匹配，不能使整个档案归属成立。"},{"url":"https://dblp.org/pid/82/1981.html","evidence":"官方 RDF 类型 AmbiguousCreator；原始 metadata 和 2025 候选记录已缓存。"}],"papers":[],"preprints":[],"excludedFormal":[],"otherRecords":[],"candidateProfileUrl":"https://dblp.org/pid/82/1981.html","labName":null,"labUrl":null,"labEvidence":"本人主页只明确 TeleAI 任职及博士阶段 Computer Graphics Research Group 经历；未把旧导师组或整个研究院当作当前个人实验室。","labSourceUrl":"https://brotherhuang.github.io/","sourceWarning":false,"excludedOther":[],"excludedHomonyms":[],"unassignedCandidates":[],"knownPreprintMinimum2025":null,"excludedMisattributed":[],"knownMinimum2025":null,"displayNotes":"DBLP 将该档案标为 AmbiguousCreator，其中混入图形学、遥感、网络控制等领域的不同作者，无法可靠拆分 2025 年的记录，故不给出总数，这绝非零。本人主页可对应至少 6 条 2025 年正式记录的标题，但这只是部分核对，不作为计数或下界展示。","labDisplayNotes":"本人主页只写明在 TeleAI 任职及博士阶段的研究组经历；不把旧导师的组或整个研究院当作当前实验室。"},{"index":48,"name":"Xu Jia","nameZh":"贾旭","role":"Professor","affiliation":"Dalian University of Technology","affiliationZh":"大连理工大学","source":"DBLP RDF via official SPARQL; primary-source identity checks","sourceUrl":"https://sparql.dblp.org/","profileUrl":"https://dblp.org/pid/95/3616-12.html","identifier":"95/3616-12","retrievedAt":"2026-10-19","count2025":19,"conference2025":12,"journal2025":7,"preprint2025":14,"status":"confirmed","notes":"","identityEvidence":[{"url":"https://dblp.org/pid/95/3616-12.html","evidence":"DBLP RDF 类型为 Person，消歧后名字为 Xu Jia 0012。机构元数据含：Dalian University of Technology, School of Artificial Intelligence and the School of Futher Technology, China；Huawei, Noah' Ark Lab；KU Leuven, Belgium"}],"papers":[{"key":"conf/cvpr/Li0IJC0LHLWB25","url":"https://dblp.org/rec/conf/cvpr/Li0IJC0LHLWB25","title":"ReNeg: Learning Negative Embedding with Reward Guidance.","year":2025,"types":["Inproceedings"],"venue":"CVPR","doi":"https://doi.org/10.1109/CVPR52734.2025.02201","eventYear":2025,"numberOfCreators":11,"category":"conference","sources":["https://dblp.org/rec/conf/cvpr/Li0IJC0LHLWB25","https://doi.org/10.1109/CVPR52734.2025.02201"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/Li0IJC0LHLWB25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/eccv/DiaoWJZZLC24","url":"https://dblp.org/rec/conf/eccv/DiaoWJZZLC24","title":"SHERL: Synthesizing High Accuracy and Efficient Memory for Resource-Limited Transfer Learning.","year":2025,"types":["Inproceedings"],"venue":"ECCV (44)","doi":"https://doi.org/10.1007/978-3-031-72784-9_5","eventYear":2024,"numberOfCreators":7,"category":"conference","sources":["https://dblp.org/rec/conf/eccv/DiaoWJZZLC24","https://doi.org/10.1007/978-3-031-72784-9_5"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2024,"sourceUrl":"https://dblp.org/rec/conf/eccv/DiaoWJZZLC24","documentUrl":null,"type":"Inproceedings"},{"key":"conf/eccv/ZhangYWCLWLJ24","url":"https://dblp.org/rec/conf/eccv/ZhangYWCLWLJ24","title":"EvSign: Sign Language Recognition and Translation with Streaming Events.","year":2025,"types":["Inproceedings"],"venue":"ECCV (5)","doi":"https://doi.org/10.1007/978-3-031-72652-1_20","eventYear":2024,"numberOfCreators":8,"category":"conference","sources":["https://dblp.org/rec/conf/eccv/ZhangYWCLWLJ24","https://doi.org/10.1007/978-3-031-72652-1_20"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2024,"sourceUrl":"https://dblp.org/rec/conf/eccv/ZhangYWCLWLJ24","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iccv/TianLMYZHLLJ25","url":"https://dblp.org/rec/conf/iccv/TianLMYZHLLJ25","title":"CCL-LGS: Contrastive Codebook Learning for 3D Language Gaussian Splatting.","year":2025,"types":["Inproceedings"],"venue":"ICCV","doi":"https://doi.org/10.1109/ICCV51701.2025.00919","eventYear":2025,"numberOfCreators":9,"category":"conference","sources":["https://dblp.org/rec/conf/iccv/TianLMYZHLLJ25","https://doi.org/10.1109/ICCV51701.2025.00919"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/TianLMYZHLLJ25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iccv/YangLZYBMWCWLJ25","url":"https://dblp.org/rec/conf/iccv/YangLZYBMWCWLJ25","title":"VLIPP: Towards Physically Plausible Video Generation with Vision and Language Informed Physical Prior.","year":2025,"types":["Inproceedings"],"venue":"ICCV","doi":"https://doi.org/10.1109/ICCV51701.2025.01149","eventYear":2025,"numberOfCreators":11,"category":"conference","sources":["https://dblp.org/rec/conf/iccv/YangLZYBMWCWLJ25","https://doi.org/10.1109/ICCV51701.2025.01149"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/YangLZYBMWCWLJ25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iccv/YuFLTYTCJYYT25","url":"https://dblp.org/rec/conf/iccv/YuFLTYTCJYYT25","title":"Evagaussians: Event Stream Assisted Gaussian Splatting from Blurry Images.","year":2025,"types":["Inproceedings"],"venue":"ICCV","doi":"https://doi.org/10.1109/ICCV51701.2025.02298","eventYear":2025,"numberOfCreators":11,"category":"conference","sources":["https://dblp.org/rec/conf/iccv/YuFLTYTCJYYT25","https://doi.org/10.1109/ICCV51701.2025.02298"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/YuFLTYTCJYYT25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/icra/XiaZHQHJ25","url":"https://dblp.org/rec/conf/icra/XiaZHQHJ25","title":"Towards Survivability in Complex Motion Scenarios: RGB-Event Object Tracking via Historical Trajectory Prompting.","year":2025,"types":["Inproceedings"],"venue":"ICRA","doi":"https://doi.org/10.1109/ICRA55743.2025.11127812","eventYear":2025,"numberOfCreators":6,"category":"conference","sources":["https://dblp.org/rec/conf/icra/XiaZHQHJ25","https://doi.org/10.1109/ICRA55743.2025.11127812"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/icra/XiaZHQHJ25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/mm/ZhuD000Z0000L25","url":"https://dblp.org/rec/conf/mm/ZhuD000Z0000L25","title":"Regularizing Subspace Redundancy of Low-Rank Adaptation.","year":2025,"types":["Inproceedings"],"venue":"ACM Multimedia","doi":"https://doi.org/10.1145/3746027.3755359","eventYear":2025,"numberOfCreators":11,"category":"conference","sources":["https://dblp.org/rec/conf/mm/ZhuD000Z0000L25","https://doi.org/10.1145/3746027.3755359"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/mm/ZhuD000Z0000L25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/prcv/HuangJSZLWL24","url":"https://dblp.org/rec/conf/prcv/HuangJSZLWL24","title":"Video Frame Interpolation for Large Motion with Generative Prior.","year":2025,"types":["Inproceedings"],"venue":"PRCV (10)","doi":"https://doi.org/10.1007/978-981-97-8792-0_28","eventYear":2024,"numberOfCreators":7,"category":"conference","sources":["https://dblp.org/rec/conf/prcv/HuangJSZLWL24","https://doi.org/10.1007/978-981-97-8792-0_28"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2024,"sourceUrl":"https://dblp.org/rec/conf/prcv/HuangJSZLWL24","documentUrl":null,"type":"Inproceedings"},{"key":"conf/siggraph/WangLS0LX000G25","url":"https://dblp.org/rec/conf/siggraph/WangLS0LX000G25","title":"CineMaster: A 3D-Aware and Controllable Framework for Cinematic Text-to-Video Generation.","year":2025,"types":["Inproceedings"],"venue":"SIGGRAPH (Conference Paper Track)","doi":"https://doi.org/10.1145/3721238.3730755","eventYear":2025,"numberOfCreators":10,"category":"conference","sources":["https://dblp.org/rec/conf/siggraph/WangLS0LX000G25","https://doi.org/10.1145/3721238.3730755"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/siggraph/WangLS0LX000G25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/wacv/0023LZLL0HTZLYL25","url":"https://dblp.org/rec/conf/wacv/0023LZLL0HTZLYL25","title":"Automated Evaluation of Large Vision-Language Models on Self-Driving Corner Cases.","year":2025,"types":["Inproceedings"],"venue":"WACV","doi":"https://doi.org/10.1109/WACV61041.2025.00759","eventYear":2025,"numberOfCreators":13,"category":"conference","sources":["https://dblp.org/rec/conf/wacv/0023LZLL0HTZLYL25","https://doi.org/10.1109/WACV61041.2025.00759"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/wacv/0023LZLL0HTZLYL25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/wacv/LiCL0HYL025","url":"https://dblp.org/rec/conf/wacv/LiCL0HYL025","title":"TrackDiffusion: Tracklet-Conditioned Video Generation via Diffusion Models.","year":2025,"types":["Inproceedings"],"venue":"WACV","doi":"https://doi.org/10.1109/WACV61041.2025.00349","eventYear":2025,"numberOfCreators":8,"category":"conference","sources":["https://dblp.org/rec/conf/wacv/LiCL0HYL025","https://doi.org/10.1109/WACV61041.2025.00349"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/wacv/LiCL0HYL025","documentUrl":null,"type":"Inproceedings"},{"key":"journals/tcsv/LiWLGJHL25","url":"https://dblp.org/rec/journals/tcsv/LiWLGJHL25","title":"MoBox: Enhancing Video Object Segmentation With Motion-Augmented Box Supervision.","year":2025,"types":["Article"],"venue":"IEEE Trans. Circuits Syst. Video Technol.","doi":"https://doi.org/10.1109/TCSVT.2024.3451981","numberOfCreators":7,"category":"journal","sources":["https://dblp.org/rec/journals/tcsv/LiWLGJHL25","https://doi.org/10.1109/TCSVT.2024.3451981"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/tcsv/LiWLGJHL25","documentUrl":null,"type":"Article"},{"key":"journals/tcsv/LiuZCZJZY25","url":"https://dblp.org/rec/journals/tcsv/LiuZCZJZY25","title":"Pyramid Learnable Bandpass Filters for Ultra-High-Definition Image Demoiréing.","year":2025,"types":["Article"],"venue":"IEEE Trans. Circuits Syst. Video Technol.","doi":"https://doi.org/10.1109/TCSVT.2025.3545898","numberOfCreators":7,"category":"journal","sources":["https://dblp.org/rec/journals/tcsv/LiuZCZJZY25","https://doi.org/10.1109/TCSVT.2025.3545898"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/tcsv/LiuZCZJZY25","documentUrl":null,"type":"Article"},{"key":"journals/tcsv/ZhangZCCZWLJY25","url":"https://dblp.org/rec/journals/tcsv/ZhangZCCZWLJY25","title":"Hierarchical Frequency-Based Upsampling and Refining for HEVC Compressed Video Enhancement.","year":2025,"types":["Article"],"venue":"IEEE Trans. Circuits Syst. Video Technol.","doi":"https://doi.org/10.1109/TCSVT.2024.3517840","numberOfCreators":9,"category":"journal","sources":["https://dblp.org/rec/journals/tcsv/ZhangZCCZWLJY25","https://doi.org/10.1109/TCSVT.2024.3517840"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/tcsv/ZhangZCCZWLJY25","documentUrl":null,"type":"Article"},{"key":"journals/tip/LiYYFJJRLZ25","url":"https://dblp.org/rec/journals/tip/LiYYFJJRLZ25","title":"Perception-Oriented Bidirectional Attention Network for Image Super-Resolution Quality Assessment.","year":2025,"types":["Article"],"venue":"IEEE Trans. Image Process.","doi":"https://doi.org/10.1109/TIP.2025.3633145","numberOfCreators":9,"category":"journal","sources":["https://dblp.org/rec/journals/tip/LiYYFJJRLZ25","https://doi.org/10.1109/TIP.2025.3633145"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/tip/LiYYFJJRLZ25","documentUrl":null,"type":"Article"},{"key":"journals/tip/WangLLCMLJ25","url":"https://dblp.org/rec/journals/tip/WangLLCMLJ25","title":"CharacterFactory: Sampling Consistent Characters With GANs for Diffusion Models.","year":2025,"types":["Article"],"venue":"IEEE Trans. Image Process.","doi":"https://doi.org/10.1109/TIP.2025.3558668","numberOfCreators":7,"category":"journal","sources":["https://dblp.org/rec/journals/tip/WangLLCMLJ25","https://doi.org/10.1109/TIP.2025.3558668"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/tip/WangLLCMLJ25","documentUrl":null,"type":"Article"},{"key":"journals/tmm/WangJLLMZL25","url":"https://dblp.org/rec/journals/tmm/WangJLLMZL25","title":"StableIdentity: Inserting Anybody Into Anywhere at First Sight.","year":2025,"types":["Article"],"venue":"IEEE Trans. Multim.","doi":"https://doi.org/10.1109/TMM.2025.3613113","numberOfCreators":7,"category":"journal","sources":["https://dblp.org/rec/journals/tmm/WangJLLMZL25","https://doi.org/10.1109/TMM.2025.3613113"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/tmm/WangJLLMZL25","documentUrl":null,"type":"Article"},{"key":"journals/tnn/ZhangJHWZLWLJ25","url":"https://dblp.org/rec/journals/tnn/ZhangJHWZLWLJ25","title":"Event-Assisted Recurrent Network for Arbitrary-Temporal-Scale Blurry Image Unfolding.","year":2025,"types":["Article"],"venue":"IEEE Trans. Neural Networks Learn. Syst.","doi":"https://doi.org/10.1109/TNNLS.2024.3459969","numberOfCreators":9,"category":"journal","sources":["https://dblp.org/rec/journals/tnn/ZhangJHWZLWLJ25","https://doi.org/10.1109/TNNLS.2024.3459969"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/tnn/ZhangJHWZLWLJ25","documentUrl":null,"type":"Article"}],"preprints":[{"key":"journals/corr/abs-2502-08639","url":"https://dblp.org/rec/journals/corr/abs-2502-08639","title":"CineMaster: A 3D-Aware and Controllable Framework for Cinematic Text-to-Video Generation.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2502.08639","numberOfCreators":10,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2502-08639","https://doi.org/10.48550/ARXIV.2502.08639"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2502-08639","documentUrl":null,"type":"Informal","arxivId":"2502.08639","arxivUrl":"https://arxiv.org/abs/2502.08639"},{"key":"journals/corr/abs-2503-23368","url":"https://dblp.org/rec/journals/corr/abs-2503-23368","title":"Towards Physically Plausible Video Generation via VLM Planning.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2503.23368","numberOfCreators":11,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2503-23368","https://doi.org/10.48550/ARXIV.2503.23368"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-23368","documentUrl":null,"type":"Informal","arxivId":"2503.23368","arxivUrl":"https://arxiv.org/abs/2503.23368"},{"key":"journals/corr/abs-2504-02402","url":"https://dblp.org/rec/journals/corr/abs-2504-02402","title":"EvMic: Event-based Non-contact sound recovery from effective spatial-temporal modeling.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2504.02402","numberOfCreators":9,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2504-02402","https://doi.org/10.48550/ARXIV.2504.02402"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2504-02402","documentUrl":null,"type":"Informal","arxivId":"2504.02402","arxivUrl":"https://arxiv.org/abs/2504.02402"},{"key":"journals/corr/abs-2505-19797","url":"https://dblp.org/rec/journals/corr/abs-2505-19797","title":"The Avengers: A Simple Recipe for Uniting Smaller Language Models to Challenge Proprietary Giants.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2505.19797","numberOfCreators":14,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2505-19797","https://doi.org/10.48550/ARXIV.2505.19797"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-19797","documentUrl":null,"type":"Informal","arxivId":"2505.19797","arxivUrl":"https://arxiv.org/abs/2505.19797"},{"key":"journals/corr/abs-2505-20469","url":"https://dblp.org/rec/journals/corr/abs-2505-20469","title":"CCL-LGS: Contrastive Codebook Learning for 3D Language Gaussian Splatting.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2505.20469","numberOfCreators":9,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2505-20469","https://doi.org/10.48550/ARXIV.2505.20469"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-20469","documentUrl":null,"type":"Informal","arxivId":"2505.20469","arxivUrl":"https://arxiv.org/abs/2505.20469"},{"key":"journals/corr/abs-2507-01735","url":"https://dblp.org/rec/journals/corr/abs-2507-01735","title":"ECCV 2024 W-CODA: 1st Workshop on Multimodal Perception and Comprehension of Corner Cases in Autonomous Driving.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2507.01735","numberOfCreators":14,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2507-01735","https://doi.org/10.48550/ARXIV.2507.01735"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2507-01735","documentUrl":null,"type":"Informal","arxivId":"2507.01735","arxivUrl":"https://arxiv.org/abs/2507.01735"},{"key":"journals/corr/abs-2507-16534","url":"https://dblp.org/rec/journals/corr/abs-2507-16534","title":"Frontier AI Risk Management Framework in Practice: A Risk Analysis Technical Report.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2507.16534","numberOfCreators":36,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2507-16534","https://doi.org/10.48550/ARXIV.2507.16534"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2507-16534","documentUrl":null,"type":"Informal","arxivId":"2507.16534","arxivUrl":"https://arxiv.org/abs/2507.16534"},{"key":"journals/corr/abs-2507-20745","url":"https://dblp.org/rec/journals/corr/abs-2507-20745","title":"Regularizing Subspace Redundancy of Low-Rank Adaptation.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2507.20745","numberOfCreators":11,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2507-20745","https://doi.org/10.48550/ARXIV.2507.20745"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2507-20745","documentUrl":null,"type":"Informal","arxivId":"2507.20745","arxivUrl":"https://arxiv.org/abs/2507.20745"},{"key":"journals/corr/abs-2508-11538","url":"https://dblp.org/rec/journals/corr/abs-2508-11538","title":"Reinforcing Video Reasoning Segmentation to Think Before It Segments.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2508.11538","numberOfCreators":6,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2508-11538","https://doi.org/10.48550/ARXIV.2508.11538"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-11538","documentUrl":null,"type":"Informal","arxivId":"2508.11538","arxivUrl":"https://arxiv.org/abs/2508.11538"},{"key":"journals/corr/abs-2509-06442","url":"https://dblp.org/rec/journals/corr/abs-2509-06442","title":"Perception-oriented Bidirectional Attention Network for Image Super-resolution Quality Assessment.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2509.06442","numberOfCreators":9,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2509-06442","https://doi.org/10.48550/ARXIV.2509.06442"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-06442","documentUrl":null,"type":"Informal","arxivId":"2509.06442","arxivUrl":"https://arxiv.org/abs/2509.06442"},{"key":"journals/corr/abs-2509-12046","url":"https://dblp.org/rec/journals/corr/abs-2509-12046","title":"Layout-Conditioned Autoregressive Text-to-Image Generation via Structured Masking.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2509.12046","numberOfCreators":14,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2509-12046","https://doi.org/10.48550/ARXIV.2509.12046"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-12046","documentUrl":null,"type":"Informal","arxivId":"2509.12046","arxivUrl":"https://arxiv.org/abs/2509.12046"},{"key":"journals/corr/abs-2510-25772","url":"https://dblp.org/rec/journals/corr/abs-2510-25772","title":"VFXMaster: Unlocking Dynamic Visual Effect Generation via In-Context Learning.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2510.25772","numberOfCreators":11,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2510-25772","https://doi.org/10.48550/ARXIV.2510.25772"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-25772","documentUrl":null,"type":"Informal","arxivId":"2510.25772","arxivUrl":"https://arxiv.org/abs/2510.25772"},{"key":"journals/corr/abs-2512-03041","url":"https://dblp.org/rec/journals/corr/abs-2512-03041","title":"MultiShotMaster: A Controllable Multi-Shot Video Generation Framework.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2512.03041","numberOfCreators":10,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2512-03041","https://doi.org/10.48550/ARXIV.2512.03041"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-03041","documentUrl":null,"type":"Informal","arxivId":"2512.03041","arxivUrl":"https://arxiv.org/abs/2512.03041"},{"key":"journals/corr/abs-2512-12324","url":"https://dblp.org/rec/journals/corr/abs-2512-12324","title":"UniMark: Artificial Intelligence Generated Content Identification Toolkit.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2512.12324","numberOfCreators":8,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2512-12324","https://doi.org/10.48550/ARXIV.2512.12324"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-12324","documentUrl":null,"type":"Informal","arxivId":"2512.12324","arxivUrl":"https://arxiv.org/abs/2512.12324"}],"excludedFormal":[],"otherRecords":[],"matchedName":"Xu Jia","databaseLabel":"Xu Jia 0012","databaseMetadata":{"type":["https://dblp.org/rdf/schema#Person","https://dblp.org/rdf/schema#Creator"],"label":["Xu Jia 0012"],"affiliation":["Dalian University of Technology, School of Artificial Intelligence and the School of Futher Technology, China","Huawei, Noah' Ark Lab","KU Leuven, Belgium"],"homepage":["https://stephenjia.github.io/"],"orcid":["https://orcid.org/0000-0003-3168-3505"],"primaryAffiliation":["Dalian University of Technology, School of Artificial Intelligence and the School of Futher Technology, China"],"primaryHomepage":["https://stephenjia.github.io/"]},"rawFormalRecordCount2025":19,"signatureAudit":{"completedAt":"2026-10-19","frozen":true,"scope":"对 B 组 39 个数值档案的全部 1074 条原始 2025 正式记录扫描 DBLP author-signature ORCID 和机构；复用既有 59 条 Crossref 核验，补查 6 条新触发记录。重点核查不同 ORCID，以及只有预期机构之外机构的条目。本轮不扩展为所有作者逐篇全文审计。","formalRecordCoverage":19,"orcidCounts":{"https://orcid.org/0000-0003-3168-3505":9},"institutionCounts":{"Dalian University of Technology (DUT)":19},"caveat":"机构名称可能由 DBLP 自动映射而失真；多 ORCID 也不自动等于异人。只有有原始资料支撑的错归才作确认排除，未解决分支则暂停总数。"},"labName":null,"labUrl":null,"labEvidence":"本人当前主页未明确命名实验室；Huawei Noah Ark、PSI/VISICS 等属于既往经历，不作为大连理工大学当前组。","labSourceUrl":"https://stephenjia.github.io/","sourceWarning":false,"excludedOther":[],"excludedHomonyms":[],"unassignedCandidates":[],"knownPreprintMinimum2025":null,"excludedMisattributed":[],"displayNotes":"身份已与原名单机构及公开资料核对确认。2025 年正式记录 19 条（会议 12、期刊 7），所有作者位置均计入，不表示主导或贡献份额；预印本 14 条单列，不加总。","labDisplayNotes":"本人主页未写当前组名；华为诺亚方舟实验室、PSI/VISICS 是既往经历，不采用。图中以「姓名及合作者」单列。"},{"index":49,"name":"Li Jiang","nameZh":"蒋理","role":"Assistant Professor","affiliation":"The Chinese University of Hong Kong, Shenzhen","affiliationZh":"香港中文大学（深圳）","source":"DBLP RDF via official SPARQL; primary-source identity checks","sourceUrl":"https://sparql.dblp.org/","profileUrl":"https://dblp.org/pid/45/4954-9.html","identifier":"45/4954-9","retrievedAt":"2026-10-19","count2025":10,"conference2025":9,"journal2025":1,"preprint2025":9,"status":"confirmed","notes":"","identityEvidence":[{"url":"https://dblp.org/pid/45/4954-9.html","evidence":"DBLP RDF 类型为 Person，消歧后名字为 Li Jiang 0009。机构元数据含：Max Planck Institute for Informatics, Saarbrücken, Germany；Chinese University of Hong Kong, Hong Kong；Chinese University of Hong Kong-Shenzhen (CUHK-SZ), Shenzhen, China"}],"papers":[{"key":"conf/aaai/XuLSLLGWJWSZJZC25","url":"https://dblp.org/rec/conf/aaai/XuLSLLGWJWSZJZC25","title":"LiON: Learning Point-Wise Abstaining Penalty for LiDAR Outlier DetectioN Using Diverse Synthetic Data.","year":2025,"types":["Inproceedings"],"venue":"AAAI","doi":"https://doi.org/10.1609/AAAI.V39I9.32968","eventYear":2025,"numberOfCreators":14,"category":"conference","sources":["https://dblp.org/rec/conf/aaai/XuLSLLGWJWSZJZC25","https://doi.org/10.1609/AAAI.V39I9.32968"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/aaai/XuLSLLGWJWSZJZC25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/cvpr/ChenS0SJL25","url":"https://dblp.org/rec/conf/cvpr/ChenS0SJL25","title":"JiSAM: Alleviate Labeling Burden and Corner Case Problems in Autonomous Driving via Minimal Real-World Data.","year":2025,"types":["Inproceedings"],"venue":"CVPR","doi":"https://doi.org/10.1109/CVPR52734.2025.00637","eventYear":2025,"numberOfCreators":6,"category":"conference","sources":["https://dblp.org/rec/conf/cvpr/ChenS0SJL25","https://doi.org/10.1109/CVPR52734.2025.00637"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/ChenS0SJL25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/eccv/DasHJS24","url":"https://dblp.org/rec/conf/eccv/DasHJS24","title":"MTA-CLIP: Language-Guided Semantic Segmentation with Mask-Text Alignment.","year":2025,"types":["Inproceedings"],"venue":"ECCV (54)","doi":"https://doi.org/10.1007/978-3-031-72949-2_3","eventYear":2024,"numberOfCreators":4,"category":"conference","sources":["https://dblp.org/rec/conf/eccv/DasHJS24","https://doi.org/10.1007/978-3-031-72949-2_3"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2024,"sourceUrl":"https://dblp.org/rec/conf/eccv/DasHJS24","documentUrl":null,"type":"Inproceedings"},{"key":"conf/eccv/WangTJSNLSW24","url":"https://dblp.org/rec/conf/eccv/WangTJSNLSW24","title":"GiT: Towards Generalist Vision Transformer Through Universal Language Interface.","year":2025,"types":["Inproceedings"],"venue":"ECCV (29)","doi":"https://doi.org/10.1007/978-3-031-73397-0_4","eventYear":2024,"numberOfCreators":8,"category":"conference","sources":["https://dblp.org/rec/conf/eccv/WangTJSNLSW24","https://doi.org/10.1007/978-3-031-73397-0_4"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2024,"sourceUrl":"https://dblp.org/rec/conf/eccv/WangTJSNLSW24","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iccv/HuangHSTJ25","url":"https://dblp.org/rec/conf/iccv/HuangHSTJ25","title":"Edit360: 2D Image Edits to 3D Assets From Any Angle.","year":2025,"types":["Inproceedings"],"venue":"ICCV","doi":"https://doi.org/10.1109/ICCV51701.2025.01543","eventYear":2025,"numberOfCreators":5,"category":"conference","sources":["https://dblp.org/rec/conf/iccv/HuangHSTJ25","https://doi.org/10.1109/ICCV51701.2025.01543"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/HuangHSTJ25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iccv/NingTSLHPJ25","url":"https://dblp.org/rec/conf/iccv/NingTSLHPJ25","title":"Enhancing Spatial Reasoning in Multimodal Large Language Models Through Reasoning-Based Segmentation.","year":2025,"types":["Inproceedings"],"venue":"ICCV","doi":"https://doi.org/10.1109/ICCV51701.2025.00736","eventYear":2025,"numberOfCreators":7,"category":"conference","sources":["https://dblp.org/rec/conf/iccv/NingTSLHPJ25","https://doi.org/10.1109/ICCV51701.2025.00736"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/NingTSLHPJ25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iccv/PengYJT25","url":"https://dblp.org/rec/conf/iccv/PengYJT25","title":"Mitigating Object Hallucinations via Sentence-Level Early Intervention.","year":2025,"types":["Inproceedings"],"venue":"ICCV","doi":"https://doi.org/10.1109/ICCV51701.2025.00067","eventYear":2025,"numberOfCreators":4,"category":"conference","sources":["https://dblp.org/rec/conf/iccv/PengYJT25","https://doi.org/10.1109/ICCV51701.2025.00067"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/PengYJT25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iccv/ShiSSZJ25","url":"https://dblp.org/rec/conf/iccv/ShiSSZJ25","title":"DriveX: Omni Scene Modeling for Learning Generalizable World Knowledge in Autonomous Driving.","year":2025,"types":["Inproceedings"],"venue":"ICCV","doi":"https://doi.org/10.1109/ICCV51701.2025.02656","eventYear":2025,"numberOfCreators":5,"category":"conference","sources":["https://dblp.org/rec/conf/iccv/ShiSSZJ25","https://doi.org/10.1109/ICCV51701.2025.02656"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/ShiSSZJ25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/siggrapha/ZhangSJXQS025","url":"https://dblp.org/rec/conf/siggrapha/ZhangSJXQS025","title":"Proteus-ID: ID-Consistent and Motion-Coherent Video Customization.","year":2025,"types":["Inproceedings"],"venue":"SIGGRAPH Asia","doi":"https://doi.org/10.1145/3757377.3763949","eventYear":2025,"numberOfCreators":7,"category":"conference","sources":["https://dblp.org/rec/conf/siggrapha/ZhangSJXQS025","https://doi.org/10.1145/3757377.3763949"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/siggrapha/ZhangSJXQS025","documentUrl":null,"type":"Inproceedings"},{"key":"journals/pami/WuZHXWJLW25","url":"https://dblp.org/rec/journals/pami/WuZHXWJLW25","title":"Unsupervised 3D Object Detection by Commonsense Clue.","year":2025,"types":["Article"],"venue":"IEEE Trans. Pattern Anal. Mach. Intell.","doi":"https://doi.org/10.1109/TPAMI.2025.3598341","numberOfCreators":8,"category":"journal","sources":["https://dblp.org/rec/journals/pami/WuZHXWJLW25","https://doi.org/10.1109/TPAMI.2025.3598341"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/pami/WuZHXWJLW25","documentUrl":null,"type":"Article"}],"preprints":[{"key":"journals/corr/abs-2503-08422","url":"https://dblp.org/rec/journals/corr/abs-2503-08422","title":"JiSAM: Alleviate Labeling Burden and Corner Case Problems in Autonomous Driving via Minimal Real-World Data.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2503.08422","numberOfCreators":6,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2503-08422","https://doi.org/10.48550/ARXIV.2503.08422"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-08422","documentUrl":null,"type":"Informal","arxivId":"2503.08422","arxivUrl":"https://arxiv.org/abs/2503.08422"},{"key":"journals/corr/abs-2505-19239","url":"https://dblp.org/rec/journals/corr/abs-2505-19239","title":"DriveX: Omni Scene Modeling for Learning Generalizable World Knowledge in Autonomous Driving.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2505.19239","numberOfCreators":5,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2505-19239","https://doi.org/10.48550/ARXIV.2505.19239"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-19239","documentUrl":null,"type":"Informal","arxivId":"2505.19239","arxivUrl":"https://arxiv.org/abs/2505.19239"},{"key":"journals/corr/abs-2506-10507","url":"https://dblp.org/rec/journals/corr/abs-2506-10507","title":"Edit360: 2D Image Edits to 3D Assets from Any Angle.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2506.10507","numberOfCreators":5,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2506-10507","https://doi.org/10.48550/ARXIV.2506.10507"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-10507","documentUrl":null,"type":"Informal","arxivId":"2506.10507","arxivUrl":"https://arxiv.org/abs/2506.10507"},{"key":"journals/corr/abs-2506-23120","url":"https://dblp.org/rec/journals/corr/abs-2506-23120","title":"Enhancing Spatial Reasoning in Multimodal Large Language Models through Reasoning-based Segmentation.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2506.23120","numberOfCreators":7,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2506-23120","https://doi.org/10.48550/ARXIV.2506.23120"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-23120","documentUrl":null,"type":"Informal","arxivId":"2506.23120","arxivUrl":"https://arxiv.org/abs/2506.23120"},{"key":"journals/corr/abs-2506-23729","url":"https://dblp.org/rec/journals/corr/abs-2506-23729","title":"Proteus-ID: ID-Consistent and Motion-Coherent Video Customization.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2506.23729","numberOfCreators":7,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2506-23729","https://doi.org/10.48550/ARXIV.2506.23729"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-23729","documentUrl":null,"type":"Informal","arxivId":"2506.23729","arxivUrl":"https://arxiv.org/abs/2506.23729"},{"key":"journals/corr/abs-2507-12455","url":"https://dblp.org/rec/journals/corr/abs-2507-12455","title":"Mitigating Object Hallucinations via Sentence-Level Early Intervention.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2507.12455","numberOfCreators":4,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2507-12455","https://doi.org/10.48550/ARXIV.2507.12455"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2507-12455","documentUrl":null,"type":"Informal","arxivId":"2507.12455","arxivUrl":"https://arxiv.org/abs/2507.12455"},{"key":"journals/corr/abs-2510-03198","url":"https://dblp.org/rec/journals/corr/abs-2510-03198","title":"Memory Forcing: Spatio-Temporal Memory for Consistent Scene Generation on Minecraft.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2510.03198","numberOfCreators":7,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2510-03198","https://doi.org/10.48550/ARXIV.2510.03198"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-03198","documentUrl":null,"type":"Informal","arxivId":"2510.03198","arxivUrl":"https://arxiv.org/abs/2510.03198"},{"key":"journals/corr/abs-2511-04595","url":"https://dblp.org/rec/journals/corr/abs-2511-04595","title":"UniSplat: Unified Spatio-Temporal Fusion via 3D Latent Scaffolds for Dynamic Driving Scene Reconstruction.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2511.04595","numberOfCreators":7,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2511-04595","https://doi.org/10.48550/ARXIV.2511.04595"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2511-04595","documentUrl":null,"type":"Informal","arxivId":"2511.04595","arxivUrl":"https://arxiv.org/abs/2511.04595"},{"key":"journals/corr/abs-2512-16811","url":"https://dblp.org/rec/journals/corr/abs-2512-16811","title":"GeoPredict: Leveraging Predictive Kinematics and 3D Gaussian Geometry for Precise VLA Manipulation.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2512.16811","numberOfCreators":7,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2512-16811","https://doi.org/10.48550/ARXIV.2512.16811"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-16811","documentUrl":null,"type":"Informal","arxivId":"2512.16811","arxivUrl":"https://arxiv.org/abs/2512.16811"}],"excludedFormal":[],"otherRecords":[],"matchedName":"Li Jiang","databaseLabel":"Li Jiang 0009","databaseMetadata":{"type":["https://dblp.org/rdf/schema#Creator","https://dblp.org/rdf/schema#Person"],"label":["Li Jiang 0009"],"affiliation":["Max Planck Institute for Informatics, Saarbrücken, Germany","Chinese University of Hong Kong, Hong Kong","Chinese University of Hong Kong-Shenzhen (CUHK-SZ), Shenzhen, China"],"homepage":["https://llijiang.github.io/"],"orcid":["https://orcid.org/0000-0001-7058-6957"],"primaryAffiliation":["Chinese University of Hong Kong-Shenzhen (CUHK-SZ), Shenzhen, China"],"primaryHomepage":["https://llijiang.github.io/"]},"rawFormalRecordCount2025":10,"signatureAudit":{"completedAt":"2026-10-19","frozen":true,"scope":"对 B 组 39 个数值档案的全部 1074 条原始 2025 正式记录扫描 DBLP author-signature ORCID 和机构；复用既有 59 条 Crossref 核验，补查 6 条新触发记录。重点核查不同 ORCID，以及只有预期机构之外机构的条目。本轮不扩展为所有作者逐篇全文审计。","formalRecordCoverage":10,"orcidCounts":{"https://orcid.org/0000-0001-7058-6957":2},"institutionCounts":{"Chinese University of Hong Kong (CUHK)":2,"Max Planck Institute for Informatics (MPI Informatik)":2,"The Chinese University of Hong Kong, Shenzhen (CUHK-SZ)":7},"caveat":"机构名称可能由 DBLP 自动映射而失真；多 ORCID 也不自动等于异人。只有有原始资料支撑的错归才作确认排除，未解决分支则暂停总数。"},"labName":null,"labUrl":null,"labEvidence":"本轮检查本人当前主页，确认香港中文大学（深圳）及上海创智学院关联，但未找到明确实验室名。","labSourceUrl":"https://llijiang.github.io/","sourceWarning":false,"excludedOther":[],"excludedHomonyms":[],"unassignedCandidates":[],"knownPreprintMinimum2025":null,"excludedMisattributed":[],"displayNotes":"身份已与原名单机构及公开资料核对确认。2025 年正式记录 10 条（会议 9、期刊 1），所有作者位置均计入；预印本 9 条单列，不加总。","labDisplayNotes":"本人主页确认其在港中文（深圳）与上海创智学院任职，但未见实验室名称；图中以「姓名及合作者」单列。"},{"index":50,"name":"Xiaojie Jin","nameZh":"靳潇杰","role":"Professor","affiliation":"Beijing Jiaotong University","affiliationZh":"北京交通大学","source":"DBLP RDF via official SPARQL; primary-source identity checks","sourceUrl":"https://sparql.dblp.org/","profileUrl":"https://dblp.org/pid/141/3317-4.html","identifier":"141/3317-4","retrievedAt":"2026-10-19","count2025":7,"conference2025":4,"journal2025":3,"preprint2025":9,"status":"confirmed","notes":"","identityEvidence":[{"url":"https://dblp.org/pid/141/3317-4.html","evidence":"DBLP RDF 类型为 Person，消歧后名字为 Xiaojie Jin 0004。机构元数据含：Beijing Jiaotong University, Beijing, China"},{"url":"https://api.crossref.org/works/10.1109/CVPR52734.2025.02703","evidence":"VideoWorld 的出版商 Crossref 数据列 Xiaojie Jin / ByteDance Seed；DBLP 将 Seed 映射到波兰大学是机构标签错误，不能据此判为异人。"},{"url":"https://faculty.bjtu.edu.cn/10327/","evidence":"北交大官方教师页确认靳潇杰为字节跳动美国研究院创始成员及技术负责人，现任北交大教授。"}],"papers":[{"key":"conf/cvpr/RenWG0KFJ25","url":"https://dblp.org/rec/conf/cvpr/RenWG0KFJ25","title":"VideoWorld: Exploring Knowledge Learning from Unlabeled Videos.","year":2025,"types":["Inproceedings"],"venue":"CVPR","doi":"https://doi.org/10.1109/CVPR52734.2025.02703","eventYear":2025,"numberOfCreators":7,"category":"conference","sources":["https://dblp.org/rec/conf/cvpr/RenWG0KFJ25","https://doi.org/10.1109/CVPR52734.2025.02703"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/RenWG0KFJ25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iccv/ZhangWTLFJ25","url":"https://dblp.org/rec/conf/iccv/ZhangWTLFJ25","title":"Flash-Vstream: Efficient Real-Time Understanding for Long Video Streams.","year":2025,"types":["Inproceedings"],"venue":"ICCV","doi":"https://doi.org/10.1109/ICCV51701.2025.01957","eventYear":2025,"numberOfCreators":6,"category":"conference","sources":["https://dblp.org/rec/conf/iccv/ZhangWTLFJ25","https://doi.org/10.1109/ICCV51701.2025.01957"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/ZhangWTLFJ25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/nips/DengYYAYJSC25","url":"https://dblp.org/rec/conf/nips/DengYYAYJSC25","title":"COCONut-PanCap: Joint Panoptic Segmentation and Grounded Captions for Fine-Grained Understanding and Generation.","year":2025,"types":["Inproceedings"],"venue":"NeurIPS","doi":null,"eventYear":2025,"numberOfCreators":8,"category":"conference","sources":["https://dblp.org/rec/conf/nips/DengYYAYJSC25"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/nips/DengYYAYJSC25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/nips/LinQHJJW25","url":"https://dblp.org/rec/conf/nips/LinQHJJW25","title":"A Unified Reasoning Framework for Holistic Zero-Shot Video Anomaly Analysis.","year":2025,"types":["Inproceedings"],"venue":"NeurIPS","doi":null,"eventYear":2025,"numberOfCreators":6,"category":"conference","sources":["https://dblp.org/rec/conf/nips/LinQHJJW25"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/nips/LinQHJJW25","documentUrl":null,"type":"Inproceedings"},{"key":"journals/pami/ZhangZJXYYW25","url":"https://dblp.org/rec/journals/pami/ZhangZJXYYW25","title":"Noise Self-Regression: A New Learning Paradigm to Enhance Low-Light Images Without Task-Related Data.","year":2025,"types":["Article"],"venue":"IEEE Trans. Pattern Anal. Mach. Intell.","doi":"https://doi.org/10.1109/TPAMI.2024.3487361","numberOfCreators":7,"category":"journal","sources":["https://dblp.org/rec/journals/pami/ZhangZJXYYW25","https://doi.org/10.1109/TPAMI.2024.3487361"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/pami/ZhangZJXYYW25","documentUrl":null,"type":"Article"},{"key":"journals/tmm/HeCMHJLFYLF25","url":"https://dblp.org/rec/journals/tmm/HeCMHJLFYLF25","title":"VLAB: Enhancing Video Language Pretraining by Feature Adapting and Blending.","year":2025,"types":["Article"],"venue":"IEEE Trans. Multim.","doi":"https://doi.org/10.1109/TMM.2024.3521729","numberOfCreators":10,"category":"journal","sources":["https://dblp.org/rec/journals/tmm/HeCMHJLFYLF25","https://doi.org/10.1109/TMM.2024.3521729"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/tmm/HeCMHJLFYLF25","documentUrl":null,"type":"Article"},{"key":"journals/tmm/WangZZJXW25","url":"https://dblp.org/rec/journals/tmm/WangZZJXW25","title":"SeaCap: Multi-Sight Embedding and Alignment for One-Stage Image Captioner.","year":2025,"types":["Article"],"venue":"IEEE Trans. Multim.","doi":"https://doi.org/10.1109/TMM.2025.3535303","numberOfCreators":6,"category":"journal","sources":["https://dblp.org/rec/journals/tmm/WangZZJXW25","https://doi.org/10.1109/TMM.2025.3535303"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/tmm/WangZZJXW25","documentUrl":null,"type":"Article"}],"preprints":[{"key":"journals/corr/abs-2501-09781","url":"https://dblp.org/rec/journals/corr/abs-2501-09781","title":"VideoWorld: Exploring Knowledge Learning from Unlabeled Videos.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2501.09781","numberOfCreators":7,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2501-09781","https://doi.org/10.48550/ARXIV.2501.09781"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2501-09781","documentUrl":null,"type":"Informal","arxivId":"2501.09781","arxivUrl":"https://arxiv.org/abs/2501.09781"},{"key":"journals/corr/abs-2502-02589","url":"https://dblp.org/rec/journals/corr/abs-2502-02589","title":"COCONut-PanCap: Joint Panoptic Segmentation and Grounded Captions for Fine-Grained Understanding and Generation.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2502.02589","numberOfCreators":8,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2502-02589","https://doi.org/10.48550/ARXIV.2502.02589"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2502-02589","documentUrl":null,"type":"Informal","arxivId":"2502.02589","arxivUrl":"https://arxiv.org/abs/2502.02589"},{"key":"journals/corr/abs-2504-15415","url":"https://dblp.org/rec/journals/corr/abs-2504-15415","title":"IV-Bench: A Benchmark for Image-Grounded Video Perception and Reasoning in Multimodal LLMs.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2504.15415","numberOfCreators":20,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2504-15415","https://doi.org/10.48550/ARXIV.2504.15415"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2504-15415","documentUrl":null,"type":"Informal","arxivId":"2504.15415","arxivUrl":"https://arxiv.org/abs/2504.15415"},{"key":"journals/corr/abs-2505-23155","url":"https://dblp.org/rec/journals/corr/abs-2505-23155","title":"PreFM: Online Audio-Visual Event Parsing via Predictive Future Modeling.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2505.23155","numberOfCreators":5,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2505-23155","https://doi.org/10.48550/ARXIV.2505.23155"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-23155","documentUrl":null,"type":"Informal","arxivId":"2505.23155","arxivUrl":"https://arxiv.org/abs/2505.23155"},{"key":"journals/corr/abs-2505-23922","url":"https://dblp.org/rec/journals/corr/abs-2505-23922","title":"ScaleLong: A Multi-Timescale Benchmark for Long Video Understanding.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2505.23922","numberOfCreators":19,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2505-23922","https://doi.org/10.48550/ARXIV.2505.23922"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-23922","documentUrl":null,"type":"Informal","arxivId":"2505.23922","arxivUrl":"https://arxiv.org/abs/2505.23922"},{"key":"journals/corr/abs-2506-23825","url":"https://dblp.org/rec/journals/corr/abs-2506-23825","title":"Flash-VStream: Efficient Real-Time Understanding for Long Video Streams.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2506.23825","numberOfCreators":6,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2506-23825","https://doi.org/10.48550/ARXIV.2506.23825"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-23825","documentUrl":null,"type":"Informal","arxivId":"2506.23825","arxivUrl":"https://arxiv.org/abs/2506.23825"},{"key":"journals/corr/abs-2509-24997","url":"https://dblp.org/rec/journals/corr/abs-2509-24997","title":"PanoWorld-X: Generating Explorable Panoramic Worlds via Sphere-Aware Video Diffusion.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2509.24997","numberOfCreators":10,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2509-24997","https://doi.org/10.48550/ARXIV.2509.24997"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-24997","documentUrl":null,"type":"Informal","arxivId":"2509.24997","arxivUrl":"https://arxiv.org/abs/2509.24997"},{"key":"journals/corr/abs-2511-00962","url":"https://dblp.org/rec/journals/corr/abs-2511-00962","title":"A Unified Reasoning Framework for Holistic Zero-Shot Video Anomaly Analysis.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2511.00962","numberOfCreators":6,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2511-00962","https://doi.org/10.48550/ARXIV.2511.00962"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2511-00962","documentUrl":null,"type":"Informal","arxivId":"2511.00962","arxivUrl":"https://arxiv.org/abs/2511.00962"},{"key":"journals/corr/abs-2512-09363","url":"https://dblp.org/rec/journals/corr/abs-2512-09363","title":"StereoWorld: Geometry-Aware Monocular-to-Stereo Video Generation.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2512.09363","numberOfCreators":11,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2512-09363","https://doi.org/10.48550/ARXIV.2512.09363"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-09363","documentUrl":null,"type":"Informal","arxivId":"2512.09363","arxivUrl":"https://arxiv.org/abs/2512.09363"}],"excludedFormal":[],"otherRecords":[],"matchedName":"Xiaojie Jin","databaseLabel":"Xiaojie Jin 0004","databaseMetadata":{"type":["https://dblp.org/rdf/schema#Person","https://dblp.org/rdf/schema#Creator"],"label":["Xiaojie Jin 0004"],"affiliation":["Beijing Jiaotong University, Beijing, China"],"orcid":["https://orcid.org/0000-0002-7850-1353"],"primaryAffiliation":["Beijing Jiaotong University, Beijing, China"]},"rawFormalRecordCount2025":7,"signatureAudit":{"completedAt":"2026-10-19","frozen":true,"scope":"对 B 组 39 个数值档案的全部 1074 条原始 2025 正式记录扫描 DBLP author-signature ORCID 和机构；复用既有 59 条 Crossref 核验，补查 6 条新触发记录。重点核查不同 ORCID，以及只有预期机构之外机构的条目。本轮不扩展为所有作者逐篇全文审计。","formalRecordCoverage":7,"orcidCounts":{"https://orcid.org/0000-0002-7850-1353":4},"institutionCounts":{"Beijing Jiaotong University (BJTU)":1,"Uniwersytet Przyrodniczo-Humanistyczny w Siedlcach":1},"caveat":"机构名称可能由 DBLP 自动映射而失真；多 ORCID 也不自动等于异人。只有有原始资料支撑的错归才作确认排除，未解决分支则暂停总数。","decision":{"decision":"retain","evidence":[{"url":"https://api.crossref.org/works/10.1109/CVPR52734.2025.02703","evidence":"VideoWorld 的出版商 Crossref 数据列 Xiaojie Jin / ByteDance Seed；DBLP 将 Seed 映射到波兰大学是机构标签错误，不能据此判为异人。"},{"url":"https://faculty.bjtu.edu.cn/10327/","evidence":"北交大官方教师页确认靳潇杰为字节跳动美国研究院创始成员及技术负责人，现任北交大教授。"}]}},"labName":null,"labUrl":null,"labEvidence":"北京交通大学本人教师页未明确实验室名称；学生页面提到共同指导及 WeiLab 不足以将其确认为本人的实验室。","labSourceUrl":"https://faculty.bjtu.edu.cn/10327/","sourceWarning":false,"excludedOther":[],"excludedHomonyms":[],"unassignedCandidates":[],"knownPreprintMinimum2025":null,"excludedMisattributed":[],"displayNotes":"身份已与原名单机构及公开资料核对确认。2025 年正式记录 7 条（会议 4、期刊 3），所有作者位置均计入；预印本 9 条单列，不加总。","labDisplayNotes":"北京交通大学本人教师页未写实验室名称；学生页面提到的共同指导与 WeiLab 不足以确认为其本人团队。图中以「姓名及合作者」单列。"},{"index":51,"name":"Chongxuan Li","nameZh":"李崇轩","role":"Associate Professor","affiliation":"Renmin University of China","affiliationZh":"中国人民大学","source":"DBLP RDF via official SPARQL; primary-source identity checks","sourceUrl":"https://sparql.dblp.org/","profileUrl":"https://dblp.org/pid/161/9965.html","identifier":"161/9965","retrievedAt":"2026-10-19","count2025":20,"conference2025":17,"journal2025":3,"preprint2025":22,"status":"confirmed","notes":"","identityEvidence":[{"url":"https://dblp.org/pid/161/9965.html","evidence":"DBLP RDF 类型为 Person，消歧后名字为 Chongxuan Li。此档案未提供可用机构元数据，以下以本人/机构/出版商来源补证。"},{"url":"https://zhenxuan00.github.io/","evidence":"个人主页为中国人民大学 Chongxuan Li，论文标题与 DBLP 记录匹配。"},{"url":"https://zhenxuan00.github.io/","evidence":"此本人或机构页面的正文与所选档案中 20 条 2025 记录标题匹配，其中 11 条为当前计入的正式记录（忽略空格、标点、大小写）。","matchedPaperKeys":["conf/eccv/WangWCXCYLSZ24","conf/iccv/ZhongYTGL25","conf/iclr/LiuDP0LX25","conf/iclr/NieZDPLZLL25","conf/iclr/OuNXZSLL25","conf/icml/WangZZLW25","conf/icml/YouOZH0L25","conf/icml/ZhaoHCZLZ25","conf/nips/NieZYZOHZLWL25","conf/nips/ZhengZWHTHZL25","journals/corr/abs-2502-09992","journals/corr/abs-2502-14583","journals/corr/abs-2502-15894","journals/corr/abs-2503-07197","journals/corr/abs-2503-13265","journals/corr/abs-2503-14151","journals/corr/abs-2505-15270","journals/corr/abs-2505-16933","journals/corr/abs-2505-19223","journals/tmlr/GuDPLL025"],"matchedFormalPaperKeys":["conf/eccv/WangWCXCYLSZ24","conf/iccv/ZhongYTGL25","conf/iclr/LiuDP0LX25","conf/iclr/NieZDPLZLL25","conf/iclr/OuNXZSLL25","conf/icml/WangZZLW25","conf/icml/YouOZH0L25","conf/icml/ZhaoHCZLZ25","conf/nips/NieZYZOHZLWL25","conf/nips/ZhengZWHTHZL25","journals/tmlr/GuDPLL025"]}],"papers":[{"key":"conf/cvpr/WangSL0LW0XW25","url":"https://dblp.org/rec/conf/cvpr/WangSL0LW0XW25","title":"Animate and Sound an Image.","year":2025,"types":["Inproceedings"],"venue":"CVPR","doi":"https://doi.org/10.1109/CVPR52734.2025.02176","eventYear":2025,"numberOfCreators":9,"category":"conference","sources":["https://dblp.org/rec/conf/cvpr/WangSL0LW0XW25","https://doi.org/10.1109/CVPR52734.2025.02176"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/WangSL0LW0XW25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/cvpr/You0G0L25","url":"https://dblp.org/rec/conf/cvpr/You0G0L25","title":"Are Images Indistinguishable to Humans Also Indistinguishable to Classifiers?","year":2025,"types":["Inproceedings"],"venue":"CVPR","doi":"https://doi.org/10.1109/CVPR52734.2025.02681","eventYear":2025,"numberOfCreators":5,"category":"conference","sources":["https://dblp.org/rec/conf/cvpr/You0G0L25","https://doi.org/10.1109/CVPR52734.2025.02681"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/You0G0L25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/eccv/WangWCXCYLSZ24","url":"https://dblp.org/rec/conf/eccv/WangWCXCYLSZ24","title":"CRM: Single Image to 3D Textured Mesh with Convolutional Reconstruction Model.","year":2025,"types":["Inproceedings"],"venue":"ECCV (31)","doi":"https://doi.org/10.1007/978-3-031-72751-1_4","eventYear":2024,"numberOfCreators":9,"category":"conference","sources":["https://dblp.org/rec/conf/eccv/WangWCXCYLSZ24","https://doi.org/10.1007/978-3-031-72751-1_4"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2024,"sourceUrl":"https://dblp.org/rec/conf/eccv/WangWCXCYLSZ24","documentUrl":null,"type":"Inproceedings"},{"key":"conf/eccv/ZhangLW24a","url":"https://dblp.org/rec/conf/eccv/ZhangLW24a","title":"Solving Inverse Problem with Unspecified Forward Operator Using Diffusion Models.","year":2025,"types":["Inproceedings"],"venue":"ECCV Workshops (9)","doi":"https://doi.org/10.1007/978-3-031-91838-4_18","eventYear":2024,"numberOfCreators":3,"category":"conference","sources":["https://dblp.org/rec/conf/eccv/ZhangLW24a","https://doi.org/10.1007/978-3-031-91838-4_18"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2024,"sourceUrl":"https://dblp.org/rec/conf/eccv/ZhangLW24a","documentUrl":null,"type":"Inproceedings"},{"key":"conf/eccv/ZhaoDYLDW24","url":"https://dblp.org/rec/conf/eccv/ZhaoDYLDW24","title":"Lost in Translation: Latent Concept Misalignment in Text-to-Image Diffusion Models.","year":2025,"types":["Inproceedings"],"venue":"ECCV (69)","doi":"https://doi.org/10.1007/978-3-031-72890-7_19","eventYear":2024,"numberOfCreators":6,"category":"conference","sources":["https://dblp.org/rec/conf/eccv/ZhaoDYLDW24","https://doi.org/10.1007/978-3-031-72890-7_19"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2024,"sourceUrl":"https://dblp.org/rec/conf/eccv/ZhaoDYLDW24","documentUrl":null,"type":"Inproceedings"},{"key":"conf/eccv/ZhongZYYZL24","url":"https://dblp.org/rec/conf/eccv/ZhongZYYZL24","title":"PoseCrafter: One-Shot Personalized Video Synthesis Following Flexible Pose Control.","year":2025,"types":["Inproceedings"],"venue":"ECCV (44)","doi":"https://doi.org/10.1007/978-3-031-72784-9_14","eventYear":2024,"numberOfCreators":6,"category":"conference","sources":["https://dblp.org/rec/conf/eccv/ZhongZYYZL24","https://doi.org/10.1007/978-3-031-72784-9_14"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2024,"sourceUrl":"https://dblp.org/rec/conf/eccv/ZhongZYYZL24","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iccv/ZhongYTGL25","url":"https://dblp.org/rec/conf/iccv/ZhongYTGL25","title":"Concat-ID: Towards Universal Identity-Preserving Video Synthesis.","year":2025,"types":["Inproceedings"],"venue":"ICCVW","doi":"https://doi.org/10.1109/ICCVW69036.2025.00202","eventYear":2025,"numberOfCreators":5,"category":"conference","sources":["https://dblp.org/rec/conf/iccv/ZhongYTGL25","https://doi.org/10.1109/ICCVW69036.2025.00202"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/ZhongYTGL25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iclr/LiuDP0LX25","url":"https://dblp.org/rec/conf/iclr/LiuDP0LX25","title":"Improving Long-Text Alignment for Text-to-Image Diffusion Models.","year":2025,"types":["Inproceedings"],"venue":"ICLR","doi":null,"eventYear":2025,"numberOfCreators":6,"category":"conference","sources":["https://dblp.org/rec/conf/iclr/LiuDP0LX25"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iclr/LiuDP0LX25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iclr/NieZDPLZLL25","url":"https://dblp.org/rec/conf/iclr/NieZDPLZLL25","title":"Scaling up Masked Diffusion Models on Text.","year":2025,"types":["Inproceedings"],"venue":"ICLR","doi":null,"eventYear":2025,"numberOfCreators":8,"category":"conference","sources":["https://dblp.org/rec/conf/iclr/NieZDPLZLL25"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iclr/NieZDPLZLL25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iclr/OuNXZSLL25","url":"https://dblp.org/rec/conf/iclr/OuNXZSLL25","title":"Your Absorbing Discrete Diffusion Secretly Models the Conditional Distributions of Clean Data.","year":2025,"types":["Inproceedings"],"venue":"ICLR","doi":null,"eventYear":2025,"numberOfCreators":7,"category":"conference","sources":["https://dblp.org/rec/conf/iclr/OuNXZSLL25"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iclr/OuNXZSLL25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/icml/WangZZLW25","url":"https://dblp.org/rec/conf/icml/WangZZLW25","title":"A Theory for Conditional Generative Modeling on Multiple Data Sources.","year":2025,"types":["Inproceedings"],"venue":"ICML","doi":null,"eventYear":2025,"numberOfCreators":5,"category":"conference","sources":["https://dblp.org/rec/conf/icml/WangZZLW25"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/icml/WangZZLW25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/icml/YouOZH0L25","url":"https://dblp.org/rec/conf/icml/YouOZH0L25","title":"Effective and Efficient Masked Image Generation Models.","year":2025,"types":["Inproceedings"],"venue":"ICML","doi":null,"eventYear":2025,"numberOfCreators":6,"category":"conference","sources":["https://dblp.org/rec/conf/icml/YouOZH0L25"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/icml/YouOZH0L25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/icml/ZhaoHCZLZ25","url":"https://dblp.org/rec/conf/icml/ZhaoHCZLZ25","title":"RIFLEx: A Free Lunch for Length Extrapolation in Video Diffusion Transformers.","year":2025,"types":["Inproceedings"],"venue":"ICML","doi":null,"eventYear":2025,"numberOfCreators":6,"category":"conference","sources":["https://dblp.org/rec/conf/icml/ZhaoHCZLZ25"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/icml/ZhaoHCZLZ25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/nips/ChenNSFLWL25","url":"https://dblp.org/rec/conf/nips/ChenNSFLWL25","title":"Masked Diffusion Models as Energy Minimization.","year":2025,"types":["Inproceedings"],"venue":"NeurIPS","doi":null,"eventYear":2025,"numberOfCreators":7,"category":"conference","sources":["https://dblp.org/rec/conf/nips/ChenNSFLWL25"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/nips/ChenNSFLWL25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/nips/ChenZZWZHSWL25","url":"https://dblp.org/rec/conf/nips/ChenZZWZHSWL25","title":"FlexWorld: Progressively Expanding 3D Scenes for Flexible-View Exploration.","year":2025,"types":["Inproceedings"],"venue":"NeurIPS","doi":null,"eventYear":2025,"numberOfCreators":9,"category":"conference","sources":["https://dblp.org/rec/conf/nips/ChenZZWZHSWL25"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/nips/ChenZZWZHSWL25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/nips/NieZYZOHZLWL25","url":"https://dblp.org/rec/conf/nips/NieZYZOHZLWL25","title":"Large Language Diffusion Models.","year":2025,"types":["Inproceedings"],"venue":"NeurIPS","doi":null,"eventYear":2025,"numberOfCreators":10,"category":"conference","sources":["https://dblp.org/rec/conf/nips/NieZYZOHZLWL25"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/nips/NieZYZOHZLWL25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/nips/ZhengZWHTHZL25","url":"https://dblp.org/rec/conf/nips/ZhengZWHTHZL25","title":"Scaling Diffusion Transformers Efficiently via μP.","year":2025,"types":["Inproceedings"],"venue":"NeurIPS","doi":null,"eventYear":2025,"numberOfCreators":8,"category":"conference","sources":["https://dblp.org/rec/conf/nips/ZhengZWHTHZL25"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/nips/ZhengZWHTHZL25","documentUrl":null,"type":"Inproceedings"},{"key":"journals/chinaf/ZhaoWBLZ25","url":"https://dblp.org/rec/journals/chinaf/ZhaoWBLZ25","title":"ControlVideo: conditional control for one-shot text-driven video editing and beyond.","year":2025,"types":["Article"],"venue":"Sci. China Inf. Sci.","doi":"https://doi.org/10.1007/S11432-023-4184-4","numberOfCreators":5,"category":"journal","sources":["https://dblp.org/rec/journals/chinaf/ZhaoWBLZ25","https://doi.org/10.1007/S11432-023-4184-4"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/chinaf/ZhaoWBLZ25","documentUrl":null,"type":"Article"},{"key":"journals/ijautcomp/LuZBCLZ25","url":"https://dblp.org/rec/journals/ijautcomp/LuZBCLZ25","title":"DPM-Solver++: Fast Solver for Guided Sampling of Diffusion Probabilistic Models.","year":2025,"types":["Article"],"venue":"Mach. Intell. Res.","doi":"https://doi.org/10.1007/S11633-025-1562-4","numberOfCreators":6,"category":"journal","sources":["https://dblp.org/rec/journals/ijautcomp/LuZBCLZ25","https://doi.org/10.1007/S11633-025-1562-4"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/ijautcomp/LuZBCLZ25","documentUrl":null,"type":"Article"},{"key":"journals/tmlr/GuDPLL025","url":"https://dblp.org/rec/journals/tmlr/GuDPLL025","title":"On Memorization in Diffusion Models.","year":2025,"types":["Article"],"venue":"Trans. Mach. Learn. Res.","doi":null,"numberOfCreators":6,"category":"journal","sources":["https://dblp.org/rec/journals/tmlr/GuDPLL025"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/tmlr/GuDPLL025","documentUrl":null,"type":"Article"}],"preprints":[{"key":"journals/corr/abs-2502-09992","url":"https://dblp.org/rec/journals/corr/abs-2502-09992","title":"Large Language Diffusion Models.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2502.09992","numberOfCreators":10,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2502-09992","https://doi.org/10.48550/ARXIV.2502.09992"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2502-09992","documentUrl":null,"type":"Informal","arxivId":"2502.09992","arxivUrl":"https://arxiv.org/abs/2502.09992"},{"key":"journals/corr/abs-2502-14583","url":"https://dblp.org/rec/journals/corr/abs-2502-14583","title":"A Theory for Conditional Generative Modeling on Multiple Data Sources.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2502.14583","numberOfCreators":5,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2502-14583","https://doi.org/10.48550/ARXIV.2502.14583"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2502-14583","documentUrl":null,"type":"Informal","arxivId":"2502.14583","arxivUrl":"https://arxiv.org/abs/2502.14583"},{"key":"journals/corr/abs-2502-15894","url":"https://dblp.org/rec/journals/corr/abs-2502-15894","title":"RIFLEx: A Free Lunch for Length Extrapolation in Video Diffusion Transformers.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2502.15894","numberOfCreators":6,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2502-15894","https://doi.org/10.48550/ARXIV.2502.15894"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2502-15894","documentUrl":null,"type":"Informal","arxivId":"2502.15894","arxivUrl":"https://arxiv.org/abs/2502.15894"},{"key":"journals/corr/abs-2503-07197","url":"https://dblp.org/rec/journals/corr/abs-2503-07197","title":"Effective and Efficient Masked Image Generation Models.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2503.07197","numberOfCreators":6,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2503-07197","https://doi.org/10.48550/ARXIV.2503.07197"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-07197","documentUrl":null,"type":"Informal","arxivId":"2503.07197","arxivUrl":"https://arxiv.org/abs/2503.07197"},{"key":"journals/corr/abs-2503-13265","url":"https://dblp.org/rec/journals/corr/abs-2503-13265","title":"FlexWorld: Progressively Expanding 3D Scenes for Flexiable-View Synthesis.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2503.13265","numberOfCreators":9,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2503-13265","https://doi.org/10.48550/ARXIV.2503.13265"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-13265","documentUrl":null,"type":"Informal","arxivId":"2503.13265","arxivUrl":"https://arxiv.org/abs/2503.13265"},{"key":"journals/corr/abs-2503-14151","url":"https://dblp.org/rec/journals/corr/abs-2503-14151","title":"Concat-ID: Towards Universal Identity-Preserving Video Synthesis.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2503.14151","numberOfCreators":5,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2503-14151","https://doi.org/10.48550/ARXIV.2503.14151"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-14151","documentUrl":null,"type":"Informal","arxivId":"2503.14151","arxivUrl":"https://arxiv.org/abs/2503.14151"},{"key":"journals/corr/abs-2505-15270","url":"https://dblp.org/rec/journals/corr/abs-2505-15270","title":"Scaling Diffusion Transformers Efficiently via μP.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2505.15270","numberOfCreators":8,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2505-15270","https://doi.org/10.48550/ARXIV.2505.15270"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-15270","documentUrl":null,"type":"Informal","arxivId":"2505.15270","arxivUrl":"https://arxiv.org/abs/2505.15270"},{"key":"journals/corr/abs-2505-16933","url":"https://dblp.org/rec/journals/corr/abs-2505-16933","title":"LLaDA-V: Large Language Diffusion Models with Visual Instruction Tuning.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2505.16933","numberOfCreators":8,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2505-16933","https://doi.org/10.48550/ARXIV.2505.16933"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-16933","documentUrl":null,"type":"Informal","arxivId":"2505.16933","arxivUrl":"https://arxiv.org/abs/2505.16933"},{"key":"journals/corr/abs-2505-19223","url":"https://dblp.org/rec/journals/corr/abs-2505-19223","title":"LLaDA 1.5: Variance-Reduced Preference Optimization for Large Language Diffusion Models.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2505.19223","numberOfCreators":11,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2505-19223","https://doi.org/10.48550/ARXIV.2505.19223"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-19223","documentUrl":null,"type":"Informal","arxivId":"2505.19223","arxivUrl":"https://arxiv.org/abs/2505.19223"},{"key":"journals/corr/abs-2505-21493","url":"https://dblp.org/rec/journals/corr/abs-2505-21493","title":"Reinforcing General Reasoning without Verifiers.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2505.21493","numberOfCreators":9,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2505-21493","https://doi.org/10.48550/ARXIV.2505.21493"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-21493","documentUrl":null,"type":"Informal","arxivId":"2505.21493","arxivUrl":"https://arxiv.org/abs/2505.21493"},{"key":"journals/corr/abs-2507-06203","url":"https://dblp.org/rec/journals/corr/abs-2507-06203","title":"A Survey on Latent Reasoning.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2507.06203","numberOfCreators":33,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2507-06203","https://doi.org/10.48550/ARXIV.2507.06203"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2507-06203","documentUrl":null,"type":"Informal","arxivId":"2507.06203","arxivUrl":"https://arxiv.org/abs/2507.06203"},{"key":"journals/corr/abs-2509-13866","url":"https://dblp.org/rec/journals/corr/abs-2509-13866","title":"Masked Diffusion Models as Energy Minimization.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2509.13866","numberOfCreators":7,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2509-13866","https://doi.org/10.48550/ARXIV.2509.13866"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-13866","documentUrl":null,"type":"Informal","arxivId":"2509.13866","arxivUrl":"https://arxiv.org/abs/2509.13866"},{"key":"journals/corr/abs-2509-22637","url":"https://dblp.org/rec/journals/corr/abs-2509-22637","title":"Variational Reasoning for Language Models.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2509.22637","numberOfCreators":8,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2509-22637","https://doi.org/10.48550/ARXIV.2509.22637"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-22637","documentUrl":null,"type":"Informal","arxivId":"2509.22637","arxivUrl":"https://arxiv.org/abs/2509.22637"},{"key":"journals/corr/abs-2509-24389","url":"https://dblp.org/rec/journals/corr/abs-2509-24389","title":"LLaDA-MoE: A Sparse MoE Diffusion Language Model.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2509.24389","numberOfCreators":26,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2509-24389","https://doi.org/10.48550/ARXIV.2509.24389"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-24389","documentUrl":null,"type":"Informal","arxivId":"2509.24389","arxivUrl":"https://arxiv.org/abs/2509.24389"},{"key":"journals/corr/abs-2510-10481","url":"https://dblp.org/rec/journals/corr/abs-2510-10481","title":"UltraLLaDA: Scaling the Context Length to 128K for Diffusion Large Language Models.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2510.10481","numberOfCreators":9,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2510-10481","https://doi.org/10.48550/ARXIV.2510.10481"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-10481","documentUrl":null,"type":"Informal","arxivId":"2510.10481","arxivUrl":"https://arxiv.org/abs/2510.10481"},{"key":"journals/corr/abs-2511-06254","url":"https://dblp.org/rec/journals/corr/abs-2511-06254","title":"LLaDA-Rec: Discrete Diffusion for Parallel Semantic ID Generation in Generative Recommendation.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2511.06254","numberOfCreators":9,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2511-06254","https://doi.org/10.48550/ARXIV.2511.06254"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2511-06254","documentUrl":null,"type":"Informal","arxivId":"2511.06254","arxivUrl":"https://arxiv.org/abs/2511.06254"},{"key":"journals/corr/abs-2511-10690","url":"https://dblp.org/rec/journals/corr/abs-2511-10690","title":"Saying the Unsaid: Revealing the Hidden Language of Multimodal Systems Through Telephone Games.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2511.10690","numberOfCreators":4,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2511-10690","https://doi.org/10.48550/ARXIV.2511.10690"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2511-10690","documentUrl":null,"type":"Informal","arxivId":"2511.10690","arxivUrl":"https://arxiv.org/abs/2511.10690"},{"key":"journals/corr/abs-2511-20123","url":"https://dblp.org/rec/journals/corr/abs-2511-20123","title":"UltraViCo: Breaking Extrapolation Limits in Video Diffusion Transformers.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2511.20123","numberOfCreators":9,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2511-20123","https://doi.org/10.48550/ARXIV.2511.20123"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2511-20123","documentUrl":null,"type":"Informal","arxivId":"2511.20123","arxivUrl":"https://arxiv.org/abs/2511.20123"},{"key":"journals/corr/abs-2512-03759","url":"https://dblp.org/rec/journals/corr/abs-2512-03759","title":"Principled RL for Diffusion LLMs Emerges from a Sequence-Level Perspective.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2512.03759","numberOfCreators":8,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2512-03759","https://doi.org/10.48550/ARXIV.2512.03759"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-03759","documentUrl":null,"type":"Informal","arxivId":"2512.03759","arxivUrl":"https://arxiv.org/abs/2512.03759"},{"key":"journals/corr/abs-2512-04504","url":"https://dblp.org/rec/journals/corr/abs-2512-04504","title":"UltraImage: Rethinking Resolution Extrapolation in Image Diffusion Transformers.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2512.04504","numberOfCreators":8,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2512-04504","https://doi.org/10.48550/ARXIV.2512.04504"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-04504","documentUrl":null,"type":"Informal","arxivId":"2512.04504","arxivUrl":"https://arxiv.org/abs/2512.04504"},{"key":"journals/corr/abs-2512-13586","url":"https://dblp.org/rec/journals/corr/abs-2512-13586","title":"ReFusion: A Diffusion Large Language Model with Parallel Autoregressive Decoding.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2512.13586","numberOfCreators":4,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2512-13586","https://doi.org/10.48550/ARXIV.2512.13586"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-13586","documentUrl":null,"type":"Informal","arxivId":"2512.13586","arxivUrl":"https://arxiv.org/abs/2512.13586"},{"key":"journals/corr/abs-2512-15745","url":"https://dblp.org/rec/journals/corr/abs-2512-15745","title":"LLaDA2.0: Scaling Up Diffusion Language Models to 100B.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2512.15745","numberOfCreators":31,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2512-15745","https://doi.org/10.48550/ARXIV.2512.15745"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-15745","documentUrl":null,"type":"Informal","arxivId":"2512.15745","arxivUrl":"https://arxiv.org/abs/2512.15745"}],"excludedFormal":[],"otherRecords":[],"matchedName":"Chongxuan Li","databaseLabel":"Chongxuan Li","databaseMetadata":{"type":["https://dblp.org/rdf/schema#Creator","https://dblp.org/rdf/schema#Person"],"label":["Chongxuan Li"]},"rawFormalRecordCount2025":20,"signatureAudit":{"completedAt":"2026-10-19","frozen":true,"scope":"对 B 组 39 个数值档案的全部 1074 条原始 2025 正式记录扫描 DBLP author-signature ORCID 和机构；复用既有 59 条 Crossref 核验，补查 6 条新触发记录。重点核查不同 ORCID，以及只有预期机构之外机构的条目。本轮不扩展为所有作者逐篇全文审计。","formalRecordCoverage":20,"orcidCounts":{"https://orcid.org/0000-0002-0912-9076":3},"institutionCounts":{"Beijing Institute of Big Data Research (BIBDR)":1,"Renmin University of China (RUC)":9},"caveat":"机构名称可能由 DBLP 自动映射而失真；多 ORCID 也不自动等于异人。只有有原始资料支撑的错归才作确认排除，未解决分支则暂停总数。"},"labName":"Machine Learning Group (GSAI-ML)","labUrl":"https://github.com/ML-GSAI","labEvidence":"本人主页在姓名与现任职信息旁标明 Machine Learning Group (GSAI-ML)，并给出 GSAI-ML GitHub；后文列本组学生。未采用其博士阶段访问的 AMLab。","labSourceUrl":"https://zhenxuan00.github.io/","sourceWarning":false,"excludedOther":[],"excludedHomonyms":[],"unassignedCandidates":[],"knownPreprintMinimum2025":null,"excludedMisattributed":[],"displayNotes":"身份已与原名单机构及公开资料核对确认。2025 年正式记录 20 条（会议 17、期刊 3），所有作者位置均计入，不表示主导或贡献份额；预印本 22 条单列，不加总。","labDisplayNotes":"个人主页在现任职信息旁标明 Machine Learning Group（GSAI-ML），给出 GitHub 并列出本组学生；不采用博士阶段访问过的 AMLab。"},{"index":52,"name":"Guanbin Li","nameZh":"李冠彬","role":"Professor","affiliation":"Sun Yat-sen University","affiliationZh":"中山大学","source":"DBLP RDF via official SPARQL; primary-source identity checks","sourceUrl":"https://sparql.dblp.org/","profileUrl":"https://dblp.org/pid/126/4457.html","identifier":"126/4457","retrievedAt":"2026-10-19","count2025":48,"conference2025":32,"journal2025":16,"preprint2025":33,"status":"matched_with_source_warning","notes":"排除 2 条数据库形式上属于期刊/会议的记录，逐条原因见 excludedFormal。 DBLP HTML 页面提示 ID conflict found in this bibliography（ORCID 冲突）；作者身份与学校/个人来源相符，但应与普通已确认记录分开展示。","identityEvidence":[{"url":"https://dblp.org/pid/126/4457.html","evidence":"DBLP RDF 类型为 Person，消歧后名字为 Guanbin Li。此档案未提供可用机构元数据，以下以本人/机构/出版商来源补证。"},{"url":"https://guanbinli.com/","evidence":"个人主页为中山大学 Guanbin Li / 李冠彬。"},{"url":"https://guanbinli.com/pb-list.html","evidence":"完整个人发表列表与 DBLP 2025 正式记录中的 38 条标题匹配；其余 12 条补查出版商提供的 Crossref 作者信息、原文或出版商页面。"},{"url":"https://link.springer.com/article/10.1007/s00371-025-04195-y","evidence":"GaPTalk 出版商页面明确 Guanbin Li 为 Sun Yat-sen University，通讯邮箱 liguanbin@mail.sysu.edu.cn。"},{"url":"https://ojs.aaai.org/index.php/AAAI/article/download/28179/28356","evidence":"AAAI 2024 原文同时列 Guanbin Li 的中山大学单位与 liguanbin@cuhk.edu.cn 邮箱，支持其跨机构合作身份；并非仅因 CUHK-Shenzhen 邮箱便排除。"},{"url":"https://guanbinli.com/pb-list.html","evidence":"此本人或机构页面的正文与所选档案中 57 条 2025 记录标题匹配，其中 38 条为当前计入的正式记录（忽略空格、标点、大小写）。","matchedPaperKeys":["conf/aaai/LengFCFLL25","conf/aaai/WuJLFQL25","conf/cvpr/HeNQWYLL25","conf/cvpr/LaiZQRWL25","conf/cvpr/LuoLCLWLL25","conf/cvpr/SongCL0LL25","conf/cvpr/YuanPRLH0ZLCL25","conf/cvpr/ZhuangKBLL25","conf/cvpr/ZhuSWTW0LY25","conf/eccv/HeCWLTL24","conf/eccv/WangCCZLZL24","conf/eccv/ZhangLZLWTLDWL24","conf/iccv/CaiLLCLXLL25","conf/iccv/HuangYCLWWWL25","conf/iccv/HuangYLWWWLL25","conf/iccv/JiangLCLCPLL25","conf/iccv/LiLCCLLL25","conf/iccv/LiYXBTSXJLZ25","conf/iccv/TangWZSLLY25","conf/iccv/WangZXZLLLZL25","conf/iccv/WangZZTLWL25","conf/iccv/YeGLCC25","conf/iccv/ZhangXZCTWL25","conf/iccv/ZhangZTYWLL25","conf/icml/HeJ0ZHLD25","conf/ijcai/ChenLHL0CF25","conf/ijcai/FangMLC0L25","conf/mm/MoCFL25","conf/nips/LiLCML25","journals/corr/abs-2503-03190","journals/corr/abs-2503-11117","journals/corr/abs-2503-12165","journals/corr/abs-2503-12838","journals/corr/abs-2503-23024","journals/corr/abs-2504-04687","journals/corr/abs-2504-08291","journals/corr/abs-2505-18612","journals/corr/abs-2506-17712","journals/corr/abs-2507-07831","journals/corr/abs-2508-02134","journals/corr/abs-2508-08252","journals/corr/abs-2509-23867","journals/corr/abs-2510-25237","journals/corr/abs-2511-06253","journals/corr/abs-2511-06256","journals/corr/abs-2511-06272","journals/corr/abs-2511-17217","journals/corr/abs-2512-14601","journals/pami/ZhangLXGTSHL25","journals/tip/ChenFLLL25","journals/tip/ChenLWZLLL25","journals/titb/DuJTLLLW25","journals/tkde/LiuCZCLL25","journals/tmi/HuangGZWWLLS25","journals/tmm/HeCZWLLL25","journals/tnn/LiuLLWLL25","journals/visintelligence/XieCZL25"],"matchedFormalPaperKeys":["conf/aaai/LengFCFLL25","conf/aaai/WuJLFQL25","conf/cvpr/HeNQWYLL25","conf/cvpr/LaiZQRWL25","conf/cvpr/LuoLCLWLL25","conf/cvpr/SongCL0LL25","conf/cvpr/YuanPRLH0ZLCL25","conf/cvpr/ZhuangKBLL25","conf/cvpr/ZhuSWTW0LY25","conf/eccv/HeCWLTL24","conf/eccv/WangCCZLZL24","conf/eccv/ZhangLZLWTLDWL24","conf/iccv/CaiLLCLXLL25","conf/iccv/HuangYCLWWWL25","conf/iccv/HuangYLWWWLL25","conf/iccv/JiangLCLCPLL25","conf/iccv/LiLCCLLL25","conf/iccv/LiYXBTSXJLZ25","conf/iccv/TangWZSLLY25","conf/iccv/WangZXZLLLZL25","conf/iccv/WangZZTLWL25","conf/iccv/YeGLCC25","conf/iccv/ZhangXZCTWL25","conf/iccv/ZhangZTYWLL25","conf/icml/HeJ0ZHLD25","conf/ijcai/ChenLHL0CF25","conf/ijcai/FangMLC0L25","conf/mm/MoCFL25","conf/nips/LiLCML25","journals/pami/ZhangLXGTSHL25","journals/tip/ChenFLLL25","journals/tip/ChenLWZLLL25","journals/titb/DuJTLLLW25","journals/tkde/LiuCZCLL25","journals/tmi/HuangGZWWLLS25","journals/tmm/HeCZWLLL25","journals/tnn/LiuLLWLL25","journals/visintelligence/XieCZL25"]}],"papers":[{"key":"conf/aaai/LengFCFLL25","url":"https://dblp.org/rec/conf/aaai/LengFCFLL25","title":"Bridging Knowledge Gap Between Image Inpainting and Large-Area Visible Watermark Removal.","year":2025,"types":["Inproceedings"],"venue":"AAAI","doi":"https://doi.org/10.1609/AAAI.V39I5.32484","eventYear":2025,"numberOfCreators":6,"category":"conference","sources":["https://dblp.org/rec/conf/aaai/LengFCFLL25","https://doi.org/10.1609/AAAI.V39I5.32484"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/aaai/LengFCFLL25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/aaai/WuJLFQL25","url":"https://dblp.org/rec/conf/aaai/WuJLFQL25","title":"Hierarchically Controlled Deformable 3D Gaussians for Talking Head Synthesis.","year":2025,"types":["Inproceedings"],"venue":"AAAI","doi":"https://doi.org/10.1609/AAAI.V39I8.32921","eventYear":2025,"numberOfCreators":6,"category":"conference","sources":["https://dblp.org/rec/conf/aaai/WuJLFQL25","https://doi.org/10.1609/AAAI.V39I8.32921"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/aaai/WuJLFQL25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/cvpr/HeNQWYLL25","url":"https://dblp.org/rec/conf/cvpr/HeNQWYLL25","title":"VTON 360: High-Fidelity Virtual Try-On from Any Viewing Direction.","year":2025,"types":["Inproceedings"],"venue":"CVPR","doi":"https://doi.org/10.1109/CVPR52734.2025.02457","eventYear":2025,"numberOfCreators":7,"category":"conference","sources":["https://dblp.org/rec/conf/cvpr/HeNQWYLL25","https://doi.org/10.1109/CVPR52734.2025.02457"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/HeNQWYLL25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/cvpr/LaiZQRWL25","url":"https://dblp.org/rec/conf/cvpr/LaiZQRWL25","title":"LLM-driven Multimodal and Multi-Identity Listening Head Generation.","year":2025,"types":["Inproceedings"],"venue":"CVPR","doi":"https://doi.org/10.1109/CVPR52734.2025.00996","eventYear":2025,"numberOfCreators":6,"category":"conference","sources":["https://dblp.org/rec/conf/cvpr/LaiZQRWL25","https://doi.org/10.1109/CVPR52734.2025.00996"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/LaiZQRWL25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/cvpr/LuoLCLWLL25","url":"https://dblp.org/rec/conf/cvpr/LuoLCLWLL25","title":"DSPNet: Dual-vision Scene Perception for Robust 3D Question Answering.","year":2025,"types":["Inproceedings"],"venue":"CVPR","doi":"https://doi.org/10.1109/CVPR52734.2025.01322","eventYear":2025,"numberOfCreators":7,"category":"conference","sources":["https://dblp.org/rec/conf/cvpr/LuoLCLWLL25","https://doi.org/10.1109/CVPR52734.2025.01322"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/LuoLCLWLL25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/cvpr/SongCL0LL25","url":"https://dblp.org/rec/conf/cvpr/SongCL0LL25","title":"Towards Long-Horizon Vision-Language Navigation: Platform, Benchmark and Method.","year":2025,"types":["Inproceedings"],"venue":"CVPR","doi":"https://doi.org/10.1109/CVPR52734.2025.01128","eventYear":2025,"numberOfCreators":6,"category":"conference","sources":["https://dblp.org/rec/conf/cvpr/SongCL0LL25","https://doi.org/10.1109/CVPR52734.2025.01128"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/SongCL0LL25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/cvpr/YuanPRLH0ZLCL25","url":"https://dblp.org/rec/conf/cvpr/YuanPRLH0ZLCL25","title":"Empowering Large Language Models with 3D Situation Awareness.","year":2025,"types":["Inproceedings"],"venue":"CVPR","doi":"https://doi.org/10.1109/CVPR52734.2025.01810","eventYear":2025,"numberOfCreators":10,"category":"conference","sources":["https://dblp.org/rec/conf/cvpr/YuanPRLH0ZLCL25","https://doi.org/10.1109/CVPR52734.2025.01810"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/YuanPRLH0ZLCL25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/cvpr/ZhuSWTW0LY25","url":"https://dblp.org/rec/conf/cvpr/ZhuSWTW0LY25","title":"Rethinking Query-based Transformer for Continual Image Segmentation.","year":2025,"types":["Inproceedings"],"venue":"CVPR","doi":"https://doi.org/10.1109/CVPR52734.2025.00433","eventYear":2025,"numberOfCreators":8,"category":"conference","sources":["https://dblp.org/rec/conf/cvpr/ZhuSWTW0LY25","https://doi.org/10.1109/CVPR52734.2025.00433"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/ZhuSWTW0LY25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/cvpr/ZhuangKBLL25","url":"https://dblp.org/rec/conf/cvpr/ZhuangKBLL25","title":"DAGSM: Disentangled Avatar Generation with GS-enhanced Mesh.","year":2025,"types":["Inproceedings"],"venue":"CVPR","doi":"https://doi.org/10.1109/CVPR52734.2025.00036","eventYear":2025,"numberOfCreators":5,"category":"conference","sources":["https://dblp.org/rec/conf/cvpr/ZhuangKBLL25","https://doi.org/10.1109/CVPR52734.2025.00036"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/ZhuangKBLL25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/eccv/HeCWLTL24","url":"https://dblp.org/rec/conf/eccv/HeCWLTL24","title":"WildVidFit: Video Virtual Try-On in the Wild via Image-Based Controlled Diffusion Models.","year":2025,"types":["Inproceedings"],"venue":"ECCV (17)","doi":"https://doi.org/10.1007/978-3-031-72643-9_8","eventYear":2024,"numberOfCreators":6,"category":"conference","sources":["https://dblp.org/rec/conf/eccv/HeCWLTL24","https://doi.org/10.1007/978-3-031-72643-9_8"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2024,"sourceUrl":"https://dblp.org/rec/conf/eccv/HeCWLTL24","documentUrl":null,"type":"Inproceedings"},{"key":"conf/eccv/WangCCZLZL24","url":"https://dblp.org/rec/conf/eccv/WangCCZLZL24","title":"MarvelOVD: Marrying Object Recognition and Vision-Language Models for Robust Open-Vocabulary Object Detection.","year":2025,"types":["Inproceedings"],"venue":"ECCV (17)","doi":"https://doi.org/10.1007/978-3-031-72643-9_7","eventYear":2024,"numberOfCreators":7,"category":"conference","sources":["https://dblp.org/rec/conf/eccv/WangCCZLZL24","https://doi.org/10.1007/978-3-031-72643-9_7"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2024,"sourceUrl":"https://dblp.org/rec/conf/eccv/WangCCZLZL24","documentUrl":null,"type":"Inproceedings"},{"key":"conf/eccv/ZhangLZLWTLDWL24","url":"https://dblp.org/rec/conf/eccv/ZhangLZLWTLDWL24","title":"Interactive 3D Object Detection with Prompts.","year":2025,"types":["Inproceedings"],"venue":"ECCV (17)","doi":"https://doi.org/10.1007/978-3-031-72643-9_9","eventYear":2024,"numberOfCreators":10,"category":"conference","sources":["https://dblp.org/rec/conf/eccv/ZhangLZLWTLDWL24","https://doi.org/10.1007/978-3-031-72643-9_9"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2024,"sourceUrl":"https://dblp.org/rec/conf/eccv/ZhangLZLWTLDWL24","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iccv/CaiLLCLXLL25","url":"https://dblp.org/rec/conf/iccv/CaiLLCLXLL25","title":"DeepShield: Fortifying Deepfake Video Detection with Local and Global Forgery Analysis.","year":2025,"types":["Inproceedings"],"venue":"ICCV","doi":"https://doi.org/10.1109/ICCV51701.2025.01164","eventYear":2025,"numberOfCreators":8,"category":"conference","sources":["https://dblp.org/rec/conf/iccv/CaiLLCLXLL25","https://doi.org/10.1109/ICCV51701.2025.01164"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/CaiLLCLXLL25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iccv/HuangYCLWWWL25","url":"https://dblp.org/rec/conf/iccv/HuangYCLWWWL25","title":"DreamLayer: Simultaneous Multi-Layer Generation via Diffusion Model.","year":2025,"types":["Inproceedings"],"venue":"ICCV","doi":"https://doi.org/10.1109/ICCV51701.2025.00321","eventYear":2025,"numberOfCreators":8,"category":"conference","sources":["https://dblp.org/rec/conf/iccv/HuangYCLWWWL25","https://doi.org/10.1109/ICCV51701.2025.00321"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/HuangYCLWWWL25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iccv/HuangYLWWWLL25","url":"https://dblp.org/rec/conf/iccv/HuangYLWWWLL25","title":"DreamFuse: Adaptive Image Fusion with Diffusion Transformer.","year":2025,"types":["Inproceedings"],"venue":"ICCV","doi":"https://doi.org/10.1109/ICCV51701.2025.01606","eventYear":2025,"numberOfCreators":8,"category":"conference","sources":["https://dblp.org/rec/conf/iccv/HuangYLWWWLL25","https://doi.org/10.1109/ICCV51701.2025.01606"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/HuangYLWWWLL25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iccv/JiangLCLCPLL25","url":"https://dblp.org/rec/conf/iccv/JiangLCLCPLL25","title":"Beyond the Destination: A Novel Benchmark for Exploration-Aware Embodied Question Answering.","year":2025,"types":["Inproceedings"],"venue":"ICCV","doi":"https://doi.org/10.1109/ICCV51701.2025.00850","eventYear":2025,"numberOfCreators":8,"category":"conference","sources":["https://dblp.org/rec/conf/iccv/JiangLCLCPLL25","https://doi.org/10.1109/ICCV51701.2025.00850"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/JiangLCLCPLL25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iccv/LiLCCLLL25","url":"https://dblp.org/rec/conf/iccv/LiLCCLLL25","title":"FakeRadar: Probing Forgery Outliers to Detect Unknown Deepfake Videos.","year":2025,"types":["Inproceedings"],"venue":"ICCV","doi":"https://doi.org/10.1109/ICCV51701.2025.01243","eventYear":2025,"numberOfCreators":7,"category":"conference","sources":["https://dblp.org/rec/conf/iccv/LiLCCLLL25","https://doi.org/10.1109/ICCV51701.2025.01243"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/LiLCCLLL25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iccv/LiYXBTSXJLZ25","url":"https://dblp.org/rec/conf/iccv/LiYXBTSXJLZ25","title":"GlassWizard: Harvesting Diffusion Priors for Glass Surface Detection.","year":2025,"types":["Inproceedings"],"venue":"ICCV","doi":"https://doi.org/10.1109/ICCV51701.2025.01658","eventYear":2025,"numberOfCreators":10,"category":"conference","sources":["https://dblp.org/rec/conf/iccv/LiYXBTSXJLZ25","https://doi.org/10.1109/ICCV51701.2025.01658"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/LiYXBTSXJLZ25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iccv/TangWZSLLY25","url":"https://dblp.org/rec/conf/iccv/TangWZSLLY25","title":"Sim-DETR: Unlock DETR for Temporal Sentence Grounding.","year":2025,"types":["Inproceedings"],"venue":"ICCV","doi":"https://doi.org/10.1109/ICCV51701.2025.02113","eventYear":2025,"numberOfCreators":7,"category":"conference","sources":["https://dblp.org/rec/conf/iccv/TangWZSLLY25","https://doi.org/10.1109/ICCV51701.2025.02113"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/TangWZSLLY25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iccv/WangZXZLLLZL25","url":"https://dblp.org/rec/conf/iccv/WangZXZLLLZL25","title":"Free-Moref: Instantly Multiplexing Context Perception Capabilities of Video-Mllms Within Single Inference.","year":2025,"types":["Inproceedings"],"venue":"ICCV","doi":"https://doi.org/10.1109/ICCV51701.2025.02089","eventYear":2025,"numberOfCreators":9,"category":"conference","sources":["https://dblp.org/rec/conf/iccv/WangZXZLLLZL25","https://doi.org/10.1109/ICCV51701.2025.02089"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/WangZXZLLLZL25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iccv/WangZZTLWL25","url":"https://dblp.org/rec/conf/iccv/WangZZTLWL25","title":"LaneDiffusion: Improving Centerline Graph Learning via Prior Injected BEV Feature Generation.","year":2025,"types":["Inproceedings"],"venue":"ICCV","doi":"https://doi.org/10.1109/ICCV51701.2025.02511","eventYear":2025,"numberOfCreators":7,"category":"conference","sources":["https://dblp.org/rec/conf/iccv/WangZZTLWL25","https://doi.org/10.1109/ICCV51701.2025.02511"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/WangZZTLWL25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iccv/YeGLCC25","url":"https://dblp.org/rec/conf/iccv/YeGLCC25","title":"GeoSplatting: Towards Geometry Guided Gaussian Splatting for Physically-Based Inverse Rendering.","year":2025,"types":["Inproceedings"],"venue":"ICCV","doi":"https://doi.org/10.1109/ICCV51701.2025.02692","eventYear":2025,"numberOfCreators":5,"category":"conference","sources":["https://dblp.org/rec/conf/iccv/YeGLCC25","https://doi.org/10.1109/ICCV51701.2025.02692"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/YeGLCC25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iccv/ZhangXZCTWL25","url":"https://dblp.org/rec/conf/iccv/ZhangXZCTWL25","title":"Adadrive: Self-Adaptive Slow-Fast System for Language-Grounded Autonomous Driving.","year":2025,"types":["Inproceedings"],"venue":"ICCV","doi":"https://doi.org/10.1109/ICCV51701.2025.00486","eventYear":2025,"numberOfCreators":7,"category":"conference","sources":["https://dblp.org/rec/conf/iccv/ZhangXZCTWL25","https://doi.org/10.1109/ICCV51701.2025.00486"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/ZhangXZCTWL25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iccv/ZhangZTYWLL25","url":"https://dblp.org/rec/conf/iccv/ZhangZTYWLL25","title":"VLDrive: Vision-Augmented Lightweight MLLMs for Efficient Language-Grounded Autonomous Driving.","year":2025,"types":["Inproceedings"],"venue":"ICCV","doi":"https://doi.org/10.1109/ICCV51701.2025.00560","eventYear":2025,"numberOfCreators":7,"category":"conference","sources":["https://dblp.org/rec/conf/iccv/ZhangZTYWLL25","https://doi.org/10.1109/ICCV51701.2025.00560"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/ZhangZTYWLL25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/icmcs/TanML25","url":"https://dblp.org/rec/conf/icmcs/TanML25","title":"NeRFSwap: A NeRF-Based Generative Model for Face Swapping.","year":2025,"types":["Inproceedings"],"venue":"ICME","doi":"https://doi.org/10.1109/ICME59968.2025.11210190","eventYear":2025,"numberOfCreators":3,"category":"conference","sources":["https://dblp.org/rec/conf/icmcs/TanML25","https://doi.org/10.1109/ICME59968.2025.11210190"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/icmcs/TanML25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/icml/HeJ0ZHLD25","url":"https://dblp.org/rec/conf/icml/HeJ0ZHLD25","title":"ReferSplat: Referring Segmentation in 3D Gaussian Splatting.","year":2025,"types":["Inproceedings"],"venue":"ICML","doi":null,"eventYear":2025,"numberOfCreators":7,"category":"conference","sources":["https://dblp.org/rec/conf/icml/HeJ0ZHLD25"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/icml/HeJ0ZHLD25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/ijcai/ChenLHL0CF25","url":"https://dblp.org/rec/conf/ijcai/ChenLHL0CF25","title":"Pseudo-Label Reconstruction for Partial Multi-Label Learning.","year":2025,"types":["Inproceedings"],"venue":"IJCAI","doi":"https://doi.org/10.24963/IJCAI.2025/545","eventYear":2025,"numberOfCreators":7,"category":"conference","sources":["https://dblp.org/rec/conf/ijcai/ChenLHL0CF25","https://doi.org/10.24963/IJCAI.2025/545"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/ijcai/ChenLHL0CF25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/ijcai/FangMLC0L25","url":"https://dblp.org/rec/conf/ijcai/FangMLC0L25","title":"Screening, Rectifying, and Re-Screening: A Unified Framework for Tuning Vision-Language Models with Noisy Labels.","year":2025,"types":["Inproceedings"],"venue":"IJCAI","doi":"https://doi.org/10.24963/IJCAI.2025/568","eventYear":2025,"numberOfCreators":6,"category":"conference","sources":["https://dblp.org/rec/conf/ijcai/FangMLC0L25","https://doi.org/10.24963/IJCAI.2025/568"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/ijcai/FangMLC0L25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/isbi/CaiFGMSL25","url":"https://dblp.org/rec/conf/isbi/CaiFGMSL25","title":"BoxPolypSAM: Leveraging SAM in Box-Supervised Polyp Segmentation.","year":2025,"types":["Inproceedings"],"venue":"ISBI","doi":"https://doi.org/10.1109/ISBI60581.2025.10980797","eventYear":2025,"numberOfCreators":6,"category":"conference","sources":["https://dblp.org/rec/conf/isbi/CaiFGMSL25","https://doi.org/10.1109/ISBI60581.2025.10980797"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/isbi/CaiFGMSL25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/mm/MoCFL25","url":"https://dblp.org/rec/conf/mm/MoCFL25","title":"PatchWiper: Leveraging Dynamic Patch-Wise Parameters for Real-World Visible Watermark Removal.","year":2025,"types":["Inproceedings"],"venue":"ACM Multimedia","doi":"https://doi.org/10.1145/3746027.3755107","eventYear":2025,"numberOfCreators":4,"category":"conference","sources":["https://dblp.org/rec/conf/mm/MoCFL25","https://doi.org/10.1145/3746027.3755107"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/mm/MoCFL25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/mm/WeiL0CLLL25","url":"https://dblp.org/rec/conf/mm/WeiL0CLLL25","title":"3DAffordSplat: Efficient Affordance Reasoning with 3D Gaussians.","year":2025,"types":["Inproceedings"],"venue":"ACM Multimedia","doi":"https://doi.org/10.1145/3746027.3754778","eventYear":2025,"numberOfCreators":7,"category":"conference","sources":["https://dblp.org/rec/conf/mm/WeiL0CLLL25","https://doi.org/10.1145/3746027.3754778"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/mm/WeiL0CLLL25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/nips/LiLCML25","url":"https://dblp.org/rec/conf/nips/LiLCML25","title":"GUIDED: Granular Understanding via Identification, Detection, and Discrimination for Fine-Grained Open-Vocabulary Object Detection.","year":2025,"types":["Inproceedings"],"venue":"NeurIPS","doi":null,"eventYear":2025,"numberOfCreators":5,"category":"conference","sources":["https://dblp.org/rec/conf/nips/LiLCML25"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/nips/LiLCML25","documentUrl":null,"type":"Inproceedings"},{"key":"journals/kbs/JiLLLW25","url":"https://dblp.org/rec/journals/kbs/JiLLLW25","title":"Sparse diffusion models for multi-annotator medical image segmentation.","year":2025,"types":["Article"],"venue":"Knowl. Based Syst.","doi":"https://doi.org/10.1016/J.KNOSYS.2025.114783","numberOfCreators":5,"category":"journal","sources":["https://dblp.org/rec/journals/kbs/JiLLLW25","https://doi.org/10.1016/J.KNOSYS.2025.114783"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/kbs/JiLLLW25","documentUrl":null,"type":"Article"},{"key":"journals/pami/ZhangLXGTSHL25","url":"https://dblp.org/rec/journals/pami/ZhangLXGTSHL25","title":"OffsetNet: Towards Efficient Multiple Object Tracking, Detection, and Segmentation.","year":2025,"types":["Article"],"venue":"IEEE Trans. Pattern Anal. Mach. Intell.","doi":"https://doi.org/10.1109/TPAMI.2024.3485644","numberOfCreators":8,"category":"journal","sources":["https://dblp.org/rec/journals/pami/ZhangLXGTSHL25","https://doi.org/10.1109/TPAMI.2024.3485644"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/pami/ZhangLXGTSHL25","documentUrl":null,"type":"Article"},{"key":"journals/pr/JiaLZLSLL25","url":"https://dblp.org/rec/journals/pr/JiaLZLSLL25","title":"Enhancing out-of-distribution detection via diversified multi-prototype contrastive learning.","year":2025,"types":["Article"],"venue":"Pattern Recognit.","doi":"https://doi.org/10.1016/J.PATCOG.2024.111214","numberOfCreators":7,"category":"journal","sources":["https://dblp.org/rec/journals/pr/JiaLZLSLL25","https://doi.org/10.1016/J.PATCOG.2024.111214"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/pr/JiaLZLSLL25","documentUrl":null,"type":"Article"},{"key":"journals/tip/ChenFLLL25","url":"https://dblp.org/rec/journals/tip/ChenFLLL25","title":"Decouple and Couple: Exploiting Prior Knowledge for Visible Video Watermark Removal.","year":2025,"types":["Article"],"venue":"IEEE Trans. Image Process.","doi":"https://doi.org/10.1109/TIP.2025.3534033","numberOfCreators":5,"category":"journal","sources":["https://dblp.org/rec/journals/tip/ChenFLLL25","https://doi.org/10.1109/TIP.2025.3534033"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/tip/ChenFLLL25","documentUrl":null,"type":"Article"},{"key":"journals/tip/ChenLWZLLL25","url":"https://dblp.org/rec/journals/tip/ChenLWZLLL25","title":"Cross-Modal Causal Representation Learning for Radiology Report Generation.","year":2025,"types":["Article"],"venue":"IEEE Trans. Image Process.","doi":"https://doi.org/10.1109/TIP.2025.3568746","numberOfCreators":7,"category":"journal","sources":["https://dblp.org/rec/journals/tip/ChenLWZLLL25","https://doi.org/10.1109/TIP.2025.3568746"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/tip/ChenLWZLLL25","documentUrl":null,"type":"Article"},{"key":"journals/titb/DuJTLLLW25","url":"https://dblp.org/rec/journals/titb/DuJTLLLW25","title":"Highlighted Diffusion Model as Plug-In Priors for Polyp Segmentation.","year":2025,"types":["Article"],"venue":"IEEE J. Biomed. Health Informatics","doi":"https://doi.org/10.1109/JBHI.2024.3485767","numberOfCreators":7,"category":"journal","sources":["https://dblp.org/rec/journals/titb/DuJTLLLW25","https://doi.org/10.1109/JBHI.2024.3485767"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/titb/DuJTLLLW25","documentUrl":null,"type":"Article"},{"key":"journals/tkde/LiuCZCLL25","url":"https://dblp.org/rec/journals/tkde/LiuCZCLL25","title":"ODMixer: Fine-Grained Spatial-Temporal MLP for Metro Origin-Destination Prediction.","year":2025,"types":["Article"],"venue":"IEEE Trans. Knowl. Data Eng.","doi":"https://doi.org/10.1109/TKDE.2025.3579370","numberOfCreators":6,"category":"journal","sources":["https://dblp.org/rec/journals/tkde/LiuCZCLL25","https://doi.org/10.1109/TKDE.2025.3579370"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/tkde/LiuCZCLL25","documentUrl":null,"type":"Article"},{"key":"journals/tmi/HuangGZWWLLS25","url":"https://dblp.org/rec/journals/tmi/HuangGZWWLLS25","title":"BCNet: Bronchus Classification via Structure Guided Representation Learning.","year":2025,"types":["Article"],"venue":"IEEE Trans. Medical Imaging","doi":"https://doi.org/10.1109/TMI.2024.3448468","numberOfCreators":8,"category":"journal","sources":["https://dblp.org/rec/journals/tmi/HuangGZWWLLS25","https://doi.org/10.1109/TMI.2024.3448468"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/tmi/HuangGZWWLLS25","documentUrl":null,"type":"Article"},{"key":"journals/tmi/LouLLLXWW25","url":"https://dblp.org/rec/journals/tmi/LouLLLXWW25","title":"Instance-Aware Multi-Task Learning for Nuclei Segmentation.","year":2025,"types":["Article"],"venue":"IEEE Trans. Medical Imaging","doi":"https://doi.org/10.1109/TMI.2025.3583014","numberOfCreators":7,"category":"journal","sources":["https://dblp.org/rec/journals/tmi/LouLLLXWW25","https://doi.org/10.1109/TMI.2025.3583014"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/tmi/LouLLLXWW25","documentUrl":null,"type":"Article"},{"key":"journals/tmm/HeCZWLLL25","url":"https://dblp.org/rec/journals/tmm/HeCZWLLL25","title":"Efficient and Robust Video Virtual Try-On via Enhanced Multi-Garment Alignment.","year":2025,"types":["Article"],"venue":"IEEE Trans. Multim.","doi":"https://doi.org/10.1109/TMM.2025.3613169","numberOfCreators":7,"category":"journal","sources":["https://dblp.org/rec/journals/tmm/HeCZWLLL25","https://doi.org/10.1109/TMM.2025.3613169"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/tmm/HeCZWLLL25","documentUrl":null,"type":"Article"},{"key":"journals/tmm/LiLGLL25","url":"https://dblp.org/rec/journals/tmm/LiLGLL25","title":"S4R: Rethinking Point Cloud Sampling via Guiding Upsampling-Aware Perception.","year":2025,"types":["Article"],"venue":"IEEE Trans. Multim.","doi":"https://doi.org/10.1109/TMM.2025.3586148","numberOfCreators":5,"category":"journal","sources":["https://dblp.org/rec/journals/tmm/LiLGLL25","https://doi.org/10.1109/TMM.2025.3586148"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/tmm/LiLGLL25","documentUrl":null,"type":"Article"},{"key":"journals/tnn/LiCZHL25","url":"https://dblp.org/rec/journals/tnn/LiCZHL25","title":"DSFedCon: Dynamic Sparse Federated Contrastive Learning for Data-Driven Intelligent Systems.","year":2025,"types":["Article"],"venue":"IEEE Trans. Neural Networks Learn. Syst.","doi":"https://doi.org/10.1109/TNNLS.2024.3349400","numberOfCreators":5,"category":"journal","sources":["https://dblp.org/rec/journals/tnn/LiCZHL25","https://doi.org/10.1109/TNNLS.2024.3349400"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/tnn/LiCZHL25","documentUrl":null,"type":"Article"},{"key":"journals/tnn/LiuLLWLL25","url":"https://dblp.org/rec/journals/tnn/LiuLLWLL25","title":"Road Network-Guided Fine-Grained Urban Traffic Flow Inference.","year":2025,"types":["Article"],"venue":"IEEE Trans. Neural Networks Learn. Syst.","doi":"https://doi.org/10.1109/TNNLS.2023.3327386","numberOfCreators":6,"category":"journal","sources":["https://dblp.org/rec/journals/tnn/LiuLLWLL25","https://doi.org/10.1109/TNNLS.2023.3327386"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/tnn/LiuLLWLL25","documentUrl":null,"type":"Article"},{"key":"journals/tvcg/ZhangYZYWLWCL25","url":"https://dblp.org/rec/journals/tvcg/ZhangYZYWLWCL25","title":"GSmoothFace: Generalized Smooth Talking Face Generation via Fine Grained 3D Face Guidance.","year":2025,"types":["Article"],"venue":"IEEE Trans. Vis. Comput. Graph.","doi":"https://doi.org/10.1109/TVCG.2025.3566382","numberOfCreators":9,"category":"journal","sources":["https://dblp.org/rec/journals/tvcg/ZhangYZYWLWCL25","https://doi.org/10.1109/TVCG.2025.3566382"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/tvcg/ZhangYZYWLWCL25","documentUrl":null,"type":"Article"},{"key":"journals/vc/HuangLTCL25","url":"https://dblp.org/rec/journals/vc/HuangLTCL25","title":"GaPTalk: precision-controlled 3D Gaussian rendering for personalized talking-head synthesis.","year":2025,"types":["Article"],"venue":"Vis. Comput.","doi":"https://doi.org/10.1007/S00371-025-04195-Y","numberOfCreators":5,"category":"journal","sources":["https://dblp.org/rec/journals/vc/HuangLTCL25","https://doi.org/10.1007/S00371-025-04195-Y"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/vc/HuangLTCL25","documentUrl":null,"type":"Article"},{"key":"journals/visintelligence/XieCZL25","url":"https://dblp.org/rec/journals/visintelligence/XieCZL25","title":"Large multimodal agents: a survey.","year":2025,"types":["Article"],"venue":"Vis. Intell.","doi":"https://doi.org/10.1007/S44267-025-00093-Y","numberOfCreators":4,"category":"journal","sources":["https://dblp.org/rec/journals/visintelligence/XieCZL25","https://doi.org/10.1007/S44267-025-00093-Y"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/visintelligence/XieCZL25","documentUrl":null,"type":"Article"}],"preprints":[{"key":"journals/corr/abs-2501-01926","url":"https://dblp.org/rec/journals/corr/abs-2501-01926","title":"Mitigating Hallucination for Large Vision Language Model by Inter-Modality Correlation Calibration Decoding.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2501.01926","numberOfCreators":5,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2501-01926","https://doi.org/10.48550/ARXIV.2501.01926"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2501-01926","documentUrl":null,"type":"Informal","arxivId":"2501.01926","arxivUrl":"https://arxiv.org/abs/2501.01926"},{"key":"journals/corr/abs-2503-03190","url":"https://dblp.org/rec/journals/corr/abs-2503-03190","title":"DSPNet: Dual-vision Scene Perception for Robust 3D Question Answering.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2503.03190","numberOfCreators":7,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2503-03190","https://doi.org/10.48550/ARXIV.2503.03190"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-03190","documentUrl":null,"type":"Informal","arxivId":"2503.03190","arxivUrl":"https://arxiv.org/abs/2503.03190"},{"key":"journals/corr/abs-2503-11091","url":"https://dblp.org/rec/journals/corr/abs-2503-11091","title":"Aerial Vision-and-Language Navigation with Grid-based View Selection and Map Construction.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2503.11091","numberOfCreators":4,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2503-11091","https://doi.org/10.48550/ARXIV.2503.11091"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-11091","documentUrl":null,"type":"Informal","arxivId":"2503.11091","arxivUrl":"https://arxiv.org/abs/2503.11091"},{"key":"journals/corr/abs-2503-11117","url":"https://dblp.org/rec/journals/corr/abs-2503-11117","title":"Beyond the Destination: A Novel Benchmark for Exploration-Aware Embodied Question Answering.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2503.11117","numberOfCreators":8,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2503-11117","https://doi.org/10.48550/ARXIV.2503.11117"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-11117","documentUrl":null,"type":"Informal","arxivId":"2503.11117","arxivUrl":"https://arxiv.org/abs/2503.11117"},{"key":"journals/corr/abs-2503-11345","url":"https://dblp.org/rec/journals/corr/abs-2503-11345","title":"EgoSplat: Open-Vocabulary Egocentric Scene Understanding with Language Embedded 3D Gaussian Splatting.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2503.11345","numberOfCreators":7,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2503-11345","https://doi.org/10.48550/ARXIV.2503.11345"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-11345","documentUrl":null,"type":"Informal","arxivId":"2503.11345","arxivUrl":"https://arxiv.org/abs/2503.11345"},{"key":"journals/corr/abs-2503-12165","url":"https://dblp.org/rec/journals/corr/abs-2503-12165","title":"VTON 360: High-Fidelity Virtual Try-On from Any Viewing Direction.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2503.12165","numberOfCreators":7,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2503-12165","https://doi.org/10.48550/ARXIV.2503.12165"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-12165","documentUrl":null,"type":"Informal","arxivId":"2503.12165","arxivUrl":"https://arxiv.org/abs/2503.12165"},{"key":"journals/corr/abs-2503-12838","url":"https://dblp.org/rec/journals/corr/abs-2503-12838","title":"DreamLayer: Simultaneous Multi-Layer Generation via Diffusion Mode.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2503.12838","numberOfCreators":8,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2503-12838","https://doi.org/10.48550/ARXIV.2503.12838"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-12838","documentUrl":null,"type":"Informal","arxivId":"2503.12838","arxivUrl":"https://arxiv.org/abs/2503.12838"},{"key":"journals/corr/abs-2503-23024","url":"https://dblp.org/rec/journals/corr/abs-2503-23024","title":"Empowering Large Language Models with 3D Situation Awareness.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2503.23024","numberOfCreators":10,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2503-23024","https://doi.org/10.48550/ARXIV.2503.23024"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-23024","documentUrl":null,"type":"Informal","arxivId":"2503.23024","arxivUrl":"https://arxiv.org/abs/2503.23024"},{"key":"journals/corr/abs-2504-04687","url":"https://dblp.org/rec/journals/corr/abs-2504-04687","title":"Bridging Knowledge Gap Between Image Inpainting and Large-Area Visible Watermark Removal.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2504.04687","numberOfCreators":6,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2504-04687","https://doi.org/10.48550/ARXIV.2504.04687"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2504-04687","documentUrl":null,"type":"Informal","arxivId":"2504.04687","arxivUrl":"https://arxiv.org/abs/2504.04687"},{"key":"journals/corr/abs-2504-08291","url":"https://dblp.org/rec/journals/corr/abs-2504-08291","title":"DreamFuse: Adaptive Image Fusion with Diffusion Transformer.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2504.08291","numberOfCreators":8,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2504-08291","https://doi.org/10.48550/ARXIV.2504.08291"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2504-08291","documentUrl":null,"type":"Informal","arxivId":"2504.08291","arxivUrl":"https://arxiv.org/abs/2504.08291"},{"key":"journals/corr/abs-2504-11218","url":"https://dblp.org/rec/journals/corr/abs-2504-11218","title":"3DAffordSplat: Efficient Affordance Reasoning with 3D Gaussians.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2504.11218","numberOfCreators":7,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2504-11218","https://doi.org/10.48550/ARXIV.2504.11218"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2504-11218","documentUrl":null,"type":"Informal","arxivId":"2504.11218","arxivUrl":"https://arxiv.org/abs/2504.11218"},{"key":"journals/corr/abs-2505-12641","url":"https://dblp.org/rec/journals/corr/abs-2505-12641","title":"Single Image Reflection Removal via inter-layer Complementarity.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2505.12641","numberOfCreators":8,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2505-12641","https://doi.org/10.48550/ARXIV.2505.12641"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-12641","documentUrl":null,"type":"Informal","arxivId":"2505.12641","arxivUrl":"https://arxiv.org/abs/2505.12641"},{"key":"journals/corr/abs-2505-18612","url":"https://dblp.org/rec/journals/corr/abs-2505-18612","title":"Mod-Adapter: Tuning-Free and Versatile Multi-concept Personalization via Modulation Adapter.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2505.18612","numberOfCreators":8,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2505-18612","https://doi.org/10.48550/ARXIV.2505.18612"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-18612","documentUrl":null,"type":"Informal","arxivId":"2505.18612","arxivUrl":"https://arxiv.org/abs/2505.18612"},{"key":"journals/corr/abs-2506-17712","url":"https://dblp.org/rec/journals/corr/abs-2506-17712","title":"PDC-Net: Pattern Divide-and-Conquer Network for Pelvic Radiation Injury Segmentation.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2506.17712","numberOfCreators":7,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2506-17712","https://doi.org/10.48550/ARXIV.2506.17712"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-17712","documentUrl":null,"type":"Informal","arxivId":"2506.17712","arxivUrl":"https://arxiv.org/abs/2506.17712"},{"key":"journals/corr/abs-2507-04293","url":"https://dblp.org/rec/journals/corr/abs-2507-04293","title":"AutoLayout: Closed-Loop Layout Synthesis via Slow-Fast Collaborative Reasoning.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2507.04293","numberOfCreators":10,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2507-04293","https://doi.org/10.48550/ARXIV.2507.04293"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2507-04293","documentUrl":null,"type":"Informal","arxivId":"2507.04293","arxivUrl":"https://arxiv.org/abs/2507.04293"},{"key":"journals/corr/abs-2507-07831","url":"https://dblp.org/rec/journals/corr/abs-2507-07831","title":"Rethinking Query-based Transformer for Continual Image Segmentation.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2507.07831","numberOfCreators":8,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2507-07831","https://doi.org/10.48550/ARXIV.2507.07831"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2507-07831","documentUrl":null,"type":"Informal","arxivId":"2507.07831","arxivUrl":"https://arxiv.org/abs/2507.07831"},{"key":"journals/corr/abs-2507-23772","url":"https://dblp.org/rec/journals/corr/abs-2507-23772","title":"SeqAffordSplat: Scene-level Sequential Affordance Reasoning on 3D Gaussian Splatting.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2507.23772","numberOfCreators":8,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2507-23772","https://doi.org/10.48550/ARXIV.2507.23772"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2507-23772","documentUrl":null,"type":"Informal","arxivId":"2507.23772","arxivUrl":"https://arxiv.org/abs/2507.23772"},{"key":"journals/corr/abs-2508-02134","url":"https://dblp.org/rec/journals/corr/abs-2508-02134","title":"Free-MoRef: Instantly Multiplexing Context Perception Capabilities of Video-MLLMs within Single Inference.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2508.02134","numberOfCreators":9,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2508-02134","https://doi.org/10.48550/ARXIV.2508.02134"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-02134","documentUrl":null,"type":"Informal","arxivId":"2508.02134","arxivUrl":"https://arxiv.org/abs/2508.02134"},{"key":"journals/corr/abs-2508-03566","url":"https://dblp.org/rec/journals/corr/abs-2508-03566","title":"SAM2-UNeXT: An Improved High-Resolution Baseline for Adapting Foundation Models to Downstream Segmentation Tasks.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2508.03566","numberOfCreators":6,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2508-03566","https://doi.org/10.48550/ARXIV.2508.03566"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-03566","documentUrl":null,"type":"Informal","arxivId":"2508.03566","arxivUrl":"https://arxiv.org/abs/2508.03566"},{"key":"journals/corr/abs-2508-04559","url":"https://dblp.org/rec/journals/corr/abs-2508-04559","title":"One Model For All: Partial Diffusion for Unified Try-On and Try-Off in Any Pose.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2508.04559","numberOfCreators":5,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2508-04559","https://doi.org/10.48550/ARXIV.2508.04559"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-04559","documentUrl":null,"type":"Informal","arxivId":"2508.04559","arxivUrl":"https://arxiv.org/abs/2508.04559"},{"key":"journals/corr/abs-2508-05186","url":"https://dblp.org/rec/journals/corr/abs-2508-05186","title":"Learning to See and Act: Task-Aware View Planning for Robotic Manipulation.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2508.05186","numberOfCreators":10,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2508-05186","https://doi.org/10.48550/ARXIV.2508.05186"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-05186","documentUrl":null,"type":"Informal","arxivId":"2508.05186","arxivUrl":"https://arxiv.org/abs/2508.05186"},{"key":"journals/corr/abs-2508-08252","url":"https://dblp.org/rec/journals/corr/abs-2508-08252","title":"ReferSplat: Referring Segmentation in 3D Gaussian Splatting.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2508.08252","numberOfCreators":7,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2508-08252","https://doi.org/10.48550/ARXIV.2508.08252"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-08252","documentUrl":null,"type":"Informal","arxivId":"2508.08252","arxivUrl":"https://arxiv.org/abs/2508.08252"},{"key":"journals/corr/abs-2508-13618","url":"https://dblp.org/rec/journals/corr/abs-2508-13618","title":"TalkVid: A Large-Scale Diversified Dataset for Audio-Driven Talking Head Synthesis.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2508.13618","numberOfCreators":13,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2508-13618","https://doi.org/10.48550/ARXIV.2508.13618"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-13618","documentUrl":null,"type":"Informal","arxivId":"2508.13618","arxivUrl":"https://arxiv.org/abs/2508.13618"},{"key":"journals/corr/abs-2509-23867","url":"https://dblp.org/rec/journals/corr/abs-2509-23867","title":"Sim-DETR: Unlock DETR for Temporal Sentence Grounding.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2509.23867","numberOfCreators":7,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2509-23867","https://doi.org/10.48550/ARXIV.2509.23867"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-23867","documentUrl":null,"type":"Informal","arxivId":"2509.23867","arxivUrl":"https://arxiv.org/abs/2509.23867"},{"key":"journals/corr/abs-2510-10991","url":"https://dblp.org/rec/journals/corr/abs-2510-10991","title":"A Survey on Agentic Multimodal Large Language Models.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2510.10991","numberOfCreators":11,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2510-10991","https://doi.org/10.48550/ARXIV.2510.10991"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-10991","documentUrl":null,"type":"Informal","arxivId":"2510.10991","arxivUrl":"https://arxiv.org/abs/2510.10991"},{"key":"journals/corr/abs-2510-25237","url":"https://dblp.org/rec/journals/corr/abs-2510-25237","title":"DeepShield: Fortifying Deepfake Video Detection with Local and Global Forgery Analysis.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2510.25237","numberOfCreators":8,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2510-25237","https://doi.org/10.48550/ARXIV.2510.25237"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-25237","documentUrl":null,"type":"Informal","arxivId":"2510.25237","arxivUrl":"https://arxiv.org/abs/2510.25237"},{"key":"journals/corr/abs-2511-06253","url":"https://dblp.org/rec/journals/corr/abs-2511-06253","title":"AdaDrive: Self-Adaptive Slow-Fast System for Language-Grounded Autonomous Driving.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2511.06253","numberOfCreators":7,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2511-06253","https://doi.org/10.48550/ARXIV.2511.06253"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2511-06253","documentUrl":null,"type":"Informal","arxivId":"2511.06253","arxivUrl":"https://arxiv.org/abs/2511.06253"},{"key":"journals/corr/abs-2511-06256","url":"https://dblp.org/rec/journals/corr/abs-2511-06256","title":"VLDrive: Vision-Augmented Lightweight MLLMs for Efficient Language-grounded Autonomous Driving.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2511.06256","numberOfCreators":7,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2511-06256","https://doi.org/10.48550/ARXIV.2511.06256"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2511-06256","documentUrl":null,"type":"Informal","arxivId":"2511.06256","arxivUrl":"https://arxiv.org/abs/2511.06256"},{"key":"journals/corr/abs-2511-06272","url":"https://dblp.org/rec/journals/corr/abs-2511-06272","title":"LaneDiffusion: Improving Centerline Graph Learning via Prior Injected BEV Feature Generation.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2511.06272","numberOfCreators":7,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2511-06272","https://doi.org/10.48550/ARXIV.2511.06272"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2511-06272","documentUrl":null,"type":"Informal","arxivId":"2511.06272","arxivUrl":"https://arxiv.org/abs/2511.06272"},{"key":"journals/corr/abs-2511-12254","url":"https://dblp.org/rec/journals/corr/abs-2511-12254","title":"Mobile-Agent-RAG: Driving Smart Multi-Agent Coordination with Contextual Knowledge Empowerment for Long-Horizon Mobile Automation.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2511.12254","numberOfCreators":5,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2511-12254","https://doi.org/10.48550/ARXIV.2511.12254"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2511-12254","documentUrl":null,"type":"Informal","arxivId":"2511.12254","arxivUrl":"https://arxiv.org/abs/2511.12254"},{"key":"journals/corr/abs-2511-17217","url":"https://dblp.org/rec/journals/corr/abs-2511-17217","title":"Dual-domain Adaptation Networks for Realistic Image Super-resolution.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2511.17217","numberOfCreators":5,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2511-17217","https://doi.org/10.48550/ARXIV.2511.17217"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2511-17217","documentUrl":null,"type":"Informal","arxivId":"2511.17217","arxivUrl":"https://arxiv.org/abs/2511.17217"},{"key":"journals/corr/abs-2512-08477","url":"https://dblp.org/rec/journals/corr/abs-2512-08477","title":"ContextDrag: Precise Drag-Based Image Editing via Context-Preserving Token Injection and Position-Consistent Attention.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2512.08477","numberOfCreators":10,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2512-08477","https://doi.org/10.48550/ARXIV.2512.08477"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-08477","documentUrl":null,"type":"Informal","arxivId":"2512.08477","arxivUrl":"https://arxiv.org/abs/2512.08477"},{"key":"journals/corr/abs-2512-14601","url":"https://dblp.org/rec/journals/corr/abs-2512-14601","title":"FakeRadar: Probing Forgery Outliers to Detect Unknown Deepfake Videos.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2512.14601","numberOfCreators":7,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2512-14601","https://doi.org/10.48550/ARXIV.2512.14601"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-14601","documentUrl":null,"type":"Informal","arxivId":"2512.14601","arxivUrl":"https://arxiv.org/abs/2512.14601"}],"excludedFormal":[{"key":"journals/patterns/GongHL25","url":"https://dblp.org/rec/journals/patterns/GongHL25","title":"Plug-and-play computational method for advancing natural and biomedical image representation.","year":2025,"types":["Article"],"venue":"Patterns","doi":"https://doi.org/10.1016/J.PATTER.2025.101412","numberOfCreators":3,"category":"journal","sources":["https://dblp.org/rec/journals/patterns/GongHL25","https://doi.org/10.1016/J.PATTER.2025.101412"],"publicationYear":2025,"eventYear":null,"exclusionReason":"作者身份符合中山大学，但该文为对他人工作的评论：PubMed publication type 为 News，出版商类型 Insights；不计入研究论文。","exclusionReasonCode":"non_research_commentary","exclusionSources":["https://pubmed.ncbi.nlm.nih.gov/41328168/","https://pmc.ncbi.nlm.nih.gov/articles/PMC12664947/"],"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/patterns/GongHL25","documentUrl":null,"type":"Article"},{"key":"journals/tcasI/CuiYLGYH25","url":"https://dblp.org/rec/journals/tcasI/CuiYLGYH25","title":"Optimal Resource Allocation Between Two Nonfully Cooperative Wireless Networks Under Malicious Attacks: A Gestalt Game Perspective.","year":2025,"types":["Article"],"venue":"IEEE Trans. Circuits Syst. I Regul. Pap.","doi":"https://doi.org/10.1109/TCSI.2025.3540608","numberOfCreators":6,"category":"journal","sources":["https://dblp.org/rec/journals/tcasI/CuiYLGYH25","https://doi.org/10.1109/TCSI.2025.3540608"],"publicationYear":2025,"eventYear":null,"exclusionReason":"同名混入：出版商提交给 Crossref 的 Guanbin Li 为深圳大学 College of Mechatronics and Control Engineering，ORCID 0009-0003-8300-9157，与中山大学李冠彬的 0000-0002-4805-0926 不同。","exclusionReasonCode":"confirmed_different_person","exclusionSources":["https://api.crossref.org/works/10.1109/TCSI.2025.3540608"],"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/tcasI/CuiYLGYH25","documentUrl":null,"type":"Article"}],"otherRecords":[],"matchedName":"Guanbin Li","databaseLabel":"Guanbin Li","databaseMetadata":{"type":["https://dblp.org/rdf/schema#Person","https://dblp.org/rdf/schema#Creator"],"label":["Guanbin Li"],"orcid":["https://orcid.org/0000-0002-4805-0926"]},"rawFormalRecordCount2025":50,"sourceWarning":true,"crossrefIdentityChecks":[{"pid":"126/4457","key":"conf/icmcs/TanML25","title":"NeRFSwap: A NeRF-Based Generative Model for Face Swapping.","crossrefUrl":"https://api.crossref.org/works/10.1109/ICME59968.2025.11210190","authors":[{"given":"Guanbin","family":"Li","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong,Shenzhen"}],"role":[{"role":"author","vocabulary":"crossref"}]}]},{"pid":"126/4457","key":"conf/isbi/CaiFGMSL25","title":"BoxPolypSAM: Leveraging SAM in Box-Supervised Polyp Segmentation.","crossrefUrl":"https://api.crossref.org/works/10.1109/ISBI60581.2025.10980797","authors":[{"given":"Guanbin","family":"Li","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University,Guangzhou,China"}],"role":[{"vocabulary":"crossref","role":"author"}]}]},{"pid":"126/4457","key":"conf/mm/WeiL0CLLL25","title":"3DAffordSplat: Efficient Affordance Reasoning with 3D Gaussians.","crossrefUrl":"https://api.crossref.org/works/10.1145/3746027.3754778","authors":[{"ORCID":"https://orcid.org/0000-0002-2486-2890","authenticated-orcid":false,"given":"Guanbin","family":"Li","sequence":"additional","affiliation":[{"name":"Sun Yat-sen University, Guangzhou, China, Peng Cheng Laboratory, Shenzhen, China, and Guangdong Key Laboratory of Big Data Analysis and Processing, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}]},{"pid":"126/4457","key":"journals/kbs/JiLLLW25","title":"Sparse diffusion models for multi-annotator medical image segmentation.","crossrefUrl":"https://api.crossref.org/works/10.1016/J.KNOSYS.2025.114783","authors":[{"given":"Guanbin","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}]},{"pid":"126/4457","key":"journals/patterns/GongHL25","title":"Plug-and-play computational method for advancing natural and biomedical image representation.","crossrefUrl":"https://api.crossref.org/works/10.1016/J.PATTER.2025.101412","authors":[{"given":"Guanbin","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}]},{"pid":"126/4457","key":"journals/pr/JiaLZLSLL25","title":"Enhancing out-of-distribution detection via diversified multi-prototype contrastive learning.","crossrefUrl":"https://api.crossref.org/works/10.1016/J.PATCOG.2024.111214","authors":[{"ORCID":"https://orcid.org/0000-0002-4805-0926","authenticated-orcid":false,"given":"Guanbin","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}]},{"pid":"126/4457","key":"journals/tcasI/CuiYLGYH25","title":"Optimal Resource Allocation Between Two Nonfully Cooperative Wireless Networks Under Malicious Attacks: A Gestalt Game Perspective.","crossrefUrl":"https://api.crossref.org/works/10.1109/TCSI.2025.3540608","authors":[{"ORCID":"https://orcid.org/0009-0003-8300-9157","authenticated-orcid":false,"given":"Guanbin","family":"Li","sequence":"additional","affiliation":[{"name":"College of Mechatronics and Control Engineering, Shenzhen University, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}]},{"pid":"126/4457","key":"journals/tmi/LouLLLXWW25","title":"Instance-Aware Multi-Task Learning for Nuclei Segmentation.","crossrefUrl":"https://api.crossref.org/works/10.1109/TMI.2025.3583014","authors":[{"ORCID":"https://orcid.org/0000-0002-4805-0926","authenticated-orcid":false,"given":"Guanbin","family":"Li","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}]},{"pid":"126/4457","key":"journals/tmm/LiLGLL25","title":"S4R: Rethinking Point Cloud Sampling via Guiding Upsampling-Aware Perception.","crossrefUrl":"https://api.crossref.org/works/10.1109/TMM.2025.3586148","authors":[{"ORCID":"https://orcid.org/0000-0002-4805-0926","authenticated-orcid":false,"given":"Guanbin","family":"Li","sequence":"additional","affiliation":[{"name":"Guangdong Key Laboratory of Big Data Analysis and Processing, School of Computer Science and Engineering, Sun Yat-Sen University, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}]},{"pid":"126/4457","key":"journals/tnn/LiCZHL25","title":"DSFedCon: Dynamic Sparse Federated Contrastive Learning for Data-Driven Intelligent Systems.","crossrefUrl":"https://api.crossref.org/works/10.1109/TNNLS.2024.3349400","authors":[{"ORCID":"https://orcid.org/0000-0002-4805-0926","authenticated-orcid":false,"given":"Guanbin","family":"Li","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}]},{"pid":"126/4457","key":"journals/tvcg/ZhangYZYWLWCL25","title":"GSmoothFace: Generalized Smooth Talking Face Generation via Fine Grained 3D Face Guidance.","crossrefUrl":"https://api.crossref.org/works/10.1109/TVCG.2025.3566382","authors":[{"ORCID":"https://orcid.org/0000-0002-4805-0926","authenticated-orcid":false,"given":"Guanbin","family":"Li","sequence":"additional","affiliation":[{"name":"Sun Yat-sen University, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}]},{"pid":"126/4457","key":"journals/vc/HuangLTCL25","title":"GaPTalk: precision-controlled 3D Gaussian rendering for personalized talking-head synthesis.","crossrefUrl":"https://api.crossref.org/works/10.1007/S00371-025-04195-Y","authors":[{"given":"Guanbin","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}]}],"identityReview":{"formalTitlesScreened":50,"crossrefRecordsChecked":12,"scope":"已筛查全部 2025 正式标题及以下 Crossref/原始来源；这不是逐篇全文审计，也不保证数据库不存在未发现的错归。","findings":["50 条正式记录全部筛查标题；38 条匹配本人公开发表页，其余 12 条查 Crossref 及补充原始来源。","发现一条明确异人记录 journals/tcasI/CuiYLGYH25，已剔除。另将已确认为 News/评论的 journals/patterns/GongHL25 剔除。","ACM 3DAffordSplat 的 ORCID 0000-0002-2486-2890 与个人档案不同，但出版商机构为中山大学/鹏城实验室；保留并提示元数据冲突。","NeRFSwap 的 Crossref 机构为 CUHK-Shenzhen；AAAI 原文可交叉证明中山大学 Guanbin Li 使用 CUHK 邮箱，与该作者长期合作者 Shuangyi Tan/Mingzhi Mao 的上下文一致。保留该条，但没有完成这篇全文身份审计。"]},"signatureAudit":{"completedAt":"2026-10-19","frozen":true,"scope":"对 B 组 39 个数值档案的全部 1074 条原始 2025 正式记录扫描 DBLP author-signature ORCID 和机构；复用既有 59 条 Crossref 核验，补查 6 条新触发记录。重点核查不同 ORCID，以及只有预期机构之外机构的条目。本轮不扩展为所有作者逐篇全文审计。","formalRecordCoverage":50,"orcidCounts":{"https://orcid.org/0000-0002-2486-2890":1,"https://orcid.org/0000-0002-4805-0926":15,"https://orcid.org/0009-0003-8300-9157":1},"institutionCounts":{"Peking University (PKU)":1,"Peng Cheng Laboratory":17,"Shenzhen Research Institute of Big Data (SRIBD)":1,"Shenzhen University (SZU)":1,"Sun Yat-sen University":41,"The Chinese University of Hong Kong, Shenzhen (CUHK-SZ)":1},"caveat":"机构名称可能由 DBLP 自动映射而失真；多 ORCID 也不自动等于异人。只有有原始资料支撑的错归才作确认排除，未解决分支则暂停总数。"},"labName":"HCP-I2 Lab: Human-Cyber-Physical Intelligence Integration","labUrl":"http://www.sysu-hcp.net","labEvidence":"本人主页明确写正在共同指导 HCP-I2 Lab: Human-Cyber-Physical Intelligence Integration，HCP-I2 文字链接指向该组网站。","labSourceUrl":"https://guanbinli.com/","excludedOther":[],"excludedHomonyms":[],"unassignedCandidates":[],"knownPreprintMinimum2025":null,"excludedMisattributed":[],"displayNotes":"DBLP 页面提示 ORCID 冲突，身份与学校及个人来源相符，单独标记。另排除 2 条形式上属于期刊或会议的记录，原因见排除记录。计入 48 条（会议 32、期刊 16）；预印本 33 条单列。","labDisplayNotes":"个人主页写明共同指导 HCP-I2 Lab，并链接该组网站，据此归组；分组只含本人参与的记录。"},{"index":53,"name":"Hongsheng Li","nameZh":"李鸿升","role":"Professor","affiliation":"The Chinese University of Hong Kong","affiliationZh":"香港中文大学","source":"DBLP RDF via official SPARQL; primary-source identity checks","sourceUrl":"https://sparql.dblp.org/","profileUrl":"https://dblp.org/pid/27/7402-1.html","identifier":"27/7402-1","retrievedAt":"2026-10-19","count2025":null,"conference2025":null,"journal2025":null,"preprint2025":null,"status":"unresolved","notes":"author-signature 机构扫描发现 journals/cea/DuYZCHXJZMWXL25 和 journals/jiii/XieYHCZLXW25 两条中国农业大学玉米播种研究挂入香港中文大学 Hongsheng Li 档案，其中前一条 signature 甚至附相同 ORCID。Crossref 作者同名但未提供机构/ORCID，不能仅靠 ORCID 或档案已消歧判为本人。由于该异机构分支未完成逐篇身份排除，全年总数暂留空，候选论文单列。","identityEvidence":[{"url":"https://dblp.org/pid/27/7402-1.html","evidence":"DBLP RDF 类型为 Person，消歧后名字为 Hongsheng Li 0001。机构元数据含：Chinese University of Hong Kong, Department of Electrical Engineering, CUHK-SenseTime Joint Laboratory, Hong Kong；Lehigh University, Department of Computer Science and Engineering, PA, USA"},{"url":"https://www.sciencedirect.com/science/article/pii/S0168169924011438","evidence":"出版商条目为玉米可变播种量控制研究；DBLP author-signature 机构仅为 China Agricultural University，Crossref 作者 Hongsheng Li 未附 ORCID 或机构。"},{"url":"https://www.sciencedirect.com/science/article/pii/S2452414X24002012","evidence":"出版商列 Hongsheng Li 与多名农业工程作者合著玉米精量播种论文；DBLP author-signature 机构仅为 China Agricultural University。现有证据无法确认是香港中文大学李鸿升。"}],"papers":[],"preprints":[],"excludedFormal":[],"otherRecords":[],"matchedName":"Hongsheng Li","databaseLabel":"Hongsheng Li 0001","databaseMetadata":{"type":["https://dblp.org/rdf/schema#Person","https://dblp.org/rdf/schema#Creator"],"label":["Hongsheng Li 0001"],"affiliation":["Chinese University of Hong Kong, Department of Electrical Engineering, CUHK-SenseTime Joint Laboratory, Hong Kong","Lehigh University, Department of Computer Science and Engineering, PA, USA"],"homepage":["https://www.ee.cuhk.edu.hk/~hsli/","https://openreview.net/profile?id=~Hongsheng_Li3"],"orcid":["https://orcid.org/0000-0002-2664-7975"],"primaryAffiliation":["Chinese University of Hong Kong, Department of Electrical Engineering, CUHK-SenseTime Joint Laboratory, Hong Kong"],"primaryHomepage":["https://www.ee.cuhk.edu.hk/~hsli/"]},"rawFormalRecordCount2025":79,"signatureAudit":{"completedAt":"2026-10-19","frozen":true,"scope":"对 B 组 39 个数值档案的全部 1074 条原始 2025 正式记录扫描 DBLP author-signature ORCID 和机构；复用既有 59 条 Crossref 核验，补查 6 条新触发记录。重点核查不同 ORCID，以及只有预期机构之外机构的条目。本轮不扩展为所有作者逐篇全文审计。","formalRecordCoverage":79,"orcidCounts":{"https://orcid.org/0000-0002-2664-7975":17},"institutionCounts":{"China Agricultural University (CAU)":2,"Chinese University of Hong Kong (CUHK)":30,"Shanghai Artificial Intelligence Laboratory":11,"Shanghai Open University":2,"University of Hong Kong (HKU)":12},"caveat":"机构名称可能由 DBLP 自动映射而失真；多 ORCID 也不自动等于异人。只有有原始资料支撑的错归才作确认排除，未解决分支则暂停总数。","decision":{"decision":"unresolved","reason":"author-signature 机构扫描发现 journals/cea/DuYZCHXJZMWXL25 和 journals/jiii/XieYHCZLXW25 两条中国农业大学玉米播种研究挂入香港中文大学 Hongsheng Li 档案，其中前一条 signature 甚至附相同 ORCID。Crossref 作者同名但未提供机构/ORCID，不能仅靠 ORCID 或档案已消歧判为本人。由于该异机构分支未完成逐篇身份排除，全年总数暂留空，候选论文单列。","flaggedKeys":["journals/cea/DuYZCHXJZMWXL25","journals/jiii/XieYHCZLXW25"],"evidence":[{"url":"https://www.sciencedirect.com/science/article/pii/S0168169924011438","evidence":"出版商条目为玉米可变播种量控制研究；DBLP author-signature 机构仅为 China Agricultural University，Crossref 作者 Hongsheng Li 未附 ORCID 或机构。"},{"url":"https://www.sciencedirect.com/science/article/pii/S2452414X24002012","evidence":"出版商列 Hongsheng Li 与多名农业工程作者合著玉米精量播种论文；DBLP author-signature 机构仅为 China Agricultural University。现有证据无法确认是香港中文大学李鸿升。"}]}},"sourceWarning":true,"candidatePapers":[{"key":"conf/aaai/0001SMZSC025","url":"https://dblp.org/rec/conf/aaai/0001SMZSC025","title":"M3Net: Multimodal Multi-task Learning for 3D Detection, Segmentation, and Occupancy Prediction in Autonomous Driving.","year":2025,"types":["Inproceedings"],"venue":["AAAI"],"doi":["https://doi.org/10.1609/AAAI.V39I2.32227"],"eventYear":2025,"numberOfCreators":7,"category":"conference","sources":["https://dblp.org/rec/conf/aaai/0001SMZSC025","https://doi.org/10.1609/AAAI.V39I2.32227"],"publicationYear":2025},{"key":"conf/aaai/YangLZPG0CG0GZ25","url":"https://dblp.org/rec/conf/aaai/YangLZPG0CG0GZ25","title":"LiDAR-LLM: Exploring the Potential of Large Language Models for 3D LiDAR Understanding.","year":2025,"types":["Inproceedings"],"venue":["AAAI"],"doi":["https://doi.org/10.1609/AAAI.V39I9.33001"],"eventYear":2025,"numberOfCreators":11,"category":"conference","sources":["https://dblp.org/rec/conf/aaai/YangLZPG0CG0GZ25","https://doi.org/10.1609/AAAI.V39I9.33001"],"publicationYear":2025},{"key":"conf/aaai/ZhouF0HL025","url":"https://dblp.org/rec/conf/aaai/ZhouF0HL025","title":"GaussianPainter: Painting Point Cloud into 3D Gaussians with Normal Guidance.","year":2025,"types":["Inproceedings"],"venue":["AAAI"],"doi":["https://doi.org/10.1609/AAAI.V39I10.33172"],"eventYear":2025,"numberOfCreators":6,"category":"conference","sources":["https://dblp.org/rec/conf/aaai/ZhouF0HL025","https://doi.org/10.1609/AAAI.V39I10.33172"],"publicationYear":2025},{"key":"conf/acl/0036PWZSL0YRZ025","url":"https://dblp.org/rec/conf/acl/0036PWZSL0YRZ025","title":"MathCoder-VL: Bridging Vision and Code for Enhanced Multimodal Mathematical Reasoning.","year":2025,"types":["Inproceedings"],"venue":["ACL (Findings)"],"doi":["https://doi.org/10.18653/V1/2025.FINDINGS-ACL.128"],"eventYear":2025,"numberOfCreators":11,"category":"conference","sources":["https://dblp.org/rec/conf/acl/0036PWZSL0YRZ025","https://doi.org/10.18653/V1/2025.FINDINGS-ACL.128"],"publicationYear":2025},{"key":"conf/acl/Chai0N0LWZRL25","url":"https://dblp.org/rec/conf/acl/Chai0N0LWZRL25","title":"AMEX: Android Multi-annotation Expo Dataset for Mobile GUI Agents.","year":2025,"types":["Inproceedings"],"venue":["ACL (Findings)"],"doi":["https://doi.org/10.18653/V1/2025.FINDINGS-ACL.110"],"eventYear":2025,"numberOfCreators":9,"category":"conference","sources":["https://dblp.org/rec/conf/acl/Chai0N0LWZRL25","https://doi.org/10.18653/V1/2025.FINDINGS-ACL.110"],"publicationYear":2025},{"key":"conf/acl/RenZWZP025","url":"https://dblp.org/rec/conf/acl/RenZWZP025","title":"ReflectionCoder: Learning from Reflection Sequence for Enhanced One-off Code Generation.","year":2025,"types":["Inproceedings"],"venue":["ACL (1)"],"doi":["https://doi.org/10.18653/V1/2025.ACL-LONG.494"],"eventYear":2025,"numberOfCreators":6,"category":"conference","sources":["https://dblp.org/rec/conf/acl/RenZWZP025","https://doi.org/10.18653/V1/2025.ACL-LONG.494"],"publicationYear":2025},{"key":"conf/acl/YangRL0SZPZ025","url":"https://dblp.org/rec/conf/acl/YangRL0SZPZ025","title":"Probability-Consistent Preference Optimization for Enhanced LLM Reasoning.","year":2025,"types":["Inproceedings"],"venue":["ACL (Findings)"],"doi":["https://doi.org/10.18653/V1/2025.FINDINGS-ACL.333"],"eventYear":2025,"numberOfCreators":9,"category":"conference","sources":["https://dblp.org/rec/conf/acl/YangRL0SZPZ025","https://doi.org/10.18653/V1/2025.FINDINGS-ACL.333"],"publicationYear":2025},{"key":"conf/cvpr/0001H0FS025","url":"https://dblp.org/rec/conf/cvpr/0001H0FS025","title":"SOLVE: Synergy of Language-Vision and End-to-End Networks for Autonomous Driving.","year":2025,"types":["Inproceedings"],"venue":["CVPR"],"doi":["https://doi.org/10.1109/CVPR52734.2025.01127"],"eventYear":2025,"numberOfCreators":6,"category":"conference","sources":["https://dblp.org/rec/conf/cvpr/0001H0FS025","https://doi.org/10.1109/CVPR52734.2025.01127"],"publicationYear":2025},{"key":"conf/cvpr/0010XTCHWZLSLGW25","url":"https://dblp.org/rec/conf/cvpr/0010XTCHWZLSLGW25","title":"Adaptive Markup Language Generation for Contextually-Grounded Visual Document Understanding.","year":2025,"types":["Inproceedings"],"venue":["CVPR"],"doi":["https://doi.org/10.1109/CVPR52734.2025.02752"],"eventYear":2025,"numberOfCreators":15,"category":"conference","sources":["https://dblp.org/rec/conf/cvpr/0010XTCHWZLSLGW25","https://doi.org/10.1109/CVPR52734.2025.02752"],"publicationYear":2025},{"key":"conf/cvpr/BianH0LW025","url":"https://dblp.org/rec/conf/cvpr/BianH0LW025","title":"GS-DiT: Advancing Video Generation with Dynamic 3D Gaussian Fields through Efficient Dense 3D Point Tracking.","year":2025,"types":["Inproceedings"],"venue":["CVPR"],"doi":["https://doi.org/10.1109/CVPR52734.2025.02023"],"eventYear":2025,"numberOfCreators":6,"category":"conference","sources":["https://dblp.org/rec/conf/cvpr/BianH0LW025","https://doi.org/10.1109/CVPR52734.2025.02023"],"publicationYear":2025},{"key":"conf/cvpr/DuanCHWYSLHLLDW25","url":"https://dblp.org/rec/conf/cvpr/DuanCHWYSLHLLDW25","title":"Docopilot: Improving Multimodal Models for Document-Level Understanding.","year":2025,"types":["Inproceedings"],"venue":["CVPR"],"doi":["https://doi.org/10.1109/CVPR52734.2025.00381"],"eventYear":2025,"numberOfCreators":12,"category":"conference","sources":["https://dblp.org/rec/conf/cvpr/DuanCHWYSLHLLDW25","https://doi.org/10.1109/CVPR52734.2025.00381"],"publicationYear":2025},{"key":"conf/cvpr/FanZWLZ25","url":"https://dblp.org/rec/conf/cvpr/FanZWLZ25","title":"FreeSim: Toward Free-viewpoint Camera Simulation in Driving Scenes.","year":2025,"types":["Inproceedings"],"venue":["CVPR"],"doi":["https://doi.org/10.1109/CVPR52734.2025.01121"],"eventYear":2025,"numberOfCreators":5,"category":"conference","sources":["https://dblp.org/rec/conf/cvpr/FanZWLZ25","https://doi.org/10.1109/CVPR52734.2025.01121"],"publicationYear":2025},{"key":"conf/cvpr/LiTSZWZDWLLD25","url":"https://dblp.org/rec/conf/cvpr/LiTSZWZDWLLD25","title":"SynerGen-VL: Towards Synergistic Image Understanding and Generation with Vision Experts and Token Folding.","year":2025,"types":["Inproceedings"],"venue":["CVPR"],"doi":["https://doi.org/10.1109/CVPR52734.2025.02771"],"eventYear":2025,"numberOfCreators":11,"category":"conference","sources":["https://dblp.org/rec/conf/cvpr/LiTSZWZDWLLD25","https://doi.org/10.1109/CVPR52734.2025.02771"],"publicationYear":2025},{"key":"conf/cvpr/LuCCTCXHTWHZWBW25","url":"https://dblp.org/rec/conf/cvpr/LuCCTCXHTWHZWBW25","title":"BlueLM-V-3B: Algorithm and System Co-Design for Multimodal Large Language Models on Mobile Devices.","year":2025,"types":["Inproceedings"],"venue":["CVPR"],"doi":["https://doi.org/10.1109/CVPR52734.2025.00392"],"eventYear":2025,"numberOfCreators":22,"category":"conference","sources":["https://dblp.org/rec/conf/cvpr/LuCCTCXHTWHZWBW25","https://doi.org/10.1109/CVPR52734.2025.00392"],"publicationYear":2025},{"key":"conf/cvpr/ZhangTZGZZL0025","url":"https://dblp.org/rec/conf/cvpr/ZhangTZGZZL0025","title":"Let's Verify and Reinforce Image Generation Step by Step.","year":2025,"types":["Inproceedings"],"venue":["CVPR"],"doi":["https://doi.org/10.1109/CVPR52734.2025.02669"],"eventYear":2025,"numberOfCreators":9,"category":"conference","sources":["https://dblp.org/rec/conf/cvpr/ZhangTZGZZL0025","https://doi.org/10.1109/CVPR52734.2025.02669"],"publicationYear":2025},{"key":"conf/cvpr/ZhouFH000025","url":"https://dblp.org/rec/conf/cvpr/ZhouFH000025","title":"FlexDrive: Toward Trajectory Flexibility in Driving Scene Gaussian Splatting Reconstruction and Rendering.","year":2025,"types":["Inproceedings"],"venue":["CVPR"],"doi":["https://doi.org/10.1109/CVPR52734.2025.00152"],"eventYear":2025,"numberOfCreators":7,"category":"conference","sources":["https://dblp.org/rec/conf/cvpr/ZhouFH000025","https://doi.org/10.1109/CVPR52734.2025.00152"],"publicationYear":2025},{"key":"conf/eccv/HuangFZSLLL24","url":"https://dblp.org/rec/conf/eccv/HuangFZSLLL24","title":"FouriScale: A Frequency Perspective on Training-Free High-Resolution Image Synthesis.","year":2025,"types":["Inproceedings"],"venue":["ECCV (12)"],"doi":["https://doi.org/10.1007/978-3-031-73254-6_12"],"eventYear":2024,"numberOfCreators":7,"category":"conference","sources":["https://dblp.org/rec/conf/eccv/HuangFZSLLL24","https://doi.org/10.1007/978-3-031-73254-6_12"],"publicationYear":2025},{"key":"conf/eccv/LiLLLMKW24","url":"https://dblp.org/rec/conf/eccv/LiLLLMKW24","title":"Delving Deep into Engagement Prediction of Short Videos.","year":2025,"types":["Inproceedings"],"venue":["ECCV (54)"],"doi":["https://doi.org/10.1007/978-3-031-72949-2_17"],"eventYear":2024,"numberOfCreators":7,"category":"conference","sources":["https://dblp.org/rec/conf/eccv/LiLLLMKW24","https://doi.org/10.1007/978-3-031-72949-2_17"],"publicationYear":2025},{"key":"conf/eccv/LiSHCBSWSBCZL24","url":"https://dblp.org/rec/conf/eccv/LiSHCBSWSBCZL24","title":"BlinkVision: A Benchmark for Optical Flow, Scene Flow and Point Tracking Estimation Using RGB Frames and Events.","year":2025,"types":["Inproceedings"],"venue":["ECCV (67)"],"doi":["https://doi.org/10.1007/978-3-031-72855-6_2"],"eventYear":2024,"numberOfCreators":12,"category":"conference","sources":["https://dblp.org/rec/conf/eccv/LiSHCBSWSBCZL24","https://doi.org/10.1007/978-3-031-72855-6_2"],"publicationYear":2025},{"key":"conf/eccv/LinLZGQXQSCHHZHQL24","url":"https://dblp.org/rec/conf/eccv/LinLZGQXQSCHHZHQL24","title":"SPHINX: A Mixer of Weights, Visual Embeddings and Image Scales for Multi-modal Large Language Models.","year":2025,"types":["Inproceedings"],"venue":["ECCV (62)"],"doi":["https://doi.org/10.1007/978-3-031-73033-7_3"],"eventYear":2024,"numberOfCreators":15,"category":"conference","sources":["https://dblp.org/rec/conf/eccv/LinLZGQXQSCHHZHQL24","https://doi.org/10.1007/978-3-031-73033-7_3"],"publicationYear":2025},{"key":"conf/eccv/SunLZLWW24","url":"https://dblp.org/rec/conf/eccv/SunLZLWW24","title":"Ponymation: Learning Articulated 3D Animal Motions from Unlabeled Online Videos.","year":2025,"types":["Inproceedings"],"venue":["ECCV (1)"],"doi":["https://doi.org/10.1007/978-3-031-73232-4_6"],"eventYear":2024,"numberOfCreators":6,"category":"conference","sources":["https://dblp.org/rec/conf/eccv/SunLZLWW24","https://doi.org/10.1007/978-3-031-73232-4_6"],"publicationYear":2025},{"key":"conf/eccv/TangZLGZWGLWL24","url":"https://dblp.org/rec/conf/eccv/TangZLGZWGLWL24","title":"Any2Point: Empowering Any-Modality Large Models for Efficient 3D Understanding.","year":2025,"types":["Inproceedings"],"venue":["ECCV (36)"],"doi":["https://doi.org/10.1007/978-3-031-72764-1_26"],"eventYear":2024,"numberOfCreators":10,"category":"conference","sources":["https://dblp.org/rec/conf/eccv/TangZLGZWGLWL24","https://doi.org/10.1007/978-3-031-72764-1_26"],"publicationYear":2025},{"key":"conf/eccv/WangHMSLBLLL24","url":"https://dblp.org/rec/conf/eccv/WangHMSLBLLL24","title":"ZoLA: Zero-Shot Creative Long Animation Generation with Short Video Model.","year":2025,"types":["Inproceedings"],"venue":["ECCV (45)"],"doi":["https://doi.org/10.1007/978-3-031-72995-9_19"],"eventYear":2024,"numberOfCreators":9,"category":"conference","sources":["https://dblp.org/rec/conf/eccv/WangHMSLBLLL24","https://doi.org/10.1007/978-3-031-72995-9_19"],"publicationYear":2025},{"key":"conf/eccv/WangTJSNLSW24","url":"https://dblp.org/rec/conf/eccv/WangTJSNLSW24","title":"GiT: Towards Generalist Vision Transformer Through Universal Language Interface.","year":2025,"types":["Inproceedings"],"venue":["ECCV (29)"],"doi":["https://doi.org/10.1007/978-3-031-73397-0_4"],"eventYear":2024,"numberOfCreators":8,"category":"conference","sources":["https://dblp.org/rec/conf/eccv/WangTJSNLSW24","https://doi.org/10.1007/978-3-031-73397-0_4"],"publicationYear":2025},{"key":"conf/eccv/WangWHSSSLL24","url":"https://dblp.org/rec/conf/eccv/WangWHSSSLL24","title":"Be-Your-Outpainter: Mastering Video Outpainting Through Input-Specific Adaptation.","year":2025,"types":["Inproceedings"],"venue":["ECCV (44)"],"doi":["https://doi.org/10.1007/978-3-031-72784-9_9"],"eventYear":2024,"numberOfCreators":8,"category":"conference","sources":["https://dblp.org/rec/conf/eccv/WangWHSSSLL24","https://doi.org/10.1007/978-3-031-72784-9_9"],"publicationYear":2025},{"key":"conf/eccv/WuHZSHSLL24","url":"https://dblp.org/rec/conf/eccv/WuHZSHSLL24","title":"Deep Reward Supervisions for Tuning Text-to-Image Diffusion Models.","year":2025,"types":["Inproceedings"],"venue":["ECCV (83)"],"doi":["https://doi.org/10.1007/978-3-031-73010-8_7"],"eventYear":2024,"numberOfCreators":8,"category":"conference","sources":["https://dblp.org/rec/conf/eccv/WuHZSHSLL24","https://doi.org/10.1007/978-3-031-73010-8_7"],"publicationYear":2025},{"key":"conf/eccv/ZhangJZLGQZLCQGL24","url":"https://dblp.org/rec/conf/eccv/ZhangJZLGQZLCQGL24","title":"MATHVERSE: Does Your Multi-modal LLM Truly See the Diagrams in Visual Math Problems?","year":2025,"types":["Inproceedings"],"venue":["ECCV (8)"],"doi":["https://doi.org/10.1007/978-3-031-73242-3_10"],"eventYear":2024,"numberOfCreators":12,"category":"conference","sources":["https://dblp.org/rec/conf/eccv/ZhangJZLGQZLCQGL24","https://doi.org/10.1007/978-3-031-73242-3_10"],"publicationYear":2025},{"key":"conf/eccv/ZhangSSLL24","url":"https://dblp.org/rec/conf/eccv/ZhangSSLL24","title":"Three Things We Need to Know About Transferring Stable Diffusion to Visual Dense Prediction Tasks.","year":2025,"types":["Inproceedings"],"venue":["ECCV (42)"],"doi":["https://doi.org/10.1007/978-3-031-72946-1_8"],"eventYear":2024,"numberOfCreators":5,"category":"conference","sources":["https://dblp.org/rec/conf/eccv/ZhangSSLL24","https://doi.org/10.1007/978-3-031-72946-1_8"],"publicationYear":2025},{"key":"conf/eccv/ZhuWL24","url":"https://dblp.org/rec/conf/eccv/ZhuWL24","title":"nuCraft: Crafting High Resolution 3D Semantic Occupancy for Unified 3D Scene Understanding.","year":2025,"types":["Inproceedings"],"venue":["ECCV (5)"],"doi":["https://doi.org/10.1007/978-3-031-72652-1_8"],"eventYear":2024,"numberOfCreators":3,"category":"conference","sources":["https://dblp.org/rec/conf/eccv/ZhuWL24","https://doi.org/10.1007/978-3-031-72652-1_8"],"publicationYear":2025},{"key":"conf/emnlp/HuLWZSZDLZL25","url":"https://dblp.org/rec/conf/emnlp/HuLWZSZDLZL25","title":"LM-Searcher: Cross-domain Neural Architecture Search with LLMs via Unified Numerical Encoding.","year":2025,"types":["Inproceedings"],"venue":["EMNLP"],"doi":["https://doi.org/10.18653/V1/2025.EMNLP-MAIN.478"],"eventYear":2025,"numberOfCreators":10,"category":"conference","sources":["https://dblp.org/rec/conf/emnlp/HuLWZSZDLZL25","https://doi.org/10.18653/V1/2025.EMNLP-MAIN.478"],"publicationYear":2025},{"key":"conf/emnlp/LuGWRCLL25","url":"https://dblp.org/rec/conf/emnlp/LuGWRCLL25","title":"SmartBench: Is Your LLM Truly a Good Chinese Smartphone Assistant?","year":2025,"types":["Inproceedings"],"venue":["EMNLP"],"doi":["https://doi.org/10.18653/V1/2025.EMNLP-MAIN.194"],"eventYear":2025,"numberOfCreators":7,"category":"conference","sources":["https://dblp.org/rec/conf/emnlp/LuGWRCLL25","https://doi.org/10.18653/V1/2025.EMNLP-MAIN.194"],"publicationYear":2025},{"key":"conf/emnlp/RenLSHYWZPZL25","url":"https://dblp.org/rec/conf/emnlp/RenLSHYWZPZL25","title":"Alignment with Fill-In-the-Middle for Enhancing Code Generation.","year":2025,"types":["Inproceedings"],"venue":["EMNLP"],"doi":["https://doi.org/10.18653/V1/2025.EMNLP-MAIN.419"],"eventYear":2025,"numberOfCreators":10,"category":"conference","sources":["https://dblp.org/rec/conf/emnlp/RenLSHYWZPZL25","https://doi.org/10.18653/V1/2025.EMNLP-MAIN.419"],"publicationYear":2025},{"key":"conf/iccv/FangDWLHTZZDLL25","url":"https://dblp.org/rec/conf/iccv/FangDWLHTZZDLL25","title":"PUMA: Empowering Unified MLLM with Multi-Granular Visual Generation.","year":2025,"types":["Inproceedings"],"venue":["ICCV"],"doi":["https://doi.org/10.1109/ICCV51701.2025.01433"],"eventYear":2025,"numberOfCreators":11,"category":"conference","sources":["https://dblp.org/rec/conf/iccv/FangDWLHTZZDLL25","https://doi.org/10.1109/ICCV51701.2025.01433"],"publicationYear":2025},{"key":"conf/iccv/HeYLXWGZWJL25","url":"https://dblp.org/rec/conf/iccv/HeYLXWGZWJL25","title":"CameraCtrl II: Dynamic Scene Exploration via Camera-Controlled Video Diffusion Models.","year":2025,"types":["Inproceedings"],"venue":["ICCV"],"doi":["https://doi.org/10.1109/ICCV51701.2025.01246"],"eventYear":2025,"numberOfCreators":10,"category":"conference","sources":["https://dblp.org/rec/conf/iccv/HeYLXWGZWJL25","https://doi.org/10.1109/ICCV51701.2025.01246"],"publicationYear":2025},{"key":"conf/iccv/LuCWGCYZZLWCRL25","url":"https://dblp.org/rec/conf/iccv/LuCWGCYZZLWCRL25","title":"GenieBlue: Integrating Both Linguistic and Multimodal Capabilities for Large Language Models on Mobile Devices.","year":2025,"types":["Inproceedings"],"venue":["ICCV"],"doi":["https://doi.org/10.1109/ICCV51701.2025.00400"],"eventYear":2025,"numberOfCreators":13,"category":"conference","sources":["https://dblp.org/rec/conf/iccv/LuCWGCYZZLWCRL25","https://doi.org/10.1109/ICCV51701.2025.00400"],"publicationYear":2025},{"key":"conf/iccv/QinZXDLFLLLZBMPWQZLLXG25","url":"https://dblp.org/rec/conf/iccv/QinZXDLFLLLZBMPWQZLLXG25","title":"Lumina-Image 2.0: a Unified and Efficient Image Generative Framework.","year":2025,"types":["Inproceedings"],"venue":["ICCV"],"doi":["https://doi.org/10.1109/ICCV51701.2025.01863"],"eventYear":2025,"numberOfCreators":20,"category":"conference","sources":["https://dblp.org/rec/conf/iccv/QinZXDLFLLLZBMPWQZLLXG25","https://doi.org/10.1109/ICCV51701.2025.01863"],"publicationYear":2025},{"key":"conf/iccv/ZhuoZPLZXGEL25","url":"https://dblp.org/rec/conf/iccv/ZhuoZPLZXGEL25","title":"From Reflection to Perfection: Scaling Inference-Time Optimization for Text-to-Image Diffusion Models via Reflection Tuning.","year":2025,"types":["Inproceedings"],"venue":["ICCV"],"doi":["https://doi.org/10.1109/ICCV51701.2025.01422"],"eventYear":2025,"numberOfCreators":9,"category":"conference","sources":["https://dblp.org/rec/conf/iccv/ZhuoZPLZXGEL25","https://doi.org/10.1109/ICCV51701.2025.01422"],"publicationYear":2025},{"key":"conf/iclr/Ding00LCLZZ25","url":"https://dblp.org/rec/conf/iclr/Ding00LCLZZ25","title":"Point Cluster: A Compact Message Unit for Communication-Efficient Collaborative Perception.","year":2025,"types":["Inproceedings"],"venue":["ICLR"],"doi":[],"eventYear":2025,"numberOfCreators":8,"category":"conference","sources":["https://dblp.org/rec/conf/iclr/Ding00LCLZZ25"],"publicationYear":2025},{"key":"conf/iclr/DuanWCZLLQ0DW25","url":"https://dblp.org/rec/conf/iclr/DuanWCZLLQ0DW25","title":"Vision-RWKV: Efficient and Scalable Visual Perception with RWKV-Like Architectures.","year":2025,"types":["Inproceedings"],"venue":["ICLR"],"doi":[],"eventYear":2025,"numberOfCreators":10,"category":"conference","sources":["https://dblp.org/rec/conf/iclr/DuanWCZLLQ0DW25"],"publicationYear":2025},{"key":"conf/iclr/GaoZLDLQZ0GZXS025","url":"https://dblp.org/rec/conf/iclr/GaoZLDLQZ0GZXS025","title":"Lumina-T2X: Scalable Flow-based Large Diffusion Transformer for Flexible Resolution Generation.","year":2025,"types":["Inproceedings"],"venue":["ICLR"],"doi":[],"eventYear":2025,"numberOfCreators":20,"category":"conference","sources":["https://dblp.org/rec/conf/iclr/GaoZLDLQZ0GZXS025"],"publicationYear":2025},{"key":"conf/iclr/HeX0W00Y25","url":"https://dblp.org/rec/conf/iclr/HeX0W00Y25","title":"CameraCtrl: Enabling Camera Control for Video Diffusion Models.","year":2025,"types":["Inproceedings"],"venue":["ICLR"],"doi":[],"eventYear":2025,"numberOfCreators":7,"category":"conference","sources":["https://dblp.org/rec/conf/iclr/HeX0W00Y25"],"publicationYear":2025},{"key":"conf/iclr/HuangLLHTZ00025","url":"https://dblp.org/rec/conf/iclr/HuangLLHTZ00025","title":"Mixture Compressor for Mixture-of-Experts LLMs Gains More.","year":2025,"types":["Inproceedings"],"venue":["ICLR"],"doi":[],"eventYear":2025,"numberOfCreators":9,"category":"conference","sources":["https://dblp.org/rec/conf/iclr/HuangLLHTZ00025"],"publicationYear":2025},{"key":"conf/iclr/JiangZGWLQLCS0025","url":"https://dblp.org/rec/conf/iclr/JiangZGWLQLCS0025","title":"MMSearch: Unveiling the Potential of Large Models as Multi-modal Search Engines.","year":2025,"types":["Inproceedings"],"venue":["ICLR"],"doi":[],"eventYear":2025,"numberOfCreators":13,"category":"conference","sources":["https://dblp.org/rec/conf/iclr/JiangZGWLQLCS0025"],"publicationYear":2025},{"key":"conf/iclr/LinWA0ZL0Z025","url":"https://dblp.org/rec/conf/iclr/LinWA0ZL0Z025","title":"Draw-and-Understand: Leveraging Visual Prompts to Enable MLLMs to Comprehend What You Want.","year":2025,"types":["Inproceedings"],"venue":["ICLR"],"doi":[],"eventYear":2025,"numberOfCreators":9,"category":"conference","sources":["https://dblp.org/rec/conf/iclr/LinWA0ZL0Z025"],"publicationYear":2025},{"key":"conf/iclr/LinWZZZ0X0025","url":"https://dblp.org/rec/conf/iclr/LinWZZZ0X0025","title":"PixWizard: Versatile Image-to-Image Visual Assistant with Open-Language Instructions.","year":2025,"types":["Inproceedings"],"venue":["ICLR"],"doi":[],"eventYear":2025,"numberOfCreators":9,"category":"conference","sources":["https://dblp.org/rec/conf/iclr/LinWZZZ0X0025"],"publicationYear":2025},{"key":"conf/iclr/LuZ0RSPZL25","url":"https://dblp.org/rec/conf/iclr/LuZ0RSPZL25","title":"MathCoder2: Better Math Reasoning from Continued Pretraining on Model-translated Mathematical Code.","year":2025,"types":["Inproceedings"],"venue":["ICLR"],"doi":[],"eventYear":2025,"numberOfCreators":8,"category":"conference","sources":["https://dblp.org/rec/conf/iclr/LuZ0RSPZL25"],"publicationYear":2025},{"key":"conf/iclr/ShuLZZXZSCZYHFL25","url":"https://dblp.org/rec/conf/iclr/ShuLZZXZSCZYHFL25","title":"LLaVA-MoD: Making LLaVA Tiny via MoE-Knowledge Distillation.","year":2025,"types":["Inproceedings"],"venue":["ICLR"],"doi":[],"eventYear":2025,"numberOfCreators":16,"category":"conference","sources":["https://dblp.org/rec/conf/iclr/ShuLZZXZSCZYHFL25"],"publicationYear":2025},{"key":"conf/iclr/Wang0HW025","url":"https://dblp.org/rec/conf/iclr/Wang0HW025","title":"Rectified Diffusion: Straightness Is Not Your Need in Rectified Flow.","year":2025,"types":["Inproceedings"],"venue":["ICLR"],"doi":[],"eventYear":2025,"numberOfCreators":5,"category":"conference","sources":["https://dblp.org/rec/conf/iclr/Wang0HW025"],"publicationYear":2025},{"key":"conf/iclr/WangSPS025","url":"https://dblp.org/rec/conf/iclr/WangSPS025","title":"Diffusion-NPO: Negative Preference Optimization for Better Preference Aligned Generation of Diffusion Models.","year":2025,"types":["Inproceedings"],"venue":["ICLR"],"doi":[],"eventYear":2025,"numberOfCreators":5,"category":"conference","sources":["https://dblp.org/rec/conf/iclr/WangSPS025"],"publicationYear":2025},{"key":"conf/iclr/WangYWKCW0L025","url":"https://dblp.org/rec/conf/iclr/WangYWKCW0L025","title":"Towards Realistic UAV Vision-Language Navigation: Platform, Benchmark, and Methodology.","year":2025,"types":["Inproceedings"],"venue":["ICLR"],"doi":[],"eventYear":2025,"numberOfCreators":9,"category":"conference","sources":["https://dblp.org/rec/conf/iclr/WangYWKCW0L025"],"publicationYear":2025},{"key":"conf/iclr/ZhangWJGZT0ZZG025","url":"https://dblp.org/rec/conf/iclr/ZhangWJGZT0ZZG025","title":"MAVIS: Mathematical Visual Instruction Tuning with an Automatic Data Engine.","year":2025,"types":["Inproceedings"],"venue":["ICLR"],"doi":[],"eventYear":2025,"numberOfCreators":11,"category":"conference","sources":["https://dblp.org/rec/conf/iclr/ZhangWJGZT0ZZG025"],"publicationYear":2025},{"key":"conf/iclr/ZhouSWW0025","url":"https://dblp.org/rec/conf/iclr/ZhouSWW0025","title":"SmartPretrain: Model-Agnostic and Dataset-Agnostic Representation Learning for Motion Prediction.","year":2025,"types":["Inproceedings"],"venue":["ICLR"],"doi":[],"eventYear":2025,"numberOfCreators":6,"category":"conference","sources":["https://dblp.org/rec/conf/iclr/ZhouSWW0025"],"publicationYear":2025},{"key":"conf/icml/JiangZGLQ0WJGY025","url":"https://dblp.org/rec/conf/icml/JiangZGLQ0WJGY025","title":"MME-CoT: Benchmarking Chain-of-Thought in Large Multimodal Models for Reasoning Quality, Robustness, and Efficiency.","year":2025,"types":["Inproceedings"],"venue":["ICML"],"doi":[],"eventYear":2025,"numberOfCreators":14,"category":"conference","sources":["https://dblp.org/rec/conf/icml/JiangZGLQ0WJGY025"],"publicationYear":2025},{"key":"conf/icml/YangX0025","url":"https://dblp.org/rec/conf/icml/YangX0025","title":"One Leaf Reveals the Season: Occlusion-Based Contrastive Learning with Semantic-Aware Views for Efficient Visual Representation.","year":2025,"types":["Inproceedings"],"venue":["ICML"],"doi":[],"eventYear":2025,"numberOfCreators":4,"category":"conference","sources":["https://dblp.org/rec/conf/icml/YangX0025"],"publicationYear":2025},{"key":"conf/icml/ZongJMSSSL025","url":"https://dblp.org/rec/conf/icml/ZongJMSSSL025","title":"EasyRef: Omni-Generalized Group Image Reference for Diffusion Models via Multimodal LLM.","year":2025,"types":["Inproceedings"],"venue":["ICML"],"doi":[],"eventYear":2025,"numberOfCreators":8,"category":"conference","sources":["https://dblp.org/rec/conf/icml/ZongJMSSSL025"],"publicationYear":2025},{"key":"conf/icra/YuHYJHLCWLLGL25","url":"https://dblp.org/rec/conf/icra/YuHYJHLCWLLGL25","title":"UniAff: A Unified Representation of Affordances for Tool Usage and Articulation with Vision-Language Models.","year":2025,"types":["Inproceedings"],"venue":["ICRA"],"doi":["https://doi.org/10.1109/ICRA55743.2025.11127736"],"eventYear":2025,"numberOfCreators":12,"category":"conference","sources":["https://dblp.org/rec/conf/icra/YuHYJHLCWLLGL25","https://doi.org/10.1109/ICRA55743.2025.11127736"],"publicationYear":2025},{"key":"conf/iros/LiHYJHZLGL25","url":"https://dblp.org/rec/conf/iros/LiHYJHZLGL25","title":"SKT: Integrating State-Aware Keypoint Trajectories with Vision-Language Models for Robotic Garment Manipulation.","year":2025,"types":["Inproceedings"],"venue":["IROS"],"doi":["https://doi.org/10.1109/IROS60139.2025.11246904"],"eventYear":2025,"numberOfCreators":9,"category":"conference","sources":["https://dblp.org/rec/conf/iros/LiHYJHZLGL25","https://doi.org/10.1109/IROS60139.2025.11246904"],"publicationYear":2025},{"key":"conf/mm/Wang0ZG0YLL025","url":"https://dblp.org/rec/conf/mm/Wang0ZG0YLL025","title":"CoPESD: A Multi-Level Surgical Motion Dataset for Training Large Vision-Language Models to Co-Pilot Endoscopic Submucosal Dissection.","year":2025,"types":["Inproceedings"],"venue":["ACM Multimedia"],"doi":["https://doi.org/10.1145/3746027.3758200"],"eventYear":2025,"numberOfCreators":9,"category":"conference","sources":["https://dblp.org/rec/conf/mm/Wang0ZG0YLL025","https://doi.org/10.1145/3746027.3758200"],"publicationYear":2025},{"key":"conf/nips/ChenZJZYLL25","url":"https://dblp.org/rec/conf/nips/ChenZJZYLL25","title":"MINT-CoT: Enabling Interleaved Visual Tokens in Mathematical Chain-of-Thought Reasoning.","year":2025,"types":["Inproceedings"],"venue":["NeurIPS"],"doi":[],"eventYear":2025,"numberOfCreators":7,"category":"conference","sources":["https://dblp.org/rec/conf/nips/ChenZJZYLL25"],"publicationYear":2025},{"key":"conf/nips/FangDWHLTYYZDLL25","url":"https://dblp.org/rec/conf/nips/FangDWHLTYYZDLL25","title":"GoT: Unleashing Reasoning Capability of MLLM for Visual Generation and Editing.","year":2025,"types":["Inproceedings"],"venue":["NeurIPS"],"doi":[],"eventYear":2025,"numberOfCreators":12,"category":"conference","sources":["https://dblp.org/rec/conf/nips/FangDWHLTYYZDLL25"],"publicationYear":2025},{"key":"conf/nips/HuangCZCLJHGLYR25","url":"https://dblp.org/rec/conf/nips/HuangCZCLJHGLYR25","title":"EnerVerse: Envisioning Embodied Future Space for Robotics Manipulation.","year":2025,"types":["Inproceedings"],"venue":["NeurIPS"],"doi":[],"eventYear":2025,"numberOfCreators":11,"category":"conference","sources":["https://dblp.org/rec/conf/nips/HuangCZCLJHGLYR25"],"publicationYear":2025},{"key":"conf/nips/JiangGZZLZYHL25","url":"https://dblp.org/rec/conf/nips/JiangGZZLZYHL25","title":"T2I-R1: Reinforcing Image Generation with Collaborative Semantic-level and Token-level CoT.","year":2025,"types":["Inproceedings"],"venue":["NeurIPS"],"doi":[],"eventYear":2025,"numberOfCreators":9,"category":"conference","sources":["https://dblp.org/rec/conf/nips/JiangGZZLZYHL25"],"publicationYear":2025},{"key":"conf/nips/LiXYLSWZHL25","url":"https://dblp.org/rec/conf/nips/LiXYLSWZHL25","title":"NopeRoomGS: Indoor 3D Gaussian Splatting Optimization without Camera Pose Input.","year":2025,"types":["Inproceedings"],"venue":["NeurIPS"],"doi":[],"eventYear":2025,"numberOfCreators":9,"category":"conference","sources":["https://dblp.org/rec/conf/nips/LiXYLSWZHL25"],"publicationYear":2025},{"key":"conf/nips/LinWARCZGZZL25","url":"https://dblp.org/rec/conf/nips/LinWARCZGZZL25","title":"Perceive Anything: Recognize, Explain, Caption, and Segment Anything in Images and Videos.","year":2025,"types":["Inproceedings"],"venue":["NeurIPS"],"doi":[],"eventYear":2025,"numberOfCreators":10,"category":"conference","sources":["https://dblp.org/rec/conf/nips/LinWARCZGZZL25"],"publicationYear":2025},{"key":"conf/nips/LuYRHXWSZZL25","url":"https://dblp.org/rec/conf/nips/LuYRHXWSZZL25","title":"WebGen-Bench: Evaluating LLMs on Generating Interactive and Functional Websites from Scratch.","year":2025,"types":["Inproceedings"],"venue":["NeurIPS"],"doi":[],"eventYear":2025,"numberOfCreators":10,"category":"conference","sources":["https://dblp.org/rec/conf/nips/LuYRHXWSZZL25"],"publicationYear":2025},{"key":"conf/nips/ShaoWZSHZQLL25","url":"https://dblp.org/rec/conf/nips/ShaoWZSHZQLL25","title":"VividFace: A Robost and High-Fidelity Video Face Swapping Framework.","year":2025,"types":["Inproceedings"],"venue":["NeurIPS"],"doi":[],"eventYear":2025,"numberOfCreators":9,"category":"conference","sources":["https://dblp.org/rec/conf/nips/ShaoWZSHZQLL25"],"publicationYear":2025},{"key":"conf/nips/TianLLZSDZSZLLW25","url":"https://dblp.org/rec/conf/nips/TianLLZSDZSZLLW25","title":"NaViL: Rethinking Scaling Properties of Native Multimodal Large Language Models under Data Constraints.","year":2025,"types":["Inproceedings"],"venue":["NeurIPS"],"doi":[],"eventYear":2025,"numberOfCreators":14,"category":"conference","sources":["https://dblp.org/rec/conf/nips/TianLLZSDZSZLLW25"],"publicationYear":2025},{"key":"conf/nips/TongGZSWXLH25","url":"https://dblp.org/rec/conf/nips/TongGZSWXLH25","title":"Delving into RL for Image Generation with CoT: A Study on DPO vs. GRPO.","year":2025,"types":["Inproceedings"],"venue":["NeurIPS"],"doi":[],"eventYear":2025,"numberOfCreators":8,"category":"conference","sources":["https://dblp.org/rec/conf/nips/TongGZSWXLH25"],"publicationYear":2025},{"key":"conf/nips/WangYLZWDLL25","url":"https://dblp.org/rec/conf/nips/WangYLZWDLL25","title":"UAV-Flow Colosseo: A Real-World Benchmark for Flying-on-a-Word UAV Imitation Learning.","year":2025,"types":["Inproceedings"],"venue":["NeurIPS"],"doi":[],"eventYear":2025,"numberOfCreators":8,"category":"conference","sources":["https://dblp.org/rec/conf/nips/WangYLZWDLL25"],"publicationYear":2025},{"key":"conf/nips/XiaoWCLLHFBHLRW25","url":"https://dblp.org/rec/conf/nips/XiaoWCLLHFBHLRW25","title":"UI-Genie: A Self-Improving Approach for Iteratively Boosting MLLM-based Mobile GUI Agents.","year":2025,"types":["Inproceedings"],"venue":["NeurIPS"],"doi":[],"eventYear":2025,"numberOfCreators":15,"category":"conference","sources":["https://dblp.org/rec/conf/nips/XiaoWCLLHFBHLRW25"],"publicationYear":2025},{"key":"conf/nips/YeJHZHYLHL25","url":"https://dblp.org/rec/conf/nips/YeJHZHYLHL25","title":"BLINK-Twice: You see, but do you observe? A Reasoning Benchmark on Visual Perception.","year":2025,"types":["Inproceedings"],"venue":["NeurIPS"],"doi":[],"eventYear":2025,"numberOfCreators":9,"category":"conference","sources":["https://dblp.org/rec/conf/nips/YeJHZHYLHL25"],"publicationYear":2025},{"key":"journals/cea/DuYZCHXJZMWXL25","url":"https://dblp.org/rec/journals/cea/DuYZCHXJZMWXL25","title":"Design and experiment of a soil organic matter sensor-based variable-rate seeding control system for maize.","year":2025,"types":["Article"],"venue":["Comput. Electron. Agric."],"doi":["https://doi.org/10.1016/J.COMPAG.2024.109752"],"numberOfCreators":12,"category":"journal","sources":["https://dblp.org/rec/journals/cea/DuYZCHXJZMWXL25","https://doi.org/10.1016/J.COMPAG.2024.109752"],"publicationYear":2025,"eventYear":null},{"key":"journals/ijon/HuangLZLWLLY25","url":"https://dblp.org/rec/journals/ijon/HuangLZLWLLY25","title":"MM-instruct: Generated visual instructions for large multimodal model alignment.","year":2025,"types":["Article"],"venue":["Neurocomputing"],"doi":["https://doi.org/10.1016/J.NEUCOM.2025.131164"],"numberOfCreators":8,"category":"journal","sources":["https://dblp.org/rec/journals/ijon/HuangLZLWLLY25","https://doi.org/10.1016/J.NEUCOM.2025.131164"],"publicationYear":2025,"eventYear":null},{"key":"journals/jiii/XieYHCZLXW25","url":"https://dblp.org/rec/journals/jiii/XieYHCZLXW25","title":"Maize precision seeding scheme based on multi-sensor information fusion.","year":2025,"types":["Article"],"venue":["J. Ind. Inf. Integr."],"doi":["https://doi.org/10.1016/J.JII.2024.100758"],"numberOfCreators":8,"category":"journal","sources":["https://dblp.org/rec/journals/jiii/XieYHCZLXW25","https://doi.org/10.1016/J.JII.2024.100758"],"publicationYear":2025,"eventYear":null},{"key":"journals/tbd/ShaoLHGXZMHLQL25","url":"https://dblp.org/rec/journals/tbd/ShaoLHGXZMHLQL25","title":"TinyLVLM-eHub: Towards Comprehensive and Efficient Evaluation for Large Vision-Language Models.","year":2025,"types":["Article"],"venue":["IEEE Trans. Big Data"],"doi":["https://doi.org/10.1109/TBDATA.2025.3536930"],"numberOfCreators":11,"category":"journal","sources":["https://dblp.org/rec/journals/tbd/ShaoLHGXZMHLQL25","https://doi.org/10.1109/TBDATA.2025.3536930"],"publicationYear":2025,"eventYear":null},{"key":"journals/tmi/YangXYXLZ25","url":"https://dblp.org/rec/journals/tmi/YangXYXLZ25","title":"Segmentation and Vascular Vectorization for Coronary Artery by Geometry-Based Cascaded Neural Network.","year":2025,"types":["Article"],"venue":["IEEE Trans. Medical Imaging"],"doi":["https://doi.org/10.1109/TMI.2024.3435714"],"numberOfCreators":6,"category":"journal","sources":["https://dblp.org/rec/journals/tmi/YangXYXLZ25","https://doi.org/10.1109/TMI.2024.3435714"],"publicationYear":2025,"eventYear":null},{"key":"journals/tmlr/LiuZLLGXLCHRWLWWLCLWXLL25","url":"https://dblp.org/rec/journals/tmlr/LiuZLLGXLCHRWLWWLCLWXLL25","title":"LLM-Powered GUI Agents in Phone Automation: Surveying Progress and Prospects.","year":2025,"types":["Article"],"venue":["Trans. Mach. Learn. Res."],"doi":[],"numberOfCreators":21,"category":"journal","sources":["https://dblp.org/rec/journals/tmlr/LiuZLLGXLCHRWLWWLCLWXLL25"],"publicationYear":2025,"eventYear":null},{"key":"journals/tmlr/LuZWRSYPZL25","url":"https://dblp.org/rec/journals/tmlr/LuZWRSYPZL25","title":"Step-Controlled DPO: Leveraging Stepwise Errors for Enhancing Mathematical Reasoning of Language Models.","year":2025,"types":["Article"],"venue":["Trans. Mach. Learn. Res."],"doi":[],"numberOfCreators":9,"category":"journal","sources":["https://dblp.org/rec/journals/tmlr/LuZWRSYPZL25"],"publicationYear":2025,"eventYear":null},{"key":"journals/tmlr/PuNYR0025","url":"https://dblp.org/rec/journals/tmlr/PuNYR0025","title":"UniZero: Generalized and Efficient Planning with Scalable Latent World Models.","year":2025,"types":["Article"],"venue":["Trans. Mach. Learn. Res."],"doi":[],"numberOfCreators":6,"category":"journal","sources":["https://dblp.org/rec/journals/tmlr/PuNYR0025"],"publicationYear":2025,"eventYear":null}],"candidatePreprints":[{"key":"journals/corr/abs-2501-01149","url":"https://dblp.org/rec/journals/corr/abs-2501-01149","title":"A3: Android Agent Arena for Mobile GUI Agents.","year":2025,"types":["Informal"],"venue":["CoRR"],"doi":["https://doi.org/10.48550/ARXIV.2501.01149"],"numberOfCreators":8,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2501-01149","https://doi.org/10.48550/ARXIV.2501.01149"],"publicationYear":2025,"eventYear":null},{"key":"journals/corr/abs-2501-01895","url":"https://dblp.org/rec/journals/corr/abs-2501-01895","title":"EnerVerse: Envisioning Embodied Future Space for Robotics Manipulation.","year":2025,"types":["Informal"],"venue":["CoRR"],"doi":["https://doi.org/10.48550/ARXIV.2501.01895"],"numberOfCreators":10,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2501-01895","https://doi.org/10.48550/ARXIV.2501.01895"],"publicationYear":2025,"eventYear":null},{"key":"journals/corr/abs-2501-02690","url":"https://dblp.org/rec/journals/corr/abs-2501-02690","title":"GS-DiT: Advancing Video Generation with Pseudo 4D Gaussian Fields through Efficient Dense 3D Point Tracking.","year":2025,"types":["Informal"],"venue":["CoRR"],"doi":["https://doi.org/10.48550/ARXIV.2501.02690"],"numberOfCreators":6,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2501-02690","https://doi.org/10.48550/ARXIV.2501.02690"],"publicationYear":2025,"eventYear":null},{"key":"journals/corr/abs-2501-13920","url":"https://dblp.org/rec/journals/corr/abs-2501-13920","title":"IMAGINE-E: Image Generation Intelligence Evaluation of State-of-the-art Text-to-Image Models.","year":2025,"types":["Informal"],"venue":["CoRR"],"doi":["https://doi.org/10.48550/ARXIV.2501.13920"],"numberOfCreators":15,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2501-13920","https://doi.org/10.48550/ARXIV.2501.13920"],"publicationYear":2025,"eventYear":null},{"key":"journals/corr/abs-2501-13926","url":"https://dblp.org/rec/journals/corr/abs-2501-13926","title":"Can We Generate Images with CoT? Let's Verify and Reinforce Image Generation Step by Step.","year":2025,"types":["Informal"],"venue":["CoRR"],"doi":["https://doi.org/10.48550/ARXIV.2501.13926"],"numberOfCreators":7,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2501-13926","https://doi.org/10.48550/ARXIV.2501.13926"],"publicationYear":2025,"eventYear":null},{"key":"journals/corr/abs-2502-06782","url":"https://dblp.org/rec/journals/corr/abs-2502-06782","title":"Lumina-Video: Efficient and Flexible Video Generation with Multi-scale Next-DiT.","year":2025,"types":["Informal"],"venue":["CoRR"],"doi":["https://doi.org/10.48550/ARXIV.2502.06782"],"numberOfCreators":19,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2502-06782","https://doi.org/10.48550/ARXIV.2502.06782"],"publicationYear":2025,"eventYear":null},{"key":"journals/corr/abs-2502-09621","url":"https://dblp.org/rec/journals/corr/abs-2502-09621","title":"MME-CoT: Benchmarking Chain-of-Thought in Large Multimodal Models for Reasoning Quality, Robustness, and Efficiency.","year":2025,"types":["Informal"],"venue":["CoRR"],"doi":["https://doi.org/10.48550/ARXIV.2502.09621"],"numberOfCreators":14,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2502-09621","https://doi.org/10.48550/ARXIV.2502.09621"],"publicationYear":2025,"eventYear":null},{"key":"journals/corr/abs-2502-21093","url":"https://dblp.org/rec/journals/corr/abs-2502-21093","title":"FlexDrive: Toward Trajectory Flexibility in Driving Scene Reconstruction and Rendering.","year":2025,"types":["Informal"],"venue":["CoRR"],"doi":["https://doi.org/10.48550/ARXIV.2502.21093"],"numberOfCreators":7,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2502-21093","https://doi.org/10.48550/ARXIV.2502.21093"],"publicationYear":2025,"eventYear":null},{"key":"journals/corr/abs-2503-06019","url":"https://dblp.org/rec/journals/corr/abs-2503-06019","title":"GenieBlue: Integrating both Linguistic and Multimodal Capabilities for Large Language Models on Mobile Devices.","year":2025,"types":["Informal"],"venue":["CoRR"],"doi":["https://doi.org/10.48550/ARXIV.2503.06019"],"numberOfCreators":13,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2503-06019","https://doi.org/10.48550/ARXIV.2503.06019"],"publicationYear":2025,"eventYear":null},{"key":"journals/corr/abs-2503-06029","url":"https://dblp.org/rec/journals/corr/abs-2503-06029","title":"SmartBench: Is Your LLM Truly a Good Chinese Smartphone Assistant?","year":2025,"types":["Informal"],"venue":["CoRR"],"doi":["https://doi.org/10.48550/ARXIV.2503.06029"],"numberOfCreators":7,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2503-06029","https://doi.org/10.48550/ARXIV.2503.06029"],"publicationYear":2025,"eventYear":null},{"key":"journals/corr/abs-2503-07050","url":"https://dblp.org/rec/journals/corr/abs-2503-07050","title":"TIDE : Temporal-Aware Sparse Autoencoders for Interpretable Diffusion Transformers in Image Generation.","year":2025,"types":["Informal"],"venue":["CoRR"],"doi":["https://doi.org/10.48550/ARXIV.2503.07050"],"numberOfCreators":6,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2503-07050","https://doi.org/10.48550/ARXIV.2503.07050"],"publicationYear":2025,"eventYear":null},{"key":"journals/corr/abs-2503-10592","url":"https://dblp.org/rec/journals/corr/abs-2503-10592","title":"CameraCtrl II: Dynamic Scene Exploration via Camera-controlled Video Diffusion Models.","year":2025,"types":["Informal"],"venue":["CoRR"],"doi":["https://doi.org/10.48550/ARXIV.2503.10592"],"numberOfCreators":10,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2503-10592","https://doi.org/10.48550/ARXIV.2503.10592"],"publicationYear":2025,"eventYear":null},{"key":"journals/corr/abs-2503-10639","url":"https://dblp.org/rec/journals/corr/abs-2503-10639","title":"GoT: Unleashing Reasoning Capability of Multimodal Large Language Model for Visual Generation and Editing.","year":2025,"types":["Informal"],"venue":["CoRR"],"doi":["https://doi.org/10.48550/ARXIV.2503.10639"],"numberOfCreators":12,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2503-10639","https://doi.org/10.48550/ARXIV.2503.10639"],"publicationYear":2025,"eventYear":null},{"key":"journals/corr/abs-2503-11646","url":"https://dblp.org/rec/journals/corr/abs-2503-11646","title":"Adversarial Data Collection: Human-Collaborative Perturbations for Efficient and Robust Robotic Imitation Learning.","year":2025,"types":["Informal"],"venue":["CoRR"],"doi":["https://doi.org/10.48550/ARXIV.2503.11646"],"numberOfCreators":8,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2503-11646","https://doi.org/10.48550/ARXIV.2503.11646"],"publicationYear":2025,"eventYear":null},{"key":"journals/corr/abs-2503-13980","url":"https://dblp.org/rec/journals/corr/abs-2503-13980","title":"Empowering LLMs in Decision Games through Algorithmic Data Synthesis.","year":2025,"types":["Informal"],"venue":["CoRR"],"doi":["https://doi.org/10.48550/ARXIV.2503.13980"],"numberOfCreators":5,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2503-13980","https://doi.org/10.48550/ARXIV.2503.13980"],"publicationYear":2025,"eventYear":null},{"key":"journals/corr/abs-2503-18100","url":"https://dblp.org/rec/journals/corr/abs-2503-18100","title":"M3Net: Multimodal Multi-task Learning for 3D Detection, Segmentation, and Occupancy Prediction in Autonomous Driving.","year":2025,"types":["Informal"],"venue":["CoRR"],"doi":["https://doi.org/10.48550/ARXIV.2503.18100"],"numberOfCreators":7,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2503-18100","https://doi.org/10.48550/ARXIV.2503.18100"],"publicationYear":2025,"eventYear":null},{"key":"journals/corr/abs-2503-21620","url":"https://dblp.org/rec/journals/corr/abs-2503-21620","title":"UI-R1: Enhancing Action Prediction of GUI Agents by Reinforcement Learning.","year":2025,"types":["Informal"],"venue":["CoRR"],"doi":["https://doi.org/10.48550/ARXIV.2503.21620"],"numberOfCreators":8,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2503-21620","https://doi.org/10.48550/ARXIV.2503.21620"],"publicationYear":2025,"eventYear":null},{"key":"journals/corr/abs-2503-21749","url":"https://dblp.org/rec/journals/corr/abs-2503-21749","title":"LeX-Art: Rethinking Text Generation via Scalable High-Quality Data Synthesis.","year":2025,"types":["Informal"],"venue":["CoRR"],"doi":["https://doi.org/10.48550/ARXIV.2503.21749"],"numberOfCreators":13,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2503-21749","https://doi.org/10.48550/ARXIV.2503.21749"],"publicationYear":2025,"eventYear":null},{"key":"journals/corr/abs-2503-21758","url":"https://dblp.org/rec/journals/corr/abs-2503-21758","title":"Lumina-Image 2.0: A Unified and Efficient Image Generative Framework.","year":2025,"types":["Informal"],"venue":["CoRR"],"doi":["https://doi.org/10.48550/ARXIV.2503.21758"],"numberOfCreators":23,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2503-21758","https://doi.org/10.48550/ARXIV.2503.21758"],"publicationYear":2025,"eventYear":null},{"key":"journals/corr/abs-2503-22179","url":"https://dblp.org/rec/journals/corr/abs-2503-22179","title":"High-Fidelity Diffusion Face Swapping with ID-Constrained Facial Conditioning.","year":2025,"types":["Informal"],"venue":["CoRR"],"doi":["https://doi.org/10.48550/ARXIV.2503.22179"],"numberOfCreators":8,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2503-22179","https://doi.org/10.48550/ARXIV.2503.22179"],"publicationYear":2025,"eventYear":null},{"key":"journals/corr/abs-2504-14709","url":"https://dblp.org/rec/journals/corr/abs-2504-14709","title":"Exposing the Copycat Problem of Imitation-based Planner: A Novel Closed-Loop Simulator, Causal Benchmark and Joint IL-RL Baseline.","year":2025,"types":["Informal"],"venue":["CoRR"],"doi":["https://doi.org/10.48550/ARXIV.2504.14709"],"numberOfCreators":3,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2504-14709","https://doi.org/10.48550/ARXIV.2504.14709"],"publicationYear":2025,"eventYear":null},{"key":"journals/corr/abs-2504-16080","url":"https://dblp.org/rec/journals/corr/abs-2504-16080","title":"From Reflection to Perfection: Scaling Inference-Time Optimization for Text-to-Image Diffusion Models via Reflection Tuning.","year":2025,"types":["Informal"],"venue":["CoRR"],"doi":["https://doi.org/10.48550/ARXIV.2504.16080"],"numberOfCreators":9,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2504-16080","https://doi.org/10.48550/ARXIV.2504.16080"],"publicationYear":2025,"eventYear":null},{"key":"journals/corr/abs-2504-19838","url":"https://dblp.org/rec/journals/corr/abs-2504-19838","title":"LLM-Powered GUI Agents in Phone Automation: Surveying Progress and Prospects.","year":2025,"types":["Informal"],"venue":["CoRR"],"doi":["https://doi.org/10.48550/ARXIV.2504.19838"],"numberOfCreators":18,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2504-19838","https://doi.org/10.48550/ARXIV.2504.19838"],"publicationYear":2025,"eventYear":null},{"key":"journals/corr/abs-2505-00703","url":"https://dblp.org/rec/journals/corr/abs-2505-00703","title":"T2I-R1: Reinforcing Image Generation with Collaborative Semantic-level and Token-level CoT.","year":2025,"types":["Informal"],"venue":["CoRR"],"doi":["https://doi.org/10.48550/ARXIV.2505.00703"],"numberOfCreators":9,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2505-00703","https://doi.org/10.48550/ARXIV.2505.00703"],"publicationYear":2025,"eventYear":null},{"key":"journals/corr/abs-2505-03733","url":"https://dblp.org/rec/journals/corr/abs-2505-03733","title":"WebGen-Bench: Evaluating LLMs on Generating Interactive and Functional Websites from Scratch.","year":2025,"types":["Informal"],"venue":["CoRR"],"doi":["https://doi.org/10.48550/ARXIV.2505.03733"],"numberOfCreators":10,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2505-03733","https://doi.org/10.48550/ARXIV.2505.03733"],"publicationYear":2025,"eventYear":null},{"key":"journals/corr/abs-2505-05446","url":"https://dblp.org/rec/journals/corr/abs-2505-05446","title":"Adaptive Markup Language Generation for Contextually-Grounded Visual Document Understanding.","year":2025,"types":["Informal"],"venue":["CoRR"],"doi":["https://doi.org/10.48550/ARXIV.2505.05446"],"numberOfCreators":15,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2505-05446","https://doi.org/10.48550/ARXIV.2505.05446"],"publicationYear":2025,"eventYear":null},{"key":"journals/corr/abs-2505-09723","url":"https://dblp.org/rec/journals/corr/abs-2505-09723","title":"EnerVerse-AC: Envisioning Embodied Environments with Action Condition.","year":2025,"types":["Informal"],"venue":["CoRR"],"doi":["https://doi.org/10.48550/ARXIV.2505.09723"],"numberOfCreators":11,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2505-09723","https://doi.org/10.48550/ARXIV.2505.09723"],"publicationYear":2025,"eventYear":null},{"key":"journals/corr/abs-2505-10557","url":"https://dblp.org/rec/journals/corr/abs-2505-10557","title":"MathCoder-VL: Bridging Vision and Code for Enhanced Multimodal Mathematical Reasoning.","year":2025,"types":["Informal"],"venue":["CoRR"],"doi":["https://doi.org/10.48550/ARXIV.2505.10557"],"numberOfCreators":11,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2505-10557","https://doi.org/10.48550/ARXIV.2505.10557"],"publicationYear":2025,"eventYear":null},{"key":"journals/corr/abs-2505-11245","url":"https://dblp.org/rec/journals/corr/abs-2505-11245","title":"Diffusion-NPO: Negative Preference Optimization for Better Preference Aligned Generation of Diffusion Models.","year":2025,"types":["Informal"],"venue":["CoRR"],"doi":["https://doi.org/10.48550/ARXIV.2505.11245"],"numberOfCreators":5,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2505-11245","https://doi.org/10.48550/ARXIV.2505.11245"],"publicationYear":2025,"eventYear":null},{"key":"journals/corr/abs-2505-11777","url":"https://dblp.org/rec/journals/corr/abs-2505-11777","title":"Self-NPO: Negative Preference Optimization of Diffusion Models by Simply Learning from Itself without Explicit Preference Annotations.","year":2025,"types":["Informal"],"venue":["CoRR"],"doi":["https://doi.org/10.48550/ARXIV.2505.11777"],"numberOfCreators":6,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2505-11777","https://doi.org/10.48550/ARXIV.2505.11777"],"publicationYear":2025,"eventYear":null},{"key":"journals/corr/abs-2505-15725","url":"https://dblp.org/rec/journals/corr/abs-2505-15725","title":"UAV-Flow Colosseo: A Real-World Benchmark for Flying-on-a-Word UAV Imitation Learning.","year":2025,"types":["Informal"],"venue":["CoRR"],"doi":["https://doi.org/10.48550/ARXIV.2505.15725"],"numberOfCreators":8,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2505-15725","https://doi.org/10.48550/ARXIV.2505.15725"],"publicationYear":2025,"eventYear":null},{"key":"journals/corr/abs-2505-16805","url":"https://dblp.org/rec/journals/corr/abs-2505-16805","title":"SOLVE: Synergy of Language-Vision and End-to-End Networks for Autonomous Driving.","year":2025,"types":["Informal"],"venue":["CoRR"],"doi":["https://doi.org/10.48550/ARXIV.2505.16805"],"numberOfCreators":6,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2505-16805","https://doi.org/10.48550/ARXIV.2505.16805"],"publicationYear":2025,"eventYear":null},{"key":"journals/corr/abs-2505-17011","url":"https://dblp.org/rec/journals/corr/abs-2505-17011","title":"Learning Adaptive and Temporally Causal Video Tokenization in a 1D Latent Space.","year":2025,"types":["Informal"],"venue":["CoRR"],"doi":["https://doi.org/10.48550/ARXIV.2505.17011"],"numberOfCreators":10,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2505-17011","https://doi.org/10.48550/ARXIV.2505.17011"],"publicationYear":2025,"eventYear":null},{"key":"journals/corr/abs-2505-17017","url":"https://dblp.org/rec/journals/corr/abs-2505-17017","title":"Delving into RL for Image Generation with CoT: A Study on DPO vs. GRPO.","year":2025,"types":["Informal"],"venue":["CoRR"],"doi":["https://doi.org/10.48550/ARXIV.2505.17017"],"numberOfCreators":8,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2505-17017","https://doi.org/10.48550/ARXIV.2505.17017"],"publicationYear":2025,"eventYear":null},{"key":"journals/corr/abs-2505-17022","url":"https://dblp.org/rec/journals/corr/abs-2505-17022","title":"GoT-R1: Unleashing Reasoning Capability of MLLM for Visual Generation with Reinforcement Learning.","year":2025,"types":["Informal"],"venue":["CoRR"],"doi":["https://doi.org/10.48550/ARXIV.2505.17022"],"numberOfCreators":8,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2505-17022","https://doi.org/10.48550/ARXIV.2505.17022"],"publicationYear":2025,"eventYear":null},{"key":"journals/corr/abs-2505-21496","url":"https://dblp.org/rec/journals/corr/abs-2505-21496","title":"UI-Genie: A Self-Improving Approach for Iteratively Boosting MLLM-based Mobile GUI Agents.","year":2025,"types":["Informal"],"venue":["CoRR"],"doi":["https://doi.org/10.48550/ARXIV.2505.21496"],"numberOfCreators":15,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2505-21496","https://doi.org/10.48550/ARXIV.2505.21496"],"publicationYear":2025,"eventYear":null},{"key":"journals/corr/abs-2505-23540","url":"https://dblp.org/rec/journals/corr/abs-2505-23540","title":"Probability-Consistent Preference Optimization for Enhanced LLM Reasoning.","year":2025,"types":["Informal"],"venue":["CoRR"],"doi":["https://doi.org/10.48550/ARXIV.2505.23540"],"numberOfCreators":9,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2505-23540","https://doi.org/10.48550/ARXIV.2505.23540"],"publicationYear":2025,"eventYear":null},{"key":"journals/corr/abs-2506-05302","url":"https://dblp.org/rec/journals/corr/abs-2506-05302","title":"Perceive Anything: Recognize, Explain, Caption, and Segment Anything in Images and Videos.","year":2025,"types":["Informal"],"venue":["CoRR"],"doi":["https://doi.org/10.48550/ARXIV.2506.05302"],"numberOfCreators":10,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2506-05302","https://doi.org/10.48550/ARXIV.2506.05302"],"publicationYear":2025,"eventYear":null},{"key":"journals/corr/abs-2506-05331","url":"https://dblp.org/rec/journals/corr/abs-2506-05331","title":"MINT-CoT: Enabling Interleaved Visual Tokens in Mathematical Chain-of-Thought Reasoning.","year":2025,"types":["Informal"],"venue":["CoRR"],"doi":["https://doi.org/10.48550/ARXIV.2506.05331"],"numberOfCreators":7,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2506-05331","https://doi.org/10.48550/ARXIV.2506.05331"],"publicationYear":2025,"eventYear":null},{"key":"journals/corr/abs-2507-13032","url":"https://dblp.org/rec/journals/corr/abs-2507-13032","title":"Resurrect Mask AutoRegressive Modeling for Efficient and Scalable Image Generation.","year":2025,"types":["Informal"],"venue":["CoRR"],"doi":["https://doi.org/10.48550/ARXIV.2507.13032"],"numberOfCreators":11,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2507-13032","https://doi.org/10.48550/ARXIV.2507.13032"],"publicationYear":2025,"eventYear":null},{"key":"journals/corr/abs-2507-14675","url":"https://dblp.org/rec/journals/corr/abs-2507-14675","title":"Docopilot: Improving Multimodal Models for Document-Level Understanding.","year":2025,"types":["Informal"],"venue":["CoRR"],"doi":["https://doi.org/10.48550/ARXIV.2507.14675"],"numberOfCreators":12,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2507-14675","https://doi.org/10.48550/ARXIV.2507.14675"],"publicationYear":2025,"eventYear":null},{"key":"journals/corr/abs-2507-17205","url":"https://dblp.org/rec/journals/corr/abs-2507-17205","title":"VBCD: A Voxel-Based Framework for Personalized Dental Crown Design.","year":2025,"types":["Informal"],"venue":["CoRR"],"doi":["https://doi.org/10.48550/ARXIV.2507.17205"],"numberOfCreators":6,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2507-17205","https://doi.org/10.48550/ARXIV.2507.17205"],"publicationYear":2025,"eventYear":null},{"key":"journals/corr/abs-2507-17801","url":"https://dblp.org/rec/journals/corr/abs-2507-17801","title":"Lumina-mGPT 2.0: Stand-Alone AutoRegressive Image Modeling.","year":2025,"types":["Informal"],"venue":["CoRR"],"doi":["https://doi.org/10.48550/ARXIV.2507.17801"],"numberOfCreators":21,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2507-17801","https://doi.org/10.48550/ARXIV.2507.17801"],"publicationYear":2025,"eventYear":null},{"key":"journals/corr/abs-2508-09987","url":"https://dblp.org/rec/journals/corr/abs-2508-09987","title":"Echo-4o: Harnessing the Power of GPT-4o Synthetic Images for Improved Image Generation.","year":2025,"types":["Informal"],"venue":["CoRR"],"doi":["https://doi.org/10.48550/ARXIV.2508.09987"],"numberOfCreators":12,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2508-09987","https://doi.org/10.48550/ARXIV.2508.09987"],"publicationYear":2025,"eventYear":null},{"key":"journals/corr/abs-2508-19532","url":"https://dblp.org/rec/journals/corr/abs-2508-19532","title":"Alignment with Fill-In-the-Middle for Enhancing Code Generation.","year":2025,"types":["Informal"],"venue":["CoRR"],"doi":["https://doi.org/10.48550/ARXIV.2508.19532"],"numberOfCreators":10,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2508-19532","https://doi.org/10.48550/ARXIV.2508.19532"],"publicationYear":2025,"eventYear":null},{"key":"journals/corr/abs-2509-05657","url":"https://dblp.org/rec/journals/corr/abs-2509-05657","title":"LM-Searcher: Cross-domain Neural Architecture Search with LLMs via Unified Numerical Encoding.","year":2025,"types":["Informal"],"venue":["CoRR"],"doi":["https://doi.org/10.48550/ARXIV.2509.05657"],"numberOfCreators":10,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2509-05657","https://doi.org/10.48550/ARXIV.2509.05657"],"publicationYear":2025,"eventYear":null},{"key":"journals/corr/abs-2509-07945","url":"https://dblp.org/rec/journals/corr/abs-2509-07945","title":"One Model for All Tasks: Leveraging Efficient World Models in Multi-Task Planning.","year":2025,"types":["Informal"],"venue":["CoRR"],"doi":["https://doi.org/10.48550/ARXIV.2509.07945"],"numberOfCreators":6,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2509-07945","https://doi.org/10.48550/ARXIV.2509.07945"],"publicationYear":2025,"eventYear":null},{"key":"journals/corr/abs-2509-09680","url":"https://dblp.org/rec/journals/corr/abs-2509-09680","title":"FLUX-Reason-6M & PRISM-Bench: A Million-Scale Text-to-Image Reasoning Dataset and Comprehensive Benchmark.","year":2025,"types":["Informal"],"venue":["CoRR"],"doi":["https://doi.org/10.48550/ARXIV.2509.09680"],"numberOfCreators":10,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2509-09680","https://doi.org/10.48550/ARXIV.2509.09680"],"publicationYear":2025,"eventYear":null},{"key":"journals/corr/abs-2509-16679","url":"https://dblp.org/rec/journals/corr/abs-2509-16679","title":"Reinforcement Learning Meets Large Language Models: A Survey of Advancements and Applications Across the LLM Lifecycle.","year":2025,"types":["Informal"],"venue":["CoRR"],"doi":["https://doi.org/10.48550/ARXIV.2509.16679"],"numberOfCreators":10,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2509-16679","https://doi.org/10.48550/ARXIV.2509.16679"],"publicationYear":2025,"eventYear":null},{"key":"journals/corr/abs-2509-22644","url":"https://dblp.org/rec/journals/corr/abs-2509-22644","title":"WebGen-Agent: Enhancing Interactive Website Generation with Multi-Level Feedback and Step-Level Reinforcement Learning.","year":2025,"types":["Informal"],"venue":["CoRR"],"doi":["https://doi.org/10.48550/ARXIV.2509.22644"],"numberOfCreators":8,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2509-22644","https://doi.org/10.48550/ARXIV.2509.22644"],"publicationYear":2025,"eventYear":null},{"key":"journals/corr/abs-2509-22651","url":"https://dblp.org/rec/journals/corr/abs-2509-22651","title":"VoiceAssistant-Eval: Benchmarking AI Assistants across Listening, Speaking, and Viewing.","year":2025,"types":["Informal"],"venue":["CoRR"],"doi":["https://doi.org/10.48550/ARXIV.2509.22651"],"numberOfCreators":5,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2509-22651","https://doi.org/10.48550/ARXIV.2509.22651"],"publicationYear":2025,"eventYear":null},{"key":"journals/corr/abs-2510-05091","url":"https://dblp.org/rec/journals/corr/abs-2510-05091","title":"Factuality Matters: When Image Generation and Editing Meet Structured Visuals.","year":2025,"types":["Informal"],"venue":["CoRR"],"doi":["https://doi.org/10.48550/ARXIV.2510.05091"],"numberOfCreators":11,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2510-05091","https://doi.org/10.48550/ARXIV.2510.05091"],"publicationYear":2025,"eventYear":null},{"key":"journals/corr/abs-2510-06308","url":"https://dblp.org/rec/journals/corr/abs-2510-06308","title":"Lumina-DiMOO: An Omni Diffusion Large Language Model for Multi-Modal Generation and Understanding.","year":2025,"types":["Informal"],"venue":["CoRR"],"doi":["https://doi.org/10.48550/ARXIV.2510.06308"],"numberOfCreators":32,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2510-06308","https://doi.org/10.48550/ARXIV.2510.06308"],"publicationYear":2025,"eventYear":null},{"key":"journals/corr/abs-2510-08565","url":"https://dblp.org/rec/journals/corr/abs-2510-08565","title":"NaViL: Rethinking Scaling Properties of Native Multimodal Large Language Models under Data Constraints.","year":2025,"types":["Informal"],"venue":["CoRR"],"doi":["https://doi.org/10.48550/ARXIV.2510.08565"],"numberOfCreators":14,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2510-08565","https://doi.org/10.48550/ARXIV.2510.08565"],"publicationYear":2025,"eventYear":null},{"key":"journals/corr/abs-2510-09361","url":"https://dblp.org/rec/journals/corr/abs-2510-09361","title":"BLINK-Twice: You see, but do you observe? A Reasoning Benchmark on Visual Perception.","year":2025,"types":["Informal"],"venue":["CoRR"],"doi":["https://doi.org/10.48550/ARXIV.2510.09361"],"numberOfCreators":9,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2510-09361","https://doi.org/10.48550/ARXIV.2510.09361"],"publicationYear":2025,"eventYear":null},{"key":"journals/corr/abs-2510-10634","url":"https://dblp.org/rec/journals/corr/abs-2510-10634","title":"ProteinAE: Protein Diffusion Autoencoders for Structure Encoding.","year":2025,"types":["Informal"],"venue":["CoRR"],"doi":["https://doi.org/10.48550/ARXIV.2510.10634"],"numberOfCreators":8,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2510-10634","https://doi.org/10.48550/ARXIV.2510.10634"],"publicationYear":2025,"eventYear":null},{"key":"journals/corr/abs-2510-11718","url":"https://dblp.org/rec/journals/corr/abs-2510-11718","title":"CodePlot-CoT: Mathematical Visual Reasoning by Thinking with Code-Driven Images.","year":2025,"types":["Informal"],"venue":["CoRR"],"doi":["https://doi.org/10.48550/ARXIV.2510.11718"],"numberOfCreators":13,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2510-11718","https://doi.org/10.48550/ARXIV.2510.11718"],"publicationYear":2025,"eventYear":null},{"key":"journals/corr/abs-2510-12709","url":"https://dblp.org/rec/journals/corr/abs-2510-12709","title":"SAIL-Embedding Technical Report: Omni-modal Embedding Foundation Model.","year":2025,"types":["Informal"],"venue":["CoRR"],"doi":["https://doi.org/10.48550/ARXIV.2510.12709"],"numberOfCreators":18,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2510-12709","https://doi.org/10.48550/ARXIV.2510.12709"],"publicationYear":2025,"eventYear":null},{"key":"journals/corr/abs-2510-14958","url":"https://dblp.org/rec/journals/corr/abs-2510-14958","title":"MathCanvas: Intrinsic Visual Chain-of-Thought for Multimodal Mathematical Reasoning.","year":2025,"types":["Informal"],"venue":["CoRR"],"doi":["https://doi.org/10.48550/ARXIV.2510.14958"],"numberOfCreators":14,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2510-14958","https://doi.org/10.48550/ARXIV.2510.14958"],"publicationYear":2025,"eventYear":null},{"key":"journals/corr/abs-2510-17681","url":"https://dblp.org/rec/journals/corr/abs-2510-17681","title":"PICABench: How Far Are We from Physically Realistic Image Editing?","year":2025,"types":["Informal"],"venue":["CoRR"],"doi":["https://doi.org/10.48550/ARXIV.2510.17681"],"numberOfCreators":13,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2510-17681","https://doi.org/10.48550/ARXIV.2510.17681"],"publicationYear":2025,"eventYear":null},{"key":"journals/corr/abs-2510-26802","url":"https://dblp.org/rec/journals/corr/abs-2510-26802","title":"Are Video Models Ready as Zero-Shot Reasoners? An Empirical Study with the MME-CoF Benchmark.","year":2025,"types":["Informal"],"venue":["CoRR"],"doi":["https://doi.org/10.48550/ARXIV.2510.26802"],"numberOfCreators":10,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2510-26802","https://doi.org/10.48550/ARXIV.2510.26802"],"publicationYear":2025,"eventYear":null},{"key":"journals/corr/abs-2511-06271","url":"https://dblp.org/rec/journals/corr/abs-2511-06271","title":"RelightMaster: Precise Video Relighting with Multi-plane Light Images.","year":2025,"types":["Informal"],"venue":["CoRR"],"doi":["https://doi.org/10.48550/ARXIV.2511.06271"],"numberOfCreators":9,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2511-06271","https://doi.org/10.48550/ARXIV.2511.06271"],"publicationYear":2025,"eventYear":null},{"key":"journals/corr/abs-2511-16955","url":"https://dblp.org/rec/journals/corr/abs-2511-16955","title":"Neighbor GRPO: Contrastive ODE Policy Optimization Aligns Flow Models.","year":2025,"types":["Informal"],"venue":["CoRR"],"doi":["https://doi.org/10.48550/ARXIV.2511.16955"],"numberOfCreators":9,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2511-16955","https://doi.org/10.48550/ARXIV.2511.16955"],"publicationYear":2025,"eventYear":null},{"key":"journals/corr/abs-2511-22663","url":"https://dblp.org/rec/journals/corr/abs-2511-22663","title":"Architecture Decoupling Is Not All You Need For Unified Multimodal Model.","year":2025,"types":["Informal"],"venue":["CoRR"],"doi":["https://doi.org/10.48550/ARXIV.2511.22663"],"numberOfCreators":13,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2511-22663","https://doi.org/10.48550/ARXIV.2511.22663"],"publicationYear":2025,"eventYear":null},{"key":"journals/corr/abs-2511-22677","url":"https://dblp.org/rec/journals/corr/abs-2511-22677","title":"Decoupled DMD: CFG Augmentation as the Spear, Distribution Matching as the Shield.","year":2025,"types":["Informal"],"venue":["CoRR"],"doi":["https://doi.org/10.48550/ARXIV.2511.22677"],"numberOfCreators":11,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2511-22677","https://doi.org/10.48550/ARXIV.2511.22677"],"publicationYear":2025,"eventYear":null},{"key":"journals/corr/abs-2512-05112","url":"https://dblp.org/rec/journals/corr/abs-2512-05112","title":"DraCo: Draft as CoT for Text-to-Image Preview and Rare Concept Generation.","year":2025,"types":["Informal"],"venue":["CoRR"],"doi":["https://doi.org/10.48550/ARXIV.2512.05112"],"numberOfCreators":12,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2512-05112","https://doi.org/10.48550/ARXIV.2512.05112"],"publicationYear":2025,"eventYear":null},{"key":"journals/corr/abs-2512-05965","url":"https://dblp.org/rec/journals/corr/abs-2512-05965","title":"EditThinker: Unlocking Iterative Reasoning for Any Image Editor.","year":2025,"types":["Informal"],"venue":["CoRR"],"doi":["https://doi.org/10.48550/ARXIV.2512.05965"],"numberOfCreators":14,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2512-05965","https://doi.org/10.48550/ARXIV.2512.05965"],"publicationYear":2025,"eventYear":null},{"key":"journals/corr/abs-2512-22939","url":"https://dblp.org/rec/journals/corr/abs-2512-22939","title":"ColaVLA: Leveraging Cognitive Latent Reasoning for Hierarchical Parallel Trajectory Planning in Autonomous Driving.","year":2025,"types":["Informal"],"venue":["CoRR"],"doi":["https://doi.org/10.48550/ARXIV.2512.22939"],"numberOfCreators":5,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2512-22939","https://doi.org/10.48550/ARXIV.2512.22939"],"publicationYear":2025,"eventYear":null}],"candidateFormalRecordCount2025":79,"candidatePreprintRecordCount2025":68,"labName":"CUHK MMLab","labUrl":"https://mmlab.ie.cuhk.edu.hk/","labEvidence":"实验室官方 People 页在 CUHK MMLab 分区列 Hongsheng Li / Associate Professor；仅确定团队关联，不改变其 DBLP 混合身份导致论文计数仍为 null 的结论。","labSourceUrl":"https://mmlab.ie.cuhk.edu.hk/people.html","excludedOther":[],"excludedHomonyms":[],"unassignedCandidates":[],"knownPreprintMinimum2025":null,"excludedMisattributed":[],"knownMinimum2025":null,"displayNotes":"该档案中挂有两条中国农业大学的玉米播种研究（journals/cea/DuYZCHXJZMWXL25、journals/jiii/XieYHCZLXW25），其中一条的署名还附有相同的 ORCID；仅凭 ORCID 或档案状态不能判定为本人。这一异机构分支尚未逐篇排除，全年总数暂不给出，这绝非零；候选论文单列。","labDisplayNotes":"港中文 MMLab 官方 People 页在 CUHK MMLab 分区列其为副教授，据此与薛天帆、岳翔宇合为一组。团队归属不能解决 DBLP 档案混杂的问题：本人仍无总数，整组也不画柱；另两位去重后 52 条，只作下界。"},{"index":54,"name":"Kun Li","nameZh":"李坤","role":"Professor","affiliation":"Tianjin University","affiliationZh":"天津大学","source":"DBLP RDF via official SPARQL; primary-source identity checks","sourceUrl":"https://sparql.dblp.org/","profileUrl":"https://dblp.org/pid/75/1458-1.html","identifier":"75/1458-1","retrievedAt":"2026-10-19","count2025":8,"conference2025":2,"journal2025":6,"preprint2025":2,"status":"confirmed","notes":"","identityEvidence":[{"url":"https://dblp.org/pid/75/1458-1.html","evidence":"DBLP RDF 类型为 Person，消歧后名字为 Kun Li 0001。机构元数据含：Tianjin University, School of Computer Science and Technology, China；École Polytechnique Fédérale de Lausanne, Switzerland；Tsinghua University, TNList, Beijing, China"},{"url":"https://cic.tju.edu.cn/faculty/likun/bio.html","evidence":"天津大学官方个人简历为 Kun Li / 李坤；2011 年清华博士、2014–2015 EPFL 博士后，与 DBLP 0001 的履历吻合，区别于其他天津大学同名者。"}],"papers":[{"key":"conf/iccv/LiuZKMWHWLL25","url":"https://dblp.org/rec/conf/iccv/LiuZKMWHWLL25","title":"RESCUE: Crowd Evacuation Simulation via Controlling SDM-United Characters.","year":2025,"types":["Inproceedings"],"venue":"ICCV","doi":"https://doi.org/10.1109/ICCV51701.2025.02314","eventYear":2025,"numberOfCreators":9,"category":"conference","sources":["https://dblp.org/rec/conf/iccv/LiuZKMWHWLL25","https://doi.org/10.1109/ICCV51701.2025.02314"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/LiuZKMWHWLL25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/siggrapha/WangM0WLL25","url":"https://dblp.org/rec/conf/siggrapha/WangM0WLL25","title":"DreamCoser: Controllable Layered 3D Character Generation and Editing.","year":2025,"types":["Inproceedings"],"venue":"SIGGRAPH Asia Technical Communications","doi":"https://doi.org/10.1145/3757376.3771404","eventYear":2025,"numberOfCreators":6,"category":"conference","sources":["https://dblp.org/rec/conf/siggrapha/WangM0WLL25","https://doi.org/10.1145/3757376.3771404"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/siggrapha/WangM0WLL25","documentUrl":null,"type":"Inproceedings"},{"key":"journals/cvm/JingYHLL25","url":"https://dblp.org/rec/journals/cvm/JingYHLL25","title":"FRNeRF: Fusion and Regularization Fields for Dynamic View Synthesis.","year":2025,"types":["Article"],"venue":"Comput. Vis. Media","doi":"https://doi.org/10.26599/CVM.2025.9450405","numberOfCreators":5,"category":"journal","sources":["https://dblp.org/rec/journals/cvm/JingYHLL25","https://doi.org/10.26599/CVM.2025.9450405"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/cvm/JingYHLL25","documentUrl":null,"type":"Article"},{"key":"journals/displays/ShenYLY25","url":"https://dblp.org/rec/journals/displays/ShenYLY25","title":"ITSRN++: Stronger and better implicit transformer network for screen content image continuous super-resolution.","year":2025,"types":["Article"],"venue":"Displays","doi":"https://doi.org/10.1016/J.DISPLA.2024.102865","numberOfCreators":4,"category":"journal","sources":["https://dblp.org/rec/journals/displays/ShenYLY25","https://doi.org/10.1016/J.DISPLA.2024.102865"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/displays/ShenYLY25","documentUrl":null,"type":"Article"},{"key":"journals/tetci/LuoLLLY25","url":"https://dblp.org/rec/journals/tetci/LuoLLLY25","title":"Efficient Low-Light Light Field Enhancement With Progressive Feature Interaction.","year":2025,"types":["Article"],"venue":"IEEE Trans. Emerg. Top. Comput. Intell.","doi":"https://doi.org/10.1109/TETCI.2024.3404015","numberOfCreators":5,"category":"journal","sources":["https://dblp.org/rec/journals/tetci/LuoLLLY25","https://doi.org/10.1109/TETCI.2024.3404015"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/tetci/LuoLLLY25","documentUrl":null,"type":"Article"},{"key":"journals/tist/BiTXLY25","url":"https://dblp.org/rec/journals/tist/BiTXLY25","title":"JASRNet: Learning Joint Adaptive Sampling and Reconstruction for Depth Sensing.","year":2025,"types":["Article"],"venue":"ACM Trans. Intell. Syst. Technol.","doi":"https://doi.org/10.1145/3716852","numberOfCreators":5,"category":"journal","sources":["https://dblp.org/rec/journals/tist/BiTXLY25","https://doi.org/10.1145/3716852"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/tist/BiTXLY25","documentUrl":null,"type":"Article"},{"key":"journals/tmm/YangXHYFL25","url":"https://dblp.org/rec/journals/tmm/YangXHYFL25","title":"High-Quality Reconstruction of Depth Maps From Graph-Based Non-Uniform Sampling.","year":2025,"types":["Article"],"venue":"IEEE Trans. Multim.","doi":"https://doi.org/10.1109/TMM.2023.3289705","numberOfCreators":6,"category":"journal","sources":["https://dblp.org/rec/journals/tmm/YangXHYFL25","https://doi.org/10.1109/TMM.2023.3289705"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/tmm/YangXHYFL25","documentUrl":null,"type":"Article"},{"key":"journals/tvcg/ZhangZZZLL25","url":"https://dblp.org/rec/journals/tvcg/ZhangZZZLL25","title":"SpeechAct: Towards Generating Whole-Body Motion From Speech.","year":2025,"types":["Article"],"venue":"IEEE Trans. Vis. Comput. Graph.","doi":"https://doi.org/10.1109/TVCG.2025.3529611","numberOfCreators":6,"category":"journal","sources":["https://dblp.org/rec/journals/tvcg/ZhangZZZLL25","https://doi.org/10.1109/TVCG.2025.3529611"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/tvcg/ZhangZZZLL25","documentUrl":null,"type":"Article"}],"preprints":[{"key":"journals/corr/abs-2507-20117","url":"https://dblp.org/rec/journals/corr/abs-2507-20117","title":"RESCUE: Crowd Evacuation Simulation via Controlling SDM-United Characters.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2507.20117","numberOfCreators":9,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2507-20117","https://doi.org/10.48550/ARXIV.2507.20117"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2507-20117","documentUrl":null,"type":"Informal","arxivId":"2507.20117","arxivUrl":"https://arxiv.org/abs/2507.20117"},{"key":"journals/corr/abs-2508-12644","url":"https://dblp.org/rec/journals/corr/abs-2508-12644","title":"DyCrowd: Towards Dynamic Crowd Reconstruction from a Large-scene Video.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2508.12644","numberOfCreators":8,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2508-12644","https://doi.org/10.48550/ARXIV.2508.12644"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-12644","documentUrl":null,"type":"Informal","arxivId":"2508.12644","arxivUrl":"https://arxiv.org/abs/2508.12644"}],"excludedFormal":[],"otherRecords":[],"matchedName":"Kun Li","databaseLabel":"Kun Li 0001","databaseMetadata":{"type":["https://dblp.org/rdf/schema#Creator","https://dblp.org/rdf/schema#Person"],"label":["Kun Li 0001"],"affiliation":["Tianjin University, School of Computer Science and Technology, China","École Polytechnique Fédérale de Lausanne, Switzerland","Tsinghua University, TNList, Beijing, China"],"orcid":["https://orcid.org/0000-0003-2326-0166"],"primaryAffiliation":["Tianjin University, School of Computer Science and Technology, China"]},"rawFormalRecordCount2025":8,"signatureAudit":{"completedAt":"2026-10-19","frozen":true,"scope":"对 B 组 39 个数值档案的全部 1074 条原始 2025 正式记录扫描 DBLP author-signature ORCID 和机构；复用既有 59 条 Crossref 核验，补查 6 条新触发记录。重点核查不同 ORCID，以及只有预期机构之外机构的条目。本轮不扩展为所有作者逐篇全文审计。","formalRecordCoverage":8,"orcidCounts":{"https://orcid.org/0000-0003-2326-0166":4},"institutionCounts":{"Tianjin University (TJU)":8},"caveat":"机构名称可能由 DBLP 自动映射而失真；多 ORCID 也不自动等于异人。只有有原始资料支撑的错归才作确认排除，未解决分支则暂停总数。"},"labName":null,"labUrl":null,"labEvidence":"已检查天津大学本人页面缓存并作本轮限定补查，未发现明确命名且可核实关联的当前实验室。","labSourceUrl":"https://cic.tju.edu.cn/faculty/likun/index_cn.html","sourceWarning":false,"excludedOther":[],"excludedHomonyms":[],"unassignedCandidates":[],"knownPreprintMinimum2025":null,"excludedMisattributed":[],"displayNotes":"身份已与原名单机构及公开资料核对确认。2025 年正式记录 8 条（会议 2、期刊 6），所有作者位置均计入；预印本 2 条单列，不加总。","labDisplayNotes":"已查看天津大学的本人页面，未见明确命名且可核实关联的当前实验室，图中以「姓名及合作者」单列。"},{"index":55,"name":"Xiang Li","nameZh":"李翔","role":"Associate Professor","affiliation":"Nankai University","affiliationZh":"南开大学","source":"DBLP RDF via official SPARQL; primary-source identity checks","sourceUrl":"https://sparql.dblp.org/","profileUrl":"https://dblp.org/pid/40/1491-41.html","identifier":"40/1491-41","retrievedAt":"2026-10-19","count2025":27,"conference2025":17,"journal2025":10,"preprint2025":23,"status":"confirmed","notes":"","identityEvidence":[{"url":"https://dblp.org/pid/40/1491-41.html","evidence":"DBLP RDF 类型为 Person，消歧后名字为 Xiang Li 0041。机构元数据含：Nankai University, College of Computer Science, Tianjin, China；Nanjing University of Science and Technology, School of Computer Science and Engineering, PCA Lab, Nanjing, China；Nanjing University of Science and Technology, Jiangsu Key Lab of Image and Video Understanding for Social Security, Nanjing, China；Momenta, China"},{"url":"https://github.com/IMPlus-PCALab/Research","evidence":"南开大学 Xiang Li 领导的 PCALab 官方研究清单；计算机视觉研究及 Large Selective Kernel Network 等论文与 DBLP 0041 一致，区别于物流、安全等同名作者。"}],"papers":[{"key":"conf/aaai/WangXLLGGC25","url":"https://dblp.org/rec/conf/aaai/WangXLLGGC25","title":"Multi-clue Consistency Learning to Bridge Gaps Between General and Oriented Object in Semi-supervised Detection.","year":2025,"types":["Inproceedings"],"venue":"AAAI","doi":"https://doi.org/10.1609/AAAI.V39I7.32816","eventYear":2025,"numberOfCreators":7,"category":"conference","sources":["https://dblp.org/rec/conf/aaai/WangXLLGGC25","https://doi.org/10.1609/AAAI.V39I7.32816"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/aaai/WangXLLGGC25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/aaai/ZhaoXD0TYC025","url":"https://dblp.org/rec/conf/aaai/ZhaoXD0TYC025","title":"From Words to Worth: Newborn Article Impact Prediction with LLM.","year":2025,"types":["Inproceedings"],"venue":"AAAI","doi":"https://doi.org/10.1609/AAAI.V39I1.32106","eventYear":2025,"numberOfCreators":8,"category":"conference","sources":["https://dblp.org/rec/conf/aaai/ZhaoXD0TYC025","https://doi.org/10.1609/AAAI.V39I1.32106"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/aaai/ZhaoXD0TYC025","documentUrl":null,"type":"Inproceedings"},{"key":"conf/acns/LiZLLZS25","url":"https://dblp.org/rec/conf/acns/LiZLLZS25","title":"Wolf in Sheep's Clothing: Understanding and Detecting Mobile Cloaking in Blackhat SEO.","year":2025,"types":["Inproceedings"],"venue":"ACNS (2)","doi":"https://doi.org/10.1007/978-3-031-95764-2_4","eventYear":2025,"numberOfCreators":6,"category":"conference","sources":["https://dblp.org/rec/conf/acns/LiZLLZS25","https://doi.org/10.1007/978-3-031-95764-2_4"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/acns/LiZLLZS25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/cvpr/FanNXZYFLYT25","url":"https://dblp.org/rec/conf/cvpr/FanNXZYFLYT25","title":"InstanceCap: Improving Text-to-Video Generation via Instance-aware Structured Caption.","year":2025,"types":["Inproceedings"],"venue":"CVPR","doi":"https://doi.org/10.1109/CVPR52734.2025.02698","eventYear":2025,"numberOfCreators":9,"category":"conference","sources":["https://dblp.org/rec/conf/cvpr/FanNXZYFLYT25","https://doi.org/10.1109/CVPR52734.2025.02698"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/FanNXZYFLYT25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/cvpr/PengWZLYDC025","url":"https://dblp.org/rec/conf/cvpr/PengWZLYDC025","title":"A Simple Detector with Frame Dynamics is a Strong Tracker.","year":2025,"types":["Inproceedings"],"venue":"CVPR Workshops","doi":null,"eventYear":2025,"numberOfCreators":8,"category":"conference","sources":["https://dblp.org/rec/conf/cvpr/PengWZLYDC025"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/PengWZLYDC025","documentUrl":null,"type":"Inproceedings"},{"key":"conf/cvpr/ZhangYLYCL25","url":"https://dblp.org/rec/conf/cvpr/ZhangYLYCL25","title":"RSAR: Restricted State Angle Resolver and Rotated SAR Benchmark.","year":2025,"types":["Inproceedings"],"venue":"CVPR","doi":"https://doi.org/10.1109/CVPR52734.2025.00695","eventYear":2025,"numberOfCreators":6,"category":"conference","sources":["https://dblp.org/rec/conf/cvpr/ZhangYLYCL25","https://doi.org/10.1109/CVPR52734.2025.00695"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/ZhangYLYCL25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/eccv/LiWLLYDQZ24","url":"https://dblp.org/rec/conf/eccv/LiWLLYDQZ24","title":"Distilling Knowledge from Large-Scale Image Models for Object Detection.","year":2025,"types":["Inproceedings"],"venue":"ECCV (84)","doi":"https://doi.org/10.1007/978-3-031-72907-2_9","eventYear":2024,"numberOfCreators":8,"category":"conference","sources":["https://dblp.org/rec/conf/eccv/LiWLLYDQZ24","https://doi.org/10.1007/978-3-031-72907-2_9"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2024,"sourceUrl":"https://dblp.org/rec/conf/eccv/LiWLLYDQZ24","documentUrl":null,"type":"Inproceedings"},{"key":"conf/eccv/WuZLCLYL24","url":"https://dblp.org/rec/conf/eccv/WuZLCLYL24","title":"Cascade Prompt Learning for Vision-Language Model Adaptation.","year":2025,"types":["Inproceedings"],"venue":"ECCV (50)","doi":"https://doi.org/10.1007/978-3-031-72973-7_18","eventYear":2024,"numberOfCreators":7,"category":"conference","sources":["https://dblp.org/rec/conf/eccv/WuZLCLYL24","https://doi.org/10.1007/978-3-031-72973-7_18"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2024,"sourceUrl":"https://dblp.org/rec/conf/eccv/WuZLCLYL24","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iccv/HanYLZLYCD25","url":"https://dblp.org/rec/conf/iccv/HanYLZLYCD25","title":"DISTA-Net: Dynamic Closely-Spaced Infrared Small Target Unmixing.","year":2025,"types":["Inproceedings"],"venue":"ICCV","doi":"https://doi.org/10.1109/ICCV51701.2025.01360","eventYear":2025,"numberOfCreators":8,"category":"conference","sources":["https://dblp.org/rec/conf/iccv/HanYLZLYCD25","https://doi.org/10.1109/ICCV51701.2025.01360"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/HanYLZLYCD25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iccv/LiSCLY25","url":"https://dblp.org/rec/conf/iccv/LiSCLY25","title":"Advancing Textual Prompt Learning with Anchored Attributes.","year":2025,"types":["Inproceedings"],"venue":"ICCV","doi":"https://doi.org/10.1109/ICCV51701.2025.00345","eventYear":2025,"numberOfCreators":5,"category":"conference","sources":["https://dblp.org/rec/conf/iccv/LiSCLY25","https://doi.org/10.1109/ICCV51701.2025.00345"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/LiSCLY25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iclr/NanXZFYCL0T25","url":"https://dblp.org/rec/conf/iclr/NanXZFYCL0T25","title":"OpenVid-1M: A Large-Scale High-Quality Dataset for Text-to-video Generation.","year":2025,"types":["Inproceedings"],"venue":"ICLR","doi":null,"eventYear":2025,"numberOfCreators":9,"category":"conference","sources":["https://dblp.org/rec/conf/iclr/NanXZFYCL0T25"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iclr/NanXZFYCL0T25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/icml/BiWL0Q0025","url":"https://dblp.org/rec/conf/icml/BiWL0Q0025","title":"Rethinking Point Cloud Data Augmentation: Topologically Consistent Deformation.","year":2025,"types":["Inproceedings"],"venue":"ICML","doi":null,"eventYear":2025,"numberOfCreators":7,"category":"conference","sources":["https://dblp.org/rec/conf/icml/BiWL0Q0025"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/icml/BiWL0Q0025","documentUrl":null,"type":"Inproceedings"},{"key":"conf/icra/WuYWLHY25","url":"https://dblp.org/rec/conf/icra/WuYWLHY25","title":"Deep Height Decoupling for Precise Vision-Based 3D Occupancy Prediction.","year":2025,"types":["Inproceedings"],"venue":"ICRA","doi":"https://doi.org/10.1109/ICRA55743.2025.11128708","eventYear":2025,"numberOfCreators":6,"category":"conference","sources":["https://dblp.org/rec/conf/icra/WuYWLHY25","https://doi.org/10.1109/ICRA55743.2025.11128708"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/icra/WuYWLHY25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/mm/XiongCZLT0025","url":"https://dblp.org/rec/conf/mm/XiongCZLT0025","title":"Category-Aware 3D Object Composition with Disentangled Texture and Shape Multi-view Diffusion.","year":2025,"types":["Inproceedings"],"venue":"ACM Multimedia","doi":"https://doi.org/10.1145/3746027.3755154","eventYear":2025,"numberOfCreators":7,"category":"conference","sources":["https://dblp.org/rec/conf/mm/XiongCZLT0025","https://doi.org/10.1145/3746027.3755154"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/mm/XiongCZLT0025","documentUrl":null,"type":"Inproceedings"},{"key":"conf/nips/TangQFZCLC25","url":"https://dblp.org/rec/conf/nips/TangQFZCLC25","title":"Revisiting End-to-End Learning with Slide-level Supervision in Computational Pathology.","year":2025,"types":["Inproceedings"],"venue":"NeurIPS","doi":null,"eventYear":2025,"numberOfCreators":7,"category":"conference","sources":["https://dblp.org/rec/conf/nips/TangQFZCLC25"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/nips/TangQFZCLC25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/nips/WuYZLY25","url":"https://dblp.org/rec/conf/nips/WuYZLY25","title":"See through the Dark: Learning Illumination-affined Representations for Nighttime Occupancy Prediction.","year":2025,"types":["Inproceedings"],"venue":"NeurIPS","doi":null,"eventYear":2025,"numberOfCreators":5,"category":"conference","sources":["https://dblp.org/rec/conf/nips/WuYZLY25"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/nips/WuYZLY25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/nips/WuZSGCWCGTYCL25","url":"https://dblp.org/rec/conf/nips/WuZSGCWCGTYCL25","title":"Representation Entanglement for Generation: Training Diffusion Transformers Is Much Easier Than You Think.","year":2025,"types":["Inproceedings"],"venue":"NeurIPS","doi":null,"eventYear":2025,"numberOfCreators":12,"category":"conference","sources":["https://dblp.org/rec/conf/nips/WuZSGCWCGTYCL25"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/nips/WuZSGCWCGTYCL25","documentUrl":null,"type":"Inproceedings"},{"key":"journals/ijcv/LiLDHLLCY25","url":"https://dblp.org/rec/journals/ijcv/LiLDHLLCY25","title":"LSKNet: A Foundation Lightweight Backbone for Remote Sensing.","year":2025,"types":["Article"],"venue":"Int. J. Comput. Vis.","doi":"https://doi.org/10.1007/S11263-024-02247-9","numberOfCreators":8,"category":"journal","sources":["https://dblp.org/rec/journals/ijcv/LiLDHLLCY25","https://doi.org/10.1007/S11263-024-02247-9"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/ijcv/LiLDHLLCY25","documentUrl":null,"type":"Article"},{"key":"journals/ijcv/YanLHZLY25","url":"https://dblp.org/rec/journals/ijcv/YanLHZLY25","title":"RigNet++: Semantic Assisted Repetitive Image Guided Network for Depth Completion.","year":2025,"types":["Article"],"venue":"Int. J. Comput. Vis.","doi":"https://doi.org/10.1007/S11263-025-02470-Y","numberOfCreators":6,"category":"journal","sources":["https://dblp.org/rec/journals/ijcv/YanLHZLY25","https://doi.org/10.1007/S11263-025-02470-Y"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/ijcv/YanLHZLY25","documentUrl":null,"type":"Article"},{"key":"journals/ijcv/ZhangLYYLZJLCLYL25","url":"https://dblp.org/rec/journals/ijcv/ZhangLYYLZJLCLYL25","title":"PointOBB-v3: Expanding Performance Boundaries of Single Point-Supervised Oriented Object Detection.","year":2025,"types":["Article"],"venue":"Int. J. Comput. Vis.","doi":"https://doi.org/10.1007/S11263-025-02486-4","numberOfCreators":12,"category":"journal","sources":["https://dblp.org/rec/journals/ijcv/ZhangLYYLZJLCLYL25","https://doi.org/10.1007/S11263-025-02486-4"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/ijcv/ZhangLYYLZJLCLYL25","documentUrl":null,"type":"Article"},{"key":"journals/pami/ChenYWWLHC25","url":"https://dblp.org/rec/journals/pami/ChenYWWLHC25","title":"YOLO-MS: Rethinking Multi-Scale Representation Learning for Real-Time Object Detection.","year":2025,"types":["Article"],"venue":"IEEE Trans. Pattern Anal. Mach. Intell.","doi":"https://doi.org/10.1109/TPAMI.2025.3538473","numberOfCreators":7,"category":"journal","sources":["https://dblp.org/rec/journals/pami/ChenYWWLHC25","https://doi.org/10.1109/TPAMI.2025.3538473"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/pami/ChenYWWLHC25","documentUrl":null,"type":"Article"},{"key":"journals/pami/YanWLGLY25","url":"https://dblp.org/rec/journals/pami/YanWLGLY25","title":"Tri-Perspective View Decomposition for Geometry Aware Depth Completion and Super-Resolution.","year":2025,"types":["Article"],"venue":"IEEE Trans. Pattern Anal. Mach. Intell.","doi":"https://doi.org/10.1109/TPAMI.2025.3596391","numberOfCreators":6,"category":"journal","sources":["https://dblp.org/rec/journals/pami/YanWLGLY25","https://doi.org/10.1109/TPAMI.2025.3596391"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/pami/YanWLGLY25","documentUrl":null,"type":"Article"},{"key":"journals/pami/YangLWWY25","url":"https://dblp.org/rec/journals/pami/YangLWWY25","title":"Fine-Grained Visual Text Prompting.","year":2025,"types":["Article"],"venue":"IEEE Trans. Pattern Anal. Mach. Intell.","doi":"https://doi.org/10.1109/TPAMI.2024.3504568","numberOfCreators":5,"category":"journal","sources":["https://dblp.org/rec/journals/pami/YangLWWY25","https://doi.org/10.1109/TPAMI.2024.3504568"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/pami/YangLWWY25","documentUrl":null,"type":"Article"},{"key":"journals/taes/DaiZLLNY25","url":"https://dblp.org/rec/journals/taes/DaiZLLNY25","title":"DenoDet: Attention as Deformable Multisubspace Feature Denoising for Target Detection in SAR Images.","year":2025,"types":["Article"],"venue":"IEEE Trans. Aerosp. Electron. Syst.","doi":"https://doi.org/10.1109/TAES.2024.3507786","numberOfCreators":6,"category":"journal","sources":["https://dblp.org/rec/journals/taes/DaiZLLNY25","https://doi.org/10.1109/TAES.2024.3507786"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/taes/DaiZLLNY25","documentUrl":null,"type":"Article"},{"key":"journals/tcsv/FanLQLY25","url":"https://dblp.org/rec/journals/tcsv/FanLQLY25","title":"Non-Aligned Supervision for Real Image Dehazing.","year":2025,"types":["Article"],"venue":"IEEE Trans. Circuits Syst. Video Technol.","doi":"https://doi.org/10.1109/TCSVT.2025.3573040","numberOfCreators":5,"category":"journal","sources":["https://dblp.org/rec/journals/tcsv/FanLQLY25","https://doi.org/10.1109/TCSVT.2025.3573040"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/tcsv/FanLQLY25","documentUrl":null,"type":"Article"},{"key":"journals/tgrs/DaiYDLLNXSY25","url":"https://dblp.org/rec/journals/tgrs/DaiYDLLNXSY25","title":"MoCoLSK: Modality-Conditioned High-Resolution Downscaling for Land Surface Temperature.","year":2025,"types":["Article"],"venue":"IEEE Trans. Geosci. Remote. Sens.","doi":"https://doi.org/10.1109/TGRS.2025.3547945","numberOfCreators":9,"category":"journal","sources":["https://dblp.org/rec/journals/tgrs/DaiYDLLNXSY25","https://doi.org/10.1109/TGRS.2025.3547945"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/tgrs/DaiYDLLNXSY25","documentUrl":null,"type":"Article"},{"key":"journals/tgrs/WangFLYL25","url":"https://dblp.org/rec/journals/tgrs/WangFLYL25","title":"MSOD: A Large-Scale Multiscene Dataset and a Novel Diagonal-Geometry Loss for SAR Object Detection.","year":2025,"types":["Article"],"venue":"IEEE Trans. Geosci. Remote. Sens.","doi":"https://doi.org/10.1109/TGRS.2025.3605720","numberOfCreators":5,"category":"journal","sources":["https://dblp.org/rec/journals/tgrs/WangFLYL25","https://doi.org/10.1109/TGRS.2025.3605720"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/tgrs/WangFLYL25","documentUrl":null,"type":"Article"}],"preprints":[{"key":"journals/corr/abs-2501-03775","url":"https://dblp.org/rec/journals/corr/abs-2501-03775","title":"Strip R-CNN: Large Strip Convolution for Remote Sensing Object Detection.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2501.03775","numberOfCreators":8,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2501-03775","https://doi.org/10.48550/ARXIV.2501.03775"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2501-03775","documentUrl":null,"type":"Informal","arxivId":"2501.03775","arxivUrl":"https://arxiv.org/abs/2501.03775"},{"key":"journals/corr/abs-2501-04440","url":"https://dblp.org/rec/journals/corr/abs-2501-04440","title":"RSAR: Restricted State Angle Resolver and Rotated SAR Benchmark.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2501.04440","numberOfCreators":6,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2501-04440","https://doi.org/10.48550/ARXIV.2501.04440"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2501-04440","documentUrl":null,"type":"Informal","arxivId":"2501.04440","arxivUrl":"https://arxiv.org/abs/2501.04440"},{"key":"journals/corr/abs-2501-13898","url":"https://dblp.org/rec/journals/corr/abs-2501-13898","title":"PointOBB-v3: Expanding Performance Boundaries of Single Point-Supervised Oriented Object Detection.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2501.13898","numberOfCreators":12,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2501-13898","https://doi.org/10.48550/ARXIV.2501.13898"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2501-13898","documentUrl":null,"type":"Informal","arxivId":"2501.13898","arxivUrl":"https://arxiv.org/abs/2501.13898"},{"key":"journals/corr/abs-2504-18765","url":"https://dblp.org/rec/journals/corr/abs-2504-18765","title":"A Vision for Auto Research with LLM Agents.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2504.18765","numberOfCreators":19,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2504-18765","https://doi.org/10.48550/ARXIV.2504.18765"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2504-18765","documentUrl":null,"type":"Informal","arxivId":"2504.18765","arxivUrl":"https://arxiv.org/abs/2504.18765"},{"key":"journals/corr/abs-2505-04917","url":"https://dblp.org/rec/journals/corr/abs-2505-04917","title":"A Simple Detector with Frame Dynamics is a Strong Tracker.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2505.04917","numberOfCreators":8,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2505-04917","https://doi.org/10.48550/ARXIV.2505.04917"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-04917","documentUrl":null,"type":"Informal","arxivId":"2505.04917","arxivUrl":"https://arxiv.org/abs/2505.04917"},{"key":"journals/corr/abs-2505-10931","url":"https://dblp.org/rec/journals/corr/abs-2505-10931","title":"M4-SAR: A Multi-Resolution, Multi-Polarization, Multi-Scene, Multi-Source Dataset and Benchmark for Optical-SAR Fusion Object Detection.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2505.10931","numberOfCreators":5,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2505-10931","https://doi.org/10.48550/ARXIV.2505.10931"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-10931","documentUrl":null,"type":"Informal","arxivId":"2505.10931","arxivUrl":"https://arxiv.org/abs/2505.10931"},{"key":"journals/corr/abs-2505-15184","url":"https://dblp.org/rec/journals/corr/abs-2505-15184","title":"AuxDet: Auxiliary Metadata Matters for Omni-Domain Infrared Small Target Detection.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2505.15184","numberOfCreators":7,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2505-15184","https://doi.org/10.48550/ARXIV.2505.15184"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-15184","documentUrl":null,"type":"Informal","arxivId":"2505.15184","arxivUrl":"https://arxiv.org/abs/2505.15184"},{"key":"journals/corr/abs-2505-19148","url":"https://dblp.org/rec/journals/corr/abs-2505-19148","title":"DISTA-Net: Dynamic Closely-Spaced Infrared Small Target Unmixing.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2505.19148","numberOfCreators":8,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2505-19148","https://doi.org/10.48550/ARXIV.2505.19148"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-19148","documentUrl":null,"type":"Informal","arxivId":"2505.19148","arxivUrl":"https://arxiv.org/abs/2505.19148"},{"key":"journals/corr/abs-2505-20641","url":"https://dblp.org/rec/journals/corr/abs-2505-20641","title":"See through the Dark: Learning Illumination-affined Representations for Nighttime Occupancy Prediction.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2505.20641","numberOfCreators":5,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2505-20641","https://doi.org/10.48550/ARXIV.2505.20641"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-20641","documentUrl":null,"type":"Informal","arxivId":"2505.20641","arxivUrl":"https://arxiv.org/abs/2505.20641"},{"key":"journals/corr/abs-2506-01674","url":"https://dblp.org/rec/journals/corr/abs-2506-01674","title":"MotionSight: Boosting Fine-Grained Motion Understanding in Multimodal LLMs.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2506.01674","numberOfCreators":9,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2506-01674","https://doi.org/10.48550/ARXIV.2506.01674"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-01674","documentUrl":null,"type":"Informal","arxivId":"2506.01674","arxivUrl":"https://arxiv.org/abs/2506.01674"},{"key":"journals/corr/abs-2506-02408","url":"https://dblp.org/rec/journals/corr/abs-2506-02408","title":"Revisiting End-to-End Learning with Slide-level Supervision in Computational Pathology.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2506.02408","numberOfCreators":7,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2506-02408","https://doi.org/10.48550/ARXIV.2506.02408"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-02408","documentUrl":null,"type":"Informal","arxivId":"2506.02408","arxivUrl":"https://arxiv.org/abs/2506.02408"},{"key":"journals/corr/abs-2507-01467","url":"https://dblp.org/rec/journals/corr/abs-2507-01467","title":"Representation Entanglement for Generation:Training Diffusion Transformers Is Much Easier Than You Think.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2507.01467","numberOfCreators":12,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2507-01467","https://doi.org/10.48550/ARXIV.2507.01467"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2507-01467","documentUrl":null,"type":"Informal","arxivId":"2507.01467","arxivUrl":"https://arxiv.org/abs/2507.01467"},{"key":"journals/corr/abs-2508-01259","url":"https://dblp.org/rec/journals/corr/abs-2508-01259","title":"SpatioTemporal Difference Network for Video Depth Super-Resolution.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2508.01259","numberOfCreators":5,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2508-01259","https://doi.org/10.48550/ARXIV.2508.01259"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-01259","documentUrl":null,"type":"Informal","arxivId":"2508.01259","arxivUrl":"https://arxiv.org/abs/2508.01259"},{"key":"journals/corr/abs-2508-09392","url":"https://dblp.org/rec/journals/corr/abs-2508-09392","title":"DenoDet V2: Phase-Amplitude Cross Denoising for SAR Object Detection.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2508.09392","numberOfCreators":7,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2508-09392","https://doi.org/10.48550/ARXIV.2508.09392"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-09392","documentUrl":null,"type":"Informal","arxivId":"2508.09392","arxivUrl":"https://arxiv.org/abs/2508.09392"},{"key":"journals/corr/abs-2509-02357","url":"https://dblp.org/rec/journals/corr/abs-2509-02357","title":"Category-Aware 3D Object Composition with Disentangled Texture and Shape Multi-view Diffusion.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2509.02357","numberOfCreators":7,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2509-02357","https://doi.org/10.48550/ARXIV.2509.02357"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-02357","documentUrl":null,"type":"Informal","arxivId":"2509.02357","arxivUrl":"https://arxiv.org/abs/2509.02357"},{"key":"journals/corr/abs-2509-17562","url":"https://dblp.org/rec/journals/corr/abs-2509-17562","title":"Visual Instruction Pretraining for Domain-Specific Foundation Models.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2509.17562","numberOfCreators":7,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2509-17562","https://doi.org/10.48550/ARXIV.2509.17562"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-17562","documentUrl":null,"type":"Informal","arxivId":"2509.17562","arxivUrl":"https://arxiv.org/abs/2509.17562"},{"key":"journals/corr/abs-2509-20923","url":"https://dblp.org/rec/journals/corr/abs-2509-20923","title":"Revisiting Data Challenges of Computational Pathology: A Pack-based Multiple Instance Learning Framework.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2509.20923","numberOfCreators":5,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2509-20923","https://doi.org/10.48550/ARXIV.2509.20923"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-20923","documentUrl":null,"type":"Informal","arxivId":"2509.20923","arxivUrl":"https://arxiv.org/abs/2509.20923"},{"key":"journals/corr/abs-2509-25179","url":"https://dblp.org/rec/journals/corr/abs-2509-25179","title":"NAIPv2: Debiased Pairwise Learning for Efficient Paper Quality Estimation.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2509.25179","numberOfCreators":8,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2509-25179","https://doi.org/10.48550/ARXIV.2509.25179"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-25179","documentUrl":null,"type":"Informal","arxivId":"2509.25179","arxivUrl":"https://arxiv.org/abs/2509.25179"},{"key":"journals/corr/abs-2509-25958","url":"https://dblp.org/rec/journals/corr/abs-2509-25958","title":"RoRecomp: Enhancing Reasoning Efficiency via Rollout Response Recomposition in Reinforcement Learning.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2509.25958","numberOfCreators":9,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2509-25958","https://doi.org/10.48550/ARXIV.2509.25958"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-25958","documentUrl":null,"type":"Informal","arxivId":"2509.25958","arxivUrl":"https://arxiv.org/abs/2509.25958"},{"key":"journals/corr/abs-2509-26281","url":"https://dblp.org/rec/journals/corr/abs-2509-26281","title":"Point2RBox-v3: Self-Bootstrapping from Point Annotations via Integrated Pseudo-Label Refinement and Utilization.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2509.26281","numberOfCreators":11,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2509-26281","https://doi.org/10.48550/ARXIV.2509.26281"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-26281","documentUrl":null,"type":"Informal","arxivId":"2509.26281","arxivUrl":"https://arxiv.org/abs/2509.26281"},{"key":"journals/corr/abs-2511-02607","url":"https://dblp.org/rec/journals/corr/abs-2511-02607","title":"UniChange: Unifying Change Detection with Multimodal Large Language Model.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2511.02607","numberOfCreators":8,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2511-02607","https://doi.org/10.48550/ARXIV.2511.02607"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2511-02607","documentUrl":null,"type":"Informal","arxivId":"2511.02607","arxivUrl":"https://arxiv.org/abs/2511.02607"},{"key":"journals/corr/abs-2511-16361","url":"https://dblp.org/rec/journals/corr/abs-2511-16361","title":"Multi-Order Matching Network for Alignment-Free Depth Super-Resolution.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2511.16361","numberOfCreators":6,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2511-16361","https://doi.org/10.48550/ARXIV.2511.16361"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2511-16361","documentUrl":null,"type":"Informal","arxivId":"2511.16361","arxivUrl":"https://arxiv.org/abs/2511.16361"},{"key":"journals/corr/abs-2511-21188","url":"https://dblp.org/rec/journals/corr/abs-2511-21188","title":"AnchorOPT: Towards Optimizing Dynamic Anchors for Adaptive Prompt Learning.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2511.21188","numberOfCreators":6,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2511-21188","https://doi.org/10.48550/ARXIV.2511.21188"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2511-21188","documentUrl":null,"type":"Informal","arxivId":"2511.21188","arxivUrl":"https://arxiv.org/abs/2511.21188"}],"excludedFormal":[],"otherRecords":[],"matchedName":"Xiang Li","databaseLabel":"Xiang Li 0041","databaseMetadata":{"type":["https://dblp.org/rdf/schema#Creator","https://dblp.org/rdf/schema#Person"],"label":["Xiang Li 0041"],"affiliation":["Nankai University, College of Computer Science, Tianjin, China","Nanjing University of Science and Technology, School of Computer Science and Engineering, PCA Lab, Nanjing, China","Nanjing University of Science and Technology, Jiangsu Key Lab of Image and Video Understanding for Social Security, Nanjing, China","Momenta, China"],"orcid":["https://orcid.org/0000-0002-4996-7365"],"primaryAffiliation":["Nankai University, College of Computer Science, Tianjin, China"]},"rawFormalRecordCount2025":27,"signatureAudit":{"completedAt":"2026-10-19","frozen":true,"scope":"对 B 组 39 个数值档案的全部 1074 条原始 2025 正式记录扫描 DBLP author-signature ORCID 和机构；复用既有 59 条 Crossref 核验，补查 6 条新触发记录。重点核查不同 ORCID，以及只有预期机构之外机构的条目。本轮不扩展为所有作者逐篇全文审计。","formalRecordCoverage":27,"orcidCounts":{"https://orcid.org/0000-0002-4996-7365":16},"institutionCounts":{"Nankai University (NKU)":19},"caveat":"机构名称可能由 DBLP 自动映射而失真；多 ORCID 也不自动等于异人。只有有原始资料支撑的错归才作确认排除，未解决分支则暂停总数。"},"labName":"IMPlus@PCALab","labUrl":"https://github.com/IMPlus-PCALab","labEvidence":"实验室官方 GitHub README 明确 IMPlus@PCALab 是由南开大学 Prof. Xiang Li 带领的研究组，并链接本人主页；当前组织显示名为 ReductLab。名称采用 README 中明确关联本人的组名。","labSourceUrl":"https://github.com/IMPlus-PCALab","sourceWarning":false,"excludedOther":[],"excludedHomonyms":[],"unassignedCandidates":[],"knownPreprintMinimum2025":null,"excludedMisattributed":[],"displayNotes":"身份已与原名单机构及公开资料核对确认。2025 年正式记录 27 条（会议 17、期刊 10），所有作者位置均计入，不表示主导或贡献份额；预印本 23 条单列，不加总。","labDisplayNotes":"实验室官方 GitHub 的 README 写明 IMPlus@PCALab 由其带领，并链接本人主页；该组织当前显示名为 ReductLab，这里采用 README 中的名称。"},{"index":56,"name":"Zhongyu Li","nameZh":"李钟毓","role":"Assistant Professor","affiliation":"The Chinese University of Hong Kong","affiliationZh":"香港中文大学","source":"DBLP RDF via official SPARQL; primary-source identity checks","sourceUrl":"https://sparql.dblp.org/","profileUrl":"https://dblp.org/pid/121/1698-3.html","identifier":"121/1698-3","retrievedAt":"2026-10-19","count2025":5,"conference2025":4,"journal2025":1,"preprint2025":6,"status":"confirmed","notes":"DBLP 的 primaryAffiliation 含历史机构；以原签名名单机构和本人履历交叉核对，未据旧机构另选同名者。","identityEvidence":[{"url":"https://dblp.org/pid/121/1698-3.html","evidence":"DBLP RDF 类型为 Person，消歧后名字为 Zhongyu Li 0003。机构元数据含：University of California Berkeley, Department of Mechanical Engineering, Berkeley, CA, USA"},{"url":"https://zyliatzju.github.io/","evidence":"个人主页为香港中文大学 Zhongyu Li，说明此前为 Berkeley 机械系博士；解释 DBLP 保留的旧机构。"},{"url":"https://zyliatzju.github.io/","evidence":"此本人或机构页面的正文与所选档案中 9 条 2025 记录标题匹配，其中 5 条为当前计入的正式记录（忽略空格、标点、大小写）。","matchedPaperKeys":["conf/icra/LiaoZHHLS25","conf/icra/RyuLLDSM25","conf/iros/ChenHWLZLSWSGP25","conf/iros/OuyangLLLYSW25","journals/corr/abs-2503-18221","journals/corr/abs-2504-17249","journals/corr/abs-2504-21738","journals/corr/abs-2505-13834","journals/ijrr/LiPALBS25"],"matchedFormalPaperKeys":["conf/icra/LiaoZHHLS25","conf/icra/RyuLLDSM25","conf/iros/ChenHWLZLSWSGP25","conf/iros/OuyangLLLYSW25","journals/ijrr/LiPALBS25"]}],"papers":[{"key":"conf/icra/LiaoZHHLS25","url":"https://dblp.org/rec/conf/icra/LiaoZHHLS25","title":"Berkeley Humanoid: A Research Platform for Learning-Based Control.","year":2025,"types":["Inproceedings"],"venue":"ICRA","doi":"https://doi.org/10.1109/ICRA55743.2025.11127524","eventYear":2025,"numberOfCreators":6,"category":"conference","sources":["https://dblp.org/rec/conf/icra/LiaoZHHLS25","https://doi.org/10.1109/ICRA55743.2025.11127524"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/icra/LiaoZHHLS25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/icra/RyuLLDSM25","url":"https://dblp.org/rec/conf/icra/RyuLLDSM25","title":"CurricuLLM: Automatic Task Curricula Design for Learning Complex Robot Skills Using Large Language Models.","year":2025,"types":["Inproceedings"],"venue":"ICRA","doi":"https://doi.org/10.1109/ICRA55743.2025.11128783","eventYear":2025,"numberOfCreators":6,"category":"conference","sources":["https://dblp.org/rec/conf/icra/RyuLLDSM25","https://doi.org/10.1109/ICRA55743.2025.11128783"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/icra/RyuLLDSM25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iros/ChenHWLZLSWSGP25","url":"https://dblp.org/rec/conf/iros/ChenHWLZLSWSGP25","title":"Learning Smooth Humanoid Locomotion through Lipschitz-Constrained Policies.","year":2025,"types":["Inproceedings"],"venue":"IROS","doi":"https://doi.org/10.1109/IROS60139.2025.11246506","eventYear":2025,"numberOfCreators":11,"category":"conference","sources":["https://dblp.org/rec/conf/iros/ChenHWLZLSWSGP25","https://doi.org/10.1109/IROS60139.2025.11246506"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iros/ChenHWLZLSWSGP25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iros/OuyangLLLYSW25","url":"https://dblp.org/rec/conf/iros/OuyangLLLYSW25","title":"Long-horizon Locomotion and Manipulation on a Quadrupedal Robot with Large Language Models.","year":2025,"types":["Inproceedings"],"venue":"IROS","doi":"https://doi.org/10.1109/IROS60139.2025.11246632","eventYear":2025,"numberOfCreators":7,"category":"conference","sources":["https://dblp.org/rec/conf/iros/OuyangLLLYSW25","https://doi.org/10.1109/IROS60139.2025.11246632"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iros/OuyangLLLYSW25","documentUrl":null,"type":"Inproceedings"},{"key":"journals/ijrr/LiPALBS25","url":"https://dblp.org/rec/journals/ijrr/LiPALBS25","title":"Reinforcement learning for versatile, dynamic, and robust bipedal locomotion control.","year":2025,"types":["Article"],"venue":"Int. J. Robotics Res.","doi":"https://doi.org/10.1177/02783649241285161","numberOfCreators":6,"category":"journal","sources":["https://dblp.org/rec/journals/ijrr/LiPALBS25","https://doi.org/10.1177/02783649241285161"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/ijrr/LiPALBS25","documentUrl":null,"type":"Article"}],"preprints":[{"key":"journals/corr/abs-2503-18221","url":"https://dblp.org/rec/journals/corr/abs-2503-18221","title":"Decentralized Navigation of a Cable-Towed Load using Quadrupedal Robot Team via MARL.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2503.18221","numberOfCreators":5,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2503-18221","https://doi.org/10.48550/ARXIV.2503.18221"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-18221","documentUrl":null,"type":"Informal","arxivId":"2503.18221","arxivUrl":"https://arxiv.org/abs/2503.18221"},{"key":"journals/corr/abs-2504-17249","url":"https://dblp.org/rec/journals/corr/abs-2504-17249","title":"Demonstrating Berkeley Humanoid Lite: An Open-source, Accessible, and Customizable 3D-printed Humanoid Robot.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2504.17249","numberOfCreators":8,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2504-17249","https://doi.org/10.48550/ARXIV.2504.17249"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2504-17249","documentUrl":null,"type":"Informal","arxivId":"2504.17249","arxivUrl":"https://arxiv.org/abs/2504.17249"},{"key":"journals/corr/abs-2504-21738","url":"https://dblp.org/rec/journals/corr/abs-2504-21738","title":"LangWBC: Language-directed Humanoid Whole-Body Control via End-to-end Learning.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2504.21738","numberOfCreators":9,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2504-21738","https://doi.org/10.48550/ARXIV.2504.21738"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2504-21738","documentUrl":null,"type":"Informal","arxivId":"2504.21738","arxivUrl":"https://arxiv.org/abs/2504.21738"},{"key":"journals/corr/abs-2505-13834","url":"https://dblp.org/rec/journals/corr/abs-2505-13834","title":"Toward Real-World Cooperative and Competitive Soccer with Quadrupedal Robot Teams.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2505.13834","numberOfCreators":11,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2505-13834","https://doi.org/10.48550/ARXIV.2505.13834"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-13834","documentUrl":null,"type":"Informal","arxivId":"2505.13834","arxivUrl":"https://arxiv.org/abs/2505.13834"},{"key":"journals/corr/abs-2510-10637","url":"https://dblp.org/rec/journals/corr/abs-2510-10637","title":"High-Fidelity Simulated Data Generation for Real-World Zero-Shot Robotic Manipulation Learning with Gaussian Splatting.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2510.10637","numberOfCreators":14,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2510-10637","https://doi.org/10.48550/ARXIV.2510.10637"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-10637","documentUrl":null,"type":"Informal","arxivId":"2510.10637","arxivUrl":"https://arxiv.org/abs/2510.10637"},{"key":"journals/corr/abs-2510-11682","url":"https://dblp.org/rec/journals/corr/abs-2510-11682","title":"Ego-Vision World Model for Humanoid Contact Planning.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2510.11682","numberOfCreators":8,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2510-11682","https://doi.org/10.48550/ARXIV.2510.11682"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-11682","documentUrl":null,"type":"Informal","arxivId":"2510.11682","arxivUrl":"https://arxiv.org/abs/2510.11682"}],"excludedFormal":[],"otherRecords":[],"matchedName":"Zhongyu Li","databaseLabel":"Zhongyu Li 0003","databaseMetadata":{"type":["https://dblp.org/rdf/schema#Person","https://dblp.org/rdf/schema#Creator"],"label":["Zhongyu Li 0003"],"affiliation":["University of California Berkeley, Department of Mechanical Engineering, Berkeley, CA, USA"],"orcid":["https://orcid.org/0000-0001-8040-1098"],"primaryAffiliation":["University of California Berkeley, Department of Mechanical Engineering, Berkeley, CA, USA"]},"rawFormalRecordCount2025":5,"signatureAudit":{"completedAt":"2026-10-19","frozen":true,"scope":"对 B 组 39 个数值档案的全部 1074 条原始 2025 正式记录扫描 DBLP author-signature ORCID 和机构；复用既有 59 条 Crossref 核验，补查 6 条新触发记录。重点核查不同 ORCID，以及只有预期机构之外机构的条目。本轮不扩展为所有作者逐篇全文审计。","formalRecordCoverage":5,"orcidCounts":{"https://orcid.org/0000-0001-8040-1098":1},"institutionCounts":{"Berkeley College":1,"University of California, Berkeley (UCB)":4},"caveat":"机构名称可能由 DBLP 自动映射而失真；多 ORCID 也不自动等于异人。只有有原始资料支撑的错归才作确认排除，未解决分支则暂停总数。"},"labName":"Hong Kong Embodied AI Lab","labUrl":null,"labEvidence":"香港中文大学官方 2026-06-15 报道将 Li Zhongyu 列为该实验室 Co-Director，并说明实验室于 2026-05-18 成立。这里只表示当前团队关联，不能把其 2025 合作论文称为这个新实验室的 2025 产量；未确认独立实验室 URL。","labSourceUrl":"https://www.focus.cuhk.edu.hk/en/20260615/cuhk-establishes-hong-kongs-first-full-stack-embodied-ai-lab/080-engineering-en/","sourceWarning":false,"excludedOther":[],"excludedHomonyms":[],"unassignedCandidates":[],"knownPreprintMinimum2025":null,"excludedMisattributed":[],"displayNotes":"DBLP 的机构字段含历史机构，已按原名单机构与本人履历交叉核对。计入 5 条（会议 4、期刊 1），所有作者位置均计入；预印本 6 条单列，不加总。","labDisplayNotes":"港中文 2026-06-15 的官方报道列其为 Hong Kong Embodied AI Lab 联合主任，该实验室 2026-05-18 才成立。这里只表示当前关联，其 2025 年的论文不是这个新实验室的产量；未确认独立网址。"},{"index":57,"name":"Zhouhui Lian","nameZh":"连宙辉","role":"Associate Professor","affiliation":"Peking University","affiliationZh":"北京大学","source":"DBLP RDF via official SPARQL; primary-source identity checks","sourceUrl":"https://sparql.dblp.org/","profileUrl":"https://dblp.org/pid/20/1780.html","identifier":"20/1780","retrievedAt":"2026-10-19","count2025":9,"conference2025":7,"journal2025":2,"preprint2025":7,"status":"confirmed","notes":"","identityEvidence":[{"url":"https://dblp.org/pid/20/1780.html","evidence":"DBLP RDF 类型为 Person，消歧后名字为 Zhouhui Lian。此档案未提供可用机构元数据，以下以本人/机构/出版商来源补证。"},{"url":"https://www.icst.pku.edu.cn/zlian/","evidence":"北京大学官方个人主页为 Zhouhui Lian / 连宙辉，研究列表可与 DBLP 标题匹配。"},{"url":"https://www.icst.pku.edu.cn/zlian/","evidence":"此本人或机构页面的正文与所选档案中 13 条 2025 记录标题匹配，其中 7 条为当前计入的正式记录（忽略空格、标点、大小写）。","matchedPaperKeys":["conf/cvpr/LiuML25","conf/cvpr/PuZTYYYCBZWLWLL25","conf/cvpr/XiongLHWWLZDL25","conf/eccv/ZhaoL24","conf/iccv/LuoTHHL25","conf/nips/LuoYCCYYDLL25","conf/siggrapha/ZhaoGLDLXL25","journals/corr/abs-2502-18364","journals/corr/abs-2503-06472","journals/corr/abs-2504-20403","journals/corr/abs-2506-10963","journals/corr/abs-2512-19024","journals/corr/abs-2512-20479"],"matchedFormalPaperKeys":["conf/cvpr/LiuML25","conf/cvpr/PuZTYYYCBZWLWLL25","conf/cvpr/XiongLHWWLZDL25","conf/eccv/ZhaoL24","conf/iccv/LuoTHHL25","conf/nips/LuoYCCYYDLL25","conf/siggrapha/ZhaoGLDLXL25"]}],"papers":[{"key":"conf/cvpr/LiuML25","url":"https://dblp.org/rec/conf/cvpr/LiuML25","title":"Creating Your Editable 3D Photorealistic Avatar with Tetrahedron-constrained Gaussian Splatting.","year":2025,"types":["Inproceedings"],"venue":"CVPR","doi":"https://doi.org/10.1109/CVPR52734.2025.01489","eventYear":2025,"numberOfCreators":3,"category":"conference","sources":["https://dblp.org/rec/conf/cvpr/LiuML25","https://doi.org/10.1109/CVPR52734.2025.01489"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/LiuML25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/cvpr/PuZTYYYCBZWLWLL25","url":"https://dblp.org/rec/conf/cvpr/PuZTYYYCBZWLWLL25","title":"ART: Anonymous Region Transformer for Variable Multi-Layer Transparent Image Generation.","year":2025,"types":["Inproceedings"],"venue":"CVPR","doi":"https://doi.org/10.1109/CVPR52734.2025.00745","eventYear":2025,"numberOfCreators":17,"category":"conference","sources":["https://dblp.org/rec/conf/cvpr/PuZTYYYCBZWLWLL25","https://doi.org/10.1109/CVPR52734.2025.00745"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/PuZTYYYCBZWLWLL25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/cvpr/XiongLHWWLZDL25","url":"https://dblp.org/rec/conf/cvpr/XiongLHWWLZDL25","title":"TexGaussian: Generating High-quality PBR Material via Octree-based 3D Gaussian Splatting.","year":2025,"types":["Inproceedings"],"venue":"CVPR","doi":"https://doi.org/10.1109/CVPR52734.2025.00060","eventYear":2025,"numberOfCreators":9,"category":"conference","sources":["https://dblp.org/rec/conf/cvpr/XiongLHWWLZDL25","https://doi.org/10.1109/CVPR52734.2025.00060"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/XiongLHWWLZDL25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/eccv/ZhaoL24","url":"https://dblp.org/rec/conf/eccv/ZhaoL24","title":"UDiffText: A Unified Framework for High-Quality Text Synthesis in Arbitrary Images via Character-Aware Diffusion Models.","year":2025,"types":["Inproceedings"],"venue":"ECCV (31)","doi":"https://doi.org/10.1007/978-3-031-72751-1_13","eventYear":2024,"numberOfCreators":2,"category":"conference","sources":["https://dblp.org/rec/conf/eccv/ZhaoL24","https://doi.org/10.1007/978-3-031-72751-1_13"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2024,"sourceUrl":"https://dblp.org/rec/conf/eccv/ZhaoL24","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iccv/LuoTHHL25","url":"https://dblp.org/rec/conf/iccv/LuoTHHL25","title":"CalliReader: Contextualizing Chinese Calligraphy via an Embedding-Aligned Vision-Language Model.","year":2025,"types":["Inproceedings"],"venue":"ICCV","doi":"https://doi.org/10.1109/ICCV51701.2025.02138","eventYear":2025,"numberOfCreators":5,"category":"conference","sources":["https://dblp.org/rec/conf/iccv/LuoTHHL25","https://doi.org/10.1109/ICCV51701.2025.02138"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/LuoTHHL25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/nips/LuoYCCYYDLL25","url":"https://dblp.org/rec/conf/nips/LuoYCCYYDLL25","title":"MMMG: A Massive, Multidisciplinary, Multi-Tier Generation Benchmark for Text-to-Image Reasoning.","year":2025,"types":["Inproceedings"],"venue":"NeurIPS","doi":null,"eventYear":2025,"numberOfCreators":9,"category":"conference","sources":["https://dblp.org/rec/conf/nips/LuoYCCYYDLL25"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/nips/LuoYCCYYDLL25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/siggrapha/ZhaoGLDLXL25","url":"https://dblp.org/rec/conf/siggrapha/ZhaoGLDLXL25","title":"UTDesign: A Unified Framework for Stylized Text Editing and Generation in Graphic Design Images.","year":2025,"types":["Inproceedings"],"venue":"SIGGRAPH Asia","doi":"https://doi.org/10.1145/3757377.3763923","eventYear":2025,"numberOfCreators":7,"category":"conference","sources":["https://dblp.org/rec/conf/siggrapha/ZhaoGLDLXL25","https://doi.org/10.1145/3757377.3763923"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/siggrapha/ZhaoGLDLXL25","documentUrl":null,"type":"Inproceedings"},{"key":"journals/cgf/XiongWZCLW25","url":"https://dblp.org/rec/journals/cgf/XiongWZCLW25","title":"OctFusion: Octree-based Diffusion Models for 3D Shape Generation.","year":2025,"types":["Article"],"venue":"Comput. Graph. Forum","doi":"https://doi.org/10.1111/CGF.70198","numberOfCreators":6,"category":"journal","sources":["https://dblp.org/rec/journals/cgf/XiongWZCLW25","https://doi.org/10.1111/CGF.70198"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/cgf/XiongWZCLW25","documentUrl":null,"type":"Article"},{"key":"journals/cvm/ZhaoGLGHFWZL25","url":"https://dblp.org/rec/journals/cvm/ZhaoGLGHFWZL25","title":"Neural-Polyptych: Content Controllable Painting Recreation for Diverse Genres.","year":2025,"types":["Article"],"venue":"Comput. Vis. Media","doi":"https://doi.org/10.26599/CVM.2025.9450411","numberOfCreators":9,"category":"journal","sources":["https://dblp.org/rec/journals/cvm/ZhaoGLGHFWZL25","https://doi.org/10.26599/CVM.2025.9450411"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/cvm/ZhaoGLGHFWZL25","documentUrl":null,"type":"Article"}],"preprints":[{"key":"journals/corr/abs-2502-18364","url":"https://dblp.org/rec/journals/corr/abs-2502-18364","title":"ART: Anonymous Region Transformer for Variable Multi-Layer Transparent Image Generation.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2502.18364","numberOfCreators":17,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2502-18364","https://doi.org/10.48550/ARXIV.2502.18364"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2502-18364","documentUrl":null,"type":"Informal","arxivId":"2502.18364","arxivUrl":"https://arxiv.org/abs/2502.18364"},{"key":"journals/corr/abs-2503-06472","url":"https://dblp.org/rec/journals/corr/abs-2503-06472","title":"CalliReader: Contextualizing Chinese Calligraphy via an Embedding-Aligned Vision-Language Model.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2503.06472","numberOfCreators":5,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2503-06472","https://doi.org/10.48550/ARXIV.2503.06472"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-06472","documentUrl":null,"type":"Informal","arxivId":"2503.06472","arxivUrl":"https://arxiv.org/abs/2503.06472"},{"key":"journals/corr/abs-2504-20403","url":"https://dblp.org/rec/journals/corr/abs-2504-20403","title":"Creating Your Editable 3D Photorealistic Avatar with Tetrahedron-constrained Gaussian Splatting.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2504.20403","numberOfCreators":3,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2504-20403","https://doi.org/10.48550/ARXIV.2504.20403"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2504-20403","documentUrl":null,"type":"Informal","arxivId":"2504.20403","arxivUrl":"https://arxiv.org/abs/2504.20403"},{"key":"journals/corr/abs-2505-17778","url":"https://dblp.org/rec/journals/corr/abs-2505-17778","title":"TextFlux: An OCR-Free DiT Model for High-Fidelity Multilingual Scene Text Synthesis.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2505.17778","numberOfCreators":12,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2505-17778","https://doi.org/10.48550/ARXIV.2505.17778"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-17778","documentUrl":null,"type":"Informal","arxivId":"2505.17778","arxivUrl":"https://arxiv.org/abs/2505.17778"},{"key":"journals/corr/abs-2506-10963","url":"https://dblp.org/rec/journals/corr/abs-2506-10963","title":"MMMG: A Massive, Multidisciplinary, Multi-Tier Generation Benchmark for Text-to-Image Reasoning.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2506.10963","numberOfCreators":9,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2506-10963","https://doi.org/10.48550/ARXIV.2506.10963"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-10963","documentUrl":null,"type":"Informal","arxivId":"2506.10963","arxivUrl":"https://arxiv.org/abs/2506.10963"},{"key":"journals/corr/abs-2512-19024","url":"https://dblp.org/rec/journals/corr/abs-2512-19024","title":"IndoorUAV: Benchmarking Vision-Language UAV Navigation in Continuous Indoor Environments.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2512.19024","numberOfCreators":5,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2512-19024","https://doi.org/10.48550/ARXIV.2512.19024"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-19024","documentUrl":null,"type":"Informal","arxivId":"2512.19024","arxivUrl":"https://arxiv.org/abs/2512.19024"},{"key":"journals/corr/abs-2512-20479","url":"https://dblp.org/rec/journals/corr/abs-2512-20479","title":"UTDesign: A Unified Framework for Stylized Text Editing and Generation in Graphic Design Images.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2512.20479","numberOfCreators":7,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2512-20479","https://doi.org/10.48550/ARXIV.2512.20479"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-20479","documentUrl":null,"type":"Informal","arxivId":"2512.20479","arxivUrl":"https://arxiv.org/abs/2512.20479"}],"excludedFormal":[],"otherRecords":[],"matchedName":"Zhouhui Lian","databaseLabel":"Zhouhui Lian","databaseMetadata":{"type":["https://dblp.org/rdf/schema#Person","https://dblp.org/rdf/schema#Creator"],"label":["Zhouhui Lian"]},"rawFormalRecordCount2025":9,"signatureAudit":{"completedAt":"2026-10-19","frozen":true,"scope":"对 B 组 39 个数值档案的全部 1074 条原始 2025 正式记录扫描 DBLP author-signature ORCID 和机构；复用既有 59 条 Crossref 核验，补查 6 条新触发记录。重点核查不同 ORCID，以及只有预期机构之外机构的条目。本轮不扩展为所有作者逐篇全文审计。","formalRecordCoverage":9,"orcidCounts":{"https://orcid.org/0000-0002-2683-7170":3},"institutionCounts":{"Microsoft Research Asia":1,"Peking University (PKU)":7},"caveat":"机构名称可能由 DBLP 自动映射而失真；多 ORCID 也不自动等于异人。只有有原始资料支撑的错归才作确认排除，未解决分支则暂停总数。"},"labName":"IGCL","labUrl":"http://igcl.pku.edu.cn/igcl/","labEvidence":"本人北京大学主页明确写 Our research group: IGCL，并给出该网址。未推断缩写全称，未采用其早期访问 NIST 的实验室。","labSourceUrl":"https://www.icst.pku.edu.cn/zlian/","sourceWarning":false,"excludedOther":[],"excludedHomonyms":[],"unassignedCandidates":[],"knownPreprintMinimum2025":null,"excludedMisattributed":[],"displayNotes":"身份已与原名单机构及公开资料核对确认。2025 年正式记录 9 条（会议 7、期刊 2），所有作者位置均计入；预印本 7 条单列，不加总。","labDisplayNotes":"北大本人主页写明 Our research group: IGCL，并给出网址；不推测缩写的全称，也不采用早期访问 NIST 时的实验室。"},{"index":58,"name":"Junwei Liang","nameZh":"梁俊卫","role":"Assistant Professor","affiliation":"The Hong Kong University of Science and Technology (Guangzhou)","affiliationZh":"香港科技大学（广州）","source":"DBLP RDF via official SPARQL; primary-source identity checks","sourceUrl":"https://sparql.dblp.org/","profileUrl":"https://dblp.org/pid/62/10704-1.html","identifier":"62/10704-1","retrievedAt":"2026-10-19","count2025":9,"conference2025":9,"journal2025":0,"preprint2025":11,"status":"confirmed","notes":"","identityEvidence":[{"url":"https://dblp.org/pid/62/10704-1.html","evidence":"DBLP RDF 类型为 Person，消歧后名字为 Junwei Liang 0001。机构元数据含：Tencent Youtu Lab, Shenzhen, China；Hong Kong University of Science and Technology Guangzhou (HKUST-GZ), Guangzhou, China；Carnegie Mellon University, Pittsburgh, PA, USA"}],"papers":[{"key":"conf/cvpr/LiLKY025","url":"https://dblp.org/rec/conf/cvpr/LiLKY025","title":"SeeGround: See and Ground for Zero-Shot Open-Vocabulary 3D Visual Grounding.","year":2025,"types":["Inproceedings"],"venue":"CVPR","doi":"https://doi.org/10.1109/CVPR52734.2025.00351","eventYear":2025,"numberOfCreators":5,"category":"conference","sources":["https://dblp.org/rec/conf/cvpr/LiLKY025","https://doi.org/10.1109/CVPR52734.2025.00351"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/LiLKY025","documentUrl":null,"type":"Inproceedings"},{"key":"conf/cvpr/ZhouMLWQ025","url":"https://dblp.org/rec/conf/cvpr/ZhouMLWQ025","title":"Mitigating the Human-Robot Domain Discrepancy in Visual Pre-training for Robotic Manipulation.","year":2025,"types":["Inproceedings"],"venue":"CVPR","doi":"https://doi.org/10.1109/CVPR52734.2025.02100","eventYear":2025,"numberOfCreators":6,"category":"conference","sources":["https://dblp.org/rec/conf/cvpr/ZhouMLWQ025","https://doi.org/10.1109/CVPR52734.2025.02100"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/ZhouMLWQ025","documentUrl":null,"type":"Inproceedings"},{"key":"conf/eccv/SunLZQL24","url":"https://dblp.org/rec/conf/eccv/SunLZQL24","title":"Prioritized Semantic Learning for Zero-Shot Instance Navigation.","year":2025,"types":["Inproceedings"],"venue":"ECCV (12)","doi":"https://doi.org/10.1007/978-3-031-73254-6_10","eventYear":2024,"numberOfCreators":5,"category":"conference","sources":["https://dblp.org/rec/conf/eccv/SunLZQL24","https://doi.org/10.1007/978-3-031-73254-6_10"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2024,"sourceUrl":"https://dblp.org/rec/conf/eccv/SunLZQL24","documentUrl":null,"type":"Inproceedings"},{"key":"conf/eccv/ZhuZXZXLHLG24","url":"https://dblp.org/rec/conf/eccv/ZhuZXZXLHLG24","title":"Open-Vocabulary 3D Semantic Segmentation with Text-to-Image Diffusion Models.","year":2025,"types":["Inproceedings"],"venue":"ECCV (29)","doi":"https://doi.org/10.1007/978-3-031-73397-0_21","eventYear":2024,"numberOfCreators":9,"category":"conference","sources":["https://dblp.org/rec/conf/eccv/ZhuZXZXLHLG24","https://doi.org/10.1007/978-3-031-73397-0_21"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2024,"sourceUrl":"https://dblp.org/rec/conf/eccv/ZhuZXZXLHLG24","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iccv/XuGQCYLZZZLC25","url":"https://dblp.org/rec/conf/iccv/XuGQCYLZZZLC25","title":"GaussianProperty: Integrating Physical Properties to 3D Gaussians with LMMs.","year":2025,"types":["Inproceedings"],"venue":"ICCV","doi":"https://doi.org/10.1109/ICCV51701.2025.00679","eventYear":2025,"numberOfCreators":11,"category":"conference","sources":["https://dblp.org/rec/conf/iccv/XuGQCYLZZZLC25","https://doi.org/10.1109/ICCV51701.2025.00679"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/XuGQCYLZZZLC25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/icra/GongHQL25","url":"https://dblp.org/rec/conf/icra/GongHQL25","title":"From Cognition to Precognition: A Future-Aware Framework for Social Navigation.","year":2025,"types":["Inproceedings"],"venue":"ICRA","doi":"https://doi.org/10.1109/ICRA55743.2025.11127910","eventYear":2025,"numberOfCreators":4,"category":"conference","sources":["https://dblp.org/rec/conf/icra/GongHQL25","https://doi.org/10.1109/ICRA55743.2025.11127910"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/icra/GongHQL25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/kdd/0047ZHC000Z0Y25","url":"https://dblp.org/rec/conf/kdd/0047ZHC000Z0Y25","title":"ClimateIQA:  A New Dataset and Benchmark to Advance Vision-Language Models in Meteorology Anomalies Analysis.","year":2025,"types":["Inproceedings"],"venue":"KDD (2)","doi":"https://doi.org/10.1145/3711896.3737406","eventYear":2025,"numberOfCreators":10,"category":"conference","sources":["https://dblp.org/rec/conf/kdd/0047ZHC000Z0Y25","https://doi.org/10.1145/3711896.3737406"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/kdd/0047ZHC000Z0Y25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/nips/LiDHLLLPKLL25","url":"https://dblp.org/rec/conf/nips/LiDHLLLPKLL25","title":"3EED: Ground Everything Everywhere in 3D.","year":2025,"types":["Inproceedings"],"venue":"NeurIPS","doi":null,"eventYear":2025,"numberOfCreators":10,"category":"conference","sources":["https://dblp.org/rec/conf/nips/LiDHLLLPKLL25"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/nips/LiDHLLLPKLL25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/nips/ZhouYLMWQLZL25","url":"https://dblp.org/rec/conf/nips/ZhouYLMWQLZL25","title":"Exploring the Limits of Vision-Language-Action Manipulation in Cross-task Generalization.","year":2025,"types":["Inproceedings"],"venue":"NeurIPS","doi":null,"eventYear":2025,"numberOfCreators":9,"category":"conference","sources":["https://dblp.org/rec/conf/nips/ZhouYLMWQLZL25"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/nips/ZhouYLMWQLZL25","documentUrl":null,"type":"Inproceedings"}],"preprints":[{"key":"journals/corr/abs-2505-11865","url":"https://dblp.org/rec/journals/corr/abs-2505-11865","title":"GLOVER++: Unleashing the Potential of Affordance Learning from Human Behaviors for Robotic Manipulation.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2505.11865","numberOfCreators":6,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2505-11865","https://doi.org/10.48550/ARXIV.2505.11865"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-11865","documentUrl":null,"type":"Informal","arxivId":"2505.11865","arxivUrl":"https://arxiv.org/abs/2505.11865"},{"key":"journals/corr/abs-2505-15660","url":"https://dblp.org/rec/journals/corr/abs-2505-15660","title":"Exploring the Limits of Vision-Language-Action Manipulations in Cross-task Generalization.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2505.15660","numberOfCreators":9,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2505-15660","https://doi.org/10.48550/ARXIV.2505.15660"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-15660","documentUrl":null,"type":"Informal","arxivId":"2505.15660","arxivUrl":"https://arxiv.org/abs/2505.15660"},{"key":"journals/corr/abs-2505-18881","url":"https://dblp.org/rec/journals/corr/abs-2505-18881","title":"SD-OVON: A Semantics-aware Dataset and Benchmark Generation Pipeline for Open-Vocabulary Object Navigation in Dynamic Scenes.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2505.18881","numberOfCreators":6,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2505-18881","https://doi.org/10.48550/ARXIV.2505.18881"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-18881","documentUrl":null,"type":"Informal","arxivId":"2505.18881","arxivUrl":"https://arxiv.org/abs/2505.18881"},{"key":"journals/corr/abs-2505-19214","url":"https://dblp.org/rec/journals/corr/abs-2505-19214","title":"Omni-Perception: Omnidirectional Collision Avoidance for Legged Locomotion in Dynamic Environments.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2505.19214","numberOfCreators":8,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2505-19214","https://doi.org/10.48550/ARXIV.2505.19214"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-19214","documentUrl":null,"type":"Informal","arxivId":"2505.19214","arxivUrl":"https://arxiv.org/abs/2505.19214"},{"key":"journals/corr/abs-2505-22429","url":"https://dblp.org/rec/journals/corr/abs-2505-22429","title":"Zero-Shot 3D Visual Grounding from Vision-Language Models.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2505.22429","numberOfCreators":5,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2505-22429","https://doi.org/10.48550/ARXIV.2505.22429"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-22429","documentUrl":null,"type":"Informal","arxivId":"2505.22429","arxivUrl":"https://arxiv.org/abs/2505.22429"},{"key":"journals/corr/abs-2505-23019","url":"https://dblp.org/rec/journals/corr/abs-2505-23019","title":"Stairway to Success: Zero-Shot Floor-Aware Object-Goal Navigation via LLM-Driven Coarse-to-Fine Exploration.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2505.23019","numberOfCreators":9,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2505-23019","https://doi.org/10.48550/ARXIV.2505.23019"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-23019","documentUrl":null,"type":"Informal","arxivId":"2505.23019","arxivUrl":"https://arxiv.org/abs/2505.23019"},{"key":"journals/corr/abs-2508-07611","url":"https://dblp.org/rec/journals/corr/abs-2508-07611","title":"End-to-End Humanoid Robot Safe and Comfortable Locomotion Policy.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2508.07611","numberOfCreators":8,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2508-07611","https://doi.org/10.48550/ARXIV.2508.07611"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-07611","documentUrl":null,"type":"Informal","arxivId":"2508.07611","arxivUrl":"https://arxiv.org/abs/2508.07611"},{"key":"journals/corr/abs-2509-22205","url":"https://dblp.org/rec/journals/corr/abs-2509-22205","title":"From Watch to Imagine: Steering Long-horizon Manipulation via Human Demonstration and Future Envisionment.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2509.22205","numberOfCreators":7,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2509-22205","https://doi.org/10.48550/ARXIV.2509.22205"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-22205","documentUrl":null,"type":"Informal","arxivId":"2509.22205","arxivUrl":"https://arxiv.org/abs/2509.22205"},{"key":"journals/corr/abs-2510-00405","url":"https://dblp.org/rec/journals/corr/abs-2510-00405","title":"EgoTraj-Bench: Towards Robust Trajectory Prediction Under Ego-view Noisy Observations.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2510.00405","numberOfCreators":6,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2510-00405","https://doi.org/10.48550/ARXIV.2510.00405"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-00405","documentUrl":null,"type":"Informal","arxivId":"2510.00405","arxivUrl":"https://arxiv.org/abs/2510.00405"},{"key":"journals/corr/abs-2511-01755","url":"https://dblp.org/rec/journals/corr/abs-2511-01755","title":"3EED: Ground Everything Everywhere in 3D.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2511.01755","numberOfCreators":10,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2511-01755","https://doi.org/10.48550/ARXIV.2511.01755"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2511-01755","documentUrl":null,"type":"Informal","arxivId":"2511.01755","arxivUrl":"https://arxiv.org/abs/2511.01755"},{"key":"journals/corr/abs-2512-16760","url":"https://dblp.org/rec/journals/corr/abs-2512-16760","title":"Vision-Language-Action Models for Autonomous Driving: Past, Present, and Future.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2512.16760","numberOfCreators":20,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2512-16760","https://doi.org/10.48550/ARXIV.2512.16760"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-16760","documentUrl":null,"type":"Informal","arxivId":"2512.16760","arxivUrl":"https://arxiv.org/abs/2512.16760"}],"excludedFormal":[],"otherRecords":[],"matchedName":"Junwei Liang","databaseLabel":"Junwei Liang 0001","databaseMetadata":{"type":["https://dblp.org/rdf/schema#Person","https://dblp.org/rdf/schema#Creator"],"label":["Junwei Liang 0001"],"affiliation":["Tencent Youtu Lab, Shenzhen, China","Hong Kong University of Science and Technology Guangzhou (HKUST-GZ), Guangzhou, China","Carnegie Mellon University, Pittsburgh, PA, USA"],"homepage":["https://www.cs.cmu.edu/~junweil/","https://www.youtube.com/@junweiliang","https://junweiliang.me/"],"orcid":["https://orcid.org/0000-0003-2219-5569"],"primaryAffiliation":["Hong Kong University of Science and Technology Guangzhou (HKUST-GZ), Guangzhou, China"],"primaryHomepage":["https://junweiliang.me/"]},"rawFormalRecordCount2025":9,"signatureAudit":{"completedAt":"2026-10-19","frozen":true,"scope":"对 B 组 39 个数值档案的全部 1074 条原始 2025 正式记录扫描 DBLP author-signature ORCID 和机构；复用既有 59 条 Crossref 核验，补查 6 条新触发记录。重点核查不同 ORCID，以及只有预期机构之外机构的条目。本轮不扩展为所有作者逐篇全文审计。","formalRecordCoverage":9,"orcidCounts":{"https://orcid.org/0000-0003-2219-5569":7},"institutionCounts":{"Hong Kong University of Science and Technology (HKUST)":7},"caveat":"机构名称可能由 DBLP 自动映射而失真；多 ORCID 也不自动等于异人。只有有原始资料支撑的错归才作确认排除，未解决分支则暂停总数。"},"labName":"Precognition Lab（智能感知与预测实验室）","labUrl":"https://precognition.team/","labEvidence":"本人当前主页明确写 I lead the Precognition Lab，并直接链接该实验室网站；采用当前页面，不采用较早 CMU 博士阶段页面。","labSourceUrl":"https://junweiliang.me/","sourceWarning":false,"excludedOther":[],"excludedHomonyms":[],"unassignedCandidates":[],"knownPreprintMinimum2025":null,"excludedMisattributed":[],"displayNotes":"身份已与原名单机构及公开资料核对确认。2025 年正式记录 9 条，均为会议论文，所有作者位置均计入；预印本 11 条单列，不加总。","labDisplayNotes":"本人当前主页写明其领导 Precognition Lab（智能感知与预测实验室），并链接实验室网站，据此归组。"},{"index":59,"name":"Jing Liao","nameZh":"廖菁","role":"Associate Professor","affiliation":"City University of Hong Kong","affiliationZh":"香港城市大学","source":"DBLP RDF via official SPARQL; primary-source identity checks","sourceUrl":"https://sparql.dblp.org/","profileUrl":"https://dblp.org/pid/48/5348-1.html","identifier":"48/5348-1","retrievedAt":"2026-10-19","count2025":18,"conference2025":11,"journal2025":7,"preprint2025":13,"status":"confirmed","notes":"","identityEvidence":[{"url":"https://dblp.org/pid/48/5348-1.html","evidence":"DBLP RDF 类型为 Person，消歧后名字为 Jing Liao 0001。机构元数据含：Hong Kong University of Science and Technology, Department of Computer Science and Engineering, Hong Kong；City University of Hong Kong, Hong Kong；Microsoft Research Asia, China；Zhejiang University, State Key Lab of CAD&CG, Hangzhou, China"}],"papers":[{"key":"conf/ACMdis/MillerZ0L25","url":"https://dblp.org/rec/conf/ACMdis/MillerZ0L25","title":"Eliciting (Immersive) Intangibles: Genai-Supported Collaborative Visual Narration in a Physically Immersive Space.","year":2025,"types":["Inproceedings"],"venue":"Conference on Designing Interactive Systems","doi":"https://doi.org/10.1145/3715336.3735682","eventYear":2025,"numberOfCreators":4,"category":"conference","sources":["https://dblp.org/rec/conf/ACMdis/MillerZ0L25","https://doi.org/10.1145/3715336.3735682"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/ACMdis/MillerZ0L25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/cvpr/Feng00CZ25","url":"https://dblp.org/rec/conf/cvpr/Feng00CZ25","title":"CASAGPT: Cuboid Arrangement and Scene Assembly for Interior Design.","year":2025,"types":["Inproceedings"],"venue":"CVPR","doi":"https://doi.org/10.1109/CVPR52734.2025.02716","eventYear":2025,"numberOfCreators":5,"category":"conference","sources":["https://dblp.org/rec/conf/cvpr/Feng00CZ25","https://doi.org/10.1109/CVPR52734.2025.02716"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/Feng00CZ25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/cvpr/WuS025","url":"https://dblp.org/rec/conf/cvpr/WuS025","title":"Chat2SVG: Vector Graphics Generation with Large Language Models and Image Diffusion Models.","year":2025,"types":["Inproceedings"],"venue":"CVPR","doi":"https://doi.org/10.1109/CVPR52734.2025.02206","eventYear":2025,"numberOfCreators":3,"category":"conference","sources":["https://dblp.org/rec/conf/cvpr/WuS025","https://doi.org/10.1109/CVPR52734.2025.02206"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/WuS025","documentUrl":null,"type":"Inproceedings"},{"key":"conf/cvpr/YeZ0LGZWL25","url":"https://dblp.org/rec/conf/cvpr/YeZ0LGZWL25","title":"Robust Message Embedding via Attention Flow-Based Steganography.","year":2025,"types":["Inproceedings"],"venue":"CVPR","doi":"https://doi.org/10.1109/CVPR52734.2025.01198","eventYear":2025,"numberOfCreators":8,"category":"conference","sources":["https://dblp.org/rec/conf/cvpr/YeZ0LGZWL25","https://doi.org/10.1109/CVPR52734.2025.01198"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/YeZ0LGZWL25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/eccv/WuWZLX24","url":"https://dblp.org/rec/conf/eccv/WuWZLX24","title":"RaFE: Generative Radiance Fields Restoration.","year":2025,"types":["Inproceedings"],"venue":"ECCV (67)","doi":"https://doi.org/10.1007/978-3-031-72855-6_10","eventYear":2024,"numberOfCreators":5,"category":"conference","sources":["https://dblp.org/rec/conf/eccv/WuWZLX24","https://doi.org/10.1007/978-3-031-72855-6_10"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2024,"sourceUrl":"https://dblp.org/rec/conf/eccv/WuWZLX24","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iccv/ChengGGLS25","url":"https://dblp.org/rec/conf/iccv/ChengGGLS25","title":"AnimeGamer: Infinite Anime Life Simulation with Next Game State Prediction.","year":2025,"types":["Inproceedings"],"venue":"ICCV","doi":"https://doi.org/10.1109/ICCV51701.2025.01012","eventYear":2025,"numberOfCreators":5,"category":"conference","sources":["https://dblp.org/rec/conf/iccv/ChengGGLS25","https://doi.org/10.1109/ICCV51701.2025.01012"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/ChengGGLS25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iccv/ZhangCL25","url":"https://dblp.org/rec/conf/iccv/ZhangCL25","title":"I2V3D: Controllable Image-to-Video Generation with 3D Guidance.","year":2025,"types":["Inproceedings"],"venue":"ICCV","doi":"https://doi.org/10.1109/ICCV51701.2025.01241","eventYear":2025,"numberOfCreators":3,"category":"conference","sources":["https://dblp.org/rec/conf/iccv/ZhangCL25","https://doi.org/10.1109/ICCV51701.2025.01241"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/ZhangCL25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iclr/SunGWYY00L25","url":"https://dblp.org/rec/conf/iclr/SunGWYY00L25","title":"EG4D: Explicit Generation of 4D Object without Score Distillation.","year":2025,"types":["Inproceedings"],"venue":"ICLR","doi":null,"eventYear":2025,"numberOfCreators":8,"category":"conference","sources":["https://dblp.org/rec/conf/iclr/SunGWYY00L25"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iclr/SunGWYY00L25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/siggraph/0002Z025","url":"https://dblp.org/rec/conf/siggraph/0002Z025","title":"Style Customization of Text-to-Vector Generation with Image Diffusion Priors.","year":2025,"types":["Inproceedings"],"venue":"SIGGRAPH (Conference Paper Track)","doi":"https://doi.org/10.1145/3721238.3730707","eventYear":2025,"numberOfCreators":3,"category":"conference","sources":["https://dblp.org/rec/conf/siggraph/0002Z025","https://doi.org/10.1145/3721238.3730707"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/siggraph/0002Z025","documentUrl":null,"type":"Inproceedings"},{"key":"conf/siggrapha/SunWSF025","url":"https://dblp.org/rec/conf/siggrapha/SunWSF025","title":"Animus3D: Text-driven 3D Animation via Motion Score Distillation.","year":2025,"types":["Inproceedings"],"venue":"SIGGRAPH Asia","doi":"https://doi.org/10.1145/3757377.3763916","eventYear":2025,"numberOfCreators":5,"category":"conference","sources":["https://dblp.org/rec/conf/siggrapha/SunWSF025","https://doi.org/10.1145/3757377.3763916"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/siggrapha/SunWSF025","documentUrl":null,"type":"Inproceedings"},{"key":"conf/siggrapha/WuS025","url":"https://dblp.org/rec/conf/siggrapha/WuS025","title":"LayerPeeler: Autoregressive Peeling for Layer-wise Image Vectorization.","year":2025,"types":["Inproceedings"],"venue":"SIGGRAPH Asia","doi":"https://doi.org/10.1145/3757377.3763964","eventYear":2025,"numberOfCreators":3,"category":"conference","sources":["https://dblp.org/rec/conf/siggrapha/WuS025","https://doi.org/10.1145/3757377.3763964"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/siggrapha/WuS025","documentUrl":null,"type":"Inproceedings"},{"key":"journals/ijcv/WuSML25","url":"https://dblp.org/rec/journals/ijcv/WuSML25","title":"AniClipart: Clipart Animation with Text-to-Video Priors.","year":2025,"types":["Article"],"venue":"Int. J. Comput. Vis.","doi":"https://doi.org/10.1007/S11263-024-02306-1","numberOfCreators":4,"category":"journal","sources":["https://dblp.org/rec/journals/ijcv/WuSML25","https://doi.org/10.1007/S11263-024-02306-1"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/ijcv/WuSML25","documentUrl":null,"type":"Article"},{"key":"journals/tbbis/Fu00H0L025","url":"https://dblp.org/rec/journals/tbbis/Fu00H0L025","title":"OASG-Net: Occlusion Aware and Structure-Guided Network for Face De-Occlusion.","year":2025,"types":["Article"],"venue":"IEEE Trans. Biom. Behav. Identity Sci.","doi":"https://doi.org/10.1109/TBIOM.2024.3476947","numberOfCreators":7,"category":"journal","sources":["https://dblp.org/rec/journals/tbbis/Fu00H0L025","https://doi.org/10.1109/TBIOM.2024.3476947"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/tbbis/Fu00H0L025","documentUrl":null,"type":"Article"},{"key":"journals/tcsv/ZhangLZZCSL25","url":"https://dblp.org/rec/journals/tcsv/ZhangLZZCSL25","title":"HumanRef-GS: Image-to-3D Human Generation With Reference-Guided Diffusion and 3D Gaussian Splatting.","year":2025,"types":["Article"],"venue":"IEEE Trans. Circuits Syst. Video Technol.","doi":"https://doi.org/10.1109/TCSVT.2025.3540969","numberOfCreators":7,"category":"journal","sources":["https://dblp.org/rec/journals/tcsv/ZhangLZZCSL25","https://doi.org/10.1109/TCSVT.2025.3540969"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/tcsv/ZhangLZZCSL25","documentUrl":null,"type":"Article"},{"key":"journals/titb/DuDXL25","url":"https://dblp.org/rec/journals/titb/DuDXL25","title":"TDFormer: Top-Down Token Generation for 3D Medical Image Segmentation.","year":2025,"types":["Article"],"venue":"IEEE J. Biomed. Health Informatics","doi":"https://doi.org/10.1109/JBHI.2025.3567590","numberOfCreators":4,"category":"journal","sources":["https://dblp.org/rec/journals/titb/DuDXL25","https://doi.org/10.1109/JBHI.2025.3567590"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/titb/DuDXL25","documentUrl":null,"type":"Article"},{"key":"journals/tvcg/SuWLHFL25","url":"https://dblp.org/rec/journals/tvcg/SuWLHFL25","title":"StyleRetoucher: Generalized Portrait Image Retouching With GAN Priors.","year":2025,"types":["Article"],"venue":"IEEE Trans. Vis. Comput. Graph.","doi":"https://doi.org/10.1109/TVCG.2024.3432910","numberOfCreators":6,"category":"journal","sources":["https://dblp.org/rec/journals/tvcg/SuWLHFL25","https://doi.org/10.1109/TVCG.2024.3432910"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/tvcg/SuWLHFL25","documentUrl":null,"type":"Article"},{"key":"journals/tvcg/ZhuangCCJLLCLL25","url":"https://dblp.org/rec/journals/tvcg/ZhuangCCJLLCLL25","title":"Learn2Talk: 3D Talking Face Learns From 2D Talking Face.","year":2025,"types":["Article"],"venue":"IEEE Trans. Vis. Comput. Graph.","doi":"https://doi.org/10.1109/TVCG.2024.3476275","numberOfCreators":9,"category":"journal","sources":["https://dblp.org/rec/journals/tvcg/ZhuangCCJLLCLL25","https://doi.org/10.1109/TVCG.2024.3476275"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/tvcg/ZhuangCCJLLCLL25","documentUrl":null,"type":"Article"},{"key":"journals/vi/ZhongWZL25","url":"https://dblp.org/rec/journals/vi/ZhongWZL25","title":"Generative object insertion in Gaussian splatting with a multi-view diffusion model.","year":2025,"types":["Article"],"venue":"Vis. Informatics","doi":"https://doi.org/10.1016/J.VISINF.2025.100238","numberOfCreators":4,"category":"journal","sources":["https://dblp.org/rec/journals/vi/ZhongWZL25","https://doi.org/10.1016/J.VISINF.2025.100238"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/vi/ZhongWZL25","documentUrl":null,"type":"Article"}],"preprints":[{"key":"journals/corr/abs-2501-09921","url":"https://dblp.org/rec/journals/corr/abs-2501-09921","title":"TalkingEyes: Pluralistic Speech-Driven 3D Eye Gaze Animation.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2501.09921","numberOfCreators":6,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2501-09921","https://doi.org/10.48550/ARXIV.2501.09921"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2501-09921","documentUrl":null,"type":"Informal","arxivId":"2501.09921","arxivUrl":"https://arxiv.org/abs/2501.09921"},{"key":"journals/corr/abs-2503-09733","url":"https://dblp.org/rec/journals/corr/abs-2503-09733","title":"I2V3D: Controllable image-to-video generation with 3D guidance.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2503.09733","numberOfCreators":3,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2503-09733","https://doi.org/10.48550/ARXIV.2503.09733"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-09733","documentUrl":null,"type":"Informal","arxivId":"2503.09733","arxivUrl":"https://arxiv.org/abs/2503.09733"},{"key":"journals/corr/abs-2503-11412","url":"https://dblp.org/rec/journals/corr/abs-2503-11412","title":"MTV-Inpaint: Multi-Task Long Video Inpainting.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2503.11412","numberOfCreators":7,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2503-11412","https://doi.org/10.48550/ARXIV.2503.11412"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-11412","documentUrl":null,"type":"Informal","arxivId":"2503.11412","arxivUrl":"https://arxiv.org/abs/2503.11412"},{"key":"journals/corr/abs-2504-01014","url":"https://dblp.org/rec/journals/corr/abs-2504-01014","title":"AnimeGamer: Infinite Anime Life Simulation with Next Game State Prediction.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2504.01014","numberOfCreators":5,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2504-01014","https://doi.org/10.48550/ARXIV.2504.01014"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2504-01014","documentUrl":null,"type":"Informal","arxivId":"2504.01014","arxivUrl":"https://arxiv.org/abs/2504.01014"},{"key":"journals/corr/abs-2504-19478","url":"https://dblp.org/rec/journals/corr/abs-2504-19478","title":"CasaGPT: Cuboid Arrangement and Scene Assembly for Interior Design.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2504.19478","numberOfCreators":5,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2504-19478","https://doi.org/10.48550/ARXIV.2504.19478"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2504-19478","documentUrl":null,"type":"Informal","arxivId":"2504.19478","arxivUrl":"https://arxiv.org/abs/2504.19478"},{"key":"journals/corr/abs-2505-10558","url":"https://dblp.org/rec/journals/corr/abs-2505-10558","title":"Style Customization of Text-to-Vector Generation with Image Diffusion Priors.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2505.10558","numberOfCreators":3,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2505-10558","https://doi.org/10.48550/ARXIV.2505.10558"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-10558","documentUrl":null,"type":"Informal","arxivId":"2505.10558","arxivUrl":"https://arxiv.org/abs/2505.10558"},{"key":"journals/corr/abs-2505-21374","url":"https://dblp.org/rec/journals/corr/abs-2505-21374","title":"Video-Holmes: Can MLLM Think Like Holmes for Complex Video Reasoning?","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2505.21374","numberOfCreators":6,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2505-21374","https://doi.org/10.48550/ARXIV.2505.21374"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-21374","documentUrl":null,"type":"Informal","arxivId":"2505.21374","arxivUrl":"https://arxiv.org/abs/2505.21374"},{"key":"journals/corr/abs-2505-23740","url":"https://dblp.org/rec/journals/corr/abs-2505-23740","title":"LayerPeeler: Autoregressive Peeling for Layer-wise Image Vectorization.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2505.23740","numberOfCreators":3,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2505-23740","https://doi.org/10.48550/ARXIV.2505.23740"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-23740","documentUrl":null,"type":"Informal","arxivId":"2505.23740","arxivUrl":"https://arxiv.org/abs/2505.23740"},{"key":"journals/corr/abs-2510-08527","url":"https://dblp.org/rec/journals/corr/abs-2510-08527","title":"FlexTraj: Image-to-Video Generation with Flexible Point Trajectory Control.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2510.08527","numberOfCreators":4,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2510-08527","https://doi.org/10.48550/ARXIV.2510.08527"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-08527","documentUrl":null,"type":"Informal","arxivId":"2510.08527","arxivUrl":"https://arxiv.org/abs/2510.08527"},{"key":"journals/corr/abs-2510-08530","url":"https://dblp.org/rec/journals/corr/abs-2510-08530","title":"X2Video: Adapting Diffusion Models for Multimodal Controllable Neural Video Rendering.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2510.08530","numberOfCreators":6,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2510-08530","https://doi.org/10.48550/ARXIV.2510.08530"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-08530","documentUrl":null,"type":"Informal","arxivId":"2510.08530","arxivUrl":"https://arxiv.org/abs/2510.08530"},{"key":"journals/corr/abs-2511-16669","url":"https://dblp.org/rec/journals/corr/abs-2511-16669","title":"Video-as-Answer: Predict and Generate Next Video Event with Joint-GRPO.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2511.16669","numberOfCreators":4,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2511-16669","https://doi.org/10.48550/ARXIV.2511.16669"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2511-16669","documentUrl":null,"type":"Informal","arxivId":"2511.16669","arxivUrl":"https://arxiv.org/abs/2511.16669"},{"key":"journals/corr/abs-2512-10894","url":"https://dblp.org/rec/journals/corr/abs-2512-10894","title":"DuetSVG: Unified Multimodal SVG Generation with Internal Visual Guidance.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2512.10894","numberOfCreators":6,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2512-10894","https://doi.org/10.48550/ARXIV.2512.10894"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-10894","documentUrl":null,"type":"Informal","arxivId":"2512.10894","arxivUrl":"https://arxiv.org/abs/2512.10894"},{"key":"journals/corr/abs-2512-12534","url":"https://dblp.org/rec/journals/corr/abs-2512-12534","title":"Animus3D: Text-driven 3D Animation via Motion Score Distillation.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2512.12534","numberOfCreators":5,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2512-12534","https://doi.org/10.48550/ARXIV.2512.12534"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-12534","documentUrl":null,"type":"Informal","arxivId":"2512.12534","arxivUrl":"https://arxiv.org/abs/2512.12534"}],"excludedFormal":[],"otherRecords":[],"matchedName":"Jing Liao","databaseLabel":"Jing Liao 0001","databaseMetadata":{"type":["https://dblp.org/rdf/schema#Creator","https://dblp.org/rdf/schema#Person"],"label":["Jing Liao 0001"],"affiliation":["Hong Kong University of Science and Technology, Department of Computer Science and Engineering, Hong Kong","City University of Hong Kong, Hong Kong","Microsoft Research Asia, China","Zhejiang University, State Key Lab of CAD&CG, Hangzhou, China"],"homepage":["https://scholars.cityu.edu.hk/en/persons/jing-liao(45757c38-f737-420d-8a7f-73b58d30c1fd).html"],"orcid":["https://orcid.org/0000-0001-7014-5377"],"primaryAffiliation":["City University of Hong Kong, Hong Kong"],"primaryHomepage":["https://scholars.cityu.edu.hk/en/persons/jing-liao(45757c38-f737-420d-8a7f-73b58d30c1fd).html"]},"rawFormalRecordCount2025":18,"signatureAudit":{"completedAt":"2026-10-19","frozen":true,"scope":"对 B 组 39 个数值档案的全部 1074 条原始 2025 正式记录扫描 DBLP author-signature ORCID 和机构；复用既有 59 条 Crossref 核验，补查 6 条新触发记录。重点核查不同 ORCID，以及只有预期机构之外机构的条目。本轮不扩展为所有作者逐篇全文审计。","formalRecordCoverage":18,"orcidCounts":{"https://orcid.org/0000-0001-7014-5377":17},"institutionCounts":{"City University of Hong Kong":16},"caveat":"机构名称可能由 DBLP 自动映射而失真；多 ORCID 也不自动等于异人。只有有原始资料支撑的错归才作确认排除，未解决分支则暂停总数。"},"labName":null,"labUrl":null,"labEvidence":"香港城市大学本人教师介绍未明确命名实验室；更大研究中心的研究列表不足以确认其个人实验室。","labSourceUrl":"https://www.cityu.edu.hk/stfprofile/jingliao.htm","sourceWarning":false,"excludedOther":[],"excludedHomonyms":[],"unassignedCandidates":[],"knownPreprintMinimum2025":null,"excludedMisattributed":[],"displayNotes":"身份已与原名单机构及公开资料核对确认。2025 年正式记录 18 条（会议 11、期刊 7），所有作者位置均计入，不表示主导或贡献份额；预印本 13 条单列，不加总。","labDisplayNotes":"城大本人教师介绍未写实验室名称；所在大型研究中心的项目列表不足以确认其个人团队。图中以「姓名及合作者」单列。"},{"index":60,"name":"Yiyi Liao","nameZh":"廖依伊","role":"Distinguished Research Fellow","affiliation":"Zhejiang University","affiliationZh":"浙江大学","source":"DBLP RDF via official SPARQL; primary-source identity checks","sourceUrl":"https://sparql.dblp.org/","profileUrl":"https://dblp.org/pid/139/0761.html","identifier":"139/0761","retrievedAt":"2026-10-19","count2025":15,"conference2025":12,"journal2025":3,"preprint2025":10,"status":"confirmed","notes":"","identityEvidence":[{"url":"https://dblp.org/pid/139/0761.html","evidence":"DBLP RDF 类型为 Person，消歧后名字为 Yiyi Liao。此档案未提供可用机构元数据，以下以本人/机构/出版商来源补证。"},{"url":"https://yiyiliao.github.io/","evidence":"个人主页为浙江大学 Yiyi Liao；个人论文标题与所选 DBLP 记录匹配。"},{"url":"https://yiyiliao.github.io/","evidence":"此本人或机构页面的正文与所选档案中 19 条 2025 记录标题匹配，其中 12 条为当前计入的正式记录（忽略空格、标点、大小写）。","matchedPaperKeys":["conf/cvpr/LiLGBYL25","conf/cvpr/LuCZZHY0L25","conf/cvpr/Miao0BYZ0L0L25","conf/cvpr/ShaoYZ0SGWPL25","conf/cvpr/YangSLS0L25","conf/eccv/ChenGBZYWSL24","conf/eccv/JiLL24","conf/eccv/MiaoHBQLGL24","conf/iccv/HuangMYML25","conf/nips/LuTJZYOHYSL25","journals/corr/abs-2503-20168","journals/corr/abs-2504-11092","journals/corr/abs-2505-07539","journals/corr/abs-2506-01822","journals/corr/abs-2506-08640","journals/corr/abs-2507-11540","journals/corr/abs-2507-17520","journals/pami/FuZCLZGL25","journals/ral/WuLJYWXL25"],"matchedFormalPaperKeys":["conf/cvpr/LiLGBYL25","conf/cvpr/LuCZZHY0L25","conf/cvpr/Miao0BYZ0L0L25","conf/cvpr/ShaoYZ0SGWPL25","conf/cvpr/YangSLS0L25","conf/eccv/ChenGBZYWSL24","conf/eccv/JiLL24","conf/eccv/MiaoHBQLGL24","conf/iccv/HuangMYML25","conf/nips/LuTJZYOHYSL25","journals/pami/FuZCLZGL25","journals/ral/WuLJYWXL25"]}],"papers":[{"key":"conf/cvpr/LiLGBYL25","url":"https://dblp.org/rec/conf/cvpr/LiLGBYL25","title":"GIFStream: 4D Gaussian-based Immersive Video with Feature Stream.","year":2025,"types":["Inproceedings"],"venue":"CVPR","doi":"https://doi.org/10.1109/CVPR52734.2025.02027","eventYear":2025,"numberOfCreators":6,"category":"conference","sources":["https://dblp.org/rec/conf/cvpr/LiLGBYL25","https://doi.org/10.1109/CVPR52734.2025.02027"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/LiLGBYL25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/cvpr/LuCZZHY0L25","url":"https://dblp.org/rec/conf/cvpr/LuCZZHY0L25","title":"UrbanCAD: Towards Highly Controllable and Photorealistic 3D Vehicles for Urban Scene Simulation.","year":2025,"types":["Inproceedings"],"venue":"CVPR","doi":"https://doi.org/10.1109/CVPR52734.2025.02563","eventYear":2025,"numberOfCreators":8,"category":"conference","sources":["https://dblp.org/rec/conf/cvpr/LuCZZHY0L25","https://doi.org/10.1109/CVPR52734.2025.02563"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/LuCZZHY0L25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/cvpr/Miao0BYZ0L0L25","url":"https://dblp.org/rec/conf/cvpr/Miao0BYZ0L0L25","title":"EVolSplat: Efficient Volume-based Gaussian Splatting for Urban View Synthesis.","year":2025,"types":["Inproceedings"],"venue":"CVPR","doi":"https://doi.org/10.1109/CVPR52734.2025.01054","eventYear":2025,"numberOfCreators":9,"category":"conference","sources":["https://dblp.org/rec/conf/cvpr/Miao0BYZ0L0L25","https://doi.org/10.1109/CVPR52734.2025.01054"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/Miao0BYZ0L0L25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/cvpr/ShaoYZ0SGWPL25","url":"https://dblp.org/rec/conf/cvpr/ShaoYZ0SGWPL25","title":"Learning Temporally Consistent Video Depth from Video Diffusion Priors.","year":2025,"types":["Inproceedings"],"venue":"CVPR","doi":"https://doi.org/10.1109/CVPR52734.2025.02127","eventYear":2025,"numberOfCreators":9,"category":"conference","sources":["https://dblp.org/rec/conf/cvpr/ShaoYZ0SGWPL25","https://doi.org/10.1109/CVPR52734.2025.02127"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/ShaoYZ0SGWPL25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/cvpr/YangSLS0L25","url":"https://dblp.org/rec/conf/cvpr/YangSLS0L25","title":"Prometheus: 3D-Aware Latent Diffusion Models for Feed-Forward Text-to-3D Scene Generation.","year":2025,"types":["Inproceedings"],"venue":"CVPR","doi":"https://doi.org/10.1109/CVPR52734.2025.00272","eventYear":2025,"numberOfCreators":6,"category":"conference","sources":["https://dblp.org/rec/conf/cvpr/YangSLS0L25","https://doi.org/10.1109/CVPR52734.2025.00272"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/YangSLS0L25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/eccv/ChenGBZYWSL24","url":"https://dblp.org/rec/conf/eccv/ChenGBZYWSL24","title":"Learning 3D-Aware GANs from Unposed Images with Template Feature Field.","year":2025,"types":["Inproceedings"],"venue":"ECCV (16)","doi":"https://doi.org/10.1007/978-3-031-72640-8_3","eventYear":2024,"numberOfCreators":8,"category":"conference","sources":["https://dblp.org/rec/conf/eccv/ChenGBZYWSL24","https://doi.org/10.1007/978-3-031-72640-8_3"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2024,"sourceUrl":"https://dblp.org/rec/conf/eccv/ChenGBZYWSL24","documentUrl":null,"type":"Inproceedings"},{"key":"conf/eccv/JiLL24","url":"https://dblp.org/rec/conf/eccv/JiLL24","title":"REFRAME: Reflective Surface Real-Time Rendering for Mobile Devices.","year":2025,"types":["Inproceedings"],"venue":"ECCV (45)","doi":"https://doi.org/10.1007/978-3-031-72995-9_14","eventYear":2024,"numberOfCreators":3,"category":"conference","sources":["https://dblp.org/rec/conf/eccv/JiLL24","https://doi.org/10.1007/978-3-031-72995-9_14"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2024,"sourceUrl":"https://dblp.org/rec/conf/eccv/JiLL24","documentUrl":null,"type":"Inproceedings"},{"key":"conf/eccv/MiaoHBQLGL24","url":"https://dblp.org/rec/conf/eccv/MiaoHBQLGL24","title":"Efficient Depth-Guided Urban View Synthesis.","year":2025,"types":["Inproceedings"],"venue":"ECCV (30)","doi":"https://doi.org/10.1007/978-3-031-73404-5_6","eventYear":2024,"numberOfCreators":7,"category":"conference","sources":["https://dblp.org/rec/conf/eccv/MiaoHBQLGL24","https://doi.org/10.1007/978-3-031-73404-5_6"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2024,"sourceUrl":"https://dblp.org/rec/conf/eccv/MiaoHBQLGL24","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iccv/HuangMYML25","url":"https://dblp.org/rec/conf/iccv/HuangMYML25","title":"Vivid4D: Improving 4D Reconstruction from Monocular Video by Video Inpainting.","year":2025,"types":["Inproceedings"],"venue":"ICCV","doi":"https://doi.org/10.1109/ICCV51701.2025.01170","eventYear":2025,"numberOfCreators":5,"category":"conference","sources":["https://dblp.org/rec/conf/iccv/HuangMYML25","https://doi.org/10.1109/ICCV51701.2025.01170"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/HuangMYML25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/nips/LuTJZYOHYSL25","url":"https://dblp.org/rec/conf/nips/LuTJZYOHYSL25","title":"Orientation Matters: Making 3D Generative Models Orientation-Aligned.","year":2025,"types":["Inproceedings"],"venue":"NeurIPS","doi":null,"eventYear":2025,"numberOfCreators":10,"category":"conference","sources":["https://dblp.org/rec/conf/nips/LuTJZYOHYSL25"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/nips/LuTJZYOHYSL25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/rcar/HuangL25","url":"https://dblp.org/rec/conf/rcar/HuangL25","title":"Seed3D: Semantic-Aware 3D Scene Editing with Diffusion Priors.","year":2025,"types":["Inproceedings"],"venue":"RCAR","doi":"https://doi.org/10.1109/RCAR65431.2025.11139764","eventYear":2025,"numberOfCreators":2,"category":"conference","sources":["https://dblp.org/rec/conf/rcar/HuangL25","https://doi.org/10.1109/RCAR65431.2025.11139764"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/rcar/HuangL25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/vcip/LiuZLLY25","url":"https://dblp.org/rec/conf/vcip/LiuZLLY25","title":"Eliminating Geometric Representation Redundancy for 3D Gaussian Splat Coding.","year":2025,"types":["Inproceedings"],"venue":"VCIP","doi":"https://doi.org/10.1109/VCIP67698.2025.11396895","eventYear":2025,"numberOfCreators":5,"category":"conference","sources":["https://dblp.org/rec/conf/vcip/LiuZLLY25","https://doi.org/10.1109/VCIP67698.2025.11396895"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/vcip/LiuZLLY25","documentUrl":null,"type":"Inproceedings"},{"key":"journals/jzusc/ZhuGYL25","url":"https://dblp.org/rec/journals/jzusc/ZhuGYL25","title":"Neural mesh refinement.","year":2025,"types":["Article"],"venue":"Frontiers Inf. Technol. Electron. Eng.","doi":"https://doi.org/10.1631/FITEE.2400344","numberOfCreators":4,"category":"journal","sources":["https://dblp.org/rec/journals/jzusc/ZhuGYL25","https://doi.org/10.1631/FITEE.2400344"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/jzusc/ZhuGYL25","documentUrl":null,"type":"Article"},{"key":"journals/pami/FuZCLZGL25","url":"https://dblp.org/rec/journals/pami/FuZCLZGL25","title":"PanopticNeRF-360: Panoramic 3D-to-2D Label Transfer in Urban Scenes.","year":2025,"types":["Article"],"venue":"IEEE Trans. Pattern Anal. Mach. Intell.","doi":"https://doi.org/10.1109/TPAMI.2025.3581608","numberOfCreators":7,"category":"journal","sources":["https://dblp.org/rec/journals/pami/FuZCLZGL25","https://doi.org/10.1109/TPAMI.2025.3581608"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/pami/FuZCLZGL25","documentUrl":null,"type":"Article"},{"key":"journals/ral/WuLJYWXL25","url":"https://dblp.org/rec/journals/ral/WuLJYWXL25","title":"DORec: Decomposed Object Reconstruction and Segmentation Utilizing 2D Self-Supervised Features.","year":2025,"types":["Article"],"venue":"IEEE Robotics Autom. Lett.","doi":"https://doi.org/10.1109/LRA.2024.3511425","numberOfCreators":7,"category":"journal","sources":["https://dblp.org/rec/journals/ral/WuLJYWXL25","https://doi.org/10.1109/LRA.2024.3511425"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/ral/WuLJYWXL25","documentUrl":null,"type":"Article"}],"preprints":[{"key":"journals/corr/abs-2501-01119","url":"https://dblp.org/rec/journals/corr/abs-2501-01119","title":"Leverage Cross-Attention for End-to-End Open-Vocabulary Panoptic Reconstruction.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2501.01119","numberOfCreators":7,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2501-01119","https://doi.org/10.48550/ARXIV.2501.01119"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2501-01119","documentUrl":null,"type":"Informal","arxivId":"2501.01119","arxivUrl":"https://arxiv.org/abs/2501.01119"},{"key":"journals/corr/abs-2503-20168","url":"https://dblp.org/rec/journals/corr/abs-2503-20168","title":"EVolSplat: Efficient Volume-based Gaussian Splatting for Urban View Synthesis.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2503.20168","numberOfCreators":9,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2503-20168","https://doi.org/10.48550/ARXIV.2503.20168"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-20168","documentUrl":null,"type":"Informal","arxivId":"2503.20168","arxivUrl":"https://arxiv.org/abs/2503.20168"},{"key":"journals/corr/abs-2504-00763","url":"https://dblp.org/rec/journals/corr/abs-2504-00763","title":"UnIRe: Unsupervised Instance Decomposition for Dynamic Urban Scene Reconstruction.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2504.00763","numberOfCreators":4,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2504-00763","https://doi.org/10.48550/ARXIV.2504.00763"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2504-00763","documentUrl":null,"type":"Informal","arxivId":"2504.00763","arxivUrl":"https://arxiv.org/abs/2504.00763"},{"key":"journals/corr/abs-2504-11092","url":"https://dblp.org/rec/journals/corr/abs-2504-11092","title":"Vivid4D: Improving 4D Reconstruction from Monocular Video by Video Inpainting.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2504.11092","numberOfCreators":5,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2504-11092","https://doi.org/10.48550/ARXIV.2504.11092"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2504-11092","documentUrl":null,"type":"Informal","arxivId":"2504.11092","arxivUrl":"https://arxiv.org/abs/2504.11092"},{"key":"journals/corr/abs-2505-07539","url":"https://dblp.org/rec/journals/corr/abs-2505-07539","title":"GIFStream: 4D Gaussian-based Immersive Video with Feature Stream.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2505.07539","numberOfCreators":6,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2505-07539","https://doi.org/10.48550/ARXIV.2505.07539"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-07539","documentUrl":null,"type":"Informal","arxivId":"2505.07539","arxivUrl":"https://arxiv.org/abs/2505.07539"},{"key":"journals/corr/abs-2506-01822","url":"https://dblp.org/rec/journals/corr/abs-2506-01822","title":"GSCodec Studio: A Modular Framework for Gaussian Splat Compression.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2506.01822","numberOfCreators":6,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2506-01822","https://doi.org/10.48550/ARXIV.2506.01822"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-01822","documentUrl":null,"type":"Informal","arxivId":"2506.01822","arxivUrl":"https://arxiv.org/abs/2506.01822"},{"key":"journals/corr/abs-2506-08640","url":"https://dblp.org/rec/journals/corr/abs-2506-08640","title":"Orientation Matters: Making 3D Generative Models Orientation-Aligned.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2506.08640","numberOfCreators":10,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2506-08640","https://doi.org/10.48550/ARXIV.2506.08640"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-08640","documentUrl":null,"type":"Informal","arxivId":"2506.08640","arxivUrl":"https://arxiv.org/abs/2506.08640"},{"key":"journals/corr/abs-2506-19117","url":"https://dblp.org/rec/journals/corr/abs-2506-19117","title":"PrITTI: Primitive-based Generation of Controllable and Editable 3D Semantic Scenes.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2506.19117","numberOfCreators":5,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2506-19117","https://doi.org/10.48550/ARXIV.2506.19117"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-19117","documentUrl":null,"type":"Informal","arxivId":"2506.19117","arxivUrl":"https://arxiv.org/abs/2506.19117"},{"key":"journals/corr/abs-2507-11540","url":"https://dblp.org/rec/journals/corr/abs-2507-11540","title":"Towards Depth Foundation Model: Recent Trends in Vision-Based Depth Estimation.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2507.11540","numberOfCreators":16,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2507-11540","https://doi.org/10.48550/ARXIV.2507.11540"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2507-11540","documentUrl":null,"type":"Informal","arxivId":"2507.11540","arxivUrl":"https://arxiv.org/abs/2507.11540"},{"key":"journals/corr/abs-2507-17520","url":"https://dblp.org/rec/journals/corr/abs-2507-17520","title":"InstructVLA: Vision-Language-Action Instruction Tuning from Understanding to Manipulation.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2507.17520","numberOfCreators":10,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2507-17520","https://doi.org/10.48550/ARXIV.2507.17520"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2507-17520","documentUrl":null,"type":"Informal","arxivId":"2507.17520","arxivUrl":"https://arxiv.org/abs/2507.17520"}],"excludedFormal":[],"otherRecords":[],"matchedName":"Yiyi Liao","databaseLabel":"Yiyi Liao","databaseMetadata":{"type":["https://dblp.org/rdf/schema#Creator","https://dblp.org/rdf/schema#Person"],"label":["Yiyi Liao"],"orcid":["https://orcid.org/0000-0001-6662-3022"]},"rawFormalRecordCount2025":15,"signatureAudit":{"completedAt":"2026-10-19","frozen":true,"scope":"对 B 组 39 个数值档案的全部 1074 条原始 2025 正式记录扫描 DBLP author-signature ORCID 和机构；复用既有 59 条 Crossref 核验，补查 6 条新触发记录。重点核查不同 ORCID，以及只有预期机构之外机构的条目。本轮不扩展为所有作者逐篇全文审计。","formalRecordCoverage":15,"orcidCounts":{"https://orcid.org/0000-0001-6662-3022":3},"institutionCounts":{"Zhejiang University (ZJU)":14,"Zhejiang University of Science and Technology (ZUST)":1},"caveat":"机构名称可能由 DBLP 自动映射而失真；多 ORCID 也不自动等于异人。只有有原始资料支撑的错归才作确认排除，未解决分支则暂停总数。"},"labName":"X-Dimensional Representations Lab (X-D Lab)","labUrl":"https://yiyiliao.github.io/xdlab","labEvidence":"本人主页明确写 leading the X-Dimensional Representations Lab (X-D Lab)，组名直接链接到 xdlab 页面。","labSourceUrl":"https://yiyiliao.github.io/","sourceWarning":false,"excludedOther":[],"excludedHomonyms":[],"unassignedCandidates":[],"knownPreprintMinimum2025":null,"excludedMisattributed":[],"displayNotes":"身份已与原名单机构及公开资料核对确认。2025 年正式记录 15 条（会议 12、期刊 3），所有作者位置均计入，不表示主导或贡献份额；预印本 10 条单列，不加总。","labDisplayNotes":"个人主页写明其领导 X-Dimensional Representations Lab（X-D Lab），并直接链接，据此归组。"},{"index":61,"name":"Guiliang Liu","nameZh":"刘桂良","role":"Assistant Professor","affiliation":"The Chinese University of Hong Kong, Shenzhen","affiliationZh":"香港中文大学（深圳）","source":"DBLP RDF via official SPARQL; primary-source identity checks","sourceUrl":"https://sparql.dblp.org/","profileUrl":"https://dblp.org/pid/220/5411.html","identifier":"220/5411","retrievedAt":"2026-10-19","count2025":11,"conference2025":9,"journal2025":2,"preprint2025":9,"status":"confirmed","notes":"","identityEvidence":[{"url":"https://dblp.org/pid/220/5411.html","evidence":"DBLP RDF 类型为 Person，消歧后名字为 Guiliang Liu。此档案未提供可用机构元数据，以下以本人/机构/出版商来源补证。"},{"url":"https://guiliang.me/index.html","evidence":"个人主页为香港中文大学（深圳）Guiliang Liu。"},{"url":"https://guiliang.me/contents/publications.html","evidence":"此本人或机构页面的正文与所选档案中 17 条 2025 记录标题匹配，其中 11 条为当前计入的正式记录（忽略空格、标点、大小写）。","matchedPaperKeys":["conf/cvpr/RuanL0ZLLJ25","conf/eccv/QiaoQQL24","conf/iclr/XuYZL25","conf/iclr/YueWGLPL25","conf/iclr/ZhaoXYL25","conf/icml/LiuDZ0CCXTJ25","conf/icml/YueLL25","conf/iros/WangZYLJ25","conf/nips/MiaoXZCL25","journals/corr/abs-2501-14208","journals/corr/abs-2503-00923","journals/corr/abs-2503-06227","journals/corr/abs-2503-11269","journals/corr/abs-2505-24266","journals/corr/abs-2510-03081","journals/tmc/ZhangCZLWW25","journals/tmlr/LiuXLGSP25"],"matchedFormalPaperKeys":["conf/cvpr/RuanL0ZLLJ25","conf/eccv/QiaoQQL24","conf/iclr/XuYZL25","conf/iclr/YueWGLPL25","conf/iclr/ZhaoXYL25","conf/icml/LiuDZ0CCXTJ25","conf/icml/YueLL25","conf/iros/WangZYLJ25","conf/nips/MiaoXZCL25","journals/tmc/ZhangCZLWW25","journals/tmlr/LiuXLGSP25"]}],"papers":[{"key":"conf/cvpr/RuanL0ZLLJ25","url":"https://dblp.org/rec/conf/cvpr/RuanL0ZLLJ25","title":"Prof. Robot: Differentiable Robot Rendering Without Static and Self-Collisions.","year":2025,"types":["Inproceedings"],"venue":"CVPR","doi":"https://doi.org/10.1109/CVPR52734.2025.02101","eventYear":2025,"numberOfCreators":7,"category":"conference","sources":["https://dblp.org/rec/conf/cvpr/RuanL0ZLLJ25","https://doi.org/10.1109/CVPR52734.2025.02101"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/RuanL0ZLLJ25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/eccv/QiaoQQL24","url":"https://dblp.org/rec/conf/eccv/QiaoQQL24","title":"Modelling Competitive Behaviors in Autonomous Driving Under Generative World Model.","year":2025,"types":["Inproceedings"],"venue":"ECCV (35)","doi":"https://doi.org/10.1007/978-3-031-72761-0_2","eventYear":2024,"numberOfCreators":4,"category":"conference","sources":["https://dblp.org/rec/conf/eccv/QiaoQQL24","https://doi.org/10.1007/978-3-031-72761-0_2"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2024,"sourceUrl":"https://dblp.org/rec/conf/eccv/QiaoQQL24","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iclr/XuYZL25","url":"https://dblp.org/rec/conf/iclr/XuYZL25","title":"A Distributional Approach to Uncertainty-Aware Preference Alignment Using Offline Demonstrations.","year":2025,"types":["Inproceedings"],"venue":"ICLR","doi":null,"eventYear":2025,"numberOfCreators":4,"category":"conference","sources":["https://dblp.org/rec/conf/iclr/XuYZL25"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iclr/XuYZL25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iclr/YueWGLPL25","url":"https://dblp.org/rec/conf/iclr/YueWGLPL25","title":"Understanding Constraint Inference in Safety-Critical Inverse Reinforcement Learning.","year":2025,"types":["Inproceedings"],"venue":"ICLR","doi":null,"eventYear":2025,"numberOfCreators":6,"category":"conference","sources":["https://dblp.org/rec/conf/iclr/YueWGLPL25"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iclr/YueWGLPL25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iclr/ZhaoXYL25","url":"https://dblp.org/rec/conf/iclr/ZhaoXYL25","title":"Toward Exploratory Inverse Constraint Inference with Generative Diffusion Verifiers.","year":2025,"types":["Inproceedings"],"venue":"ICLR","doi":null,"eventYear":2025,"numberOfCreators":4,"category":"conference","sources":["https://dblp.org/rec/conf/iclr/ZhaoXYL25"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iclr/ZhaoXYL25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/icml/LiuDZ0CCXTJ25","url":"https://dblp.org/rec/conf/icml/LiuDZ0CCXTJ25","title":"DexScale: Automating Data Scaling for Sim2Real Generalizable Robot Control.","year":2025,"types":["Inproceedings"],"venue":"ICML","doi":null,"eventYear":2025,"numberOfCreators":9,"category":"conference","sources":["https://dblp.org/rec/conf/icml/LiuDZ0CCXTJ25"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/icml/LiuDZ0CCXTJ25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/icml/YueLL25","url":"https://dblp.org/rec/conf/icml/YueLL25","title":"Provably Efficient Exploration in Inverse Constrained Reinforcement Learning.","year":2025,"types":["Inproceedings"],"venue":"ICML","doi":null,"eventYear":2025,"numberOfCreators":3,"category":"conference","sources":["https://dblp.org/rec/conf/icml/YueLL25"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/icml/YueLL25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iros/WangZYLJ25","url":"https://dblp.org/rec/conf/iros/WangZYLJ25","title":"GAT-Grasp: Gesture-Driven Affordance Transfer for Task-Aware Robotic Grasping.","year":2025,"types":["Inproceedings"],"venue":"IROS","doi":"https://doi.org/10.1109/IROS60139.2025.11246111","eventYear":2025,"numberOfCreators":5,"category":"conference","sources":["https://dblp.org/rec/conf/iros/WangZYLJ25","https://doi.org/10.1109/IROS60139.2025.11246111"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iros/WangZYLJ25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/nips/MiaoXZCL25","url":"https://dblp.org/rec/conf/nips/MiaoXZCL25","title":"Uncertainty-aware Preference Alignment for Diffusion Policies.","year":2025,"types":["Inproceedings"],"venue":"NeurIPS","doi":null,"eventYear":2025,"numberOfCreators":5,"category":"conference","sources":["https://dblp.org/rec/conf/nips/MiaoXZCL25"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/nips/MiaoXZCL25","documentUrl":null,"type":"Inproceedings"},{"key":"journals/tmc/ZhangCZLWW25","url":"https://dblp.org/rec/journals/tmc/ZhangCZLWW25","title":"Unimodal Training-Multimodal Prediction: Cross-Modal Federated Learning With Hierarchical Aggregation.","year":2025,"types":["Article"],"venue":"IEEE Trans. Mob. Comput.","doi":"https://doi.org/10.1109/TMC.2025.3567535","numberOfCreators":6,"category":"journal","sources":["https://dblp.org/rec/journals/tmc/ZhangCZLWW25","https://doi.org/10.1109/TMC.2025.3567535"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/tmc/ZhangCZLWW25","documentUrl":null,"type":"Article"},{"key":"journals/tmlr/LiuXLGSP25","url":"https://dblp.org/rec/journals/tmlr/LiuXLGSP25","title":"A Comprehensive Survey on Inverse Constrained Reinforcement Learning: Definitions, Progress and Challenges.","year":2025,"types":["Article"],"venue":"Trans. Mach. Learn. Res.","doi":null,"numberOfCreators":6,"category":"journal","sources":["https://dblp.org/rec/journals/tmlr/LiuXLGSP25"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/tmlr/LiuXLGSP25","documentUrl":null,"type":"Article"}],"preprints":[{"key":"journals/corr/abs-2501-14208","url":"https://dblp.org/rec/journals/corr/abs-2501-14208","title":"You Only Teach Once: Learn One-Shot Bimanual Robotic Manipulation from Video Demonstrations.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2501.14208","numberOfCreators":6,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2501-14208","https://doi.org/10.48550/ARXIV.2501.14208"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2501-14208","documentUrl":null,"type":"Informal","arxivId":"2501.14208","arxivUrl":"https://arxiv.org/abs/2501.14208"},{"key":"journals/corr/abs-2503-00923","url":"https://dblp.org/rec/journals/corr/abs-2503-00923","title":"HWC-Loco: A Hierarchical Whole-Body Control Approach to Robust Humanoid Locomotion.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2503.00923","numberOfCreators":6,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2503-00923","https://doi.org/10.48550/ARXIV.2503.00923"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-00923","documentUrl":null,"type":"Informal","arxivId":"2503.00923","arxivUrl":"https://arxiv.org/abs/2503.00923"},{"key":"journals/corr/abs-2503-06227","url":"https://dblp.org/rec/journals/corr/abs-2503-06227","title":"GAT-Grasp: Gesture-Driven Affordance Transfer for Task-Aware Robotic Grasping.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2503.06227","numberOfCreators":5,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2503-06227","https://doi.org/10.48550/ARXIV.2503.06227"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-06227","documentUrl":null,"type":"Informal","arxivId":"2503.06227","arxivUrl":"https://arxiv.org/abs/2503.06227"},{"key":"journals/corr/abs-2503-11269","url":"https://dblp.org/rec/journals/corr/abs-2503-11269","title":"Prof. Robot: Differentiable Robot Rendering Without Static and Self-Collisions.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2503.11269","numberOfCreators":7,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2503-11269","https://doi.org/10.48550/ARXIV.2503.11269"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-11269","documentUrl":null,"type":"Informal","arxivId":"2503.11269","arxivUrl":"https://arxiv.org/abs/2503.11269"},{"key":"journals/corr/abs-2505-11175","url":"https://dblp.org/rec/journals/corr/abs-2505-11175","title":"Real-Time Verification of Embodied Reasoning for Generative Skill Acquisition.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2505.11175","numberOfCreators":7,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2505-11175","https://doi.org/10.48550/ARXIV.2505.11175"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-11175","documentUrl":null,"type":"Informal","arxivId":"2505.11175","arxivUrl":"https://arxiv.org/abs/2505.11175"},{"key":"journals/corr/abs-2505-24266","url":"https://dblp.org/rec/journals/corr/abs-2505-24266","title":"SignBot: Learning Human-to-Humanoid Sign Language Interaction.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2505.24266","numberOfCreators":6,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2505-24266","https://doi.org/10.48550/ARXIV.2505.24266"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-24266","documentUrl":null,"type":"Informal","arxivId":"2505.24266","arxivUrl":"https://arxiv.org/abs/2505.24266"},{"key":"journals/corr/abs-2510-03081","url":"https://dblp.org/rec/journals/corr/abs-2510-03081","title":"Embracing Evolution: A Call for Body-Control Co-Design in Embodied Humanoid Robot.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2510.03081","numberOfCreators":4,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2510-03081","https://doi.org/10.48550/ARXIV.2510.03081"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-03081","documentUrl":null,"type":"Informal","arxivId":"2510.03081","arxivUrl":"https://arxiv.org/abs/2510.03081"},{"key":"journals/corr/abs-2510-22336","url":"https://dblp.org/rec/journals/corr/abs-2510-22336","title":"Toward Humanoid Brain-Body Co-design: Joint Optimization of Control and Morphology for Fall Recovery.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2510.22336","numberOfCreators":4,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2510-22336","https://doi.org/10.48550/ARXIV.2510.22336"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-22336","documentUrl":null,"type":"Informal","arxivId":"2510.22336","arxivUrl":"https://arxiv.org/abs/2510.22336"},{"key":"journals/corr/abs-2512-01022","url":"https://dblp.org/rec/journals/corr/abs-2512-01022","title":"CycleManip: Enabling Cyclic Task Manipulation via Effective Historical Perception and Understanding.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2512.01022","numberOfCreators":7,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2512-01022","https://doi.org/10.48550/ARXIV.2512.01022"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-01022","documentUrl":null,"type":"Informal","arxivId":"2512.01022","arxivUrl":"https://arxiv.org/abs/2512.01022"}],"excludedFormal":[],"otherRecords":[],"matchedName":"Guiliang Liu","databaseLabel":"Guiliang Liu","databaseMetadata":{"type":["https://dblp.org/rdf/schema#Person","https://dblp.org/rdf/schema#Creator"],"label":["Guiliang Liu"],"orcid":["https://orcid.org/0000-0001-7464-523X"]},"rawFormalRecordCount2025":11,"signatureAudit":{"completedAt":"2026-10-19","frozen":true,"scope":"对 B 组 39 个数值档案的全部 1074 条原始 2025 正式记录扫描 DBLP author-signature ORCID 和机构；复用既有 59 条 Crossref 核验，补查 6 条新触发记录。重点核查不同 ORCID，以及只有预期机构之外机构的条目。本轮不扩展为所有作者逐篇全文审计。","formalRecordCoverage":11,"orcidCounts":{"https://orcid.org/0000-0001-7464-523X":4},"institutionCounts":{"Chinese University of Hong Kong (CUHK)":2,"The Chinese University of Hong Kong, Shenzhen (CUHK-SZ)":4},"caveat":"机构名称可能由 DBLP 自动映射而失真；多 ORCID 也不自动等于异人。只有有原始资料支撑的错归才作确认排除，未解决分支则暂停总数。"},"labName":"Embodied Decision-Making (EDeM) Lab","labUrl":"https://guiliang.me/contents/group.html","labEvidence":"本人主页将当前研究介绍链接至 our Embodied Decision-Making (EdeM) Lab，导航也列 EDeM-Lab。","labSourceUrl":"https://guiliang.me/index.html","sourceWarning":false,"excludedOther":[],"excludedHomonyms":[],"unassignedCandidates":[],"knownPreprintMinimum2025":null,"excludedMisattributed":[],"displayNotes":"身份已与原名单机构及公开资料核对确认。2025 年正式记录 11 条（会议 9、期刊 2），所有作者位置均计入；预印本 9 条单列，不加总。","labDisplayNotes":"个人主页的研究介绍链接至 Embodied Decision-Making（EDeM）Lab，导航栏也列出该组，据此归组。"},{"index":62,"name":"Ligang Liu","nameZh":"刘利刚","role":"Professor","affiliation":"University of Science and Technology of China","affiliationZh":"中国科学技术大学","source":"DBLP RDF via official SPARQL; primary-source identity checks","sourceUrl":"https://sparql.dblp.org/","profileUrl":"https://dblp.org/pid/07/1830-1.html","identifier":"07/1830-1","retrievedAt":"2026-10-19","count2025":29,"conference2025":12,"journal2025":17,"preprint2025":16,"status":"confirmed","notes":"","identityEvidence":[{"url":"https://dblp.org/pid/07/1830-1.html","evidence":"DBLP RDF 类型为 Person，消歧后名字为 Ligang Liu 0001。机构元数据含：University of Science and Technology of China (USTC), School of Mathematical Sciences, Hefei, Anhui, China"}],"papers":[{"key":"conf/aaai/TangDPWLLT25","url":"https://dblp.org/rec/conf/aaai/TangDPWLLT25","title":"Imperceptible 3D Point Cloud Attacks on Lattice-based Barycentric Coordinates.","year":2025,"types":["Inproceedings"],"venue":"AAAI","doi":"https://doi.org/10.1609/AAAI.V39I19.34294","eventYear":2025,"numberOfCreators":7,"category":"conference","sources":["https://dblp.org/rec/conf/aaai/TangDPWLLT25","https://doi.org/10.1609/AAAI.V39I19.34294"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/aaai/TangDPWLLT25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/cvpr/GuoXL0LH25","url":"https://dblp.org/rec/conf/cvpr/GuoXL0LH25","title":"ArticulatedGS: Self-supervised Digital Twin Modeling of Articulated Objects using 3D Gaussian Splatting.","year":2025,"types":["Inproceedings"],"venue":"CVPR","doi":"https://doi.org/10.1109/CVPR52734.2025.02528","eventYear":2025,"numberOfCreators":6,"category":"conference","sources":["https://dblp.org/rec/conf/cvpr/GuoXL0LH25","https://doi.org/10.1109/CVPR52734.2025.02528"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/GuoXL0LH25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/cvpr/Lin0FWL0LY25","url":"https://dblp.org/rec/conf/cvpr/Lin0FWL0LY25","title":"HybridGS: Decoupling Transients and Statics with 2D and 3D Gaussian Splatting.","year":2025,"types":["Inproceedings"],"venue":"CVPR","doi":"https://doi.org/10.1109/CVPR52734.2025.00082","eventYear":2025,"numberOfCreators":8,"category":"conference","sources":["https://dblp.org/rec/conf/cvpr/Lin0FWL0LY25","https://doi.org/10.1109/CVPR52734.2025.00082"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/Lin0FWL0LY25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/eccv/LinGWFCLY24","url":"https://dblp.org/rec/conf/eccv/LinGWFCLY24","title":"Learning Neural Volumetric Pose Features for Camera Localization.","year":2025,"types":["Inproceedings"],"venue":"ECCV (45)","doi":"https://doi.org/10.1007/978-3-031-72995-9_12","eventYear":2024,"numberOfCreators":7,"category":"conference","sources":["https://dblp.org/rec/conf/eccv/LinGWFCLY24","https://doi.org/10.1007/978-3-031-72995-9_12"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2024,"sourceUrl":"https://dblp.org/rec/conf/eccv/LinGWFCLY24","documentUrl":null,"type":"Inproceedings"},{"key":"conf/eccv/TangHPLWMLT24","url":"https://dblp.org/rec/conf/eccv/TangHPLWMLT24","title":"FLAT: Flux-Aware Imperceptible Adversarial Attacks on 3D Point Clouds.","year":2025,"types":["Inproceedings"],"venue":"ECCV (6)","doi":"https://doi.org/10.1007/978-3-031-72658-3_12","eventYear":2024,"numberOfCreators":8,"category":"conference","sources":["https://dblp.org/rec/conf/eccv/TangHPLWMLT24","https://doi.org/10.1007/978-3-031-72658-3_12"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2024,"sourceUrl":"https://dblp.org/rec/conf/eccv/TangHPLWMLT24","documentUrl":null,"type":"Inproceedings"},{"key":"conf/mm/QinLHWFL25","url":"https://dblp.org/rec/conf/mm/QinLHWFL25","title":"Drawing2CAD: Sequence-to-Sequence Learning for CAD Generation from Vector Drawings.","year":2025,"types":["Inproceedings"],"venue":"ACM Multimedia","doi":"https://doi.org/10.1145/3746027.3755782","eventYear":2025,"numberOfCreators":6,"category":"conference","sources":["https://dblp.org/rec/conf/mm/QinLHWFL25","https://doi.org/10.1145/3746027.3755782"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/mm/QinLHWFL25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/rt/LiLWSLW25","url":"https://dblp.org/rec/conf/rt/LiLWSLW25","title":"Bidirectional Plateau-Border Scattering Distribution Function for Realistic and Efficient Foam Rendering.","year":2025,"types":["Inproceedings"],"venue":"EGSR (Symposium Track)","doi":"https://doi.org/10.2312/SR.20251195","eventYear":2025,"numberOfCreators":6,"category":"conference","sources":["https://dblp.org/rec/conf/rt/LiLWSLW25","https://doi.org/10.2312/SR.20251195"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/rt/LiLWSLW25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/rt/ZhuangLL25","url":"https://dblp.org/rec/conf/rt/ZhuangLL25","title":"Differentiable Block Compression for Neural Texture.","year":2025,"types":["Inproceedings"],"venue":"EGSR (Symposium Track)","doi":"https://doi.org/10.2312/SR.20251199","eventYear":2025,"numberOfCreators":3,"category":"conference","sources":["https://dblp.org/rec/conf/rt/ZhuangLL25","https://doi.org/10.2312/SR.20251199"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/rt/ZhuangLL25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/siggraph/00010LSWX0025","url":"https://dblp.org/rec/conf/siggraph/00010LSWX0025","title":"Appearance-aware Multi-view SVBRDF Reconstruction via Deep Reinforcement Learning.","year":2025,"types":["Inproceedings"],"venue":"SIGGRAPH (Conference Paper Track)","doi":"https://doi.org/10.1145/3721238.3730718","eventYear":2025,"numberOfCreators":8,"category":"conference","sources":["https://dblp.org/rec/conf/siggraph/00010LSWX0025","https://doi.org/10.1145/3721238.3730718"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/siggraph/00010LSWX0025","documentUrl":null,"type":"Inproceedings"},{"key":"conf/siggraph/ChengF0025","url":"https://dblp.org/rec/conf/siggraph/ChengF0025","title":"Divide-and-Conquer Embedding.","year":2025,"types":["Inproceedings"],"venue":"SIGGRAPH (Conference Paper Track)","doi":"https://doi.org/10.1145/3721238.3730693","eventYear":2025,"numberOfCreators":4,"category":"conference","sources":["https://dblp.org/rec/conf/siggraph/ChengF0025","https://doi.org/10.1145/3721238.3730693"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/siggraph/ChengF0025","documentUrl":null,"type":"Inproceedings"},{"key":"conf/siggraph/LiX0SZ0H25","url":"https://dblp.org/rec/conf/siggraph/LiX0SZ0H25","title":"MASH: Masked Anchored SpHerical Distances for 3D Shape Representation and Generation.","year":2025,"types":["Inproceedings"],"venue":"SIGGRAPH (Conference Paper Track)","doi":"https://doi.org/10.1145/3721238.3730610","eventYear":2025,"numberOfCreators":7,"category":"conference","sources":["https://dblp.org/rec/conf/siggraph/LiX0SZ0H25","https://doi.org/10.1145/3721238.3730610"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/siggraph/LiX0SZ0H25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/siggrapha/00010025","url":"https://dblp.org/rec/conf/siggrapha/00010025","title":"Closed-form Cauchy Coordinates and Their Derivatives for 2D High-order Cages.","year":2025,"types":["Inproceedings"],"venue":"SIGGRAPH Asia","doi":"https://doi.org/10.1145/3757377.3763886","eventYear":2025,"numberOfCreators":3,"category":"conference","sources":["https://dblp.org/rec/conf/siggrapha/00010025","https://doi.org/10.1145/3757377.3763886"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/siggrapha/00010025","documentUrl":null,"type":"Inproceedings"},{"key":"journals/cagd/ZhuLXCL25","url":"https://dblp.org/rec/journals/cagd/ZhuLXCL25","title":"Projection-driven grid-BSP tree for real-time trimming on GPU.","year":2025,"types":["Article"],"venue":"Comput. Aided Geom. Des.","doi":"https://doi.org/10.1016/J.CAGD.2025.102451","numberOfCreators":5,"category":"journal","sources":["https://dblp.org/rec/journals/cagd/ZhuLXCL25","https://doi.org/10.1016/J.CAGD.2025.102451"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/cagd/ZhuLXCL25","documentUrl":null,"type":"Article"},{"key":"journals/cg/LiuLWCZZLXF25","url":"https://dblp.org/rec/journals/cg/LiuLWCZZLXF25","title":"Computational multi-layered wood carving art.","year":2025,"types":["Article"],"venue":"Comput. Graph.","doi":"https://doi.org/10.1016/J.CAG.2025.104337","numberOfCreators":9,"category":"journal","sources":["https://dblp.org/rec/journals/cg/LiuLWCZZLXF25","https://doi.org/10.1016/J.CAG.2025.104337"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/cg/LiuLWCZZLXF25","documentUrl":null,"type":"Article"},{"key":"journals/cg/ZhangLWZLWLF25","url":"https://dblp.org/rec/journals/cg/ZhangLWZLWLF25","title":"Carving shapes with ruled surfaces for rough machining.","year":2025,"types":["Article"],"venue":"Comput. Graph.","doi":"https://doi.org/10.1016/J.CAG.2025.104386","numberOfCreators":8,"category":"journal","sources":["https://dblp.org/rec/journals/cg/ZhangLWZLWLF25","https://doi.org/10.1016/J.CAG.2025.104386"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/cg/ZhangLWZLWLF25","documentUrl":null,"type":"Article"},{"key":"journals/cgf/ChengLF25","url":"https://dblp.org/rec/journals/cgf/ChengLF25","title":"Eigenvalue Blending for Projected Newton.","year":2025,"types":["Article"],"venue":"Comput. Graph. Forum","doi":"https://doi.org/10.1111/CGF.70027","numberOfCreators":3,"category":"journal","sources":["https://dblp.org/rec/journals/cgf/ChengLF25","https://doi.org/10.1111/CGF.70027"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/cgf/ChengLF25","documentUrl":null,"type":"Article"},{"key":"journals/cgf/ShiCWGFCLY25","url":"https://dblp.org/rec/journals/cgf/ShiCWGFCLY25","title":"NoPe-NeRF++: Local-to-Global Optimization of NeRF with No Pose Prior.","year":2025,"types":["Article"],"venue":"Comput. Graph. Forum","doi":"https://doi.org/10.1111/CGF.70012","numberOfCreators":8,"category":"journal","sources":["https://dblp.org/rec/journals/cgf/ShiCWGFCLY25","https://doi.org/10.1111/CGF.70012"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/cgf/ShiCWGFCLY25","documentUrl":null,"type":"Article"},{"key":"journals/pami/ZhangNZLLC25","url":"https://dblp.org/rec/journals/pami/ZhangNZLLC25","title":"PointNorm-Net: Self-Supervised Normal Prediction of 3D Point Clouds via Multi-Modal Distribution Estimation.","year":2025,"types":["Article"],"venue":"IEEE Trans. Pattern Anal. Mach. Intell.","doi":"https://doi.org/10.1109/TPAMI.2025.3562051","numberOfCreators":6,"category":"journal","sources":["https://dblp.org/rec/journals/pami/ZhangNZLLC25","https://doi.org/10.1109/TPAMI.2025.3562051"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/pami/ZhangNZLLC25","documentUrl":null,"type":"Article"},{"key":"journals/tmm/ShuLXL25","url":"https://dblp.org/rec/journals/tmm/ShuLXL25","title":"3D Shape Segmentation With Potential Consistency Mining and Enhancement.","year":2025,"types":["Article"],"venue":"IEEE Trans. Multim.","doi":"https://doi.org/10.1109/TMM.2024.3521674","numberOfCreators":4,"category":"journal","sources":["https://dblp.org/rec/journals/tmm/ShuLXL25","https://doi.org/10.1109/TMM.2024.3521674"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/tmm/ShuLXL25","documentUrl":null,"type":"Article"},{"key":"journals/tog/LiuDLF25","url":"https://dblp.org/rec/journals/tog/LiuDLF25","title":"Polynomial 2D Biharmonic Coordinates for High-order Cages.","year":2025,"types":["Article"],"venue":"ACM Trans. Graph.","doi":"https://doi.org/10.1145/3730887","numberOfCreators":4,"category":"journal","sources":["https://dblp.org/rec/journals/tog/LiuDLF25","https://doi.org/10.1145/3730887"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/tog/LiuDLF25","documentUrl":null,"type":"Article"},{"key":"journals/tog/LiuLF25","url":"https://dblp.org/rec/journals/tog/LiuLF25","title":"Closed-form Generalized Winding Numbers of Rational Parametric Curves for Robust Containment Queries.","year":2025,"types":["Article"],"venue":"ACM Trans. Graph.","doi":"https://doi.org/10.1145/3730886","numberOfCreators":3,"category":"journal","sources":["https://dblp.org/rec/journals/tog/LiuLF25","https://doi.org/10.1145/3730886"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/tog/LiuLF25","documentUrl":null,"type":"Article"},{"key":"journals/tog/ZengLCL25","url":"https://dblp.org/rec/journals/tog/ZengLCL25","title":"WATER: Watertight Tessellation for Real-Time Pixel-Accurate Rendering of Large-Scale Surfaces.","year":2025,"types":["Article"],"venue":"ACM Trans. Graph.","doi":"https://doi.org/10.1145/3763317","numberOfCreators":4,"category":"journal","sources":["https://dblp.org/rec/journals/tog/ZengLCL25","https://doi.org/10.1145/3763317"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/tog/ZengLCL25","documentUrl":null,"type":"Article"},{"key":"journals/tog/ZhangL25","url":"https://dblp.org/rec/journals/tog/ZhangL25","title":"Asymptotic analysis and design of linear elastic shell lattice metamaterials.","year":2025,"types":["Article"],"venue":"ACM Trans. Graph.","doi":"https://doi.org/10.1145/3730888","numberOfCreators":2,"category":"journal","sources":["https://dblp.org/rec/journals/tog/ZhangL25","https://doi.org/10.1145/3730888"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/tog/ZhangL25","documentUrl":null,"type":"Article"},{"key":"journals/tog/ZhuHXDYGLZZLZ25","url":"https://dblp.org/rec/journals/tog/ZhuHXDYGLZZLZ25","title":"Imaginarium: Vision-guided High-Quality 3D Scene Layout Generation.","year":2025,"types":["Article"],"venue":"ACM Trans. Graph.","doi":"https://doi.org/10.1145/3763353","numberOfCreators":11,"category":"journal","sources":["https://dblp.org/rec/journals/tog/ZhuHXDYGLZZLZ25","https://doi.org/10.1145/3763353"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/tog/ZhuHXDYGLZZLZ25","documentUrl":null,"type":"Article"},{"key":"journals/tvcg/ChengFLF25","url":"https://dblp.org/rec/journals/tvcg/ChengFLF25","title":"Developable Approximation via Isomap on Gauss Image.","year":2025,"types":["Article"],"venue":"IEEE Trans. Vis. Comput. Graph.","doi":"https://doi.org/10.1109/TVCG.2025.3566887","numberOfCreators":4,"category":"journal","sources":["https://dblp.org/rec/journals/tvcg/ChengFLF25","https://doi.org/10.1109/TVCG.2025.3566887"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/tvcg/ChengFLF25","documentUrl":null,"type":"Article"},{"key":"journals/tvcg/Du0G0025","url":"https://dblp.org/rec/journals/tvcg/Du0G0025","title":"Robust and Efficient Preservation of High-Order Continuous Geometric Validity.","year":2025,"types":["Article"],"venue":"IEEE Trans. Vis. Comput. Graph.","doi":"https://doi.org/10.1109/TVCG.2025.3603025","numberOfCreators":5,"category":"journal","sources":["https://dblp.org/rec/journals/tvcg/Du0G0025","https://doi.org/10.1109/TVCG.2025.3603025"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/tvcg/Du0G0025","documentUrl":null,"type":"Article"},{"key":"journals/tvcg/ShuWLXL25","url":"https://dblp.org/rec/journals/tvcg/ShuWLXL25","title":"Diff-3DCap: Shape Captioning With Diffusion Models.","year":2025,"types":["Article"],"venue":"IEEE Trans. Vis. Comput. Graph.","doi":"https://doi.org/10.1109/TVCG.2025.3564664","numberOfCreators":5,"category":"journal","sources":["https://dblp.org/rec/journals/tvcg/ShuWLXL25","https://doi.org/10.1109/TVCG.2025.3564664"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/tvcg/ShuWLXL25","documentUrl":null,"type":"Article"},{"key":"journals/tvcg/ShuYCXL25","url":"https://dblp.org/rec/journals/tvcg/ShuYCXL25","title":"A Multi-Modal Attention-Based Approach for Points of Interest Detection on 3D Shapes.","year":2025,"types":["Article"],"venue":"IEEE Trans. Vis. Comput. Graph.","doi":"https://doi.org/10.1109/TVCG.2024.3368767","numberOfCreators":5,"category":"journal","sources":["https://dblp.org/rec/journals/tvcg/ShuYCXL25","https://doi.org/10.1109/TVCG.2024.3368767"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/tvcg/ShuYCXL25","documentUrl":null,"type":"Article"},{"key":"journals/tvcg/ShuYCXL25a","url":"https://dblp.org/rec/journals/tvcg/ShuYCXL25a","title":"GaussEdit: Adaptive 3D Scene Editing With Text and Image Prompts.","year":2025,"types":["Article"],"venue":"IEEE Trans. Vis. Comput. Graph.","doi":"https://doi.org/10.1109/TVCG.2025.3556745","numberOfCreators":5,"category":"journal","sources":["https://dblp.org/rec/journals/tvcg/ShuYCXL25a","https://doi.org/10.1109/TVCG.2025.3556745"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/tvcg/ShuYCXL25a","documentUrl":null,"type":"Article"}],"preprints":[{"key":"journals/corr/abs-2501-15279","url":"https://dblp.org/rec/journals/corr/abs-2501-15279","title":"Polynomial 2D Biharmonic Coordinates for High-order Cages.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2501.15279","numberOfCreators":3,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2501-15279","https://doi.org/10.48550/ARXIV.2501.15279"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2501-15279","documentUrl":null,"type":"Informal","arxivId":"2501.15279","arxivUrl":"https://arxiv.org/abs/2501.15279"},{"key":"journals/corr/abs-2502-19800","url":"https://dblp.org/rec/journals/corr/abs-2502-19800","title":"No Parameters, No Problem: 3D Gaussian Splatting without Camera Intrinsics and Extrinsics.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2502.19800","numberOfCreators":8,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2502-19800","https://doi.org/10.48550/ARXIV.2502.19800"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2502-19800","documentUrl":null,"type":"Informal","arxivId":"2502.19800","arxivUrl":"https://arxiv.org/abs/2502.19800"},{"key":"journals/corr/abs-2503-08135","url":"https://dblp.org/rec/journals/corr/abs-2503-08135","title":"ArticulatedGS: Self-supervised Digital Twin Modeling of Articulated Objects using 3D Gaussian Splatting.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2503.08135","numberOfCreators":6,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2503-08135","https://doi.org/10.48550/ARXIV.2503.08135"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-08135","documentUrl":null,"type":"Informal","arxivId":"2503.08135","arxivUrl":"https://arxiv.org/abs/2503.08135"},{"key":"journals/corr/abs-2504-09149","url":"https://dblp.org/rec/journals/corr/abs-2504-09149","title":"MASH: Masked Anchored SpHerical Distances for 3D Shape Representation and Generation.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2504.09149","numberOfCreators":7,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2504-09149","https://doi.org/10.48550/ARXIV.2504.09149"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2504-09149","documentUrl":null,"type":"Informal","arxivId":"2504.09149","arxivUrl":"https://arxiv.org/abs/2504.09149"},{"key":"journals/corr/abs-2506-18910","url":"https://dblp.org/rec/journals/corr/abs-2506-18910","title":"Asymptotic analysis and design of linear elastic shell lattice metamaterials.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2506.18910","numberOfCreators":2,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2506-18910","https://doi.org/10.48550/ARXIV.2506.18910"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-18910","documentUrl":null,"type":"Informal","arxivId":"2506.18910","arxivUrl":"https://arxiv.org/abs/2506.18910"},{"key":"journals/corr/abs-2506-22319","url":"https://dblp.org/rec/journals/corr/abs-2506-22319","title":"Asymptotic analysis and design of shell-based thermal lattice metamaterials.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2506.22319","numberOfCreators":2,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2506-22319","https://doi.org/10.48550/ARXIV.2506.22319"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-22319","documentUrl":null,"type":"Informal","arxivId":"2506.22319","arxivUrl":"https://arxiv.org/abs/2506.22319"},{"key":"journals/corr/abs-2507-00690","url":"https://dblp.org/rec/journals/corr/abs-2507-00690","title":"Cage-Based Deformation for Transferable and Undefendable Point Cloud Attack.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2507.00690","numberOfCreators":7,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2507-00690","https://doi.org/10.48550/ARXIV.2507.00690"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2507-00690","documentUrl":null,"type":"Informal","arxivId":"2507.00690","arxivUrl":"https://arxiv.org/abs/2507.00690"},{"key":"journals/corr/abs-2507-02419","url":"https://dblp.org/rec/journals/corr/abs-2507-02419","title":"AvatarMakeup: Realistic Makeup Transfer for 3D Animatable Head Avatars.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2507.02419","numberOfCreators":5,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2507-02419","https://doi.org/10.48550/ARXIV.2507.02419"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2507-02419","documentUrl":null,"type":"Informal","arxivId":"2507.02419","arxivUrl":"https://arxiv.org/abs/2507.02419"},{"key":"journals/corr/abs-2508-18733","url":"https://dblp.org/rec/journals/corr/abs-2508-18733","title":"Drawing2CAD: Sequence-to-Sequence Learning for CAD Generation from Vector Drawings.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2508.18733","numberOfCreators":6,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2508-18733","https://doi.org/10.48550/ARXIV.2508.18733"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-18733","documentUrl":null,"type":"Informal","arxivId":"2508.18733","arxivUrl":"https://arxiv.org/abs/2508.18733"},{"key":"journals/corr/abs-2509-00840","url":"https://dblp.org/rec/journals/corr/abs-2509-00840","title":"Outer Contour-driven Ruled Surface Generation for Linear Hot-wire Rough Machining.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2509.00840","numberOfCreators":7,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2509-00840","https://doi.org/10.48550/ARXIV.2509.00840"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-00840","documentUrl":null,"type":"Informal","arxivId":"2509.00840","arxivUrl":"https://arxiv.org/abs/2509.00840"},{"key":"journals/corr/abs-2509-23718","url":"https://dblp.org/rec/journals/corr/abs-2509-23718","title":"Diff-3DCap: Shape Captioning with Diffusion Models.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2509.23718","numberOfCreators":5,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2509-23718","https://doi.org/10.48550/ARXIV.2509.23718"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-23718","documentUrl":null,"type":"Informal","arxivId":"2509.23718","arxivUrl":"https://arxiv.org/abs/2509.23718"},{"key":"journals/corr/abs-2509-26055","url":"https://dblp.org/rec/journals/corr/abs-2509-26055","title":"GaussEdit: Adaptive 3D Scene Editing with Text and Image Prompts.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2509.26055","numberOfCreators":5,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2509-26055","https://doi.org/10.48550/ARXIV.2509.26055"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-26055","documentUrl":null,"type":"Informal","arxivId":"2509.26055","arxivUrl":"https://arxiv.org/abs/2509.26055"},{"key":"journals/corr/abs-2510-15564","url":"https://dblp.org/rec/journals/corr/abs-2510-15564","title":"Imaginarium: Vision-guided High-Quality 3D Scene Layout Generation.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2510.15564","numberOfCreators":11,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2510-15564","https://doi.org/10.48550/ARXIV.2510.15564"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-15564","documentUrl":null,"type":"Informal","arxivId":"2510.15564","arxivUrl":"https://arxiv.org/abs/2510.15564"},{"key":"journals/corr/abs-2511-12474","url":"https://dblp.org/rec/journals/corr/abs-2511-12474","title":"Co-Layout: LLM-driven Co-optimization for Interior Layout.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2511.12474","numberOfCreators":7,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2511-12474","https://doi.org/10.48550/ARXIV.2511.12474"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2511-12474","documentUrl":null,"type":"Informal","arxivId":"2511.12474","arxivUrl":"https://arxiv.org/abs/2511.12474"},{"key":"journals/corr/abs-2511-17322","url":"https://dblp.org/rec/journals/corr/abs-2511-17322","title":"NoPe-NeRF++: Local-to-Global Optimization of NeRF with No Pose Prior.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2511.17322","numberOfCreators":8,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2511-17322","https://doi.org/10.48550/ARXIV.2511.17322"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2511-17322","documentUrl":null,"type":"Informal","arxivId":"2511.17322","arxivUrl":"https://arxiv.org/abs/2511.17322"},{"key":"journals/corr/abs-2512-20904","url":"https://dblp.org/rec/journals/corr/abs-2512-20904","title":"Efficient Computation of Integer-constrained Cones for Conformal Parameterizations.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2512.20904","numberOfCreators":4,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2512-20904","https://doi.org/10.48550/ARXIV.2512.20904"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-20904","documentUrl":null,"type":"Informal","arxivId":"2512.20904","arxivUrl":"https://arxiv.org/abs/2512.20904"}],"excludedFormal":[],"otherRecords":[],"matchedName":"Ligang Liu","databaseLabel":"Ligang Liu 0001","databaseMetadata":{"type":["https://dblp.org/rdf/schema#Person","https://dblp.org/rdf/schema#Creator"],"label":["Ligang Liu 0001"],"affiliation":["University of Science and Technology of China (USTC), School of Mathematical Sciences, Hefei, Anhui, China"],"orcid":["https://orcid.org/0000-0003-4352-1431"],"primaryAffiliation":["University of Science and Technology of China (USTC), School of Mathematical Sciences, Hefei, Anhui, China"]},"rawFormalRecordCount2025":29,"signatureAudit":{"completedAt":"2026-10-19","frozen":true,"scope":"对 B 组 39 个数值档案的全部 1074 条原始 2025 正式记录扫描 DBLP author-signature ORCID 和机构；复用既有 59 条 Crossref 核验，补查 6 条新触发记录。重点核查不同 ORCID，以及只有预期机构之外机构的条目。本轮不扩展为所有作者逐篇全文审计。","formalRecordCoverage":29,"orcidCounts":{"https://orcid.org/0000-0003-4352-1431":20},"institutionCounts":{"University of Science and Technology of China (USTC)":26},"caveat":"机构名称可能由 DBLP 自动映射而失真；多 ORCID 也不自动等于异人。只有有原始资料支撑的错归才作确认排除，未解决分支则暂停总数。"},"labName":"安徽省图形计算与感知交互重点实验室（GCL）","labUrl":null,"labEvidence":"中国科学技术大学数学科学学院官方 GCL 实验室年度总结报道明确实验室正式名称，并列刘利刚教授为实验室主任；报道对应 2024-12-21 会议。未核实独立实验室 URL。","labSourceUrl":"https://math.ustc.edu.cn/2025/0102/c18649a670512/pagem.htm","sourceWarning":false,"excludedOther":[],"excludedHomonyms":[],"unassignedCandidates":[],"knownPreprintMinimum2025":null,"excludedMisattributed":[],"displayNotes":"身份已与原名单机构及公开资料核对确认。2025 年正式记录 29 条（会议 12、期刊 17），所有作者位置均计入，不表示主导或贡献份额；预印本 16 条单列，不加总。","labDisplayNotes":"中国科大数学科学学院的官方报道列其为安徽省图形计算与感知交互重点实验室（GCL）主任，据此归组。这是省级重点实验室，分组只含本人参与的记录；未确认独立网址。"},{"index":63,"name":"Xihui Liu","nameZh":"刘希慧","role":"Assistant Professor","affiliation":"The University of Hong Kong","affiliationZh":"香港大学","source":"DBLP RDF via official SPARQL; primary-source identity checks","sourceUrl":"https://sparql.dblp.org/","profileUrl":"https://dblp.org/pid/184/3911.html","identifier":"184/3911","retrievedAt":"2026-10-19","count2025":32,"conference2025":30,"journal2025":2,"preprint2025":46,"status":"confirmed","notes":"","identityEvidence":[{"url":"https://dblp.org/pid/184/3911.html","evidence":"DBLP RDF 类型为 Person，消歧后名字为 Xihui Liu。此档案未提供可用机构元数据，以下以本人/机构/出版商来源补证。"},{"url":"https://xh-liu.github.io/","evidence":"个人主页为香港大学 Xihui Liu，论文列表与所选 DBLP 记录匹配。"},{"url":"https://xh-liu.github.io/","evidence":"此本人或机构页面的正文与所选档案中 27 条 2025 记录标题匹配，其中 12 条为当前计入的正式记录（忽略空格、标点、大小写）。","matchedPaperKeys":["conf/cvpr/SunHL0XLL25","conf/cvpr/WangR0HGYZFL25","conf/iccv/FangDWLHTZZDLL25","conf/iccv/WangLTZRFL25","conf/iccv/XiongLHFL25","conf/iccv/ZhuWZPL25","conf/iclr/TengSLND0LL25","conf/nips/ChenCCZWZL25","conf/nips/TengWLCSWLLZL25","conf/siggrapha/YangZGZHLXLCL25","conf/siggrapha/YuBQL000L25","journals/corr/abs-2501-08325","journals/corr/abs-2503-16430","journals/corr/abs-2504-07943","journals/corr/abs-2504-08736","journals/corr/abs-2506-03141","journals/corr/abs-2506-17206","journals/corr/abs-2506-18899","journals/corr/abs-2507-02299","journals/corr/abs-2507-06165","journals/corr/abs-2507-18537","journals/corr/abs-2509-16063","journals/corr/abs-2510-08994","journals/corr/abs-2510-12784","journals/corr/abs-2510-26800","journals/corr/abs-2512-08186","journals/pami/HuangDSXLL25"],"matchedFormalPaperKeys":["conf/cvpr/SunHL0XLL25","conf/cvpr/WangR0HGYZFL25","conf/iccv/FangDWLHTZZDLL25","conf/iccv/WangLTZRFL25","conf/iccv/XiongLHFL25","conf/iccv/ZhuWZPL25","conf/iclr/TengSLND0LL25","conf/nips/ChenCCZWZL25","conf/nips/TengWLCSWLLZL25","conf/siggrapha/YangZGZHLXLCL25","conf/siggrapha/YuBQL000L25","journals/pami/HuangDSXLL25"]}],"papers":[{"key":"conf/cvpr/HuangGAY0ZLLCS25","url":"https://dblp.org/rec/conf/cvpr/HuangGAY0ZLLCS25","title":"MIDI: Multi-Instance Diffusion for Single Image to 3D Scene Generation.","year":2025,"types":["Inproceedings"],"venue":"CVPR","doi":"https://doi.org/10.1109/CVPR52734.2025.02202","eventYear":2025,"numberOfCreators":10,"category":"conference","sources":["https://dblp.org/rec/conf/cvpr/HuangGAY0ZLLCS25","https://doi.org/10.1109/CVPR52734.2025.02202"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/HuangGAY0ZLLCS25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/cvpr/KumbongLLLLLFRR25","url":"https://dblp.org/rec/conf/cvpr/KumbongLLLLLFRR25","title":"HMAR: Efficient Hierarchical Masked Auto-Regressive Image Generation.","year":2025,"types":["Inproceedings"],"venue":"CVPR","doi":"https://doi.org/10.1109/CVPR52734.2025.00242","eventYear":2025,"numberOfCreators":9,"category":"conference","sources":["https://dblp.org/rec/conf/cvpr/KumbongLLLLLFRR25","https://doi.org/10.1109/CVPR52734.2025.00242"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/KumbongLLLLLFRR25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/cvpr/LiHNLHJLYRDYY025","url":"https://dblp.org/rec/conf/cvpr/LiHNLHJLYRDYY025","title":"MBQ: Modality-Balanced Quantization for Large Vision-Language Models.","year":2025,"types":["Inproceedings"],"venue":"CVPR","doi":"https://doi.org/10.1109/CVPR52734.2025.00394","eventYear":2025,"numberOfCreators":13,"category":"conference","sources":["https://dblp.org/rec/conf/cvpr/LiHNLHJLYRDYY025","https://doi.org/10.1109/CVPR52734.2025.00394"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/LiHNLHJLYRDYY025","documentUrl":null,"type":"Inproceedings"},{"key":"conf/cvpr/LiSHDQLSS25","url":"https://dblp.org/rec/conf/cvpr/LiSHDQLSS25","title":"T2ISafety: Benchmark for Assessing Fairness, Toxicity, and Privacy in Image Generation.","year":2025,"types":["Inproceedings"],"venue":"CVPR","doi":"https://doi.org/10.1109/CVPR52734.2025.01249","eventYear":2025,"numberOfCreators":8,"category":"conference","sources":["https://dblp.org/rec/conf/cvpr/LiSHDQLSS25","https://doi.org/10.1109/CVPR52734.2025.01249"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/LiSHDQLSS25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/cvpr/SunHL0XLL25","url":"https://dblp.org/rec/conf/cvpr/SunHL0XLL25","title":"T2V-CompBench: A Comprehensive Benchmark for Compositional Text-to-video Generation.","year":2025,"types":["Inproceedings"],"venue":"CVPR","doi":"https://doi.org/10.1109/CVPR52734.2025.00787","eventYear":2025,"numberOfCreators":7,"category":"conference","sources":["https://dblp.org/rec/conf/cvpr/SunHL0XLL25","https://doi.org/10.1109/CVPR52734.2025.00787"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/SunHL0XLL25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/cvpr/WangR0HGYZFL25","url":"https://dblp.org/rec/conf/cvpr/WangR0HGYZFL25","title":"Parallelized Autoregressive Visual Generation.","year":2025,"types":["Inproceedings"],"venue":"CVPR","doi":"https://doi.org/10.1109/CVPR52734.2025.01209","eventYear":2025,"numberOfCreators":9,"category":"conference","sources":["https://dblp.org/rec/conf/cvpr/WangR0HGYZFL25","https://doi.org/10.1109/CVPR52734.2025.01209"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/WangR0HGYZFL25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/eccv/BahmaniLYSRLLPTWTL24","url":"https://dblp.org/rec/conf/eccv/BahmaniLYSRLLPTWTL24","title":"TC4D: Trajectory-Conditioned Text-to-4D Generation.","year":2025,"types":["Inproceedings"],"venue":"ECCV (46)","doi":"https://doi.org/10.1007/978-3-031-72952-2_4","eventYear":2024,"numberOfCreators":12,"category":"conference","sources":["https://dblp.org/rec/conf/eccv/BahmaniLYSRLLPTWTL24","https://doi.org/10.1007/978-3-031-72952-2_4"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2024,"sourceUrl":"https://dblp.org/rec/conf/eccv/BahmaniLYSRLLPTWTL24","documentUrl":null,"type":"Inproceedings"},{"key":"conf/eccv/WangLHHLOB24","url":"https://dblp.org/rec/conf/eccv/WangLHHLOB24","title":"PredBench: Benchmarking Spatio-Temporal Prediction Across Diverse Disciplines.","year":2025,"types":["Inproceedings"],"venue":"ECCV (58)","doi":"https://doi.org/10.1007/978-3-031-73636-0_17","eventYear":2024,"numberOfCreators":7,"category":"conference","sources":["https://dblp.org/rec/conf/eccv/WangLHHLOB24","https://doi.org/10.1007/978-3-031-73636-0_17"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2024,"sourceUrl":"https://dblp.org/rec/conf/eccv/WangLHHLOB24","documentUrl":null,"type":"Inproceedings"},{"key":"conf/eccv/ZhuWZCL24","url":"https://dblp.org/rec/conf/eccv/ZhuWZCL24","title":"ScanReason: Empowering 3D Visual Grounding with Reasoning Capabilities.","year":2025,"types":["Inproceedings"],"venue":"ECCV (8)","doi":"https://doi.org/10.1007/978-3-031-73242-3_9","eventYear":2024,"numberOfCreators":5,"category":"conference","sources":["https://dblp.org/rec/conf/eccv/ZhuWZCL24","https://doi.org/10.1007/978-3-031-73242-3_9"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2024,"sourceUrl":"https://dblp.org/rec/conf/eccv/ZhuWZCL24","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iccv/ChenGTLGDSL25","url":"https://dblp.org/rec/conf/iccv/ChenGTLGDSL25","title":"Moto: Latent Motion Token as the Bridging Language for Learning Robot Manipulation from Videos.","year":2025,"types":["Inproceedings"],"venue":"ICCV","doi":"https://doi.org/10.1109/ICCV51701.2025.01837","eventYear":2025,"numberOfCreators":8,"category":"conference","sources":["https://dblp.org/rec/conf/iccv/ChenGTLGDSL25","https://doi.org/10.1109/ICCV51701.2025.01837"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/ChenGTLGDSL25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iccv/FangDWLHTZZDLL25","url":"https://dblp.org/rec/conf/iccv/FangDWLHTZZDLL25","title":"PUMA: Empowering Unified MLLM with Multi-Granular Visual Generation.","year":2025,"types":["Inproceedings"],"venue":"ICCV","doi":"https://doi.org/10.1109/ICCV51701.2025.01433","eventYear":2025,"numberOfCreators":11,"category":"conference","sources":["https://dblp.org/rec/conf/iccv/FangDWLHTZZDLL25","https://doi.org/10.1109/ICCV51701.2025.01433"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/FangDWLHTZZDLL25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iccv/GeCLZLDZ25","url":"https://dblp.org/rec/conf/iccv/GeCLZLDZ25","title":"V2PE: Improving Multimodal Long-Context Capability of Vision-Language Models with Variable Visual Position Encoding.","year":2025,"types":["Inproceedings"],"venue":"ICCV","doi":"https://doi.org/10.1109/ICCV51701.2025.01958","eventYear":2025,"numberOfCreators":7,"category":"conference","sources":["https://dblp.org/rec/conf/iccv/GeCLZLDZ25","https://doi.org/10.1109/ICCV51701.2025.01958"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/GeCLZLDZ25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iccv/HuangZWHL25","url":"https://dblp.org/rec/conf/iccv/HuangZWHL25","title":"DreamCube: RGB-D Panorama Generation via Multi-Plane Synchronization.","year":2025,"types":["Inproceedings"],"venue":"ICCV","doi":"https://doi.org/10.1109/ICCV51701.2025.02311","eventYear":2025,"numberOfCreators":5,"category":"conference","sources":["https://dblp.org/rec/conf/iccv/HuangZWHL25","https://doi.org/10.1109/ICCV51701.2025.02311"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/HuangZWHL25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iccv/QinKSYLLZB25","url":"https://dblp.org/rec/conf/iccv/QinKSYLLZB25","title":"RoboFactory: Exploring Embodied Agent Collaboration with Compositional Constraints.","year":2025,"types":["Inproceedings"],"venue":"ICCV","doi":"https://doi.org/10.1109/ICCV51701.2025.00939","eventYear":2025,"numberOfCreators":8,"category":"conference","sources":["https://dblp.org/rec/conf/iccv/QinKSYLLZB25","https://doi.org/10.1109/ICCV51701.2025.00939"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/QinKSYLLZB25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iccv/WangKYCWZXLWLZZSLL25","url":"https://dblp.org/rec/conf/iccv/WangKYCWZXLWLZZSLL25","title":"LiT: Delving into a Simple Linear Diffusion Transformer for Image Generation.","year":2025,"types":["Inproceedings"],"venue":"ICCV","doi":"https://doi.org/10.1109/ICCV51701.2025.01491","eventYear":2025,"numberOfCreators":15,"category":"conference","sources":["https://dblp.org/rec/conf/iccv/WangKYCWZXLWLZZSLL25","https://doi.org/10.1109/ICCV51701.2025.01491"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/WangKYCWZXLWLZZSLL25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iccv/WangLTZRFL25","url":"https://dblp.org/rec/conf/iccv/WangLTZRFL25","title":"Bridging Continuous and Discrete Tokens for Autoregressive Visual Generation.","year":2025,"types":["Inproceedings"],"venue":"ICCV","doi":"https://doi.org/10.1109/ICCV51701.2025.01728","eventYear":2025,"numberOfCreators":7,"category":"conference","sources":["https://dblp.org/rec/conf/iccv/WangLTZRFL25","https://doi.org/10.1109/ICCV51701.2025.01728"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/WangLTZRFL25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iccv/XiongLHFL25","url":"https://dblp.org/rec/conf/iccv/XiongLHFL25","title":"GigaTok: Scaling Visual Tokenizers to 3 Billion Parameters for Autoregressive Image Generation.","year":2025,"types":["Inproceedings"],"venue":"ICCV","doi":"https://doi.org/10.1109/ICCV51701.2025.01744","eventYear":2025,"numberOfCreators":5,"category":"conference","sources":["https://dblp.org/rec/conf/iccv/XiongLHFL25","https://doi.org/10.1109/ICCV51701.2025.01744"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/XiongLHFL25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iccv/YuQWWZL25","url":"https://dblp.org/rec/conf/iccv/YuQWWZL25","title":"GameFactorly: Creating New Games with Generative Interactive Videos.","year":2025,"types":["Inproceedings"],"venue":"ICCV","doi":"https://doi.org/10.1109/ICCV51701.2025.01078","eventYear":2025,"numberOfCreators":6,"category":"conference","sources":["https://dblp.org/rec/conf/iccv/YuQWWZL25","https://doi.org/10.1109/ICCV51701.2025.01078"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/YuQWWZL25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iccv/ZhuWZPL25","url":"https://dblp.org/rec/conf/iccv/ZhuWZPL25","title":"LLaVA-3D: A Simple Yet Effective Pathway to Empowering LMMs with 3D Capabilities.","year":2025,"types":["Inproceedings"],"venue":"ICCV","doi":"https://doi.org/10.1109/ICCV51701.2025.00409","eventYear":2025,"numberOfCreators":5,"category":"conference","sources":["https://dblp.org/rec/conf/iccv/ZhuWZPL25","https://doi.org/10.1109/ICCV51701.2025.00409"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/ZhuWZPL25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iclr/TengSLND0LL25","url":"https://dblp.org/rec/conf/iclr/TengSLND0LL25","title":"Accelerating Auto-regressive Text-to-Image Generation with Training-free Speculative Jacobi Decoding.","year":2025,"types":["Inproceedings"],"venue":"ICLR","doi":null,"eventYear":2025,"numberOfCreators":8,"category":"conference","sources":["https://dblp.org/rec/conf/iclr/TengSLND0LL25"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iclr/TengSLND0LL25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/icml/GuoZYY0GS0L025","url":"https://dblp.org/rec/conf/icml/GuoZYY0GS0L025","title":"UniMC: Taming Diffusion Transformer for Unified Keypoint-Guided Multi-Class Image Generation.","year":2025,"types":["Inproceedings"],"venue":"ICML","doi":null,"eventYear":2025,"numberOfCreators":10,"category":"conference","sources":["https://dblp.org/rec/conf/icml/GuoZYY0GS0L025"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/icml/GuoZYY0GS0L025","documentUrl":null,"type":"Inproceedings"},{"key":"conf/icml/QinSYWZLYLSS0Z25","url":"https://dblp.org/rec/conf/icml/QinSYWZLYLSS0Z25","title":"WorldSimBench: Towards Video Generation Models as World Simulators.","year":2025,"types":["Inproceedings"],"venue":"ICML","doi":null,"eventYear":2025,"numberOfCreators":12,"category":"conference","sources":["https://dblp.org/rec/conf/icml/QinSYWZLYLSS0Z25"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/icml/QinSYWZLYLSS0Z25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/nips/ChenCCZWZL25","url":"https://dblp.org/rec/conf/nips/ChenCCZWZL25","title":"TTS-VAR: A Test-Time Scaling Framework for Visual Auto-Regressive Generation.","year":2025,"types":["Inproceedings"],"venue":"NeurIPS","doi":null,"eventYear":2025,"numberOfCreators":7,"category":"conference","sources":["https://dblp.org/rec/conf/nips/ChenCCZWZL25"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/nips/ChenCCZWZL25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/nips/ChuHCZXxWYLZLZY25","url":"https://dblp.org/rec/conf/nips/ChuHCZXxWYLZLZY25","title":"Wan-Move: Motion-controllable Video Generation via Latent Trajectory Guidance.","year":2025,"types":["Inproceedings"],"venue":"NeurIPS","doi":null,"eventYear":2025,"numberOfCreators":13,"category":"conference","sources":["https://dblp.org/rec/conf/nips/ChuHCZXxWYLZLZY25"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/nips/ChuHCZXxWYLZLZY25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/nips/FangDWHLTYYZDLL25","url":"https://dblp.org/rec/conf/nips/FangDWHLTYYZDLL25","title":"GoT: Unleashing Reasoning Capability of MLLM for Visual Generation and Editing.","year":2025,"types":["Inproceedings"],"venue":"NeurIPS","doi":null,"eventYear":2025,"numberOfCreators":12,"category":"conference","sources":["https://dblp.org/rec/conf/nips/FangDWHLTYYZDLL25"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/nips/FangDWHLTYYZDLL25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/nips/LinZXMLWP25","url":"https://dblp.org/rec/conf/nips/LinZXMLWP25","title":"OST-Bench: Evaluating the Capabilities of MLLMs in Online Spatio-temporal Scene Understanding.","year":2025,"types":["Inproceedings"],"venue":"NeurIPS","doi":null,"eventYear":2025,"numberOfCreators":7,"category":"conference","sources":["https://dblp.org/rec/conf/nips/LinZXMLWP25"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/nips/LinZXMLWP25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/nips/TengWLCSWLLZL25","url":"https://dblp.org/rec/conf/nips/TengWLCSWLLZL25","title":"Speculative Jacobi-Denoising Decoding for Accelerating Autoregressive Text-to-image Generation.","year":2025,"types":["Inproceedings"],"venue":"NeurIPS","doi":null,"eventYear":2025,"numberOfCreators":10,"category":"conference","sources":["https://dblp.org/rec/conf/nips/TengWLCSWLLZL25"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/nips/TengWLCSWLLZL25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/nips/YueWWZLOBZ25","url":"https://dblp.org/rec/conf/nips/YueWWZLOBZ25","title":"Understand Before You Generate: Self-Guided Training for Autoregressive Image Generation.","year":2025,"types":["Inproceedings"],"venue":"NeurIPS","doi":null,"eventYear":2025,"numberOfCreators":8,"category":"conference","sources":["https://dblp.org/rec/conf/nips/YueWWZLOBZ25"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/nips/YueWWZLOBZ25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/siggrapha/YangZGZHLXLCL25","url":"https://dblp.org/rec/conf/siggrapha/YangZGZHLXLCL25","title":"OmniPart: Part-Aware 3D Generation with Semantic Decoupling and Structural Cohesion.","year":2025,"types":["Inproceedings"],"venue":"SIGGRAPH Asia","doi":"https://doi.org/10.1145/3757377.3763872","eventYear":2025,"numberOfCreators":10,"category":"conference","sources":["https://dblp.org/rec/conf/siggrapha/YangZGZHLXLCL25","https://doi.org/10.1145/3757377.3763872"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/siggrapha/YangZGZHLXLCL25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/siggrapha/YuBQL000L25","url":"https://dblp.org/rec/conf/siggrapha/YuBQL000L25","title":"Context as Memory: Scene-Consistent Interactive Long Video Generation with Memory Retrieval.","year":2025,"types":["Inproceedings"],"venue":"SIGGRAPH Asia","doi":"https://doi.org/10.1145/3757377.3763833","eventYear":2025,"numberOfCreators":8,"category":"conference","sources":["https://dblp.org/rec/conf/siggrapha/YuBQL000L25","https://doi.org/10.1145/3757377.3763833"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/siggrapha/YuBQL000L25","documentUrl":null,"type":"Inproceedings"},{"key":"journals/csur/SunZXLCQXDLGWWCYRFHYLLL25","url":"https://dblp.org/rec/journals/csur/SunZXLCQXDLGWWCYRFHYLLL25","title":"A Survey of Reasoning with Foundation Models: Concepts, Methodologies, and Outlook.","year":2025,"types":["Article"],"venue":"ACM Comput. Surv.","doi":"https://doi.org/10.1145/3729218","numberOfCreators":34,"category":"journal","sources":["https://dblp.org/rec/journals/csur/SunZXLCQXDLGWWCYRFHYLLL25","https://doi.org/10.1145/3729218"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/csur/SunZXLCQXDLGWWCYRFHYLLL25","documentUrl":null,"type":"Article"},{"key":"journals/pami/HuangDSXLL25","url":"https://dblp.org/rec/journals/pami/HuangDSXLL25","title":"T2I-CompBench++: An Enhanced and Comprehensive Benchmark for Compositional Text-to-Image Generation.","year":2025,"types":["Article"],"venue":"IEEE Trans. Pattern Anal. Mach. Intell.","doi":"https://doi.org/10.1109/TPAMI.2025.3531907","numberOfCreators":6,"category":"journal","sources":["https://dblp.org/rec/journals/pami/HuangDSXLL25","https://doi.org/10.1109/TPAMI.2025.3531907"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/pami/HuangDSXLL25","documentUrl":null,"type":"Article"}],"preprints":[{"key":"journals/corr/abs-2501-08325","url":"https://dblp.org/rec/journals/corr/abs-2501-08325","title":"GameFactory: Creating New Games with Generative Interactive Videos.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2501.08325","numberOfCreators":6,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2501-08325","https://doi.org/10.48550/ARXIV.2501.08325"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2501-08325","documentUrl":null,"type":"Informal","arxivId":"2501.08325","arxivUrl":"https://arxiv.org/abs/2501.08325"},{"key":"journals/corr/abs-2501-12612","url":"https://dblp.org/rec/journals/corr/abs-2501-12612","title":"T2ISafety: Benchmark for Assessing Fairness, Toxicity, and Privacy in Image Generation.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2501.12612","numberOfCreators":8,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2501-12612","https://doi.org/10.48550/ARXIV.2501.12612"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2501-12612","documentUrl":null,"type":"Informal","arxivId":"2501.12612","arxivUrl":"https://arxiv.org/abs/2501.12612"},{"key":"journals/corr/abs-2501-12976","url":"https://dblp.org/rec/journals/corr/abs-2501-12976","title":"LiT: Delving into a Simplified Linear Diffusion Transformer for Image Generation.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2501.12976","numberOfCreators":15,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2501-12976","https://doi.org/10.48550/ARXIV.2501.12976"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2501-12976","documentUrl":null,"type":"Informal","arxivId":"2501.12976","arxivUrl":"https://arxiv.org/abs/2501.12976"},{"key":"journals/corr/abs-2502-00359","url":"https://dblp.org/rec/journals/corr/abs-2502-00359","title":"Exploring Representation-Aligned Latent Space for Better Generation.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2502.00359","numberOfCreators":9,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2502-00359","https://doi.org/10.48550/ARXIV.2502.00359"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2502-00359","documentUrl":null,"type":"Informal","arxivId":"2502.00359","arxivUrl":"https://arxiv.org/abs/2502.00359"},{"key":"journals/corr/abs-2503-10639","url":"https://dblp.org/rec/journals/corr/abs-2503-10639","title":"GoT: Unleashing Reasoning Capability of Multimodal Large Language Model for Visual Generation and Editing.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2503.10639","numberOfCreators":12,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2503-10639","https://doi.org/10.48550/ARXIV.2503.10639"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-10639","documentUrl":null,"type":"Informal","arxivId":"2503.10639","arxivUrl":"https://arxiv.org/abs/2503.10639"},{"key":"journals/corr/abs-2503-16408","url":"https://dblp.org/rec/journals/corr/abs-2503-16408","title":"RoboFactory: Exploring Embodied Agent Collaboration with Compositional Constraints.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2503.16408","numberOfCreators":8,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2503-16408","https://doi.org/10.48550/ARXIV.2503.16408"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-16408","documentUrl":null,"type":"Informal","arxivId":"2503.16408","arxivUrl":"https://arxiv.org/abs/2503.16408"},{"key":"journals/corr/abs-2503-16430","url":"https://dblp.org/rec/journals/corr/abs-2503-16430","title":"Bridging Continuous and Discrete Tokens for Autoregressive Visual Generation.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2503.16430","numberOfCreators":7,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2503-16430","https://doi.org/10.48550/ARXIV.2503.16430"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-16430","documentUrl":null,"type":"Informal","arxivId":"2503.16430","arxivUrl":"https://arxiv.org/abs/2503.16430"},{"key":"journals/corr/abs-2503-17359","url":"https://dblp.org/rec/journals/corr/abs-2503-17359","title":"Position: Interactive Generative Video as Next-Generation Game Engine.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2503.17359","numberOfCreators":8,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2503-17359","https://doi.org/10.48550/ARXIV.2503.17359"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-17359","documentUrl":null,"type":"Informal","arxivId":"2503.17359","arxivUrl":"https://arxiv.org/abs/2503.17359"},{"key":"journals/corr/abs-2503-19462","url":"https://dblp.org/rec/journals/corr/abs-2503-19462","title":"AccVideo: Accelerating Video Diffusion Model with Synthetic Dataset.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2503.19462","numberOfCreators":6,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2503-19462","https://doi.org/10.48550/ARXIV.2503.19462"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-19462","documentUrl":null,"type":"Informal","arxivId":"2503.19462","arxivUrl":"https://arxiv.org/abs/2503.19462"},{"key":"journals/corr/abs-2503-24376","url":"https://dblp.org/rec/journals/corr/abs-2503-24376","title":"Exploring the Effect of Reinforcement Learning on Video Understanding: Insights from SEED-Bench-R1.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2503.24376","numberOfCreators":7,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2503-24376","https://doi.org/10.48550/ARXIV.2503.24376"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-24376","documentUrl":null,"type":"Informal","arxivId":"2503.24376","arxivUrl":"https://arxiv.org/abs/2503.24376"},{"key":"journals/corr/abs-2504-07943","url":"https://dblp.org/rec/journals/corr/abs-2504-07943","title":"HoloPart: Generative 3D Part Amodal Segmentation.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2504.07943","numberOfCreators":8,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2504-07943","https://doi.org/10.48550/ARXIV.2504.07943"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2504-07943","documentUrl":null,"type":"Informal","arxivId":"2504.07943","arxivUrl":"https://arxiv.org/abs/2504.07943"},{"key":"journals/corr/abs-2504-08736","url":"https://dblp.org/rec/journals/corr/abs-2504-08736","title":"GigaTok: Scaling Visual Tokenizers to 3 Billion Parameters for Autoregressive Image Generation.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2504.08736","numberOfCreators":5,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2504-08736","https://doi.org/10.48550/ARXIV.2504.08736"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2504-08736","documentUrl":null,"type":"Informal","arxivId":"2504.08736","arxivUrl":"https://arxiv.org/abs/2504.08736"},{"key":"journals/corr/abs-2504-13162","url":"https://dblp.org/rec/journals/corr/abs-2504-13162","title":"Personalized Text-to-Image Generation with Auto-Regressive Models.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2504.13162","numberOfCreators":4,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2504-13162","https://doi.org/10.48550/ARXIV.2504.13162"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2504-13162","documentUrl":null,"type":"Informal","arxivId":"2504.13162","arxivUrl":"https://arxiv.org/abs/2504.13162"},{"key":"journals/corr/abs-2504-21853","url":"https://dblp.org/rec/journals/corr/abs-2504-21853","title":"A Survey of Interactive Generative Video.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2504.21853","numberOfCreators":10,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2504-21853","https://doi.org/10.48550/ARXIV.2504.21853"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2504-21853","documentUrl":null,"type":"Informal","arxivId":"2504.21853","arxivUrl":"https://arxiv.org/abs/2504.21853"},{"key":"journals/corr/abs-2505-11777","url":"https://dblp.org/rec/journals/corr/abs-2505-11777","title":"Self-NPO: Negative Preference Optimization of Diffusion Models by Simply Learning from Itself without Explicit Preference Annotations.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2505.11777","numberOfCreators":6,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2505-11777","https://doi.org/10.48550/ARXIV.2505.11777"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-11777","documentUrl":null,"type":"Informal","arxivId":"2505.11777","arxivUrl":"https://arxiv.org/abs/2505.11777"},{"key":"journals/corr/abs-2505-17022","url":"https://dblp.org/rec/journals/corr/abs-2505-17022","title":"GoT-R1: Unleashing Reasoning Capability of MLLM for Visual Generation with Reinforcement Learning.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2505.17022","numberOfCreators":8,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2505-17022","https://doi.org/10.48550/ARXIV.2505.17022"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-17022","documentUrl":null,"type":"Informal","arxivId":"2505.17022","arxivUrl":"https://arxiv.org/abs/2505.17022"},{"key":"journals/corr/abs-2505-17099","url":"https://dblp.org/rec/journals/corr/abs-2505-17099","title":"Learning Interpretable Representations Leads to Semantically Faithful EEG-to-Text Generation.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2505.17099","numberOfCreators":3,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2505-17099","https://doi.org/10.48550/ARXIV.2505.17099"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-17099","documentUrl":null,"type":"Informal","arxivId":"2505.17099","arxivUrl":"https://arxiv.org/abs/2505.17099"},{"key":"journals/corr/abs-2506-03126","url":"https://dblp.org/rec/journals/corr/abs-2506-03126","title":"AnimeShooter: A Multi-Shot Animation Dataset for Reference-Guided Video Generation.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2506.03126","numberOfCreators":6,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2506-03126","https://doi.org/10.48550/ARXIV.2506.03126"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-03126","documentUrl":null,"type":"Informal","arxivId":"2506.03126","arxivUrl":"https://arxiv.org/abs/2506.03126"},{"key":"journals/corr/abs-2506-03141","url":"https://dblp.org/rec/journals/corr/abs-2506-03141","title":"Context as Memory: Scene-Consistent Interactive Long Video Generation with Memory Retrieval.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2506.03141","numberOfCreators":8,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2506-03141","https://doi.org/10.48550/ARXIV.2506.03141"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-03141","documentUrl":null,"type":"Informal","arxivId":"2506.03141","arxivUrl":"https://arxiv.org/abs/2506.03141"},{"key":"journals/corr/abs-2506-04421","url":"https://dblp.org/rec/journals/corr/abs-2506-04421","title":"HMAR: Efficient Hierarchical Masked Auto-Regressive Image Generation.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2506.04421","numberOfCreators":9,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2506-04421","https://doi.org/10.48550/ARXIV.2506.04421"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-04421","documentUrl":null,"type":"Informal","arxivId":"2506.04421","arxivUrl":"https://arxiv.org/abs/2506.04421"},{"key":"journals/corr/abs-2506-16141","url":"https://dblp.org/rec/journals/corr/abs-2506-16141","title":"GRPO-CARE: Consistency-Aware Reinforcement Learning for Multimodal Reasoning.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2506.16141","numberOfCreators":7,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2506-16141","https://doi.org/10.48550/ARXIV.2506.16141"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-16141","documentUrl":null,"type":"Informal","arxivId":"2506.16141","arxivUrl":"https://arxiv.org/abs/2506.16141"},{"key":"journals/corr/abs-2506-17206","url":"https://dblp.org/rec/journals/corr/abs-2506-17206","title":"DreamCube: 3D Panorama Generation via Multi-plane Synchronization.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2506.17206","numberOfCreators":5,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2506-17206","https://doi.org/10.48550/ARXIV.2506.17206"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-17206","documentUrl":null,"type":"Informal","arxivId":"2506.17206","arxivUrl":"https://arxiv.org/abs/2506.17206"},{"key":"journals/corr/abs-2506-18899","url":"https://dblp.org/rec/journals/corr/abs-2506-18899","title":"FilMaster: Bridging Cinematic Principles and Generative AI for Automated Film Generation.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2506.18899","numberOfCreators":9,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2506-18899","https://doi.org/10.48550/ARXIV.2506.18899"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-18899","documentUrl":null,"type":"Informal","arxivId":"2506.18899","arxivUrl":"https://arxiv.org/abs/2506.18899"},{"key":"journals/corr/abs-2507-02299","url":"https://dblp.org/rec/journals/corr/abs-2507-02299","title":"DreamComposer++: Empowering Diffusion Models with Multi-View Conditions for 3D Content Generation.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2507.02299","numberOfCreators":9,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2507-02299","https://doi.org/10.48550/ARXIV.2507.02299"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2507-02299","documentUrl":null,"type":"Informal","arxivId":"2507.02299","arxivUrl":"https://arxiv.org/abs/2507.02299"},{"key":"journals/corr/abs-2507-02713","url":"https://dblp.org/rec/journals/corr/abs-2507-02713","title":"UniMC: Taming Diffusion Transformer for Unified Keypoint-Guided Multi-Class Image Generation.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2507.02713","numberOfCreators":10,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2507-02713","https://doi.org/10.48550/ARXIV.2507.02713"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2507-02713","documentUrl":null,"type":"Informal","arxivId":"2507.02713","arxivUrl":"https://arxiv.org/abs/2507.02713"},{"key":"journals/corr/abs-2507-05240","url":"https://dblp.org/rec/journals/corr/abs-2507-05240","title":"StreamVLN: Streaming Vision-and-Language Navigation via SlowFast Context Modeling.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2507.05240","numberOfCreators":12,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2507-05240","https://doi.org/10.48550/ARXIV.2507.05240"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2507-05240","documentUrl":null,"type":"Informal","arxivId":"2507.05240","arxivUrl":"https://arxiv.org/abs/2507.05240"},{"key":"journals/corr/abs-2507-06165","url":"https://dblp.org/rec/journals/corr/abs-2507-06165","title":"OmniPart: Part-Aware 3D Generation with Semantic Decoupling and Structural Cohesion.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2507.06165","numberOfCreators":10,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2507-06165","https://doi.org/10.48550/ARXIV.2507.06165"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2507-06165","documentUrl":null,"type":"Informal","arxivId":"2507.06165","arxivUrl":"https://arxiv.org/abs/2507.06165"},{"key":"journals/corr/abs-2507-07984","url":"https://dblp.org/rec/journals/corr/abs-2507-07984","title":"OST-Bench: Evaluating the Capabilities of MLLMs in Online Spatio-temporal Scene Understanding.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2507.07984","numberOfCreators":7,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2507-07984","https://doi.org/10.48550/ARXIV.2507.07984"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2507-07984","documentUrl":null,"type":"Informal","arxivId":"2507.07984","arxivUrl":"https://arxiv.org/abs/2507.07984"},{"key":"journals/corr/abs-2507-18537","url":"https://dblp.org/rec/journals/corr/abs-2507-18537","title":"TTS-VAR: A Test-Time Scaling Framework for Visual Auto-Regressive Generation.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2507.18537","numberOfCreators":7,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2507-18537","https://doi.org/10.48550/ARXIV.2507.18537"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2507-18537","documentUrl":null,"type":"Informal","arxivId":"2507.18537","arxivUrl":"https://arxiv.org/abs/2507.18537"},{"key":"journals/corr/abs-2508-14036","url":"https://dblp.org/rec/journals/corr/abs-2508-14036","title":"GeoSAM2: Unleashing the Power of SAM2 for 3D Part Segmentation.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2508.14036","numberOfCreators":7,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2508-14036","https://doi.org/10.48550/ARXIV.2508.14036"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-14036","documentUrl":null,"type":"Informal","arxivId":"2508.14036","arxivUrl":"https://arxiv.org/abs/2508.14036"},{"key":"journals/corr/abs-2508-17472","url":"https://dblp.org/rec/journals/corr/abs-2508-17472","title":"T2I-ReasonBench: Benchmarking Reasoning-Informed Text-to-Image Generation.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2508.17472","numberOfCreators":5,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2508-17472","https://doi.org/10.48550/ARXIV.2508.17472"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-17472","documentUrl":null,"type":"Informal","arxivId":"2508.17472","arxivUrl":"https://arxiv.org/abs/2508.17472"},{"key":"journals/corr/abs-2509-08736","url":"https://dblp.org/rec/journals/corr/abs-2509-08736","title":"ChemBOMAS: Accelerated BO in Chemistry with LLM-Enhanced Multi-Agent System.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2509.08736","numberOfCreators":18,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2509-08736","https://doi.org/10.48550/ARXIV.2509.08736"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-08736","documentUrl":null,"type":"Informal","arxivId":"2509.08736","arxivUrl":"https://arxiv.org/abs/2509.08736"},{"key":"journals/corr/abs-2509-09680","url":"https://dblp.org/rec/journals/corr/abs-2509-09680","title":"FLUX-Reason-6M & PRISM-Bench: A Million-Scale Text-to-Image Reasoning Dataset and Comprehensive Benchmark.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2509.09680","numberOfCreators":10,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2509-09680","https://doi.org/10.48550/ARXIV.2509.09680"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-09680","documentUrl":null,"type":"Informal","arxivId":"2509.09680","arxivUrl":"https://arxiv.org/abs/2509.09680"},{"key":"journals/corr/abs-2509-10463","url":"https://dblp.org/rec/journals/corr/abs-2509-10463","title":"The 1st International Workshop on Disentangled Representation Learning for Controllable Generation (DRL4Real): Methods and Results.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2509.10463","numberOfCreators":47,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2509-10463","https://doi.org/10.48550/ARXIV.2509.10463"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-10463","documentUrl":null,"type":"Informal","arxivId":"2509.10463","arxivUrl":"https://arxiv.org/abs/2509.10463"},{"key":"journals/corr/abs-2509-15185","url":"https://dblp.org/rec/journals/corr/abs-2509-15185","title":"Understand Before You Generate: Self-Guided Training for Autoregressive Image Generation.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2509.15185","numberOfCreators":8,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2509-15185","https://doi.org/10.48550/ARXIV.2509.15185"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-15185","documentUrl":null,"type":"Informal","arxivId":"2509.15185","arxivUrl":"https://arxiv.org/abs/2509.15185"},{"key":"journals/corr/abs-2509-16063","url":"https://dblp.org/rec/journals/corr/abs-2509-16063","title":"DSPv2: Improved Dense Policy for Effective and Generalizable Whole-body Mobile Manipulation.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2509.16063","numberOfCreators":7,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2509-16063","https://doi.org/10.48550/ARXIV.2509.16063"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-16063","documentUrl":null,"type":"Informal","arxivId":"2509.16063","arxivUrl":"https://arxiv.org/abs/2509.16063"},{"key":"journals/corr/abs-2509-17398","url":"https://dblp.org/rec/journals/corr/abs-2509-17398","title":"Optimizing Split Federated Learning with Unstable Client Participation.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2509.17398","numberOfCreators":6,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2509-17398","https://doi.org/10.48550/ARXIV.2509.17398"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-17398","documentUrl":null,"type":"Informal","arxivId":"2509.17398","arxivUrl":"https://arxiv.org/abs/2509.17398"},{"key":"journals/corr/abs-2510-08994","url":"https://dblp.org/rec/journals/corr/abs-2510-08994","title":"Speculative Jacobi-Denoising Decoding for Accelerating Autoregressive Text-to-image Generation.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2510.08994","numberOfCreators":10,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2510-08994","https://doi.org/10.48550/ARXIV.2510.08994"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-08994","documentUrl":null,"type":"Informal","arxivId":"2510.08994","arxivUrl":"https://arxiv.org/abs/2510.08994"},{"key":"journals/corr/abs-2510-11718","url":"https://dblp.org/rec/journals/corr/abs-2510-11718","title":"CodePlot-CoT: Mathematical Visual Reasoning by Thinking with Code-Driven Images.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2510.11718","numberOfCreators":13,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2510-11718","https://doi.org/10.48550/ARXIV.2510.11718"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-11718","documentUrl":null,"type":"Informal","arxivId":"2510.11718","arxivUrl":"https://arxiv.org/abs/2510.11718"},{"key":"journals/corr/abs-2510-12784","url":"https://dblp.org/rec/journals/corr/abs-2510-12784","title":"SRUM: Fine-Grained Self-Rewarding for Unified Multimodal Models.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2510.12784","numberOfCreators":7,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2510-12784","https://doi.org/10.48550/ARXIV.2510.12784"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-12784","documentUrl":null,"type":"Informal","arxivId":"2510.12784","arxivUrl":"https://arxiv.org/abs/2510.12784"},{"key":"journals/corr/abs-2510-24711","url":"https://dblp.org/rec/journals/corr/abs-2510-24711","title":"Routing Matters in MoE: Scaling Diffusion Transformers with Explicit Routing Guidance.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2510.24711","numberOfCreators":11,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2510-24711","https://doi.org/10.48550/ARXIV.2510.24711"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-24711","documentUrl":null,"type":"Informal","arxivId":"2510.24711","arxivUrl":"https://arxiv.org/abs/2510.24711"},{"key":"journals/corr/abs-2510-26800","url":"https://dblp.org/rec/journals/corr/abs-2510-26800","title":"OmniX: From Unified Panoramic Generation and Perception to Graphics-Ready 3D Scenes.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2510.26800","numberOfCreators":7,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2510-26800","https://doi.org/10.48550/ARXIV.2510.26800"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-26800","documentUrl":null,"type":"Informal","arxivId":"2510.26800","arxivUrl":"https://arxiv.org/abs/2510.26800"},{"key":"journals/corr/abs-2512-07503","url":"https://dblp.org/rec/journals/corr/abs-2512-07503","title":"SJD++: Improved Speculative Jacobi Decoding for Training-free Acceleration of Discrete Auto-regressive Text-to-Image Generation.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2512.07503","numberOfCreators":9,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2512-07503","https://doi.org/10.48550/ARXIV.2512.07503"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-07503","documentUrl":null,"type":"Informal","arxivId":"2512.07503","arxivUrl":"https://arxiv.org/abs/2512.07503"},{"key":"journals/corr/abs-2512-08186","url":"https://dblp.org/rec/journals/corr/abs-2512-08186","title":"Ground Slow, Move Fast: A Dual-System Foundation Model for Generalizable Vision-and-Language Navigation.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2512.08186","numberOfCreators":11,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2512-08186","https://doi.org/10.48550/ARXIV.2512.08186"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-08186","documentUrl":null,"type":"Informal","arxivId":"2512.08186","arxivUrl":"https://arxiv.org/abs/2512.08186"},{"key":"journals/corr/abs-2512-08765","url":"https://dblp.org/rec/journals/corr/abs-2512-08765","title":"Wan-Move: Motion-controllable Video Generation via Latent Trajectory Guidance.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2512.08765","numberOfCreators":13,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2512-08765","https://doi.org/10.48550/ARXIV.2512.08765"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-08765","documentUrl":null,"type":"Informal","arxivId":"2512.08765","arxivUrl":"https://arxiv.org/abs/2512.08765"},{"key":"journals/corr/abs-2512-22342","url":"https://dblp.org/rec/journals/corr/abs-2512-22342","title":"VL-LN Bench: Towards Long-horizon Goal-oriented Navigation with Active Dialogs.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2512.22342","numberOfCreators":9,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2512-22342","https://doi.org/10.48550/ARXIV.2512.22342"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-22342","documentUrl":null,"type":"Informal","arxivId":"2512.22342","arxivUrl":"https://arxiv.org/abs/2512.22342"}],"excludedFormal":[],"otherRecords":[],"matchedName":"Xihui Liu","databaseLabel":"Xihui Liu","databaseMetadata":{"type":["https://dblp.org/rdf/schema#Person","https://dblp.org/rdf/schema#Creator"],"label":["Xihui Liu"],"orcid":["https://orcid.org/0000-0003-1831-9952"]},"rawFormalRecordCount2025":32,"signatureAudit":{"completedAt":"2026-10-19","frozen":true,"scope":"对 B 组 39 个数值档案的全部 1074 条原始 2025 正式记录扫描 DBLP author-signature ORCID 和机构；复用既有 59 条 Crossref 核验，补查 6 条新触发记录。重点核查不同 ORCID，以及只有预期机构之外机构的条目。本轮不扩展为所有作者逐篇全文审计。","formalRecordCoverage":32,"orcidCounts":{"https://orcid.org/0000-0003-1831-9952":7},"institutionCounts":{"Chinese University of Hong Kong (CUHK)":1,"Nvidia":1,"Shanghai Artificial Intelligence Laboratory":1,"Shanghai Jiao Tong University (SJTU)":1,"University of Hong Kong (HKU)":23},"caveat":"机构名称可能由 DBLP 自动映射而失真；多 ORCID 也不自动等于异人。只有有原始资料支撑的错归才作确认排除，未解决分支则暂停总数。"},"labName":"HKU-MMLab","labUrl":"https://mmlab.hk/about-us","labEvidence":"本人主页当前身份栏在香港大学下明确列 HKU-MMLab，并链接其 about-us 页面；没有将博士阶段的 CUHK MMLab 作为当前组。","labSourceUrl":"https://xh-liu.github.io/","sourceWarning":false,"excludedOther":[],"excludedHomonyms":[],"unassignedCandidates":[],"knownPreprintMinimum2025":null,"excludedMisattributed":[],"displayNotes":"身份已与原名单机构及公开资料核对确认。2025 年正式记录 32 条（会议 30、期刊 2），所有作者位置均计入，不表示主导或贡献份额；预印本 46 条单列，不加总。","labDisplayNotes":"个人主页在港大职位下列出 HKU-MMLab 并附链接。与罗平同组，去重后 90 条（两人共享 2 条），两人的数字不能直接相加。该组与港中文 MMLab、MMLab@NTU 分开计数。"},{"index":64,"name":"Yebin Liu","nameZh":"刘烨斌","role":"Professor","affiliation":"Tsinghua University","affiliationZh":"清华大学","source":"DBLP RDF via official SPARQL; primary-source identity checks","sourceUrl":"https://sparql.dblp.org/","profileUrl":"https://dblp.org/pid/84/1411.html","identifier":"84/1411","retrievedAt":"2026-10-19","count2025":17,"conference2025":9,"journal2025":8,"preprint2025":18,"status":"confirmed","notes":"","identityEvidence":[{"url":"https://dblp.org/pid/84/1411.html","evidence":"DBLP RDF 类型为 Person，消歧后名字为 Yebin Liu。机构元数据含：Tsinghua University, Beijing, China"}],"papers":[{"key":"conf/cvpr/LyuZG0CL0025","url":"https://dblp.org/rec/conf/cvpr/LyuZG0CL0025","title":"AniMer: Animal Pose and Shape Estimation Using Family Aware Transformer.","year":2025,"types":["Inproceedings"],"venue":"CVPR","doi":"https://doi.org/10.1109/CVPR52734.2025.01629","eventYear":2025,"numberOfCreators":8,"category":"conference","sources":["https://dblp.org/rec/conf/cvpr/LyuZG0CL0025","https://doi.org/10.1109/CVPR52734.2025.01629"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/LyuZG0CL0025","documentUrl":null,"type":"Inproceedings"},{"key":"conf/cvpr/PangSZT0Z0L25","url":"https://dblp.org/rec/conf/cvpr/PangSZT0Z0L25","title":"ManiVideo: Generating Hand-Object Manipulation Video with Dexterous and Generalizable Grasping.","year":2025,"types":["Inproceedings"],"venue":"CVPR","doi":"https://doi.org/10.1109/CVPR52734.2025.01140","eventYear":2025,"numberOfCreators":8,"category":"conference","sources":["https://dblp.org/rec/conf/cvpr/PangSZT0Z0L25","https://doi.org/10.1109/CVPR52734.2025.01140"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/PangSZT0Z0L25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/cvpr/TuLZZZZWL25","url":"https://dblp.org/rec/conf/cvpr/TuLZZZZWL25","title":"GBC-Splat: Generalizable Gaussian-Based Clothed Human Digitalization under Sparse RGB Cameras.","year":2025,"types":["Inproceedings"],"venue":"CVPR","doi":"https://doi.org/10.1109/CVPR52734.2025.02456","eventYear":2025,"numberOfCreators":8,"category":"conference","sources":["https://dblp.org/rec/conf/cvpr/TuLZZZZWL25","https://doi.org/10.1109/CVPR52734.2025.02456"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/TuLZZZZWL25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/eccv/ChenZLXL24","url":"https://dblp.org/rec/conf/eccv/ChenZLXL24","title":"MeshAvatar: Learning High-Quality Triangular Human Avatars from Multi-view Videos.","year":2025,"types":["Inproceedings"],"venue":"ECCV (68)","doi":"https://doi.org/10.1007/978-3-031-73113-6_15","eventYear":2024,"numberOfCreators":5,"category":"conference","sources":["https://dblp.org/rec/conf/eccv/ChenZLXL24","https://doi.org/10.1007/978-3-031-73113-6_15"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2024,"sourceUrl":"https://dblp.org/rec/conf/eccv/ChenZLXL24","documentUrl":null,"type":"Inproceedings"},{"key":"conf/eccv/XuWZSL24","url":"https://dblp.org/rec/conf/eccv/XuWZSL24","title":"3D Gaussian Parametric Head Model.","year":2025,"types":["Inproceedings"],"venue":"ECCV (35)","doi":"https://doi.org/10.1007/978-3-031-72761-0_8","eventYear":2024,"numberOfCreators":5,"category":"conference","sources":["https://dblp.org/rec/conf/eccv/XuWZSL24","https://doi.org/10.1007/978-3-031-72761-0_8"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2024,"sourceUrl":"https://dblp.org/rec/conf/eccv/XuWZSL24","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iccv/LiaoTPZZL25","url":"https://dblp.org/rec/conf/iccv/LiaoTPZZL25","title":"HADES: Human Avatar with Dynamic Explicit Hair Strands.","year":2025,"types":["Inproceedings"],"venue":"ICCV","doi":"https://doi.org/10.1109/ICCV51701.2025.01145","eventYear":2025,"numberOfCreators":6,"category":"conference","sources":["https://dblp.org/rec/conf/iccv/LiaoTPZZL25","https://doi.org/10.1109/ICCV51701.2025.01145"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/LiaoTPZZL25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iccv/ZhangLZPWLL25","url":"https://dblp.org/rec/conf/iccv/ZhangLZPWLL25","title":"A Plug-And-Play Physical Motion Restoration Approach for In-The-Wild High-Difficulty Motions.","year":2025,"types":["Inproceedings"],"venue":"ICCV","doi":"https://doi.org/10.1109/ICCV51701.2025.01234","eventYear":2025,"numberOfCreators":7,"category":"conference","sources":["https://dblp.org/rec/conf/iccv/ZhangLZPWLL25","https://doi.org/10.1109/ICCV51701.2025.01234"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/ZhangLZPWLL25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iclr/ZhaoXSXZ0LSL25","url":"https://dblp.org/rec/conf/iclr/ZhaoXSXZ0LSL25","title":"X-NeMo: Expressive Neural Motion Reenactment via Disentangled Latent Attention.","year":2025,"types":["Inproceedings"],"venue":"ICLR","doi":null,"eventYear":2025,"numberOfCreators":9,"category":"conference","sources":["https://dblp.org/rec/conf/iclr/ZhaoXSXZ0LSL25"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iclr/ZhaoXSXZ0LSL25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/nips/DangSZMLW25","url":"https://dblp.org/rec/conf/nips/DangSZMLW25","title":"SViMo: Synchronized Diffusion for Video and Motion Generation in Hand-object Interaction Scenarios.","year":2025,"types":["Inproceedings"],"venue":"NeurIPS","doi":null,"eventYear":2025,"numberOfCreators":6,"category":"conference","sources":["https://dblp.org/rec/conf/nips/DangSZMLW25"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/nips/DangSZMLW25","documentUrl":null,"type":"Inproceedings"},{"key":"journals/pami/TangZLH25","url":"https://dblp.org/rec/journals/pami/TangZLH25","title":"Human as Points: Explicit Point-Based 3D Human Reconstruction From Single-View RGB Images.","year":2025,"types":["Article"],"venue":"IEEE Trans. Pattern Anal. Mach. Intell.","doi":"https://doi.org/10.1109/TPAMI.2025.3552408","numberOfCreators":4,"category":"journal","sources":["https://dblp.org/rec/journals/pami/TangZLH25","https://doi.org/10.1109/TPAMI.2025.3552408"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/pami/TangZLH25","documentUrl":null,"type":"Article"},{"key":"journals/pami/WuZFLC25","url":"https://dblp.org/rec/journals/pami/WuZFLC25","title":"Geo-NI: Geometry-Aware Neural Interpolation for Light Field Rendering.","year":2025,"types":["Article"],"venue":"IEEE Trans. Pattern Anal. Mach. Intell.","doi":"https://doi.org/10.1109/TPAMI.2025.3594705","numberOfCreators":5,"category":"journal","sources":["https://dblp.org/rec/journals/pami/WuZFLC25","https://doi.org/10.1109/TPAMI.2025.3594705"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/pami/WuZFLC25","documentUrl":null,"type":"Article"},{"key":"journals/pami/ZhangZZZZSHL25","url":"https://dblp.org/rec/journals/pami/ZhangZZZZSHL25","title":"Ins-HOI: Instance Aware Human-Object Interactions Recovery.","year":2025,"types":["Article"],"venue":"IEEE Trans. Pattern Anal. Mach. Intell.","doi":"https://doi.org/10.1109/TPAMI.2025.3588268","numberOfCreators":8,"category":"journal","sources":["https://dblp.org/rec/journals/pami/ZhangZZZZSHL25","https://doi.org/10.1109/TPAMI.2025.3588268"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/pami/ZhangZZZZSHL25","documentUrl":null,"type":"Article"},{"key":"journals/tmm/LuoDYMXCGL25","url":"https://dblp.org/rec/journals/tmm/LuoDYMXCGL25","title":"TrAME: Trajectory-Anchored Multi-View Editing for Text-Guided 3D Gaussian Manipulation.","year":2025,"types":["Article"],"venue":"IEEE Trans. Multim.","doi":"https://doi.org/10.1109/TMM.2025.3557618","numberOfCreators":8,"category":"journal","sources":["https://dblp.org/rec/journals/tmm/LuoDYMXCGL25","https://doi.org/10.1109/TMM.2025.3557618"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/tmm/LuoDYMXCGL25","documentUrl":null,"type":"Article"},{"key":"journals/tog/ShaoXSYZCLW25","url":"https://dblp.org/rec/journals/tog/ShaoXSYZCLW25","title":"Interspatial Attention for Efficient 4D Human Video Generation.","year":2025,"types":["Article"],"venue":"ACM Trans. Graph.","doi":"https://doi.org/10.1145/3731165","numberOfCreators":8,"category":"journal","sources":["https://dblp.org/rec/journals/tog/ShaoXSYZCLW25","https://doi.org/10.1145/3731165"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/tog/ShaoXSYZCLW25","documentUrl":null,"type":"Article"},{"key":"journals/tvcg/ZhangZZZLL25","url":"https://dblp.org/rec/journals/tvcg/ZhangZZZLL25","title":"SpeechAct: Towards Generating Whole-Body Motion From Speech.","year":2025,"types":["Article"],"venue":"IEEE Trans. Vis. Comput. Graph.","doi":"https://doi.org/10.1109/TVCG.2025.3529611","numberOfCreators":6,"category":"journal","sources":["https://dblp.org/rec/journals/tvcg/ZhangZZZLL25","https://doi.org/10.1109/TVCG.2025.3529611"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/tvcg/ZhangZZZLL25","documentUrl":null,"type":"Article"},{"key":"journals/tvcg/ZhouLCCZYL25","url":"https://dblp.org/rec/journals/tvcg/ZhouLCCZYL25","title":"Real-Time High-Resolution View Synthesis of Complex Scenes With Explicit 3D Visibility Reasoning.","year":2025,"types":["Article"],"venue":"IEEE Trans. Vis. Comput. Graph.","doi":"https://doi.org/10.1109/TVCG.2024.3499874","numberOfCreators":7,"category":"journal","sources":["https://dblp.org/rec/journals/tvcg/ZhouLCCZYL25","https://doi.org/10.1109/TVCG.2024.3499874"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/tvcg/ZhouLCCZYL25","documentUrl":null,"type":"Article"},{"key":"journals/tvcg/ZhouYZWZJFL25","url":"https://dblp.org/rec/journals/tvcg/ZhouYZWZJFL25","title":"ProbIBR: Fast Image-Based Rendering With Learned Probability-Guided Sampling.","year":2025,"types":["Article"],"venue":"IEEE Trans. Vis. Comput. Graph.","doi":"https://doi.org/10.1109/TVCG.2024.3372152","numberOfCreators":8,"category":"journal","sources":["https://dblp.org/rec/journals/tvcg/ZhouYZWZJFL25","https://doi.org/10.1109/TVCG.2024.3372152"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/tvcg/ZhouYZWZJFL25","documentUrl":null,"type":"Article"}],"preprints":[{"key":"journals/corr/abs-2503-00382","url":"https://dblp.org/rec/journals/corr/abs-2503-00382","title":"EigenActor: Variant Body-Object Interaction Generation Evolved from Invariant Action Basis Reasoning.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2503.00382","numberOfCreators":6,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2503-00382","https://doi.org/10.48550/ARXIV.2503.00382"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-00382","documentUrl":null,"type":"Informal","arxivId":"2503.00382","arxivUrl":"https://arxiv.org/abs/2503.00382"},{"key":"journals/corr/abs-2503-21847","url":"https://dblp.org/rec/journals/corr/abs-2503-21847","title":"ReCoM: Realistic Co-Speech Motion Generation with Recurrent Embedded Transformer.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2503.21847","numberOfCreators":5,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2503-21847","https://doi.org/10.48550/ARXIV.2503.21847"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-21847","documentUrl":null,"type":"Informal","arxivId":"2503.21847","arxivUrl":"https://arxiv.org/abs/2503.21847"},{"key":"journals/corr/abs-2505-15800","url":"https://dblp.org/rec/journals/corr/abs-2505-15800","title":"Interspatial Attention for Efficient 4D Human Video Generation.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2505.15800","numberOfCreators":8,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2505-15800","https://doi.org/10.48550/ARXIV.2505.15800"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-15800","documentUrl":null,"type":"Informal","arxivId":"2505.15800","arxivUrl":"https://arxiv.org/abs/2505.15800"},{"key":"journals/corr/abs-2506-01579","url":"https://dblp.org/rec/journals/corr/abs-2506-01579","title":"HOSIG: Full-Body Human-Object-Scene Interaction Generation with Hierarchical Scene Perception.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2506.01579","numberOfCreators":5,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2506-01579","https://doi.org/10.48550/ARXIV.2506.01579"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-01579","documentUrl":null,"type":"Informal","arxivId":"2506.01579","arxivUrl":"https://arxiv.org/abs/2506.01579"},{"key":"journals/corr/abs-2506-02444","url":"https://dblp.org/rec/journals/corr/abs-2506-02444","title":"SViMo: Synchronized Diffusion for Video and Motion Generation in Hand-object Interaction Scenarios.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2506.02444","numberOfCreators":6,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2506-02444","https://doi.org/10.48550/ARXIV.2506.02444"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-02444","documentUrl":null,"type":"Informal","arxivId":"2506.02444","arxivUrl":"https://arxiv.org/abs/2506.02444"},{"key":"journals/corr/abs-2506-06645","url":"https://dblp.org/rec/journals/corr/abs-2506-06645","title":"Parametric Gaussian Human Model: Generalizable Prior for Efficient and Realistic Human Avatar Modeling.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2506.06645","numberOfCreators":6,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2506-06645","https://doi.org/10.48550/ARXIV.2506.06645"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-06645","documentUrl":null,"type":"Informal","arxivId":"2506.06645","arxivUrl":"https://arxiv.org/abs/2506.06645"},{"key":"journals/corr/abs-2506-09565","url":"https://dblp.org/rec/journals/corr/abs-2506-09565","title":"SemanticSplat: Feed-Forward 3D Scene Understanding with Language-Aware Gaussian Fields.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2506.09565","numberOfCreators":6,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2506-09565","https://doi.org/10.48550/ARXIV.2506.09565"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-09565","documentUrl":null,"type":"Informal","arxivId":"2506.09565","arxivUrl":"https://arxiv.org/abs/2506.09565"},{"key":"journals/corr/abs-2506-14135","url":"https://dblp.org/rec/journals/corr/abs-2506-14135","title":"GAF: Gaussian Action Field as a Dynamic World Model for Robotic Manipulation.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2506.14135","numberOfCreators":7,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2506-14135","https://doi.org/10.48550/ARXIV.2506.14135"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-14135","documentUrl":null,"type":"Informal","arxivId":"2506.14135","arxivUrl":"https://arxiv.org/abs/2506.14135"},{"key":"journals/corr/abs-2507-04258","url":"https://dblp.org/rec/journals/corr/abs-2507-04258","title":"MoReMouse: Monocular Reconstruction of Laboratory Mouse.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2507.04258","numberOfCreators":4,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2507-04258","https://doi.org/10.48550/ARXIV.2507.04258"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2507-04258","documentUrl":null,"type":"Informal","arxivId":"2507.04258","arxivUrl":"https://arxiv.org/abs/2507.04258"},{"key":"journals/corr/abs-2507-23143","url":"https://dblp.org/rec/journals/corr/abs-2507-23143","title":"X-NeMo: Expressive Neural Motion Reenactment via Disentangled Latent Attention.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2507.23143","numberOfCreators":9,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2507-23143","https://doi.org/10.48550/ARXIV.2507.23143"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2507-23143","documentUrl":null,"type":"Informal","arxivId":"2507.23143","arxivUrl":"https://arxiv.org/abs/2507.23143"},{"key":"journals/corr/abs-2508-00298","url":"https://dblp.org/rec/journals/corr/abs-2508-00298","title":"AniMer+: Unified Pose and Shape Estimation Across Mammalia and Aves via Family-Aware Transformer.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2508.00298","numberOfCreators":6,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2508-00298","https://doi.org/10.48550/ARXIV.2508.00298"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-00298","documentUrl":null,"type":"Informal","arxivId":"2508.00298","arxivUrl":"https://arxiv.org/abs/2508.00298"},{"key":"journals/corr/abs-2508-14036","url":"https://dblp.org/rec/journals/corr/abs-2508-14036","title":"GeoSAM2: Unleashing the Power of SAM2 for 3D Part Segmentation.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2508.14036","numberOfCreators":7,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2508-14036","https://doi.org/10.48550/ARXIV.2508.14036"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-14036","documentUrl":null,"type":"Informal","arxivId":"2508.14036","arxivUrl":"https://arxiv.org/abs/2508.14036"},{"key":"journals/corr/abs-2509-00403","url":"https://dblp.org/rec/journals/corr/abs-2509-00403","title":"DevilSight: Augmenting Monocular Human Avatar Reconstruction through a Virtual Perspective.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2509.00403","numberOfCreators":7,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2509-00403","https://doi.org/10.48550/ARXIV.2509.00403"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-00403","documentUrl":null,"type":"Informal","arxivId":"2509.00403","arxivUrl":"https://arxiv.org/abs/2509.00403"},{"key":"journals/corr/abs-2511-22704","url":"https://dblp.org/rec/journals/corr/abs-2511-22704","title":"Splat-SAP: Feed-Forward Gaussian Splatting for Human-Centered Scene with Scale-Aware Point Map Reconstruction.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2511.22704","numberOfCreators":7,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2511-22704","https://doi.org/10.48550/ARXIV.2511.22704"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2511-22704","documentUrl":null,"type":"Informal","arxivId":"2511.22704","arxivUrl":"https://arxiv.org/abs/2511.22704"},{"key":"journals/corr/abs-2512-03034","url":"https://dblp.org/rec/journals/corr/abs-2512-03034","title":"MAViD: A Multimodal Framework for Audio-Visual Dialogue Understanding and Generation.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2512.03034","numberOfCreators":9,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2512-03034","https://doi.org/10.48550/ARXIV.2512.03034"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-03034","documentUrl":null,"type":"Informal","arxivId":"2512.03034","arxivUrl":"https://arxiv.org/abs/2512.03034"},{"key":"journals/corr/abs-2512-03918","url":"https://dblp.org/rec/journals/corr/abs-2512-03918","title":"UniMo: Unifying 2D Video and 3D Human Motion with an Autoregressive Framework.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2512.03918","numberOfCreators":8,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2512-03918","https://doi.org/10.48550/ARXIV.2512.03918"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-03918","documentUrl":null,"type":"Informal","arxivId":"2512.03918","arxivUrl":"https://arxiv.org/abs/2512.03918"},{"key":"journals/corr/abs-2512-07381","url":"https://dblp.org/rec/journals/corr/abs-2512-07381","title":"Tessellation GS: Neural Mesh Gaussians for Robust Monocular Reconstruction of Dynamic Objects.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2512.07381","numberOfCreators":5,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2512-07381","https://doi.org/10.48550/ARXIV.2512.07381"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-07381","documentUrl":null,"type":"Informal","arxivId":"2512.07381","arxivUrl":"https://arxiv.org/abs/2512.07381"},{"key":"journals/corr/abs-2512-17717","url":"https://dblp.org/rec/journals/corr/abs-2512-17717","title":"FlexAvatar: Flexible Large Reconstruction Model for Animatable Gaussian Head Avatars with Detailed Deformation.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2512.17717","numberOfCreators":10,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2512-17717","https://doi.org/10.48550/ARXIV.2512.17717"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-17717","documentUrl":null,"type":"Informal","arxivId":"2512.17717","arxivUrl":"https://arxiv.org/abs/2512.17717"}],"excludedFormal":[],"otherRecords":[],"matchedName":"Yebin Liu","databaseLabel":"Yebin Liu","databaseMetadata":{"type":["https://dblp.org/rdf/schema#Person","https://dblp.org/rdf/schema#Creator"],"label":["Yebin Liu"],"affiliation":["Tsinghua University, Beijing, China"],"orcid":["https://orcid.org/0000-0003-3215-0225"],"primaryAffiliation":["Tsinghua University, Beijing, China"]},"rawFormalRecordCount2025":17,"signatureAudit":{"completedAt":"2026-10-19","frozen":true,"scope":"对 B 组 39 个数值档案的全部 1074 条原始 2025 正式记录扫描 DBLP author-signature ORCID 和机构；复用既有 59 条 Crossref 核验，补查 6 条新触发记录。重点核查不同 ORCID，以及只有预期机构之外机构的条目。本轮不扩展为所有作者逐篇全文审计。","formalRecordCoverage":17,"orcidCounts":{"https://orcid.org/0000-0003-3215-0225":10},"institutionCounts":{"Tsinghua University (THU)":15},"caveat":"机构名称可能由 DBLP 自动映射而失真；多 ORCID 也不自动等于异人。只有有原始资料支撑的错归才作确认排除，未解决分支则暂停总数。"},"labName":null,"labUrl":null,"labEvidence":"清华大学自动化系官方本人页没有提供可核实的当前独立实验室名。旧个人域名已跳转无关内容，因此未使用该域名作实验室证据。","labSourceUrl":"https://www.au.tsinghua.edu.cn/info/1096/1538.htm","sourceWarning":false,"excludedOther":[],"excludedHomonyms":[],"unassignedCandidates":[],"knownPreprintMinimum2025":null,"excludedMisattributed":[],"displayNotes":"身份已与原名单机构及公开资料核对确认。2025 年正式记录 17 条（会议 9、期刊 8），所有作者位置均计入，不表示主导或贡献份额；预印本 18 条单列，不加总。","labDisplayNotes":"清华自动化系官方本人页未写独立的实验室名称；旧个人域名已跳转到无关内容，不作证据。图中以「姓名及合作者」单列。"},{"index":65,"name":"Yuan Liu","nameZh":"刘缘","role":"Assistant Professor","affiliation":"The Hong Kong University of Science and Technology","affiliationZh":"香港科技大学","source":"DBLP RDF via official SPARQL; primary-source identity checks","sourceUrl":"https://sparql.dblp.org/","profileUrl":"https://dblp.org/pid/87/2948-25.html","identifier":"87/2948-25","retrievedAt":"2026-10-19","count2025":40,"conference2025":28,"journal2025":12,"preprint2025":28,"status":"matched_with_source_warning","notes":"排除 1 条数据库形式上属于期刊/会议的记录，逐条原因见 excludedFormal。 DBLP 的 primaryAffiliation 含历史机构；以原签名名单机构和本人履历交叉核对，未据旧机构另选同名者。 终审发现 1 条明确错归：DBLP 将牙科作者 Yuan Li 的论文挂入 Yuan Liu（刘缘）档案。已剔除该条，正式记录从 41 修正为 40；其余正式记录 signature 的非空 ORCID 与所选档案一致，机构为 HKUST/HKU/NTU/上海AI实验室或缺失。主数保留数据库归属警告，不再标普通确认。","identityEvidence":[{"url":"https://dblp.org/pid/87/2948-25.html","evidence":"DBLP RDF 类型为 Person，消歧后名字为 Yuan Liu 0025。机构元数据含：University of Hong Kong, Department of Computer Science, Hong Kong"},{"url":"https://liuyuan-pal.github.io/","evidence":"个人主页为香港科技大学 Yuan Liu，说明此前香港大学经历；与 DBLP 0025 的旧机构及论文列表一致。"},{"url":"https://liuyuan-pal.github.io/pub.html","evidence":"此本人或机构页面的正文与所选档案中 10 条 2025 记录标题匹配，其中 6 条为当前计入的正式记录（忽略空格、标点、大小写）。","matchedPaperKeys":["conf/cvpr/LiZLY0QCXCXLG25","conf/cvpr/LuHLDLC0YWL25","conf/iccv/WangLLWDY25","conf/nips/ChenLZZLZDWL25","conf/nips/LuXDLHDLYL25","conf/siggraph/GuYLLDS0L000025","journals/corr/abs-2501-03847","journals/corr/abs-2509-21965","journals/corr/abs-2510-07723","journals/corr/abs-2512-08358"],"matchedFormalPaperKeys":["conf/cvpr/LiZLY0QCXCXLG25","conf/cvpr/LuHLDLC0YWL25","conf/iccv/WangLLWDY25","conf/nips/ChenLZZLZDWL25","conf/nips/LuXDLHDLYL25","conf/siggraph/GuYLLDS0L000025"]},{"url":"https://api.crossref.org/works/10.1016/J.MEDIA.2024.103376","evidence":"出版商提交的作者 given=Yuan、family=Li，非 Liu；作者列表不存在 Yuan Liu。"},{"url":"https://hub.hku.hk/handle/10722/351703","evidence":"香港大学机构知识库同样列 Li, Yuan；与 Crossref 互相确认姓名错挂。"}],"papers":[{"key":"conf/3dim/LiuLLZLYT25","url":"https://dblp.org/rec/conf/3dim/LiuLLZLYT25","title":"Gaussianavatar-Editor: Photorealistic Animatable Gaussian Head Avatar Editor.","year":2025,"types":["Inproceedings"],"venue":"3DV","doi":"https://doi.org/10.1109/3DV66043.2025.00108","eventYear":2025,"numberOfCreators":7,"category":"conference","sources":["https://dblp.org/rec/conf/3dim/LiuLLZLYT25","https://doi.org/10.1109/3DV66043.2025.00108"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/3dim/LiuLLZLYT25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/cvm/SunSLMY25","url":"https://dblp.org/rec/conf/cvm/SunSLMY25","title":"Extreme Two-View Geometry From Object Poses with Diffusion Models.","year":2025,"types":["Inproceedings"],"venue":"CVM (2)","doi":"https://doi.org/10.1007/978-981-96-5812-1_16","eventYear":2025,"numberOfCreators":5,"category":"conference","sources":["https://dblp.org/rec/conf/cvm/SunSLMY25","https://doi.org/10.1007/978-981-96-5812-1_16"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/cvm/SunSLMY25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/cvpr/LiLLLZWLWG25","url":"https://dblp.org/rec/conf/cvpr/LiLLLZWLWG25","title":"CADDreamer: CAD Object Generation from Single-view Images.","year":2025,"types":["Inproceedings"],"venue":"CVPR","doi":"https://doi.org/10.1109/CVPR52734.2025.01998","eventYear":2025,"numberOfCreators":9,"category":"conference","sources":["https://dblp.org/rec/conf/cvpr/LiLLLZWLWG25","https://doi.org/10.1109/CVPR52734.2025.01998"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/LiLLLZWLWG25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/cvpr/LiZLY0QCXCXLG25","url":"https://dblp.org/rec/conf/cvpr/LiZLY0QCXCXLG25","title":"PSHuman: Photorealistic Single-image 3D Human Reconstruction using Cross-Scale Multiview Diffusion and Explicit Remeshing.","year":2025,"types":["Inproceedings"],"venue":"CVPR","doi":"https://doi.org/10.1109/CVPR52734.2025.01492","eventYear":2025,"numberOfCreators":12,"category":"conference","sources":["https://dblp.org/rec/conf/cvpr/LiZLY0QCXCXLG25","https://doi.org/10.1109/CVPR52734.2025.01492"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/LiZLY0QCXCXLG25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/cvpr/LiuLY0HTMW25","url":"https://dblp.org/rec/conf/cvpr/LiuLY0HTMW25","title":"EasyHOI: Unleashing the Power of Large Models for Reconstructing Hand-Object Interactions in the Wild.","year":2025,"types":["Inproceedings"],"venue":"CVPR","doi":"https://doi.org/10.1109/CVPR52734.2025.00660","eventYear":2025,"numberOfCreators":8,"category":"conference","sources":["https://dblp.org/rec/conf/cvpr/LiuLY0HTMW25","https://doi.org/10.1109/CVPR52734.2025.00660"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/LiuLY0HTMW25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/cvpr/LuHLDLC0YWL25","url":"https://dblp.org/rec/conf/cvpr/LuHLDLC0YWL25","title":"Align3R: Aligned Monocular Depth Estimation for Dynamic Videos.","year":2025,"types":["Inproceedings"],"venue":"CVPR","doi":"https://doi.org/10.1109/CVPR52734.2025.02125","eventYear":2025,"numberOfCreators":10,"category":"conference","sources":["https://dblp.org/rec/conf/cvpr/LuHLDLC0YWL25","https://doi.org/10.1109/CVPR52734.2025.02125"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/LuHLDLC0YWL25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/eccv/ChenPYLPLZ24","url":"https://dblp.org/rec/conf/eccv/ChenPYLPLZ24","title":"IntrinsicAnything: Learning Diffusion Priors for Inverse Rendering Under Unknown Illumination.","year":2025,"types":["Inproceedings"],"venue":"ECCV (60)","doi":"https://doi.org/10.1007/978-3-031-73027-6_26","eventYear":2024,"numberOfCreators":7,"category":"conference","sources":["https://dblp.org/rec/conf/eccv/ChenPYLPLZ24","https://doi.org/10.1007/978-3-031-73027-6_26"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2024,"sourceUrl":"https://dblp.org/rec/conf/eccv/ChenPYLPLZ24","documentUrl":null,"type":"Inproceedings"},{"key":"conf/eccv/LiuDZLZZYWHLCL24","url":"https://dblp.org/rec/conf/eccv/LiuDZLZZYWHLCL24","title":"MMBench: Is Your Multi-modal Model an All-Around Player?","year":2025,"types":["Inproceedings"],"venue":"ECCV (6)","doi":"https://doi.org/10.1007/978-3-031-72658-3_13","eventYear":2024,"numberOfCreators":12,"category":"conference","sources":["https://dblp.org/rec/conf/eccv/LiuDZLZZYWHLCL24","https://doi.org/10.1007/978-3-031-72658-3_13"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2024,"sourceUrl":"https://dblp.org/rec/conf/eccv/LiuDZLZZYWHLCL24","documentUrl":null,"type":"Inproceedings"},{"key":"conf/eccv/WangLDYLLXSLW24","url":"https://dblp.org/rec/conf/eccv/WangLDYLLXSLW24","title":"Disentangled Clothed Avatar Generation from Text Descriptions.","year":2025,"types":["Inproceedings"],"venue":"ECCV (52)","doi":"https://doi.org/10.1007/978-3-031-72943-0_22","eventYear":2024,"numberOfCreators":10,"category":"conference","sources":["https://dblp.org/rec/conf/eccv/WangLDYLLXSLW24","https://doi.org/10.1007/978-3-031-72943-0_22"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2024,"sourceUrl":"https://dblp.org/rec/conf/eccv/WangLDYLLXSLW24","documentUrl":null,"type":"Inproceedings"},{"key":"conf/eccv/XuLZLCDY24","url":"https://dblp.org/rec/conf/eccv/XuLZLCDY24","title":"Explicitly Guided Information Interaction Network for Cross-Modal Point Cloud Completion.","year":2025,"types":["Inproceedings"],"venue":"ECCV (12)","doi":"https://doi.org/10.1007/978-3-031-73254-6_24","eventYear":2024,"numberOfCreators":7,"category":"conference","sources":["https://dblp.org/rec/conf/eccv/XuLZLCDY24","https://doi.org/10.1007/978-3-031-73254-6_24"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2024,"sourceUrl":"https://dblp.org/rec/conf/eccv/XuLZLCDY24","documentUrl":null,"type":"Inproceedings"},{"key":"conf/eccv/YuDLLLLMKHTLW24","url":"https://dblp.org/rec/conf/eccv/YuDLLLLMKHTLW24","title":"Surf-D: Generating High-Quality Surfaces of Arbitrary Topologies Using Diffusion Models.","year":2025,"types":["Inproceedings"],"venue":"ECCV (39)","doi":"https://doi.org/10.1007/978-3-031-72933-1_24","eventYear":2024,"numberOfCreators":12,"category":"conference","sources":["https://dblp.org/rec/conf/eccv/YuDLLLLMKHTLW24","https://doi.org/10.1007/978-3-031-72933-1_24"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2024,"sourceUrl":"https://dblp.org/rec/conf/eccv/YuDLLLLMKHTLW24","documentUrl":null,"type":"Inproceedings"},{"key":"conf/eccv/ZhouDCLWWLKWL24","url":"https://dblp.org/rec/conf/eccv/ZhouDCLWWLKWL24","title":"EMDM: Efficient Motion Diffusion Model for Fast and High-Quality Motion Generation.","year":2025,"types":["Inproceedings"],"venue":"ECCV (2)","doi":"https://doi.org/10.1007/978-3-031-72627-9_2","eventYear":2024,"numberOfCreators":10,"category":"conference","sources":["https://dblp.org/rec/conf/eccv/ZhouDCLWWLKWL24","https://doi.org/10.1007/978-3-031-72627-9_2"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2024,"sourceUrl":"https://dblp.org/rec/conf/eccv/ZhouDCLWWLKWL24","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iccv/RenZXPLWZL25","url":"https://dblp.org/rec/conf/iccv/RenZXPLWZL25","title":"GauUpdate: New Object Insertion in 3D Gaussian Fields with Consistent Global Illumination.","year":2025,"types":["Inproceedings"],"venue":"ICCV","doi":"https://doi.org/10.1109/ICCV51701.2025.02661","eventYear":2025,"numberOfCreators":8,"category":"conference","sources":["https://dblp.org/rec/conf/iccv/RenZXPLWZL25","https://doi.org/10.1109/ICCV51701.2025.02661"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/RenZXPLWZL25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iccv/WangLLWDY25","url":"https://dblp.org/rec/conf/iccv/WangLLWDY25","title":"Vistadream: Sampling Multiview Consistent Images for Single-View Scene Reconstruction.","year":2025,"types":["Inproceedings"],"venue":"ICCV","doi":"https://doi.org/10.1109/ICCV51701.2025.02485","eventYear":2025,"numberOfCreators":6,"category":"conference","sources":["https://dblp.org/rec/conf/iccv/WangLLWDY25","https://doi.org/10.1109/ICCV51701.2025.02485"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/WangLLWDY25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iccv/ZhangTHPGLHYZLCY25","url":"https://dblp.org/rec/conf/iccv/ZhangTHPGLHYZLCY25","title":"Epona: Autoregressive Diffusion World Model for Autonomous Driving.","year":2025,"types":["Inproceedings"],"venue":"ICCV","doi":"https://doi.org/10.1109/ICCV51701.2025.02527","eventYear":2025,"numberOfCreators":12,"category":"conference","sources":["https://dblp.org/rec/conf/iccv/ZhangTHPGLHYZLCY25","https://doi.org/10.1109/ICCV51701.2025.02527"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/ZhangTHPGLHYZLCY25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iclr/Huang0Z0DY25","url":"https://dblp.org/rec/conf/iclr/Huang0Z0DY25","title":"MVTokenFlow: High-quality 4D Content Generation using Multiview Token Flow.","year":2025,"types":["Inproceedings"],"venue":"ICLR","doi":null,"eventYear":2025,"numberOfCreators":6,"category":"conference","sources":["https://dblp.org/rec/conf/iclr/Huang0Z0DY25"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iclr/Huang0Z0DY25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iclr/Li0CLDMYLW0Y25","url":"https://dblp.org/rec/conf/iclr/Li0CLDMYLW0Y25","title":"CityAnchor: City-scale 3D Visual Grounding with Multi-modality LLMs.","year":2025,"types":["Inproceedings"],"venue":"ICLR","doi":null,"eventYear":2025,"numberOfCreators":11,"category":"conference","sources":["https://dblp.org/rec/conf/iclr/Li0CLDMYLW0Y25"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iclr/Li0CLDMYLW0Y25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iclr/Liu00L0WH25","url":"https://dblp.org/rec/conf/iclr/Liu00L0WH25","title":"MoDGS: Dynamic Gaussian Splatting from Casually-captured Monocular Videos with Depth Priors.","year":2025,"types":["Inproceedings"],"venue":"ICLR","doi":null,"eventYear":2025,"numberOfCreators":7,"category":"conference","sources":["https://dblp.org/rec/conf/iclr/Liu00L0WH25"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iclr/Liu00L0WH25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iclr/WuD0S0Y0LCKGTWL25","url":"https://dblp.org/rec/conf/iclr/WuD0S0Y0LCKGTWL25","title":"DICE: End-to-end Deformation Capture of Hand-Face Interactions from a Single Image.","year":2025,"types":["Inproceedings"],"venue":"ICLR","doi":null,"eventYear":2025,"numberOfCreators":14,"category":"conference","sources":["https://dblp.org/rec/conf/iclr/WuD0S0Y0LCKGTWL25"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iclr/WuD0S0Y0LCKGTWL25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/nips/ChenLZZLZDWL25","url":"https://dblp.org/rec/conf/nips/ChenLZZLZDWL25","title":"SyncHuman: Synchronizing 2D and 3D Generative Models for Single-view Human Reconstruction.","year":2025,"types":["Inproceedings"],"venue":"NeurIPS","doi":null,"eventYear":2025,"numberOfCreators":9,"category":"conference","sources":["https://dblp.org/rec/conf/nips/ChenLZZLZDWL25"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/nips/ChenLZZLZDWL25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/nips/LuXDLHDLYL25","url":"https://dblp.org/rec/conf/nips/LuXDLHDLYL25","title":"TrackingWorld: World-centric Monocular 3D Tracking of Almost All Pixels.","year":2025,"types":["Inproceedings"],"venue":"NeurIPS","doi":null,"eventYear":2025,"numberOfCreators":9,"category":"conference","sources":["https://dblp.org/rec/conf/nips/LuXDLHDLYL25"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/nips/LuXDLHDLYL25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/nips/WangCHDLGL25","url":"https://dblp.org/rec/conf/nips/WangCHDLGL25","title":"PhysCtrl: Generative Physics for Controllable and Physics-Grounded Video Generation.","year":2025,"types":["Inproceedings"],"venue":"NeurIPS","doi":null,"eventYear":2025,"numberOfCreators":7,"category":"conference","sources":["https://dblp.org/rec/conf/nips/WangCHDLGL25"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/nips/WangCHDLGL25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/nips/XuDSPHWLLMWK25","url":"https://dblp.org/rec/conf/nips/XuDSPHWLLMWK25","title":"🎧MOSPA: Human Motion Generation Driven by Spatial Audio.","year":2025,"types":["Inproceedings"],"venue":"NeurIPS","doi":null,"eventYear":2025,"numberOfCreators":11,"category":"conference","sources":["https://dblp.org/rec/conf/nips/XuDSPHWLLMWK25"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/nips/XuDSPHWLLMWK25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/siggraph/GuYLLDS0L000025","url":"https://dblp.org/rec/conf/siggraph/GuYLLDS0L000025","title":"Diffusion as Shader: 3D-aware Video Diffusion for Versatile Video Generation Control.","year":2025,"types":["Inproceedings"],"venue":"SIGGRAPH (Conference Paper Track)","doi":"https://doi.org/10.1145/3721238.3730607","eventYear":2025,"numberOfCreators":12,"category":"conference","sources":["https://dblp.org/rec/conf/siggraph/GuYLLDS0L000025","https://doi.org/10.1145/3721238.3730607"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/siggraph/GuYLLDS0L000025","documentUrl":null,"type":"Inproceedings"},{"key":"conf/siggraph/LiMC000LS0G25","url":"https://dblp.org/rec/conf/siggraph/LiMC000LS0G25","title":"CMD: Controllable Multiview Diffusion for 3D Editing and Progressive Generation.","year":2025,"types":["Inproceedings"],"venue":"SIGGRAPH (Conference Paper Track)","doi":"https://doi.org/10.1145/3721238.3730722","eventYear":2025,"numberOfCreators":10,"category":"conference","sources":["https://dblp.org/rec/conf/siggraph/LiMC000LS0G25","https://doi.org/10.1145/3721238.3730722"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/siggraph/LiMC000LS0G25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/siggraph/Wang000DLGK0025","url":"https://dblp.org/rec/conf/siggraph/Wang000DLGK0025","title":"PDT: Point Distribution Transformation with Diffusion Models.","year":2025,"types":["Inproceedings"],"venue":"SIGGRAPH (Conference Paper Track)","doi":"https://doi.org/10.1145/3721238.3730717","eventYear":2025,"numberOfCreators":10,"category":"conference","sources":["https://dblp.org/rec/conf/siggraph/Wang000DLGK0025","https://doi.org/10.1145/3721238.3730717"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/siggraph/Wang000DLGK0025","documentUrl":null,"type":"Inproceedings"},{"key":"conf/siggrapha/Zhang00WYSY0025","url":"https://dblp.org/rec/conf/siggrapha/Zhang00WYSY0025","title":"SPGen: Spherical Projection as Consistent and Flexible Representation for Single Image 3D Shape Generation.","year":2025,"types":["Inproceedings"],"venue":"SIGGRAPH Asia","doi":"https://doi.org/10.1145/3757377.3763959","eventYear":2025,"numberOfCreators":9,"category":"conference","sources":["https://dblp.org/rec/conf/siggrapha/Zhang00WYSY0025","https://doi.org/10.1145/3757377.3763959"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/siggrapha/Zhang00WYSY0025","documentUrl":null,"type":"Inproceedings"},{"key":"conf/wacv/0001S0MY25","url":"https://dblp.org/rec/conf/wacv/0001S0MY25","title":"Generalizable Single-View Object Pose Estimation by Two-Side Generating and Matching.","year":2025,"types":["Inproceedings"],"venue":"WACV","doi":"https://doi.org/10.1109/WACV61041.2025.00063","eventYear":2025,"numberOfCreators":5,"category":"conference","sources":["https://dblp.org/rec/conf/wacv/0001S0MY25","https://doi.org/10.1109/WACV61041.2025.00063"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/wacv/0001S0MY25","documentUrl":null,"type":"Inproceedings"},{"key":"journals/cvm/LiuLLLW25","url":"https://dblp.org/rec/journals/cvm/LiuLLLW25","title":"Sem-iNeRF: Camera Pose Refinement by Inverting Neural Radiance Fields with Semantic Feature Consistency.","year":2025,"types":["Article"],"venue":"Comput. Vis. Media","doi":"https://doi.org/10.26599/CVM.2025.9450404","numberOfCreators":5,"category":"journal","sources":["https://dblp.org/rec/journals/cvm/LiuLLLW25","https://doi.org/10.26599/CVM.2025.9450404"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/cvm/LiuLLLW25","documentUrl":null,"type":"Article"},{"key":"journals/pami/YangZWMHLW25","url":"https://dblp.org/rec/journals/pami/YangZWMHLW25","title":"Monge-Ampere Regularization for Learning Arbitrary Shapes From Point Clouds.","year":2025,"types":["Article"],"venue":"IEEE Trans. Pattern Anal. Mach. Intell.","doi":"https://doi.org/10.1109/TPAMI.2025.3563601","numberOfCreators":7,"category":"journal","sources":["https://dblp.org/rec/journals/pami/YangZWMHLW25","https://doi.org/10.1109/TPAMI.2025.3563601"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/pami/YangZWMHLW25","documentUrl":null,"type":"Article"},{"key":"journals/ral/LuZWRLDY25","url":"https://dblp.org/rec/journals/ral/LuZWRLDY25","title":"Exploiting Motion Prior for Accurate Pose Estimation of Dashboard Cameras.","year":2025,"types":["Article"],"venue":"IEEE Robotics Autom. Lett.","doi":"https://doi.org/10.1109/LRA.2024.3511381","numberOfCreators":7,"category":"journal","sources":["https://dblp.org/rec/journals/ral/LuZWRLDY25","https://doi.org/10.1109/LRA.2024.3511381"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/ral/LuZWRLDY25","documentUrl":null,"type":"Article"},{"key":"journals/tmi/LiuFLWLSC25","url":"https://dblp.org/rec/journals/tmi/LiuFLWLSC25","title":"Geometry-Aware Attenuation Learning for Sparse-View CBCT Reconstruction.","year":2025,"types":["Article"],"venue":"IEEE Trans. Medical Imaging","doi":"https://doi.org/10.1109/TMI.2024.3473970","numberOfCreators":7,"category":"journal","sources":["https://dblp.org/rec/journals/tmi/LiuFLWLSC25","https://doi.org/10.1109/TMI.2024.3473970"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/tmi/LiuFLWLSC25","documentUrl":null,"type":"Article"},{"key":"journals/tog/DongWXLLXZLTKKSW25","url":"https://dblp.org/rec/journals/tog/DongWXLLXZLTKKSW25","title":"CrossGen: Learning and Generating Cross Fields for Quad Meshing.","year":2025,"types":["Article"],"venue":"ACM Trans. Graph.","doi":"https://doi.org/10.1145/3763299","numberOfCreators":13,"category":"journal","sources":["https://dblp.org/rec/journals/tog/DongWXLLXZLTKKSW25","https://doi.org/10.1145/3763299"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/tog/DongWXLLXZLTKKSW25","documentUrl":null,"type":"Article"},{"key":"journals/tog/DongXDXLCXTKW25","url":"https://dblp.org/rec/journals/tog/DongXDXLCXTKW25","title":"KISSColor: Kinetic and Intuitive Stroke Stretching for Vector Drawing Colorization.","year":2025,"types":["Article"],"venue":"ACM Trans. Graph.","doi":"https://doi.org/10.1145/3763307","numberOfCreators":10,"category":"journal","sources":["https://dblp.org/rec/journals/tog/DongXDXLCXTKW25","https://doi.org/10.1145/3763307"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/tog/DongXDXLCXTKW25","documentUrl":null,"type":"Article"},{"key":"journals/tog/DouPLYFLWGLK25","url":"https://dblp.org/rec/journals/tog/DouPLYFLWGLK25","title":"CFC: Simulating Character-Fluid Coupling using a Two-Level World Model.","year":2025,"types":["Article"],"venue":"ACM Trans. Graph.","doi":"https://doi.org/10.1145/3763318","numberOfCreators":10,"category":"journal","sources":["https://dblp.org/rec/journals/tog/DouPLYFLWGLK25","https://doi.org/10.1145/3763318"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/tog/DouPLYFLWGLK25","documentUrl":null,"type":"Article"},{"key":"journals/tvcg/0049GLLL25","url":"https://dblp.org/rec/journals/tvcg/0049GLLL25","title":"GECO : Fast Generative Image-to-3D Within One SECOnd.","year":2025,"types":["Article"],"venue":"IEEE Trans. Vis. Comput. Graph.","doi":"https://doi.org/10.1109/TVCG.2025.3602405","numberOfCreators":5,"category":"journal","sources":["https://dblp.org/rec/journals/tvcg/0049GLLL25","https://doi.org/10.1109/TVCG.2025.3602405"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/tvcg/0049GLLL25","documentUrl":null,"type":"Article"},{"key":"journals/tvcg/LiLLLLLLWG25","url":"https://dblp.org/rec/journals/tvcg/LiLLLLLLWG25","title":"Multi-View Large Reconstruction Model via Geometry-Aware Positional Encoding and Attention.","year":2025,"types":["Article"],"venue":"IEEE Trans. Vis. Comput. Graph.","doi":"https://doi.org/10.1109/TVCG.2025.3572341","numberOfCreators":9,"category":"journal","sources":["https://dblp.org/rec/journals/tvcg/LiLLLLLLWG25","https://doi.org/10.1109/TVCG.2025.3572341"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/tvcg/LiLLLLLLWG25","documentUrl":null,"type":"Article"},{"key":"journals/tvcg/LinYLZHJKKW25","url":"https://dblp.org/rec/journals/tvcg/LinYLZHJKKW25","title":"On Optimal Sampling for Learning SDF Using MLPs Equipped With Positional Encoding.","year":2025,"types":["Article"],"venue":"IEEE Trans. Vis. Comput. Graph.","doi":"https://doi.org/10.1109/TVCG.2024.3522082","numberOfCreators":9,"category":"journal","sources":["https://dblp.org/rec/journals/tvcg/LinYLZHJKKW25","https://doi.org/10.1109/TVCG.2024.3522082"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/tvcg/LinYLZHJKKW25","documentUrl":null,"type":"Article"},{"key":"journals/tvcg/LiuLLWLLW25","url":"https://dblp.org/rec/journals/tvcg/LiuLLWLLW25","title":"NeRFBuff: Fast Neural Rendering via Inter-Frame Feature Buffering.","year":2025,"types":["Article"],"venue":"IEEE Trans. Vis. Comput. Graph.","doi":"https://doi.org/10.1109/TVCG.2024.3393715","numberOfCreators":7,"category":"journal","sources":["https://dblp.org/rec/journals/tvcg/LiuLLWLLW25","https://doi.org/10.1109/TVCG.2024.3393715"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/tvcg/LiuLLWLLW25","documentUrl":null,"type":"Article"},{"key":"journals/tvcg/WangDL0DGZ00G25","url":"https://dblp.org/rec/journals/tvcg/WangDL0DGZ00G25","title":"WonderHuman: Hallucinating Unseen Parts in Dynamic 3D Human Reconstruction.","year":2025,"types":["Article"],"venue":"IEEE Trans. Vis. Comput. Graph.","doi":"https://doi.org/10.1109/TVCG.2025.3618268","numberOfCreators":10,"category":"journal","sources":["https://dblp.org/rec/journals/tvcg/WangDL0DGZ00G25","https://doi.org/10.1109/TVCG.2025.3618268"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/tvcg/WangDL0DGZ00G25","documentUrl":null,"type":"Article"}],"preprints":[{"key":"journals/corr/abs-2501-03847","url":"https://dblp.org/rec/journals/corr/abs-2501-03847","title":"Diffusion as Shader: 3D-aware Video Diffusion for Versatile Video Generation Control.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2501.03847","numberOfCreators":12,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2501-03847","https://doi.org/10.48550/ARXIV.2501.03847"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2501-03847","documentUrl":null,"type":"Informal","arxivId":"2501.03847","arxivUrl":"https://arxiv.org/abs/2501.03847"},{"key":"journals/corr/abs-2501-09978","url":"https://dblp.org/rec/journals/corr/abs-2501-09978","title":"GaussianAvatar-Editor: Photorealistic Animatable Gaussian Head Avatar Editor.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2501.09978","numberOfCreators":7,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2501-09978","https://doi.org/10.48550/ARXIV.2501.09978"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2501-09978","documentUrl":null,"type":"Informal","arxivId":"2501.09978","arxivUrl":"https://arxiv.org/abs/2501.09978"},{"key":"journals/corr/abs-2502-01045","url":"https://dblp.org/rec/journals/corr/abs-2502-01045","title":"WonderHuman: Hallucinating Unseen Parts in Dynamic 3D Human Reconstruction.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2502.01045","numberOfCreators":10,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2502-01045","https://doi.org/10.48550/ARXIV.2502.01045"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2502-01045","documentUrl":null,"type":"Informal","arxivId":"2502.01045","arxivUrl":"https://arxiv.org/abs/2502.01045"},{"key":"journals/corr/abs-2502-11697","url":"https://dblp.org/rec/journals/corr/abs-2502-11697","title":"MVTokenFlow: High-quality 4D Content Generation using Multiview Token Flow.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2502.11697","numberOfCreators":6,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2502-11697","https://doi.org/10.48550/ARXIV.2502.11697"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2502-11697","documentUrl":null,"type":"Informal","arxivId":"2502.11697","arxivUrl":"https://arxiv.org/abs/2502.11697"},{"key":"journals/corr/abs-2502-20732","url":"https://dblp.org/rec/journals/corr/abs-2502-20732","title":"CADDreamer: CAD object Generation from Single-view Images.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2502.20732","numberOfCreators":9,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2502-20732","https://doi.org/10.48550/ARXIV.2502.20732"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2502-20732","documentUrl":null,"type":"Informal","arxivId":"2502.20732","arxivUrl":"https://arxiv.org/abs/2502.20732"},{"key":"journals/corr/abs-2503-20644","url":"https://dblp.org/rec/journals/corr/abs-2503-20644","title":"MMGen: Unified Multi-modal Image Generation and Understanding in One Go.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2503.20644","numberOfCreators":7,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2503-20644","https://doi.org/10.48550/ARXIV.2503.20644"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-20644","documentUrl":null,"type":"Informal","arxivId":"2503.20644","arxivUrl":"https://arxiv.org/abs/2503.20644"},{"key":"journals/corr/abs-2503-23162","url":"https://dblp.org/rec/journals/corr/abs-2503-23162","title":"NeuralGS: Bridging Neural Fields and 3D Gaussian Splatting for Compact 3D Representations.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2503.23162","numberOfCreators":9,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2503-23162","https://doi.org/10.48550/ARXIV.2503.23162"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-23162","documentUrl":null,"type":"Informal","arxivId":"2503.23162","arxivUrl":"https://arxiv.org/abs/2503.23162"},{"key":"journals/corr/abs-2504-04294","url":"https://dblp.org/rec/journals/corr/abs-2504-04294","title":"3R-GS: Best Practice in Optimizing Camera Poses Along with 3DGS.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2504.04294","numberOfCreators":6,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2504-04294","https://doi.org/10.48550/ARXIV.2504.04294"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2504-04294","documentUrl":null,"type":"Informal","arxivId":"2504.04294","arxivUrl":"https://arxiv.org/abs/2504.04294"},{"key":"journals/corr/abs-2505-07003","url":"https://dblp.org/rec/journals/corr/abs-2505-07003","title":"CMD: Controllable Multiview Diffusion for 3D Editing and Progressive Generation.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2505.07003","numberOfCreators":10,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2505-07003","https://doi.org/10.48550/ARXIV.2505.07003"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-07003","documentUrl":null,"type":"Informal","arxivId":"2505.07003","arxivUrl":"https://arxiv.org/abs/2505.07003"},{"key":"journals/corr/abs-2505-12703","url":"https://dblp.org/rec/journals/corr/abs-2505-12703","title":"SpatialLLM: From Multi-modality Data to Urban Spatial Intelligence.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2505.12703","numberOfCreators":6,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2505-12703","https://doi.org/10.48550/ARXIV.2505.12703"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-12703","documentUrl":null,"type":"Informal","arxivId":"2505.12703","arxivUrl":"https://arxiv.org/abs/2505.12703"},{"key":"journals/corr/abs-2506-07020","url":"https://dblp.org/rec/journals/corr/abs-2506-07020","title":"CrossGen: Learning and Generating Cross Fields for Quad Meshing.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2506.07020","numberOfCreators":13,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2506-07020","https://doi.org/10.48550/ARXIV.2506.07020"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-07020","documentUrl":null,"type":"Informal","arxivId":"2506.07020","arxivUrl":"https://arxiv.org/abs/2506.07020"},{"key":"journals/corr/abs-2506-24113","url":"https://dblp.org/rec/journals/corr/abs-2506-24113","title":"Epona: Autoregressive Diffusion World Model for Autonomous Driving.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2506.24113","numberOfCreators":12,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2506-24113","https://doi.org/10.48550/ARXIV.2506.24113"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-24113","documentUrl":null,"type":"Informal","arxivId":"2506.24113","arxivUrl":"https://arxiv.org/abs/2506.24113"},{"key":"journals/corr/abs-2507-11949","url":"https://dblp.org/rec/journals/corr/abs-2507-11949","title":"MOSPA: Human Motion Generation Driven by Spatial Audio.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2507.11949","numberOfCreators":11,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2507-11949","https://doi.org/10.48550/ARXIV.2507.11949"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2507-11949","documentUrl":null,"type":"Informal","arxivId":"2507.11949","arxivUrl":"https://arxiv.org/abs/2507.11949"},{"key":"journals/corr/abs-2507-18939","url":"https://dblp.org/rec/journals/corr/abs-2507-18939","title":"PDT: Point Distribution Transformation with Diffusion Models.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2507.18939","numberOfCreators":10,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2507-18939","https://doi.org/10.48550/ARXIV.2507.18939"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2507-18939","documentUrl":null,"type":"Informal","arxivId":"2507.18939","arxivUrl":"https://arxiv.org/abs/2507.18939"},{"key":"journals/corr/abs-2507-21045","url":"https://dblp.org/rec/journals/corr/abs-2507-21045","title":"Reconstructing 4D Spatial Intelligence: A Survey.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2507.21045","numberOfCreators":11,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2507-21045","https://doi.org/10.48550/ARXIV.2507.21045"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2507-21045","documentUrl":null,"type":"Informal","arxivId":"2507.21045","arxivUrl":"https://arxiv.org/abs/2507.21045"},{"key":"journals/corr/abs-2509-00066","url":"https://dblp.org/rec/journals/corr/abs-2509-00066","title":"T-MLP: Tailed Multi-Layer Perceptron for Level-of-Detail Signal Representation.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2509.00066","numberOfCreators":7,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2509-00066","https://doi.org/10.48550/ARXIV.2509.00066"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-00066","documentUrl":null,"type":"Informal","arxivId":"2509.00066","arxivUrl":"https://arxiv.org/abs/2509.00066"},{"key":"journals/corr/abs-2509-07552","url":"https://dblp.org/rec/journals/corr/abs-2509-07552","title":"PanoLAM: Large Avatar Model for Gaussian Full-Head Synthesis from One-shot Unposed Image.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2509.07552","numberOfCreators":8,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2509-07552","https://doi.org/10.48550/ARXIV.2509.07552"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-07552","documentUrl":null,"type":"Informal","arxivId":"2509.07552","arxivUrl":"https://arxiv.org/abs/2509.07552"},{"key":"journals/corr/abs-2509-12721","url":"https://dblp.org/rec/journals/corr/abs-2509-12721","title":"SPGen: Spherical Projection as Consistent and Flexible Representation for Single Image 3D Shape Generation.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2509.12721","numberOfCreators":9,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2509-12721","https://doi.org/10.48550/ARXIV.2509.12721"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-12721","documentUrl":null,"type":"Informal","arxivId":"2509.12721","arxivUrl":"https://arxiv.org/abs/2509.12721"},{"key":"journals/corr/abs-2509-14981","url":"https://dblp.org/rec/journals/corr/abs-2509-14981","title":"SPATIALGEN: Layout-guided 3D Indoor Scene Generation.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2509.14981","numberOfCreators":9,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2509-14981","https://doi.org/10.48550/ARXIV.2509.14981"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-14981","documentUrl":null,"type":"Informal","arxivId":"2509.14981","arxivUrl":"https://arxiv.org/abs/2509.14981"},{"key":"journals/corr/abs-2509-19995","url":"https://dblp.org/rec/journals/corr/abs-2509-19995","title":"MeshMosaic: Scaling Artist Mesh Generation via Local-to-Global Assembly.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2509.19995","numberOfCreators":12,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2509-19995","https://doi.org/10.48550/ARXIV.2509.19995"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-19995","documentUrl":null,"type":"Informal","arxivId":"2509.19995","arxivUrl":"https://arxiv.org/abs/2509.19995"},{"key":"journals/corr/abs-2509-20358","url":"https://dblp.org/rec/journals/corr/abs-2509-20358","title":"PhysCtrl: Generative Physics for Controllable and Physics-Grounded Video Generation.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2509.20358","numberOfCreators":7,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2509-20358","https://doi.org/10.48550/ARXIV.2509.20358"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-20358","documentUrl":null,"type":"Informal","arxivId":"2509.20358","arxivUrl":"https://arxiv.org/abs/2509.20358"},{"key":"journals/corr/abs-2509-21965","url":"https://dblp.org/rec/journals/corr/abs-2509-21965","title":"PartSAM: A Scalable Promptable Part Segmentation Model Trained on Native 3D Data.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2509.21965","numberOfCreators":9,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2509-21965","https://doi.org/10.48550/ARXIV.2509.21965"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-21965","documentUrl":null,"type":"Informal","arxivId":"2509.21965","arxivUrl":"https://arxiv.org/abs/2509.21965"},{"key":"journals/corr/abs-2510-07723","url":"https://dblp.org/rec/journals/corr/abs-2510-07723","title":"SyncHuman: Synchronizing 2D and 3D Generative Models for Single-view Human Reconstruction.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2510.07723","numberOfCreators":9,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2510-07723","https://doi.org/10.48550/ARXIV.2510.07723"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-07723","documentUrl":null,"type":"Informal","arxivId":"2510.07723","arxivUrl":"https://arxiv.org/abs/2510.07723"},{"key":"journals/corr/abs-2511-01767","url":"https://dblp.org/rec/journals/corr/abs-2511-01767","title":"Wonder3D++: Cross-domain Diffusion for High-fidelity 3D Generation from a Single Image.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2511.01767","numberOfCreators":10,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2511-01767","https://doi.org/10.48550/ARXIV.2511.01767"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2511-01767","documentUrl":null,"type":"Informal","arxivId":"2511.01767","arxivUrl":"https://arxiv.org/abs/2511.01767"},{"key":"journals/corr/abs-2511-11175","url":"https://dblp.org/rec/journals/corr/abs-2511-11175","title":"Dynamic Gaussian Scene Reconstruction from Unsynchronized Videos.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2511.11175","numberOfCreators":7,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2511-11175","https://doi.org/10.48550/ARXIV.2511.11175"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2511-11175","documentUrl":null,"type":"Informal","arxivId":"2511.11175","arxivUrl":"https://arxiv.org/abs/2511.11175"},{"key":"journals/corr/abs-2511-21978","url":"https://dblp.org/rec/journals/corr/abs-2511-21978","title":"PAT3D: Physics-Augmented Text-to-3D Scene Generation.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2511.21978","numberOfCreators":11,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2511-21978","https://doi.org/10.48550/ARXIV.2511.21978"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2511-21978","documentUrl":null,"type":"Informal","arxivId":"2511.21978","arxivUrl":"https://arxiv.org/abs/2511.21978"},{"key":"journals/corr/abs-2512-08358","url":"https://dblp.org/rec/journals/corr/abs-2512-08358","title":"TrackingWorld: World-centric Monocular 3D Tracking of Almost All Pixels.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2512.08358","numberOfCreators":9,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2512-08358","https://doi.org/10.48550/ARXIV.2512.08358"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-08358","documentUrl":null,"type":"Informal","arxivId":"2512.08358","arxivUrl":"https://arxiv.org/abs/2512.08358"},{"key":"journals/corr/abs-2512-22808","url":"https://dblp.org/rec/journals/corr/abs-2512-22808","title":"EgoReAct: Egocentric Video-Driven 3D Human Reaction Generation.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2512.22808","numberOfCreators":13,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2512-22808","https://doi.org/10.48550/ARXIV.2512.22808"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-22808","documentUrl":null,"type":"Informal","arxivId":"2512.22808","arxivUrl":"https://arxiv.org/abs/2512.22808"}],"excludedFormal":[{"key":"journals/mia/MeiDCFLLTS25","url":"https://dblp.org/rec/journals/mia/MeiDCFLLTS25","title":"Clinical knowledge-guided hybrid classification network for automatic periodontal disease diagnosis in X-ray image.","year":2025,"types":["Article"],"venue":"Medical Image Anal.","doi":"https://doi.org/10.1016/J.MEDIA.2024.103376","numberOfCreators":8,"category":"journal","sources":["https://dblp.org/rec/journals/mia/MeiDCFLLTS25","https://doi.org/10.1016/J.MEDIA.2024.103376"],"publicationYear":2025,"eventYear":null,"exclusionReason":"DBLP 错挂：Crossref 与香港大学机构知识库的作者是 Yuan Li（姓 Li），而非名单中的 Yuan Liu（刘缘）。原文机构为上海交通大学口腔医学系统，ORCID 0000-0002-0133-7516 也不同。","exclusionReasonCode":"confirmed_different_person","exclusionSources":["https://api.crossref.org/works/10.1016/J.MEDIA.2024.103376","https://hub.hku.hk/handle/10722/351703"],"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/mia/MeiDCFLLTS25","documentUrl":null,"type":"Article"}],"otherRecords":[],"matchedName":"Yuan Liu","databaseLabel":"Yuan Liu 0025","databaseMetadata":{"type":["https://dblp.org/rdf/schema#Person","https://dblp.org/rdf/schema#Creator"],"label":["Yuan Liu 0025"],"affiliation":["University of Hong Kong, Department of Computer Science, Hong Kong"],"homepage":["https://openreview.net/profile?id=~Yuan_Liu3"],"orcid":["https://orcid.org/0000-0003-2933-5667"],"primaryAffiliation":["University of Hong Kong, Department of Computer Science, Hong Kong"],"primaryHomepage":["https://openreview.net/profile?id=~Yuan_Liu3"]},"rawFormalRecordCount2025":41,"signatureAudit":{"completedAt":"2026-10-19","frozen":true,"scope":"对 B 组 39 个数值档案的全部 1074 条原始 2025 正式记录扫描 DBLP author-signature ORCID 和机构；复用既有 59 条 Crossref 核验，补查 6 条新触发记录。重点核查不同 ORCID，以及只有预期机构之外机构的条目。本轮不扩展为所有作者逐篇全文审计。","formalRecordCoverage":41,"orcidCounts":{"https://orcid.org/0000-0002-0133-7516":1,"https://orcid.org/0000-0003-2933-5667":15},"institutionCounts":{"Hong Kong University of Science and Technology (HKUST)":20,"Nanyang Technological University (NTU)":4,"Shanghai Artificial Intelligence Laboratory":1,"Shanghai Jiao Tong University (SJTU)":1,"University of Hong Kong (HKU)":14},"caveat":"机构名称可能由 DBLP 自动映射而失真；多 ORCID 也不自动等于异人。只有有原始资料支撑的错归才作确认排除，未解决分支则暂停总数。","decision":{"decision":"matched_with_source_warning","reason":"终审发现 1 条明确错归：DBLP 将牙科作者 Yuan Li 的论文挂入 Yuan Liu（刘缘）档案。已剔除该条，正式记录从 41 修正为 40；其余正式记录 signature 的非空 ORCID 与所选档案一致，机构为 HKUST/HKU/NTU/上海AI实验室或缺失。主数保留数据库归属警告，不再标普通确认。","flaggedKeys":["journals/mia/MeiDCFLLTS25"],"evidence":[{"url":"https://api.crossref.org/works/10.1016/J.MEDIA.2024.103376","evidence":"出版商提交的作者 given=Yuan、family=Li，非 Liu；作者列表不存在 Yuan Liu。"},{"url":"https://hub.hku.hk/handle/10722/351703","evidence":"香港大学机构知识库同样列 Li, Yuan；与 Crossref 互相确认姓名错挂。"}]}},"sourceWarning":true,"labName":"Intelligent Graphics Lab","labUrl":"https://github.com/IGL-HKUST","labEvidence":"本人主页明确写在 HKUST 任教并 leading the Intelligent Graphics Lab，组名直接链接官方 GitHub 组织。","labSourceUrl":"https://liuyuan-pal.github.io/","excludedOther":[],"excludedHomonyms":[],"unassignedCandidates":[],"knownPreprintMinimum2025":null,"excludedMisattributed":[],"displayNotes":"已剔除 1 条明确错归：DBLP 把牙科作者 Yuan Li 的论文挂入了本档案，正式记录由 41 条修正为 40 条，逐条原因见排除记录。其余署名的 ORCID 与档案一致。计入 40 条（会议 28、期刊 12）；预印本 28 条单列。该档案保留归属警告。","labDisplayNotes":"个人主页写明在港科大领导 Intelligent Graphics Lab，并链接其 GitHub 组织，据此归组。"},{"index":66,"name":"Zhen Liu","nameZh":"刘圳","role":"Assistant Professor","affiliation":"The Chinese University of Hong Kong, Shenzhen","affiliationZh":"香港中文大学（深圳）","source":"DBLP RDF via official SPARQL; primary-source identity checks","sourceUrl":"https://sparql.dblp.org/","profileUrl":"https://dblp.org/pid/77/35-19.html","identifier":"77/35-19","retrievedAt":"2026-10-19","count2025":3,"conference2025":3,"journal2025":0,"preprint2025":1,"status":"confirmed","notes":"DBLP 的 primaryAffiliation 含历史机构；以原签名名单机构和本人履历交叉核对，未据旧机构另选同名者。","identityEvidence":[{"url":"https://dblp.org/pid/77/35-19.html","evidence":"DBLP RDF 类型为 Person，消歧后名字为 Zhen Liu 0019。机构元数据含：Mila - Quebec AI Institute, Montreal, QC, Canada；Georgia Institute of Technology, Atlanta, GA, USA；University of Montreal, Montreal, QC, Canada"},{"url":"https://itszhen.com/","evidence":"个人主页为香港中文大学（深圳）Zhen Liu；DBLP 0019 直接链接该域名，Mila/Georgia Tech 为历史机构。"},{"url":"https://itszhen.com/publications.js?v=20261019-advising","evidence":"此本人或机构页面的正文与所选档案中 4 条 2025 记录标题匹配，其中 3 条为当前计入的正式记录（忽略空格、标点、大小写）。","matchedPaperKeys":["conf/cvpr/BianXX00LB025","conf/iclr/LiuXLBZ25","conf/iclr/QiuLF0XCTWBS25","journals/corr/abs-2506-09998"],"matchedFormalPaperKeys":["conf/cvpr/BianXX00LB025","conf/iclr/LiuXLBZ25","conf/iclr/QiuLF0XCTWBS25"]}],"papers":[{"key":"conf/cvpr/BianXX00LB025","url":"https://dblp.org/rec/conf/cvpr/BianXX00LB025","title":"ChatGarment: Garment Estimation, Generation and Editing via Large Language Models.","year":2025,"types":["Inproceedings"],"venue":"CVPR","doi":"https://doi.org/10.1109/CVPR52734.2025.00278","eventYear":2025,"numberOfCreators":8,"category":"conference","sources":["https://dblp.org/rec/conf/cvpr/BianXX00LB025","https://doi.org/10.1109/CVPR52734.2025.00278"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/BianXX00LB025","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iclr/LiuXLBZ25","url":"https://dblp.org/rec/conf/iclr/LiuXLBZ25","title":"Efficient Diversity-Preserving Diffusion Alignment via Gradient-Informed GFlowNets.","year":2025,"types":["Inproceedings"],"venue":"ICLR","doi":null,"eventYear":2025,"numberOfCreators":5,"category":"conference","sources":["https://dblp.org/rec/conf/iclr/LiuXLBZ25"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iclr/LiuXLBZ25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iclr/QiuLF0XCTWBS25","url":"https://dblp.org/rec/conf/iclr/QiuLF0XCTWBS25","title":"Can Large Language Models Understand Symbolic Graphics Programs?","year":2025,"types":["Inproceedings"],"venue":"ICLR","doi":null,"eventYear":2025,"numberOfCreators":10,"category":"conference","sources":["https://dblp.org/rec/conf/iclr/QiuLF0XCTWBS25"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iclr/QiuLF0XCTWBS25","documentUrl":null,"type":"Inproceedings"}],"preprints":[{"key":"journals/corr/abs-2506-09998","url":"https://dblp.org/rec/journals/corr/abs-2506-09998","title":"Flipping Against All Odds: Reducing LLM Coin Flip Bias via Verbalized Rejection Sampling.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2506.09998","numberOfCreators":6,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2506-09998","https://doi.org/10.48550/ARXIV.2506.09998"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-09998","documentUrl":null,"type":"Informal","arxivId":"2506.09998","arxivUrl":"https://arxiv.org/abs/2506.09998"}],"excludedFormal":[],"otherRecords":[],"matchedName":"Zhen Liu","databaseLabel":"Zhen Liu 0019","databaseMetadata":{"type":["https://dblp.org/rdf/schema#Person","https://dblp.org/rdf/schema#Creator"],"label":["Zhen Liu 0019"],"affiliation":["Mila - Quebec AI Institute, Montreal, QC, Canada","Georgia Institute of Technology, Atlanta, GA, USA","University of Montreal, Montreal, QC, Canada"],"homepage":["https://openreview.net/profile?id=~Zhen_Liu6","https://mila.quebec/en/person/zhen-liu/","http://itszhen.com/"],"orcid":["https://orcid.org/0009-0009-4599-3206"],"primaryAffiliation":["Mila - Quebec AI Institute, Montreal, QC, Canada"],"primaryHomepage":["http://itszhen.com/"]},"rawFormalRecordCount2025":3,"signatureAudit":{"completedAt":"2026-10-19","frozen":true,"scope":"对 B 组 39 个数值档案的全部 1074 条原始 2025 正式记录扫描 DBLP author-signature ORCID 和机构；复用既有 59 条 Crossref 核验，补查 6 条新触发记录。重点核查不同 ORCID，以及只有预期机构之外机构的条目。本轮不扩展为所有作者逐篇全文审计。","formalRecordCoverage":3,"orcidCounts":{},"institutionCounts":{"Manipal International University (MIU)":1,"Max Planck Institute for Intelligent Systems (MPI-IS)":1},"caveat":"机构名称可能由 DBLP 自动映射而失真；多 ORCID 也不自动等于异人。只有有原始资料支撑的错归才作确认排除，未解决分支则暂停总数。"},"labName":"Generative Intelligence Lab (GenLab)","labUrl":"https://thegenlab.ai/","labEvidence":"本人主页明确写在香港中文大学（深圳）lead the Generative Intelligence Lab (GenLab)，组名链接至 thegenlab.ai。","labSourceUrl":"https://itszhen.com/","sourceWarning":false,"excludedOther":[],"excludedHomonyms":[],"unassignedCandidates":[],"knownPreprintMinimum2025":null,"excludedMisattributed":[],"displayNotes":"DBLP 的机构字段含历史机构，已按原名单机构与本人履历交叉核对。计入 3 条，均为会议论文，所有作者位置均计入；预印本 1 条单列，不加总。","labDisplayNotes":"个人主页写明在港中文（深圳）领导 Generative Intelligence Lab（GenLab）。它与 CMU Jun-Yan Zhu 的同名实验室无关，不合并。"},{"index":67,"name":"Xiaoxiao Long","nameZh":"龙霄潇","role":"Tenure-Track Associate Professor","affiliation":"Nanjing University","affiliationZh":"南京大学","source":"DBLP RDF via official SPARQL; primary-source identity checks","sourceUrl":"https://sparql.dblp.org/","profileUrl":"https://dblp.org/pid/262/3688.html","identifier":"262/3688","retrievedAt":"2026-10-19","count2025":21,"conference2025":16,"journal2025":5,"preprint2025":19,"status":"confirmed","notes":"","identityEvidence":[{"url":"https://dblp.org/pid/262/3688.html","evidence":"DBLP RDF 类型为 Person，消歧后名字为 Xiaoxiao Long。此档案未提供可用机构元数据，以下以本人/机构/出版商来源补证。"},{"url":"https://www.xxlong.site/","evidence":"个人主页为南京大学 Xiao-Xiao Long / 龙霄潇，与 DBLP Xiaoxiao Long 拼写变体对应；发表页有多个共同标题。"},{"url":"https://www.xxlong.site/publication.html","evidence":"此本人或机构页面的正文与所选档案中 10 条 2025 记录标题匹配，其中 5 条为当前计入的正式记录（忽略空格、标点、大小写）。","matchedPaperKeys":["conf/cvpr/LiuLY0HTMW25","conf/eccv/FuYHWMTSLL24","conf/iccv/ZhangTHPGLHYZLCY25","conf/icra/WangYLZXGZ25","journals/corr/abs-2506-24113","journals/corr/abs-2507-00917","journals/corr/abs-2509-09676","journals/corr/abs-2511-02483","journals/corr/abs-2512-04939","journals/tvcg/LiuLLWLLW25"],"matchedFormalPaperKeys":["conf/cvpr/LiuLY0HTMW25","conf/eccv/FuYHWMTSLL24","conf/iccv/ZhangTHPGLHYZLCY25","conf/icra/WangYLZXGZ25","journals/tvcg/LiuLLWLLW25"]}],"papers":[{"key":"conf/aaai/HanZLWX25","url":"https://dblp.org/rec/conf/aaai/HanZLWX25","title":"GGS: Generalizable Gaussian Splatting for Lane Switching in Autonomous Driving.","year":2025,"types":["Inproceedings"],"venue":"AAAI","doi":"https://doi.org/10.1609/AAAI.V39I3.32344","eventYear":2025,"numberOfCreators":5,"category":"conference","sources":["https://dblp.org/rec/conf/aaai/HanZLWX25","https://doi.org/10.1609/AAAI.V39I3.32344"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/aaai/HanZLWX25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/cvpr/ChenZLLLLLLFT25","url":"https://dblp.org/rec/conf/cvpr/ChenZLLLLLLFT25","title":"Dora: Sampling and Benchmarking for 3D Shape Variational Auto-Encoders.","year":2025,"types":["Inproceedings"],"venue":"CVPR","doi":"https://doi.org/10.1109/CVPR52734.2025.01515","eventYear":2025,"numberOfCreators":10,"category":"conference","sources":["https://dblp.org/rec/conf/cvpr/ChenZLLLLLLFT25","https://doi.org/10.1109/CVPR52734.2025.01515"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/ChenZLLLLLLFT25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/cvpr/LiLLLZWLWG25","url":"https://dblp.org/rec/conf/cvpr/LiLLLZWLWG25","title":"CADDreamer: CAD Object Generation from Single-view Images.","year":2025,"types":["Inproceedings"],"venue":"CVPR","doi":"https://doi.org/10.1109/CVPR52734.2025.01998","eventYear":2025,"numberOfCreators":9,"category":"conference","sources":["https://dblp.org/rec/conf/cvpr/LiLLLZWLWG25","https://doi.org/10.1109/CVPR52734.2025.01998"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/LiLLLZWLWG25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/cvpr/LiLYCLCTL25","url":"https://dblp.org/rec/conf/cvpr/LiLYCLCTL25","title":"CraftsMan3D: High-fidelity Mesh Generation with 3D Native Diffusion and Interactive Geometry Refiner.","year":2025,"types":["Inproceedings"],"venue":"CVPR","doi":"https://doi.org/10.1109/CVPR52734.2025.00500","eventYear":2025,"numberOfCreators":8,"category":"conference","sources":["https://dblp.org/rec/conf/cvpr/LiLYCLCTL25","https://doi.org/10.1109/CVPR52734.2025.00500"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/LiLYCLCTL25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/cvpr/LiuLY0HTMW25","url":"https://dblp.org/rec/conf/cvpr/LiuLY0HTMW25","title":"EasyHOI: Unleashing the Power of Large Models for Reconstructing Hand-Object Interactions in the Wild.","year":2025,"types":["Inproceedings"],"venue":"CVPR","doi":"https://doi.org/10.1109/CVPR52734.2025.00660","eventYear":2025,"numberOfCreators":8,"category":"conference","sources":["https://dblp.org/rec/conf/cvpr/LiuLY0HTMW25","https://doi.org/10.1109/CVPR52734.2025.00660"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/LiuLY0HTMW25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/cvpr/Wang0LLHL25","url":"https://dblp.org/rec/conf/cvpr/Wang0LLHL25","title":"MAGE : Single Image to Material-Aware 3D via the Multi-View G-Buffer Estimation Model.","year":2025,"types":["Inproceedings"],"venue":"CVPR","doi":"https://doi.org/10.1109/CVPR52734.2025.01026","eventYear":2025,"numberOfCreators":6,"category":"conference","sources":["https://dblp.org/rec/conf/cvpr/Wang0LLHL25","https://doi.org/10.1109/CVPR52734.2025.01026"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/Wang0LLHL25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/cvpr/XingZHJHZLY25","url":"https://dblp.org/rec/conf/cvpr/XingZHJHZLY25","title":"GoalFlow: Goal-Driven Flow Matching for Multimodal Trajectories Generation in End-to-End Autonomous Driving.","year":2025,"types":["Inproceedings"],"venue":"CVPR","doi":"https://doi.org/10.1109/CVPR52734.2025.00157","eventYear":2025,"numberOfCreators":8,"category":"conference","sources":["https://dblp.org/rec/conf/cvpr/XingZHJHZLY25","https://doi.org/10.1109/CVPR52734.2025.00157"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/XingZHJHZLY25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/eccv/FuYHWMTSLL24","url":"https://dblp.org/rec/conf/eccv/FuYHWMTSLL24","title":"GeoWizard: Unleashing the Diffusion Priors for 3D Geometry Estimation from a Single Image.","year":2025,"types":["Inproceedings"],"venue":"ECCV (22)","doi":"https://doi.org/10.1007/978-3-031-72670-5_14","eventYear":2024,"numberOfCreators":9,"category":"conference","sources":["https://dblp.org/rec/conf/eccv/FuYHWMTSLL24","https://doi.org/10.1007/978-3-031-72670-5_14"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2024,"sourceUrl":"https://dblp.org/rec/conf/eccv/FuYHWMTSLL24","documentUrl":null,"type":"Inproceedings"},{"key":"conf/eccv/JinZLLZHLZYSZJLCZ24","url":"https://dblp.org/rec/conf/eccv/JinZLLZHLZYSZJLCZ24","title":"TOD3Cap: Towards 3D Dense Captioning in Outdoor Scenes.","year":2025,"types":["Inproceedings"],"venue":"ECCV (18)","doi":"https://doi.org/10.1007/978-3-031-72649-1_21","eventYear":2024,"numberOfCreators":15,"category":"conference","sources":["https://dblp.org/rec/conf/eccv/JinZLLZHLZYSZJLCZ24","https://doi.org/10.1007/978-3-031-72649-1_21"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2024,"sourceUrl":"https://dblp.org/rec/conf/eccv/JinZLLZHLZYSZJLCZ24","documentUrl":null,"type":"Inproceedings"},{"key":"conf/eccv/RenHYLSM24","url":"https://dblp.org/rec/conf/eccv/RenHYLSM24","title":"LiveHPS++: Robust and Coherent Motion Capture in Dynamic Free Environment.","year":2025,"types":["Inproceedings"],"venue":"ECCV (29)","doi":"https://doi.org/10.1007/978-3-031-73397-0_8","eventYear":2024,"numberOfCreators":6,"category":"conference","sources":["https://dblp.org/rec/conf/eccv/RenHYLSM24","https://doi.org/10.1007/978-3-031-73397-0_8"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2024,"sourceUrl":"https://dblp.org/rec/conf/eccv/RenHYLSM24","documentUrl":null,"type":"Inproceedings"},{"key":"conf/eccv/YuDLLLLMKHTLW24","url":"https://dblp.org/rec/conf/eccv/YuDLLLLMKHTLW24","title":"Surf-D: Generating High-Quality Surfaces of Arbitrary Topologies Using Diffusion Models.","year":2025,"types":["Inproceedings"],"venue":"ECCV (39)","doi":"https://doi.org/10.1007/978-3-031-72933-1_24","eventYear":2024,"numberOfCreators":12,"category":"conference","sources":["https://dblp.org/rec/conf/eccv/YuDLLLLMKHTLW24","https://doi.org/10.1007/978-3-031-72933-1_24"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2024,"sourceUrl":"https://dblp.org/rec/conf/eccv/YuDLLLLMKHTLW24","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iccv/DengYGZHRLT25","url":"https://dblp.org/rec/conf/iccv/DengYGZHRLT25","title":"Boost 3D Reconstruction Using Diffusion-Based Monocular Camera Calibration.","year":2025,"types":["Inproceedings"],"venue":"ICCV","doi":"https://doi.org/10.1109/ICCV51701.2025.00668","eventYear":2025,"numberOfCreators":8,"category":"conference","sources":["https://dblp.org/rec/conf/iccv/DengYGZHRLT25","https://doi.org/10.1109/ICCV51701.2025.00668"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/DengYGZHRLT25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iccv/ZhangTHPGLHYZLCY25","url":"https://dblp.org/rec/conf/iccv/ZhangTHPGLHYZLCY25","title":"Epona: Autoregressive Diffusion World Model for Autonomous Driving.","year":2025,"types":["Inproceedings"],"venue":"ICCV","doi":"https://doi.org/10.1109/ICCV51701.2025.02527","eventYear":2025,"numberOfCreators":12,"category":"conference","sources":["https://dblp.org/rec/conf/iccv/ZhangTHPGLHYZLCY25","https://doi.org/10.1109/ICCV51701.2025.02527"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/ZhangTHPGLHYZLCY25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/icra/WangYLZXGZ25","url":"https://dblp.org/rec/conf/icra/WangYLZXGZ25","title":"OccRWKV: Rethinking Efficient 3D Semantic Occupancy Prediction with Linear Complexity.","year":2025,"types":["Inproceedings"],"venue":"ICRA","doi":"https://doi.org/10.1109/ICRA55743.2025.11128516","eventYear":2025,"numberOfCreators":7,"category":"conference","sources":["https://dblp.org/rec/conf/icra/WangYLZXGZ25","https://doi.org/10.1109/ICRA55743.2025.11128516"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/icra/WangYLZXGZ25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iros/WangZXGGHSZLY25","url":"https://dblp.org/rec/conf/iros/WangZXGGHSZLY25","title":"ComDrive: Comfort-Oriented End-to-End Autonomous Driving.","year":2025,"types":["Inproceedings"],"venue":"IROS","doi":"https://doi.org/10.1109/IROS60139.2025.11247215","eventYear":2025,"numberOfCreators":10,"category":"conference","sources":["https://dblp.org/rec/conf/iros/WangZXGGHSZLY25","https://doi.org/10.1109/IROS60139.2025.11247215"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iros/WangZXGGHSZLY25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/siggraph/Wang000DLGK0025","url":"https://dblp.org/rec/conf/siggraph/Wang000DLGK0025","title":"PDT: Point Distribution Transformation with Diffusion Models.","year":2025,"types":["Inproceedings"],"venue":"SIGGRAPH (Conference Paper Track)","doi":"https://doi.org/10.1145/3721238.3730717","eventYear":2025,"numberOfCreators":10,"category":"conference","sources":["https://dblp.org/rec/conf/siggraph/Wang000DLGK0025","https://doi.org/10.1145/3721238.3730717"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/siggraph/Wang000DLGK0025","documentUrl":null,"type":"Inproceedings"},{"key":"journals/cvm/LiuLLLW25","url":"https://dblp.org/rec/journals/cvm/LiuLLLW25","title":"Sem-iNeRF: Camera Pose Refinement by Inverting Neural Radiance Fields with Semantic Feature Consistency.","year":2025,"types":["Article"],"venue":"Comput. Vis. Media","doi":"https://doi.org/10.26599/CVM.2025.9450404","numberOfCreators":5,"category":"journal","sources":["https://dblp.org/rec/journals/cvm/LiuLLLW25","https://doi.org/10.26599/CVM.2025.9450404"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/cvm/LiuLLLW25","documentUrl":null,"type":"Article"},{"key":"journals/tvcg/0049GLLL25","url":"https://dblp.org/rec/journals/tvcg/0049GLLL25","title":"GECO : Fast Generative Image-to-3D Within One SECOnd.","year":2025,"types":["Article"],"venue":"IEEE Trans. Vis. Comput. Graph.","doi":"https://doi.org/10.1109/TVCG.2025.3602405","numberOfCreators":5,"category":"journal","sources":["https://dblp.org/rec/journals/tvcg/0049GLLL25","https://doi.org/10.1109/TVCG.2025.3602405"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/tvcg/0049GLLL25","documentUrl":null,"type":"Article"},{"key":"journals/tvcg/LaiHGCPLLLG25","url":"https://dblp.org/rec/journals/tvcg/LaiHGCPLLLG25","title":"GlossyGS: Inverse Rendering of Glossy Objects With 3D Gaussian Splatting.","year":2025,"types":["Article"],"venue":"IEEE Trans. Vis. Comput. Graph.","doi":"https://doi.org/10.1109/TVCG.2025.3547063","numberOfCreators":9,"category":"journal","sources":["https://dblp.org/rec/journals/tvcg/LaiHGCPLLLG25","https://doi.org/10.1109/TVCG.2025.3547063"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/tvcg/LaiHGCPLLLG25","documentUrl":null,"type":"Article"},{"key":"journals/tvcg/LiLLLLLLWG25","url":"https://dblp.org/rec/journals/tvcg/LiLLLLLLWG25","title":"Multi-View Large Reconstruction Model via Geometry-Aware Positional Encoding and Attention.","year":2025,"types":["Article"],"venue":"IEEE Trans. Vis. Comput. Graph.","doi":"https://doi.org/10.1109/TVCG.2025.3572341","numberOfCreators":9,"category":"journal","sources":["https://dblp.org/rec/journals/tvcg/LiLLLLLLWG25","https://doi.org/10.1109/TVCG.2025.3572341"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/tvcg/LiLLLLLLWG25","documentUrl":null,"type":"Article"},{"key":"journals/tvcg/LiuLLWLLW25","url":"https://dblp.org/rec/journals/tvcg/LiuLLWLLW25","title":"NeRFBuff: Fast Neural Rendering via Inter-Frame Feature Buffering.","year":2025,"types":["Article"],"venue":"IEEE Trans. Vis. Comput. Graph.","doi":"https://doi.org/10.1109/TVCG.2024.3393715","numberOfCreators":7,"category":"journal","sources":["https://dblp.org/rec/journals/tvcg/LiuLLWLLW25","https://doi.org/10.1109/TVCG.2024.3393715"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/tvcg/LiuLLWLLW25","documentUrl":null,"type":"Article"}],"preprints":[{"key":"journals/corr/abs-2502-20732","url":"https://dblp.org/rec/journals/corr/abs-2502-20732","title":"CADDreamer: CAD object Generation from Single-view Images.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2502.20732","numberOfCreators":9,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2502-20732","https://doi.org/10.48550/ARXIV.2502.20732"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2502-20732","documentUrl":null,"type":"Informal","arxivId":"2502.20732","arxivUrl":"https://arxiv.org/abs/2502.20732"},{"key":"journals/corr/abs-2503-05689","url":"https://dblp.org/rec/journals/corr/abs-2503-05689","title":"GoalFlow: Goal-Driven Flow Matching for Multimodal Trajectories Generation in End-to-End Autonomous Driving.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2503.05689","numberOfCreators":8,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2503-05689","https://doi.org/10.48550/ARXIV.2503.05689"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-05689","documentUrl":null,"type":"Informal","arxivId":"2503.05689","arxivUrl":"https://arxiv.org/abs/2503.05689"},{"key":"journals/corr/abs-2503-23162","url":"https://dblp.org/rec/journals/corr/abs-2503-23162","title":"NeuralGS: Bridging Neural Fields and 3D Gaussian Splatting for Compact 3D Representations.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2503.23162","numberOfCreators":9,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2503-23162","https://doi.org/10.48550/ARXIV.2503.23162"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-23162","documentUrl":null,"type":"Informal","arxivId":"2503.23162","arxivUrl":"https://arxiv.org/abs/2503.23162"},{"key":"journals/corr/abs-2505-18078","url":"https://dblp.org/rec/journals/corr/abs-2505-18078","title":"DanceTogether! Identity-Preserving Multi-Person Interactive Video Generation.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2505.18078","numberOfCreators":12,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2505-18078","https://doi.org/10.48550/ARXIV.2505.18078"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-18078","documentUrl":null,"type":"Informal","arxivId":"2505.18078","arxivUrl":"https://arxiv.org/abs/2505.18078"},{"key":"journals/corr/abs-2506-21319","url":"https://dblp.org/rec/journals/corr/abs-2506-21319","title":"SimVecVis: A Dataset for Enhancing MLLMs in Visualization Understanding.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2506.21319","numberOfCreators":6,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2506-21319","https://doi.org/10.48550/ARXIV.2506.21319"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-21319","documentUrl":null,"type":"Informal","arxivId":"2506.21319","arxivUrl":"https://arxiv.org/abs/2506.21319"},{"key":"journals/corr/abs-2506-24113","url":"https://dblp.org/rec/journals/corr/abs-2506-24113","title":"Epona: Autoregressive Diffusion World Model for Autonomous Driving.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2506.24113","numberOfCreators":12,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2506-24113","https://doi.org/10.48550/ARXIV.2506.24113"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-24113","documentUrl":null,"type":"Informal","arxivId":"2506.24113","arxivUrl":"https://arxiv.org/abs/2506.24113"},{"key":"journals/corr/abs-2507-00917","url":"https://dblp.org/rec/journals/corr/abs-2507-00917","title":"A Survey: Learning Embodied Intelligence from Physical Simulators and World Models.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2507.00917","numberOfCreators":18,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2507-00917","https://doi.org/10.48550/ARXIV.2507.00917"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2507-00917","documentUrl":null,"type":"Informal","arxivId":"2507.00917","arxivUrl":"https://arxiv.org/abs/2507.00917"},{"key":"journals/corr/abs-2507-07997","url":"https://dblp.org/rec/journals/corr/abs-2507-07997","title":"MGVQ: Could VQ-VAE Beat VAE? A Generalizable Tokenizer with Multi-group Quantization.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2507.07997","numberOfCreators":8,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2507-07997","https://doi.org/10.48550/ARXIV.2507.07997"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2507-07997","documentUrl":null,"type":"Informal","arxivId":"2507.07997","arxivUrl":"https://arxiv.org/abs/2507.07997"},{"key":"journals/corr/abs-2507-14501","url":"https://dblp.org/rec/journals/corr/abs-2507-14501","title":"Advances in Feed-Forward 3D Reconstruction and View Synthesis: A Survey.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2507.14501","numberOfCreators":16,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2507-14501","https://doi.org/10.48550/ARXIV.2507.14501"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2507-14501","documentUrl":null,"type":"Informal","arxivId":"2507.14501","arxivUrl":"https://arxiv.org/abs/2507.14501"},{"key":"journals/corr/abs-2507-18939","url":"https://dblp.org/rec/journals/corr/abs-2507-18939","title":"PDT: Point Distribution Transformation with Diffusion Models.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2507.18939","numberOfCreators":10,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2507-18939","https://doi.org/10.48550/ARXIV.2507.18939"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2507-18939","documentUrl":null,"type":"Informal","arxivId":"2507.18939","arxivUrl":"https://arxiv.org/abs/2507.18939"},{"key":"journals/corr/abs-2509-03887","url":"https://dblp.org/rec/journals/corr/abs-2509-03887","title":"OccTENS: 3D Occupancy World Model via Temporal Next-Scale Prediction.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2509.03887","numberOfCreators":8,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2509-03887","https://doi.org/10.48550/ARXIV.2509.03887"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-03887","documentUrl":null,"type":"Informal","arxivId":"2509.03887","arxivUrl":"https://arxiv.org/abs/2509.03887"},{"key":"journals/corr/abs-2509-09676","url":"https://dblp.org/rec/journals/corr/abs-2509-09676","title":"SpatialVID: A Large-Scale Video Dataset with Spatial Annotations.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2509.09676","numberOfCreators":15,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2509-09676","https://doi.org/10.48550/ARXIV.2509.09676"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-09676","documentUrl":null,"type":"Informal","arxivId":"2509.09676","arxivUrl":"https://arxiv.org/abs/2509.09676"},{"key":"journals/corr/abs-2510-07729","url":"https://dblp.org/rec/journals/corr/abs-2510-07729","title":"ComGS: Efficient 3D Object-Scene Composition via Surface Octahedral Probes.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2510.07729","numberOfCreators":11,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2510-07729","https://doi.org/10.48550/ARXIV.2510.07729"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-07729","documentUrl":null,"type":"Informal","arxivId":"2510.07729","arxivUrl":"https://arxiv.org/abs/2510.07729"},{"key":"journals/corr/abs-2511-01767","url":"https://dblp.org/rec/journals/corr/abs-2511-01767","title":"Wonder3D++: Cross-domain Diffusion for High-fidelity 3D Generation from a Single Image.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2511.01767","numberOfCreators":10,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2511-01767","https://doi.org/10.48550/ARXIV.2511.01767"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2511-01767","documentUrl":null,"type":"Informal","arxivId":"2511.01767","arxivUrl":"https://arxiv.org/abs/2511.01767"},{"key":"journals/corr/abs-2511-02483","url":"https://dblp.org/rec/journals/corr/abs-2511-02483","title":"OLATverse: A Large-scale Real-world Object Dataset with Precise Lighting Control.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2511.02483","numberOfCreators":10,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2511-02483","https://doi.org/10.48550/ARXIV.2511.02483"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2511-02483","documentUrl":null,"type":"Informal","arxivId":"2511.02483","arxivUrl":"https://arxiv.org/abs/2511.02483"},{"key":"journals/corr/abs-2511-05038","url":"https://dblp.org/rec/journals/corr/abs-2511-05038","title":"Pressure2Motion: Hierarchical Motion Synthesis from Ground Pressure with Text Guidance.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2511.05038","numberOfCreators":10,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2511-05038","https://doi.org/10.48550/ARXIV.2511.05038"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2511-05038","documentUrl":null,"type":"Informal","arxivId":"2511.05038","arxivUrl":"https://arxiv.org/abs/2511.05038"},{"key":"journals/corr/abs-2511-20565","url":"https://dblp.org/rec/journals/corr/abs-2511-20565","title":"DINO-Tok: Adapting DINO for Visual Tokenizers.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2511.20565","numberOfCreators":11,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2511-20565","https://doi.org/10.48550/ARXIV.2511.20565"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2511-20565","documentUrl":null,"type":"Informal","arxivId":"2511.20565","arxivUrl":"https://arxiv.org/abs/2511.20565"},{"key":"journals/corr/abs-2512-04939","url":"https://dblp.org/rec/journals/corr/abs-2512-04939","title":"LiteVGGT: Boosting Vanilla VGGT via Geometry-aware Cached Token Merging.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2512.04939","numberOfCreators":11,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2512-04939","https://doi.org/10.48550/ARXIV.2512.04939"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-04939","documentUrl":null,"type":"Informal","arxivId":"2512.04939","arxivUrl":"https://arxiv.org/abs/2512.04939"},{"key":"journals/corr/abs-2512-22808","url":"https://dblp.org/rec/journals/corr/abs-2512-22808","title":"EgoReAct: Egocentric Video-Driven 3D Human Reaction Generation.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2512.22808","numberOfCreators":13,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2512-22808","https://doi.org/10.48550/ARXIV.2512.22808"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-22808","documentUrl":null,"type":"Informal","arxivId":"2512.22808","arxivUrl":"https://arxiv.org/abs/2512.22808"}],"excludedFormal":[],"otherRecords":[],"matchedName":"Xiaoxiao Long","databaseLabel":"Xiaoxiao Long","databaseMetadata":{"type":["https://dblp.org/rdf/schema#Person","https://dblp.org/rdf/schema#Creator"],"label":["Xiaoxiao Long"],"orcid":["https://orcid.org/0000-0002-3386-8805"]},"rawFormalRecordCount2025":21,"signatureAudit":{"completedAt":"2026-10-19","frozen":true,"scope":"对 B 组 39 个数值档案的全部 1074 条原始 2025 正式记录扫描 DBLP author-signature ORCID 和机构；复用既有 59 条 Crossref 核验，补查 6 条新触发记录。重点核查不同 ORCID，以及只有预期机构之外机构的条目。本轮不扩展为所有作者逐篇全文审计。","formalRecordCoverage":21,"orcidCounts":{"https://orcid.org/0000-0002-3386-8805":7},"institutionCounts":{"Hong Kong University of Science and Technology (HKUST)":3,"Max Planck Institute for Informatics (MPI Informatik)":1,"Nanjing University (NJU)":9,"Nanjing University of Science and Technology (NUST)":1,"University of Hong Kong (HKU)":7},"caveat":"机构名称可能由 DBLP 自动映射而失真；多 ORCID 也不自动等于异人。只有有原始资料支撑的错归才作确认排除，未解决分支则暂停总数。"},"labName":"3D Vision Lab","labUrl":"https://www.xxlong.site/group.html","labEvidence":"本人主页及 Group 页面均将龙霄潇/Long 标为南京大学 3D Vision Lab 的 Principal Investigator，Group 页面展示本组学生。","labSourceUrl":"https://www.xxlong.site/group.html","sourceWarning":false,"excludedOther":[],"excludedHomonyms":[],"unassignedCandidates":[],"knownPreprintMinimum2025":null,"excludedMisattributed":[],"displayNotes":"身份已与原名单机构及公开资料核对确认。2025 年正式记录 21 条（会议 16、期刊 5），所有作者位置均计入，不表示主导或贡献份额；预印本 19 条单列，不加总。","labDisplayNotes":"个人主页与 Group 页面均列其为南京大学 3D Vision Lab 的 PI，并展示本组学生，据此归组。"},{"index":68,"name":"Cewu Lu","nameZh":"卢策吾","role":"Professor","affiliation":"Shanghai Jiao Tong University","affiliationZh":"上海交通大学","source":"DBLP RDF via official SPARQL; primary-source identity checks","sourceUrl":"https://sparql.dblp.org/","profileUrl":"https://dblp.org/pid/96/10571.html","identifier":"96/10571","retrievedAt":"2026-10-19","count2025":51,"conference2025":42,"journal2025":9,"preprint2025":32,"status":"confirmed","notes":"","identityEvidence":[{"url":"https://dblp.org/pid/96/10571.html","evidence":"DBLP RDF 类型为 Person，消歧后名字为 Cewu Lu。机构元数据含：Stanford University；Chinese University of Hong Kong；Shanghai Jiao Tong University, Department of Computer Science and Engineering, China"}],"papers":[{"key":"conf/aaai/0003LXWCL25","url":"https://dblp.org/rec/conf/aaai/0003LXWCL25","title":"Discovering Conceptual Knowledge with Analytic Ontology Templates for Articulated Objects.","year":2025,"types":["Inproceedings"],"venue":"AAAI","doi":"https://doi.org/10.1609/AAAI.V39I14.33609","eventYear":2025,"numberOfCreators":6,"category":"conference","sources":["https://dblp.org/rec/conf/aaai/0003LXWCL25","https://doi.org/10.1609/AAAI.V39I14.33609"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/aaai/0003LXWCL25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/aaai/LiuW0ZFLMC025","url":"https://dblp.org/rec/conf/aaai/LiuW0ZFLMC025","title":"Interacted Object Grounding in Spatio-Temporal Human-Object Interactions.","year":2025,"types":["Inproceedings"],"venue":"AAAI","doi":"https://doi.org/10.1609/AAAI.V39I6.32599","eventYear":2025,"numberOfCreators":9,"category":"conference","sources":["https://dblp.org/rec/conf/aaai/LiuW0ZFLMC025","https://doi.org/10.1609/AAAI.V39I6.32599"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/aaai/LiuW0ZFLMC025","documentUrl":null,"type":"Inproceedings"},{"key":"conf/cvpr/0002LZCL025","url":"https://dblp.org/rec/conf/cvpr/0002LZCL025","title":"Homogeneous Dynamics Space for Heterogeneous Humans.","year":2025,"types":["Inproceedings"],"venue":"CVPR","doi":"https://doi.org/10.1109/CVPR52734.2025.02587","eventYear":2025,"numberOfCreators":6,"category":"conference","sources":["https://dblp.org/rec/conf/cvpr/0002LZCL025","https://doi.org/10.1109/CVPR52734.2025.02587"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/0002LZCL025","documentUrl":null,"type":"Inproceedings"},{"key":"conf/cvpr/BianXX00LB025","url":"https://dblp.org/rec/conf/cvpr/BianXX00LB025","title":"ChatGarment: Garment Estimation, Generation and Editing via Large Language Models.","year":2025,"types":["Inproceedings"],"venue":"CVPR","doi":"https://doi.org/10.1109/CVPR52734.2025.00278","eventYear":2025,"numberOfCreators":8,"category":"conference","sources":["https://dblp.org/rec/conf/cvpr/BianXX00LB025","https://doi.org/10.1109/CVPR52734.2025.00278"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/BianXX00LB025","documentUrl":null,"type":"Inproceedings"},{"key":"conf/cvpr/ChenLLTGL025","url":"https://dblp.org/rec/conf/cvpr/ChenLLTGL025","title":"M^3-VOS: Multi-Phase, Multi-Transition, and Multi-Scenery Video Object Segmentation.","year":2025,"types":["Inproceedings"],"venue":"CVPR","doi":"https://doi.org/10.1109/CVPR52734.2025.02718","eventYear":2025,"numberOfCreators":7,"category":"conference","sources":["https://dblp.org/rec/conf/cvpr/ChenLLTGL025","https://doi.org/10.1109/CVPR52734.2025.02718"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/ChenLLTGL025","documentUrl":null,"type":"Inproceedings"},{"key":"conf/cvpr/ZhangXWYYLLWL25","url":"https://dblp.org/rec/conf/cvpr/ZhangXWYYLLWL25","title":"GaPT-DAR: Category-level Garments Pose Tracking via Integrated 2D Deformation and 3D Reconstruction.","year":2025,"types":["Inproceedings"],"venue":"CVPR","doi":"https://doi.org/10.1109/CVPR52734.2025.02108","eventYear":2025,"numberOfCreators":9,"category":"conference","sources":["https://dblp.org/rec/conf/cvpr/ZhangXWYYLLWL25","https://doi.org/10.1109/CVPR52734.2025.02108"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/ZhangXWYYLLWL25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/eccv/LiWYLD24","url":"https://dblp.org/rec/conf/eccv/LiWYLD24","title":"SemGrasp : Semantic Grasp Generation via Language Aligned Discretization.","year":2025,"types":["Inproceedings"],"venue":"ECCV (2)","doi":"https://doi.org/10.1007/978-3-031-72627-9_7","eventYear":2024,"numberOfCreators":5,"category":"conference","sources":["https://dblp.org/rec/conf/eccv/LiWYLD24","https://doi.org/10.1007/978-3-031-72627-9_7"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2024,"sourceUrl":"https://dblp.org/rec/conf/eccv/LiWYLD24","documentUrl":null,"type":"Inproceedings"},{"key":"conf/eccv/LiYRZMLKI24","url":"https://dblp.org/rec/conf/eccv/LiYRZMLKI24","title":"COIN: Control-Inpainting Diffusion Prior for Human and Camera Motion Estimation.","year":2025,"types":["Inproceedings"],"venue":"ECCV (16)","doi":"https://doi.org/10.1007/978-3-031-72640-8_24","eventYear":2024,"numberOfCreators":8,"category":"conference","sources":["https://dblp.org/rec/conf/eccv/LiYRZMLKI24","https://doi.org/10.1007/978-3-031-72640-8_24"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2024,"sourceUrl":"https://dblp.org/rec/conf/eccv/LiYRZMLKI24","documentUrl":null,"type":"Inproceedings"},{"key":"conf/eccv/LiuHYLL24","url":"https://dblp.org/rec/conf/eccv/LiuHYLL24","title":"Revisit Human-Scene Interaction via Space Occupancy.","year":2025,"types":["Inproceedings"],"venue":"ECCV (50)","doi":"https://doi.org/10.1007/978-3-031-72973-7_1","eventYear":2024,"numberOfCreators":5,"category":"conference","sources":["https://dblp.org/rec/conf/eccv/LiuHYLL24","https://doi.org/10.1007/978-3-031-72973-7_1"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2024,"sourceUrl":"https://dblp.org/rec/conf/eccv/LiuHYLL24","documentUrl":null,"type":"Inproceedings"},{"key":"conf/eccv/LiuLZZYL24","url":"https://dblp.org/rec/conf/eccv/LiuLZZYL24","title":"Bridging the Gap Between Human Motion and Action Semantics via Kinematic Phrases.","year":2025,"types":["Inproceedings"],"venue":"ECCV (8)","doi":"https://doi.org/10.1007/978-3-031-73242-3_13","eventYear":2024,"numberOfCreators":6,"category":"conference","sources":["https://dblp.org/rec/conf/eccv/LiuLZZYL24","https://doi.org/10.1007/978-3-031-73242-3_13"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2024,"sourceUrl":"https://dblp.org/rec/conf/eccv/LiuLZZYL24","documentUrl":null,"type":"Inproceedings"},{"key":"conf/eccv/XuLCWLTT24","url":"https://dblp.org/rec/conf/eccv/XuLCWLTT24","title":"Distill Gold from Massive Ores: Bi-level Data Pruning Towards Efficient Dataset Distillation.","year":2025,"types":["Inproceedings"],"venue":"ECCV (20)","doi":"https://doi.org/10.1007/978-3-031-72661-3_14","eventYear":2024,"numberOfCreators":7,"category":"conference","sources":["https://dblp.org/rec/conf/eccv/XuLCWLTT24","https://doi.org/10.1007/978-3-031-72661-3_14"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2024,"sourceUrl":"https://dblp.org/rec/conf/eccv/XuLCWLTT24","documentUrl":null,"type":"Inproceedings"},{"key":"conf/eccv/XuLYLL24","url":"https://dblp.org/rec/conf/eccv/XuLYLL24","title":"DISCO: Embodied Navigation and Interaction via Differentiable Scene Semantics and Dual-Level Control.","year":2025,"types":["Inproceedings"],"venue":"ECCV (18)","doi":"https://doi.org/10.1007/978-3-031-72649-1_7","eventYear":2024,"numberOfCreators":5,"category":"conference","sources":["https://dblp.org/rec/conf/eccv/XuLYLL24","https://doi.org/10.1007/978-3-031-72649-1_7"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2024,"sourceUrl":"https://dblp.org/rec/conf/eccv/XuLYLL24","documentUrl":null,"type":"Inproceedings"},{"key":"conf/eccv/YouXYHZSFHGL24","url":"https://dblp.org/rec/conf/eccv/YouXYHZSFHGL24","title":"PACE: A Large-Scale Dataset with Pose Annotations in Cluttered Environments.","year":2025,"types":["Inproceedings"],"venue":"ECCV (51)","doi":"https://doi.org/10.1007/978-3-031-72983-6_27","eventYear":2024,"numberOfCreators":10,"category":"conference","sources":["https://dblp.org/rec/conf/eccv/YouXYHZSFHGL24","https://doi.org/10.1007/978-3-031-72983-6_27"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2024,"sourceUrl":"https://dblp.org/rec/conf/eccv/YouXYHZSFHGL24","documentUrl":null,"type":"Inproceedings"},{"key":"conf/eccv/ZhangCLXLL24","url":"https://dblp.org/rec/conf/eccv/ZhangCLXLL24","title":"Take a Step Back: Rethinking the Two Stages in Visual Reasoning.","year":2025,"types":["Inproceedings"],"venue":"ECCV (43)","doi":"https://doi.org/10.1007/978-3-031-72775-7_8","eventYear":2024,"numberOfCreators":6,"category":"conference","sources":["https://dblp.org/rec/conf/eccv/ZhangCLXLL24","https://doi.org/10.1007/978-3-031-72775-7_8"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2024,"sourceUrl":"https://dblp.org/rec/conf/eccv/ZhangCLXLL24","documentUrl":null,"type":"Inproceedings"},{"key":"conf/icassp/YuHYZ0HAL25","url":"https://dblp.org/rec/conf/icassp/YuHYZ0HAL25","title":"Generalizable Articulated Object Perception with Superpoints.","year":2025,"types":["Inproceedings"],"venue":"ICASSP","doi":"https://doi.org/10.1109/ICASSP49660.2025.10890874","eventYear":2025,"numberOfCreators":8,"category":"conference","sources":["https://dblp.org/rec/conf/icassp/YuHYZ0HAL25","https://doi.org/10.1109/ICASSP49660.2025.10890874"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/icassp/YuHYZ0HAL25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iccv/SuZFXFLLY25","url":"https://dblp.org/rec/conf/iccv/SuZFXFLLY25","title":"Dense Policy: Bidirectional Autoregressive Learning of Actions.","year":2025,"types":["Inproceedings"],"venue":"ICCV","doi":"https://doi.org/10.1109/ICCV51701.2025.01344","eventYear":2025,"numberOfCreators":8,"category":"conference","sources":["https://dblp.org/rec/conf/iccv/SuZFXFLLY25","https://doi.org/10.1109/ICCV51701.2025.01344"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/SuZFXFLLY25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iccv/SunLWXWZL25","url":"https://dblp.org/rec/conf/iccv/SunLWXWZL25","title":"Arti-PG: A Toolbox for Procedurally Synthesizing Large-Scale and Diverse Articulated Objects with Rich Annotations.","year":2025,"types":["Inproceedings"],"venue":"ICCV","doi":"https://doi.org/10.1109/ICCV51701.2025.00603","eventYear":2025,"numberOfCreators":7,"category":"conference","sources":["https://dblp.org/rec/conf/iccv/SunLWXWZL25","https://doi.org/10.1109/ICCV51701.2025.00603"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/SunLWXWZL25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iccv/YuXXLAZL25","url":"https://dblp.org/rec/conf/iccv/YuXXLAZL25","title":"Dynamic Reconstruction of Hand-Object Interaction with Distributed Force-Aware Contact Representation.","year":2025,"types":["Inproceedings"],"venue":"ICCV","doi":"https://doi.org/10.1109/ICCV51701.2025.00804","eventYear":2025,"numberOfCreators":7,"category":"conference","sources":["https://dblp.org/rec/conf/iccv/YuXXLAZL25","https://doi.org/10.1109/ICCV51701.2025.00804"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/YuXXLAZL25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iclr/0002LLH0L25","url":"https://dblp.org/rec/conf/iclr/0002LLH0L25","title":"ImDy: Human Inverse Dynamics from Imitated Observations.","year":2025,"types":["Inproceedings"],"venue":"ICLR","doi":null,"eventYear":2025,"numberOfCreators":6,"category":"conference","sources":["https://dblp.org/rec/conf/iclr/0002LLH0L25"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iclr/0002LLH0L25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iclr/0003LCL25","url":"https://dblp.org/rec/conf/iclr/0003LCL25","title":"Interactive Adjustment for Human Trajectory Prediction with Individual Feedback.","year":2025,"types":["Inproceedings"],"venue":"ICLR","doi":null,"eventYear":2025,"numberOfCreators":4,"category":"conference","sources":["https://dblp.org/rec/conf/iclr/0003LCL25"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iclr/0003LCL25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iclr/LiLCZGL025","url":"https://dblp.org/rec/conf/iclr/LiLCZGL025","title":"The Labyrinth of Links: Navigating the Associative Maze of Multi-modal LLMs.","year":2025,"types":["Inproceedings"],"venue":"ICLR","doi":null,"eventYear":2025,"numberOfCreators":7,"category":"conference","sources":["https://dblp.org/rec/conf/iclr/LiLCZGL025"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iclr/LiLCZGL025","documentUrl":null,"type":"Inproceedings"},{"key":"conf/icra/ChenFFL25","url":"https://dblp.org/rec/conf/icra/ChenFFL25","title":"Towards Effective Utilization of Mixed-Quality Demonstrations in Robotic Manipulation via Segment-Level Selection and Optimization.","year":2025,"types":["Inproceedings"],"venue":"ICRA","doi":"https://doi.org/10.1109/ICRA55743.2025.11128787","eventYear":2025,"numberOfCreators":4,"category":"conference","sources":["https://dblp.org/rec/conf/icra/ChenFFL25","https://doi.org/10.1109/ICRA55743.2025.11128787"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/icra/ChenFFL25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/icra/ChenXZFL25","url":"https://dblp.org/rec/conf/icra/ChenXZFL25","title":"Deformpam: Data-Efficient Learning for Long-Horizon Deformable Object Manipulation Via Preference-Based Action Alignment.","year":2025,"types":["Inproceedings"],"venue":"ICRA","doi":"https://doi.org/10.1109/ICRA55743.2025.11127926","eventYear":2025,"numberOfCreators":5,"category":"conference","sources":["https://dblp.org/rec/conf/icra/ChenXZFL25","https://doi.org/10.1109/ICRA55743.2025.11127926"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/icra/ChenXZFL25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/icra/LiuWWWL25","url":"https://dblp.org/rec/conf/icra/LiuWWWL25","title":"ForceMimic: Force-Centric Imitation Learning with Force-Motion Capture System for Contact-Rich Manipulation.","year":2025,"types":["Inproceedings"],"venue":"ICRA","doi":"https://doi.org/10.1109/ICRA55743.2025.11128061","eventYear":2025,"numberOfCreators":5,"category":"conference","sources":["https://dblp.org/rec/conf/icra/LiuWWWL25","https://doi.org/10.1109/ICRA55743.2025.11128061"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/icra/LiuWWWL25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/icra/LuoPLHDLL25","url":"https://dblp.org/rec/conf/icra/LuoPLHDLL25","title":"Human-Agent Joint Learning for Efficient Robot Manipulation Skill Acquisition.","year":2025,"types":["Inproceedings"],"venue":"ICRA","doi":"https://doi.org/10.1109/ICRA55743.2025.11127637","eventYear":2025,"numberOfCreators":7,"category":"conference","sources":["https://dblp.org/rec/conf/icra/LuoPLHDLL25","https://doi.org/10.1109/ICRA55743.2025.11127637"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/icra/LuoPLHDLL25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/icra/XiaFLF25","url":"https://dblp.org/rec/conf/icra/XiaFLF25","title":"Cage: Causal Attention Enables Data-Efficient Generalizable Robotic Manipulation.","year":2025,"types":["Inproceedings"],"venue":"ICRA","doi":"https://doi.org/10.1109/ICRA55743.2025.11127739","eventYear":2025,"numberOfCreators":4,"category":"conference","sources":["https://dblp.org/rec/conf/icra/XiaFLF25","https://doi.org/10.1109/ICRA55743.2025.11127739"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/icra/XiaFLF25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/icra/YuHYJHLCWLLGL25","url":"https://dblp.org/rec/conf/icra/YuHYJHLCWLLGL25","title":"UniAff: A Unified Representation of Affordances for Tool Usage and Articulation with Vision-Language Models.","year":2025,"types":["Inproceedings"],"venue":"ICRA","doi":"https://doi.org/10.1109/ICRA55743.2025.11127736","eventYear":2025,"numberOfCreators":12,"category":"conference","sources":["https://dblp.org/rec/conf/icra/YuHYJHLCWLLGL25","https://doi.org/10.1109/ICRA55743.2025.11127736"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/icra/YuHYJHLCWLLGL25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iros/ChenSLHQZYOSQLS25","url":"https://dblp.org/rec/conf/iros/ChenSLHQZYOSQLS25","title":"RH20T-P: A Primitive-Level Robotic Manipulation Dataset towards Composable Generalization Agents in Real-world Scenarios.","year":2025,"types":["Inproceedings"],"venue":"IROS","doi":"https://doi.org/10.1109/IROS60139.2025.11246228","eventYear":2025,"numberOfCreators":12,"category":"conference","sources":["https://dblp.org/rec/conf/iros/ChenSLHQZYOSQLS25","https://doi.org/10.1109/IROS60139.2025.11246228"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iros/ChenSLHQZYOSQLS25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iros/JinLJL25","url":"https://dblp.org/rec/conf/iros/JinLJL25","title":"DiffGen: Robot Demonstration Generation via Differentiable Physics Simulation, Differentiable Rendering, and Vision-Language Model.","year":2025,"types":["Inproceedings"],"venue":"IROS","doi":"https://doi.org/10.1109/IROS60139.2025.11247245","eventYear":2025,"numberOfCreators":4,"category":"conference","sources":["https://dblp.org/rec/conf/iros/JinLJL25","https://doi.org/10.1109/IROS60139.2025.11247245"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iros/JinLJL25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iros/JinLYFLL25","url":"https://dblp.org/rec/conf/iros/JinLYFLL25","title":"SIME: Enhancing Policy Self-Improvement with Modal-level Exploration.","year":2025,"types":["Inproceedings"],"venue":"IROS","doi":"https://doi.org/10.1109/IROS60139.2025.11245841","eventYear":2025,"numberOfCreators":6,"category":"conference","sources":["https://dblp.org/rec/conf/iros/JinLYFLL25","https://doi.org/10.1109/IROS60139.2025.11245841"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iros/JinLYFLL25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iros/LiHYJHZLGL25","url":"https://dblp.org/rec/conf/iros/LiHYJHZLGL25","title":"SKT: Integrating State-Aware Keypoint Trajectories with Vision-Language Models for Robotic Garment Manipulation.","year":2025,"types":["Inproceedings"],"venue":"IROS","doi":"https://doi.org/10.1109/IROS60139.2025.11246904","eventYear":2025,"numberOfCreators":9,"category":"conference","sources":["https://dblp.org/rec/conf/iros/LiHYJHZLGL25","https://doi.org/10.1109/IROS60139.2025.11246904"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iros/LiHYJHZLGL25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iros/LiZXTL25","url":"https://dblp.org/rec/conf/iros/LiZXTL25","title":"FSGlove: An Inertial-Based Hand Tracking System with Shape-Aware Calibration.","year":2025,"types":["Inproceedings"],"venue":"IROS","doi":"https://doi.org/10.1109/IROS60139.2025.11245803","eventYear":2025,"numberOfCreators":5,"category":"conference","sources":["https://dblp.org/rec/conf/iros/LiZXTL25","https://doi.org/10.1109/IROS60139.2025.11245803"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iros/LiZXTL25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iros/MiaoLFJL25","url":"https://dblp.org/rec/conf/iros/MiaoLFJL25","title":"Knowledge-Driven Imitation Learning: Enabling Generalization Across Diverse Conditions.","year":2025,"types":["Inproceedings"],"venue":"IROS","doi":"https://doi.org/10.1109/IROS60139.2025.11246479","eventYear":2025,"numberOfCreators":5,"category":"conference","sources":["https://dblp.org/rec/conf/iros/MiaoLFJL25","https://doi.org/10.1109/IROS60139.2025.11246479"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iros/MiaoLFJL25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iros/QianZWLL25","url":"https://dblp.org/rec/conf/iros/QianZWLL25","title":"Generalizable and Actionable Part Detection and Manipulation with SAM-rectified Segmentation and Iterative Pose Refinement.","year":2025,"types":["Inproceedings"],"venue":"IROS","doi":"https://doi.org/10.1109/IROS60139.2025.11246094","eventYear":2025,"numberOfCreators":5,"category":"conference","sources":["https://dblp.org/rec/conf/iros/QianZWLL25","https://doi.org/10.1109/IROS60139.2025.11246094"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iros/QianZWLL25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iros/TangLXL25","url":"https://dblp.org/rec/conf/iros/TangLXL25","title":"Kalib: Easy Hand-Eye Calibration with Reference Point Tracking.","year":2025,"types":["Inproceedings"],"venue":"IROS","doi":"https://doi.org/10.1109/IROS60139.2025.11247188","eventYear":2025,"numberOfCreators":4,"category":"conference","sources":["https://dblp.org/rec/conf/iros/TangLXL25","https://doi.org/10.1109/IROS60139.2025.11247188"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iros/TangLXL25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iros/YanFL25","url":"https://dblp.org/rec/conf/iros/YanFL25","title":"Dexterous Manipulation Based on Prior Dexterous Grasp Pose Knowledge.","year":2025,"types":["Inproceedings"],"venue":"IROS","doi":"https://doi.org/10.1109/IROS60139.2025.11247095","eventYear":2025,"numberOfCreators":3,"category":"conference","sources":["https://dblp.org/rec/conf/iros/YanFL25","https://doi.org/10.1109/IROS60139.2025.11247095"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iros/YanFL25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iros/YanWFYL25","url":"https://dblp.org/rec/conf/iros/YanWFYL25","title":"LDexMM: Language-Guided Dexterous Multi-Task Manipulation with Reinforcement Learning.","year":2025,"types":["Inproceedings"],"venue":"IROS","doi":"https://doi.org/10.1109/IROS60139.2025.11247524","eventYear":2025,"numberOfCreators":5,"category":"conference","sources":["https://dblp.org/rec/conf/iros/YanWFYL25","https://doi.org/10.1109/IROS60139.2025.11247524"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iros/YanWFYL25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iros/YuYJCZHYCMLL25","url":"https://dblp.org/rec/conf/iros/YuYJCZHYCMLL25","title":"ArtGS: 3D Gaussian Splatting for Interactive Visual-Physical Modeling and Manipulation of Articulated Objects.","year":2025,"types":["Inproceedings"],"venue":"IROS","doi":"https://doi.org/10.1109/IROS60139.2025.11246522","eventYear":2025,"numberOfCreators":11,"category":"conference","sources":["https://dblp.org/rec/conf/iros/YuYJCZHYCMLL25","https://doi.org/10.1109/IROS60139.2025.11246522"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iros/YuYJCZHYCMLL25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/nips/TangHHXLC25","url":"https://dblp.org/rec/conf/nips/TangHHXLC25","title":"Tru-POMDP: Task Planning Under Uncertainty via Tree of Hypotheses and Open-Ended POMDPs.","year":2025,"types":["Inproceedings"],"venue":"NeurIPS","doi":null,"eventYear":2025,"numberOfCreators":6,"category":"conference","sources":["https://dblp.org/rec/conf/nips/TangHHXLC25"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/nips/TangHHXLC25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/nips/WuLLHSYWL25","url":"https://dblp.org/rec/conf/nips/WuLLHSYWL25","title":"REArtGS: Reconstructing and Generating Articulated Objects via 3D Gaussian Splatting with Geometric and Motion Constraints.","year":2025,"types":["Inproceedings"],"venue":"NeurIPS","doi":null,"eventYear":2025,"numberOfCreators":8,"category":"conference","sources":["https://dblp.org/rec/conf/nips/WuLLHSYWL25"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/nips/WuLLHSYWL25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/nips/YeXLC25","url":"https://dblp.org/rec/conf/nips/YeXLC25","title":"UniDomain: Pretraining a Unified PDDL Domain from Real-World Demonstrations for Generalizable Robot Task Planning.","year":2025,"types":["Inproceedings"],"venue":"NeurIPS","doi":null,"eventYear":2025,"numberOfCreators":4,"category":"conference","sources":["https://dblp.org/rec/conf/nips/YeXLC25"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/nips/YeXLC25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/nips/YuLYRHDHHSCZL25","url":"https://dblp.org/rec/conf/nips/YuLYRHDHHSCZL25","title":"ForceVLA: Enhancing VLA Models with a Force-aware MoE for Contact-rich Manipulation.","year":2025,"types":["Inproceedings"],"venue":"NeurIPS","doi":null,"eventYear":2025,"numberOfCreators":12,"category":"conference","sources":["https://dblp.org/rec/conf/nips/YuLYRHDHHSCZL25"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/nips/YuLYRHDHHSCZL25","documentUrl":null,"type":"Inproceedings"},{"key":"journals/ijrr/FirooziTTMSLZSKHIDWLS25","url":"https://dblp.org/rec/journals/ijrr/FirooziTTMSLZSKHIDWLS25","title":"Foundation models in robotics: Applications, challenges, and the future.","year":2025,"types":["Article"],"venue":"Int. J. Robotics Res.","doi":"https://doi.org/10.1177/02783649241281508","numberOfCreators":15,"category":"journal","sources":["https://dblp.org/rec/journals/ijrr/FirooziTTMSLZSKHIDWLS25","https://doi.org/10.1177/02783649241281508"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/ijrr/FirooziTTMSLZSKHIDWLS25","documentUrl":null,"type":"Article"},{"key":"journals/ijrr/LvFZZSL25","url":"https://dblp.org/rec/journals/ijrr/LvFZZSL25","title":"SAM-RL: Sensing-aware model-based reinforcement learning via differentiable physics-based simulation and rendering.","year":2025,"types":["Article"],"venue":"Int. J. Robotics Res.","doi":"https://doi.org/10.1177/02783649241284653","numberOfCreators":6,"category":"journal","sources":["https://dblp.org/rec/journals/ijrr/LvFZZSL25","https://doi.org/10.1177/02783649241284653"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/ijrr/LvFZZSL25","documentUrl":null,"type":"Article"},{"key":"journals/pami/LiBXCYL25","url":"https://dblp.org/rec/journals/pami/LiBXCYL25","title":"HybrIK-X: Hybrid Analytical-Neural Inverse Kinematics for Whole-Body Mesh Recovery.","year":2025,"types":["Article"],"venue":"IEEE Trans. Pattern Anal. Mach. Intell.","doi":"https://doi.org/10.1109/TPAMI.2025.3528979","numberOfCreators":6,"category":"journal","sources":["https://dblp.org/rec/journals/pami/LiBXCYL25","https://doi.org/10.1109/TPAMI.2025.3528979"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/pami/LiBXCYL25","documentUrl":null,"type":"Article"},{"key":"journals/pami/PangWLL25","url":"https://dblp.org/rec/journals/pami/PangWLL25","title":"Auto-Pairing Positives Through Implicit Relation Circulation for Discriminative Self-Learning.","year":2025,"types":["Article"],"venue":"IEEE Trans. Pattern Anal. Mach. Intell.","doi":"https://doi.org/10.1109/TPAMI.2025.3526802","numberOfCreators":4,"category":"journal","sources":["https://dblp.org/rec/journals/pami/PangWLL25","https://doi.org/10.1109/TPAMI.2025.3526802"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/pami/PangWLL25","documentUrl":null,"type":"Article"},{"key":"journals/pami/QuZRLCTJ25","url":"https://dblp.org/rec/journals/pami/QuZRLCTJ25","title":"GLC++: Source-Free Universal Domain Adaptation Through Global-Local Clustering and Contrastive Affinity Learning.","year":2025,"types":["Article"],"venue":"IEEE Trans. Pattern Anal. Mach. Intell.","doi":"https://doi.org/10.1109/TPAMI.2025.3593669","numberOfCreators":7,"category":"journal","sources":["https://dblp.org/rec/journals/pami/QuZRLCTJ25","https://doi.org/10.1109/TPAMI.2025.3593669"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/pami/QuZRLCTJ25","documentUrl":null,"type":"Article"},{"key":"journals/pami/YangZZZKXL25","url":"https://dblp.org/rec/journals/pami/YangZZZKXL25","title":"Multi-View Hand Reconstruction With a Point-Embedded Transformer.","year":2025,"types":["Article"],"venue":"IEEE Trans. Pattern Anal. Mach. Intell.","doi":"https://doi.org/10.1109/TPAMI.2025.3598089","numberOfCreators":7,"category":"journal","sources":["https://dblp.org/rec/journals/pami/YangZZZKXL25","https://doi.org/10.1109/TPAMI.2025.3598089"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/pami/YangZZZKXL25","documentUrl":null,"type":"Article"},{"key":"journals/ral/HeFCFL25","url":"https://dblp.org/rec/journals/ral/HeFCFL25","title":"FoAR: Force-Aware Reactive Policy for Contact-Rich Robotic Manipulation.","year":2025,"types":["Article"],"venue":"IEEE Robotics Autom. Lett.","doi":"https://doi.org/10.1109/LRA.2025.3560871","numberOfCreators":5,"category":"journal","sources":["https://dblp.org/rec/journals/ral/HeFCFL25","https://doi.org/10.1109/LRA.2025.3560871"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/ral/HeFCFL25","documentUrl":null,"type":"Article"},{"key":"journals/ral/SuZFLLY25","url":"https://dblp.org/rec/journals/ral/SuZFLLY25","title":"Motion Before Action: Diffusing Object Motion as Manipulation Condition.","year":2025,"types":["Article"],"venue":"IEEE Robotics Autom. Lett.","doi":"https://doi.org/10.1109/LRA.2025.3577424","numberOfCreators":6,"category":"journal","sources":["https://dblp.org/rec/journals/ral/SuZFLLY25","https://doi.org/10.1109/LRA.2025.3577424"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/ral/SuZFLLY25","documentUrl":null,"type":"Article"},{"key":"journals/ral/ZhangXYXTL25","url":"https://dblp.org/rec/journals/ral/ZhangXYXTL25","title":"DexTOG: Learning Task-Oriented Dexterous Grasp With Language Condition.","year":2025,"types":["Article"],"venue":"IEEE Robotics Autom. Lett.","doi":"https://doi.org/10.1109/LRA.2024.3518116","numberOfCreators":6,"category":"journal","sources":["https://dblp.org/rec/journals/ral/ZhangXYXTL25","https://doi.org/10.1109/LRA.2024.3518116"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/ral/ZhangXYXTL25","documentUrl":null,"type":"Article"}],"preprints":[{"key":"journals/corr/abs-2502-16420","url":"https://dblp.org/rec/journals/corr/abs-2502-16420","title":"AnyDexGrasp: General Dexterous Grasping for Different Hands with Human-level Learning Efficiency.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2502.16420","numberOfCreators":6,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2502-16420","https://doi.org/10.48550/ARXIV.2502.16420"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2502-16420","documentUrl":null,"type":"Informal","arxivId":"2502.16420","arxivUrl":"https://arxiv.org/abs/2502.16420"},{"key":"journals/corr/abs-2503-02881","url":"https://dblp.org/rec/journals/corr/abs-2503-02881","title":"Reactive Diffusion Policy: Slow-Fast Visual-Tactile Policy Learning for Contact-Rich Manipulation.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2503.02881","numberOfCreators":8,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2503-02881","https://doi.org/10.48550/ARXIV.2503.02881"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-02881","documentUrl":null,"type":"Informal","arxivId":"2503.02881","arxivUrl":"https://arxiv.org/abs/2503.02881"},{"key":"journals/corr/abs-2503-03081","url":"https://dblp.org/rec/journals/corr/abs-2503-03081","title":"AirExo-2: Scaling up Generalizable Robotic Imitation Learning with Low-Cost Exoskeletons.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2503.03081","numberOfCreators":14,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2503-03081","https://doi.org/10.48550/ARXIV.2503.03081"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-03081","documentUrl":null,"type":"Informal","arxivId":"2503.03081","arxivUrl":"https://arxiv.org/abs/2503.03081"},{"key":"journals/corr/abs-2503-06677","url":"https://dblp.org/rec/journals/corr/abs-2503-06677","title":"REArtGS: Reconstructing and Generating Articulated Objects via 3D Gaussian Splatting with Geometric and Motion Constraints.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2503.06677","numberOfCreators":8,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2503-06677","https://doi.org/10.48550/ARXIV.2503.06677"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-06677","documentUrl":null,"type":"Informal","arxivId":"2503.06677","arxivUrl":"https://arxiv.org/abs/2503.06677"},{"key":"journals/corr/abs-2503-13217","url":"https://dblp.org/rec/journals/corr/abs-2503-13217","title":"Dense Policy: Bidirectional Autoregressive Learning of Actions.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2503.13217","numberOfCreators":8,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2503-13217","https://doi.org/10.48550/ARXIV.2503.13217"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-13217","documentUrl":null,"type":"Informal","arxivId":"2503.13217","arxivUrl":"https://arxiv.org/abs/2503.13217"},{"key":"journals/corr/abs-2503-23348","url":"https://dblp.org/rec/journals/corr/abs-2503-23348","title":"Physically Ground Commonsense Knowledge for Articulated Object Manipulation with Analytic Concepts.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2503.23348","numberOfCreators":4,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2503-23348","https://doi.org/10.48550/ARXIV.2503.23348"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-23348","documentUrl":null,"type":"Informal","arxivId":"2503.23348","arxivUrl":"https://arxiv.org/abs/2503.23348"},{"key":"journals/corr/abs-2504-02312","url":"https://dblp.org/rec/journals/corr/abs-2504-02312","title":"OmniCam: Unified Multimodal Video Generation via Camera Control.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2504.02312","numberOfCreators":12,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2504-02312","https://doi.org/10.48550/ARXIV.2504.02312"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2504-02312","documentUrl":null,"type":"Informal","arxivId":"2504.02312","arxivUrl":"https://arxiv.org/abs/2504.02312"},{"key":"journals/corr/abs-2504-04170","url":"https://dblp.org/rec/journals/corr/abs-2504-04170","title":"Digital Gene: Learning about the Physical World through Analytic Concepts.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2504.04170","numberOfCreators":2,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2504-04170","https://doi.org/10.48550/ARXIV.2504.04170"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2504-04170","documentUrl":null,"type":"Informal","arxivId":"2504.04170","arxivUrl":"https://arxiv.org/abs/2504.04170"},{"key":"journals/corr/abs-2504-04573","url":"https://dblp.org/rec/journals/corr/abs-2504-04573","title":"DexTOG: Learning Task-Oriented Dexterous Grasp with Language.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2504.04573","numberOfCreators":6,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2504-04573","https://doi.org/10.48550/ARXIV.2504.04573"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2504-04573","documentUrl":null,"type":"Informal","arxivId":"2504.04573","arxivUrl":"https://arxiv.org/abs/2504.04573"},{"key":"journals/corr/abs-2504-13175","url":"https://dblp.org/rec/journals/corr/abs-2504-13175","title":"Novel Demonstration Generation with Gaussian Splatting Enables Robust One-Shot Manipulation.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2504.13175","numberOfCreators":8,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2504-13175","https://doi.org/10.48550/ARXIV.2504.13175"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2504-13175","documentUrl":null,"type":"Informal","arxivId":"2504.13175","arxivUrl":"https://arxiv.org/abs/2504.13175"},{"key":"journals/corr/abs-2505-01396","url":"https://dblp.org/rec/journals/corr/abs-2505-01396","title":"SIME: Enhancing Policy Self-Improvement with Modal-level Exploration.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2505.01396","numberOfCreators":6,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2505-01396","https://doi.org/10.48550/ARXIV.2505.01396"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-01396","documentUrl":null,"type":"Informal","arxivId":"2505.01396","arxivUrl":"https://arxiv.org/abs/2505.01396"},{"key":"journals/corr/abs-2505-22159","url":"https://dblp.org/rec/journals/corr/abs-2505-22159","title":"ForceVLA: Enhancing VLA Models with a Force-aware MoE for Contact-rich Manipulation.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2505.22159","numberOfCreators":12,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2505-22159","https://doi.org/10.48550/ARXIV.2505.22159"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-22159","documentUrl":null,"type":"Informal","arxivId":"2505.22159","arxivUrl":"https://arxiv.org/abs/2505.22159"},{"key":"journals/corr/abs-2506-01551","url":"https://dblp.org/rec/journals/corr/abs-2506-01551","title":"EvolveNav: Self-Improving Embodied Reasoning for LLM-Based Vision-Language Navigation.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2506.01551","numberOfCreators":11,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2506-01551","https://doi.org/10.48550/ARXIV.2506.01551"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-01551","documentUrl":null,"type":"Informal","arxivId":"2506.01551","arxivUrl":"https://arxiv.org/abs/2506.01551"},{"key":"journals/corr/abs-2506-02860","url":"https://dblp.org/rec/journals/corr/abs-2506-02860","title":"Tru-POMDP: Task Planning Under Uncertainty via Tree of Hypotheses and Open-Ended POMDPs.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2506.02860","numberOfCreators":6,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2506-02860","https://doi.org/10.48550/ARXIV.2506.02860"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-02860","documentUrl":null,"type":"Informal","arxivId":"2506.02860","arxivUrl":"https://arxiv.org/abs/2506.02860"},{"key":"journals/corr/abs-2506-08334","url":"https://dblp.org/rec/journals/corr/abs-2506-08334","title":"Generalizable Articulated Object Reconstruction from Casually Captured RGBD Videos.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2506.08334","numberOfCreators":4,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2506-08334","https://doi.org/10.48550/ARXIV.2506.08334"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-08334","documentUrl":null,"type":"Informal","arxivId":"2506.08334","arxivUrl":"https://arxiv.org/abs/2506.08334"},{"key":"journals/corr/abs-2506-21057","url":"https://dblp.org/rec/journals/corr/abs-2506-21057","title":"Knowledge-Driven Imitation Learning: Enabling Generalization Across Diverse Conditions.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2506.21057","numberOfCreators":5,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2506-21057","https://doi.org/10.48550/ARXIV.2506.21057"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-21057","documentUrl":null,"type":"Informal","arxivId":"2506.21057","arxivUrl":"https://arxiv.org/abs/2506.21057"},{"key":"journals/corr/abs-2507-02600","url":"https://dblp.org/rec/journals/corr/abs-2507-02600","title":"ArtGS:3D Gaussian Splatting for Interactive Visual-Physical Modeling and Manipulation of Articulated Objects.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2507.02600","numberOfCreators":11,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2507-02600","https://doi.org/10.48550/ARXIV.2507.02600"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2507-02600","documentUrl":null,"type":"Informal","arxivId":"2507.02600","arxivUrl":"https://arxiv.org/abs/2507.02600"},{"key":"journals/corr/abs-2507-21545","url":"https://dblp.org/rec/journals/corr/abs-2507-21545","title":"Pretraining a Unified PDDL Domain from Real-World Demonstrations for Generalizable Robot Task Planning.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2507.21545","numberOfCreators":4,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2507-21545","https://doi.org/10.48550/ARXIV.2507.21545"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2507-21545","documentUrl":null,"type":"Informal","arxivId":"2507.21545","arxivUrl":"https://arxiv.org/abs/2507.21545"},{"key":"journals/corr/abs-2508-07770","url":"https://dblp.org/rec/journals/corr/abs-2508-07770","title":"AgentWorld: An Interactive Simulation Platform for Scene Construction and Mobile Robotic Manipulation.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2508.07770","numberOfCreators":5,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2508-07770","https://doi.org/10.48550/ARXIV.2508.07770"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-07770","documentUrl":null,"type":"Informal","arxivId":"2508.07770","arxivUrl":"https://arxiv.org/abs/2508.07770"},{"key":"journals/corr/abs-2508-14441","url":"https://dblp.org/rec/journals/corr/abs-2508-14441","title":"FBI: Learning Dexterous In-hand Manipulation with Dynamic Visuotactile Shortcut Policy.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2508.14441","numberOfCreators":7,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2508-14441","https://doi.org/10.48550/ARXIV.2508.14441"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-14441","documentUrl":null,"type":"Informal","arxivId":"2508.14441","arxivUrl":"https://arxiv.org/abs/2508.14441"},{"key":"journals/corr/abs-2509-11839","url":"https://dblp.org/rec/journals/corr/abs-2509-11839","title":"TrajBooster: Boosting Humanoid Whole-Body Manipulation via Trajectory-Centric Learning.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2509.11839","numberOfCreators":11,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2509-11839","https://doi.org/10.48550/ARXIV.2509.11839"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-11839","documentUrl":null,"type":"Informal","arxivId":"2509.11839","arxivUrl":"https://arxiv.org/abs/2509.11839"},{"key":"journals/corr/abs-2509-15953","url":"https://dblp.org/rec/journals/corr/abs-2509-15953","title":"Right-Side-Out: Learning Zero-Shot Sim-to-Real Garment Reversal.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2509.15953","numberOfCreators":12,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2509-15953","https://doi.org/10.48550/ARXIV.2509.15953"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-15953","documentUrl":null,"type":"Informal","arxivId":"2509.15953","arxivUrl":"https://arxiv.org/abs/2509.15953"},{"key":"journals/corr/abs-2509-17141","url":"https://dblp.org/rec/journals/corr/abs-2509-17141","title":"History-Aware Visuomotor Policy Learning via Point Tracking.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2509.17141","numberOfCreators":5,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2509-17141","https://doi.org/10.48550/ARXIV.2509.17141"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-17141","documentUrl":null,"type":"Informal","arxivId":"2509.17141","arxivUrl":"https://arxiv.org/abs/2509.17141"},{"key":"journals/corr/abs-2509-17450","url":"https://dblp.org/rec/journals/corr/abs-2509-17450","title":"Learning Dexterous Manipulation with Quantized Hand State.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2509.17450","numberOfCreators":8,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2509-17450","https://doi.org/10.48550/ARXIV.2509.17450"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-17450","documentUrl":null,"type":"Informal","arxivId":"2509.17450","arxivUrl":"https://arxiv.org/abs/2509.17450"},{"key":"journals/corr/abs-2509-19292","url":"https://dblp.org/rec/journals/corr/abs-2509-19292","title":"SOE: Sample-Efficient Robot Policy Self-Improvement via On-Manifold Exploration.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2509.19292","numberOfCreators":6,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2509-19292","https://doi.org/10.48550/ARXIV.2509.19292"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-19292","documentUrl":null,"type":"Informal","arxivId":"2509.19292","arxivUrl":"https://arxiv.org/abs/2509.19292"},{"key":"journals/corr/abs-2509-21242","url":"https://dblp.org/rec/journals/corr/abs-2509-21242","title":"FSGlove: An Inertial-Based Hand Tracking System with Shape-Aware Calibration.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2509.21242","numberOfCreators":5,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2509-21242","https://doi.org/10.48550/ARXIV.2509.21242"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-21242","documentUrl":null,"type":"Informal","arxivId":"2509.21242","arxivUrl":"https://arxiv.org/abs/2509.21242"},{"key":"journals/corr/abs-2510-02298","url":"https://dblp.org/rec/journals/corr/abs-2510-02298","title":"ARMADA: Autonomous Online Failure Detection and Human Shared Control Empower Scalable Real-world Deployment and Adaptation.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2510.02298","numberOfCreators":6,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2510-02298","https://doi.org/10.48550/ARXIV.2510.02298"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-02298","documentUrl":null,"type":"Informal","arxivId":"2510.02298","arxivUrl":"https://arxiv.org/abs/2510.02298"},{"key":"journals/corr/abs-2510-07975","url":"https://dblp.org/rec/journals/corr/abs-2510-07975","title":"Executable Analytic Concepts as the Missing Link Between VLM Insight and Precise Manipulation.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2510.07975","numberOfCreators":6,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2510-07975","https://doi.org/10.48550/ARXIV.2510.07975"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-07975","documentUrl":null,"type":"Informal","arxivId":"2510.07975","arxivUrl":"https://arxiv.org/abs/2510.07975"},{"key":"journals/corr/abs-2511-05996","url":"https://dblp.org/rec/journals/corr/abs-2511-05996","title":"Exploring Category-level Articulated Object Pose Tracking on SE(3) Manifolds.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2511.05996","numberOfCreators":9,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2511-05996","https://doi.org/10.48550/ARXIV.2511.05996"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2511-05996","documentUrl":null,"type":"Informal","arxivId":"2511.05996","arxivUrl":"https://arxiv.org/abs/2511.05996"},{"key":"journals/corr/abs-2511-17059","url":"https://dblp.org/rec/journals/corr/abs-2511-17059","title":"REArtGS++: Generalizable Articulation Reconstruction with Temporal Geometry Constraint via Planar Gaussian Splatting.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2511.17059","numberOfCreators":8,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2511-17059","https://doi.org/10.48550/ARXIV.2511.17059"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2511-17059","documentUrl":null,"type":"Informal","arxivId":"2511.17059","arxivUrl":"https://arxiv.org/abs/2511.17059"},{"key":"journals/corr/abs-2511-17898","url":"https://dblp.org/rec/journals/corr/abs-2511-17898","title":"L1 Sample Flow for Efficient Visuomotor Learning.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2511.17898","numberOfCreators":9,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2511-17898","https://doi.org/10.48550/ARXIV.2511.17898"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2511-17898","documentUrl":null,"type":"Informal","arxivId":"2511.17898","arxivUrl":"https://arxiv.org/abs/2511.17898"},{"key":"journals/corr/abs-2512-10946","url":"https://dblp.org/rec/journals/corr/abs-2512-10946","title":"ImplicitRDP: An End-to-End Visual-Force Diffusion Policy with Structural Slow-Fast Learning.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2512.10946","numberOfCreators":9,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2512-10946","https://doi.org/10.48550/ARXIV.2512.10946"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-10946","documentUrl":null,"type":"Informal","arxivId":"2512.10946","arxivUrl":"https://arxiv.org/abs/2512.10946"}],"excludedFormal":[],"otherRecords":[],"matchedName":"Cewu Lu","databaseLabel":"Cewu Lu","databaseMetadata":{"type":["https://dblp.org/rdf/schema#Creator","https://dblp.org/rdf/schema#Person"],"label":["Cewu Lu"],"affiliation":["Stanford University","Chinese University of Hong Kong","Shanghai Jiao Tong University, Department of Computer Science and Engineering, China"],"homepage":["http://web.stanford.edu/~lucewu/WWW.html"],"orcid":["https://orcid.org/0000-0003-1533-8576","https://orcid.org/0000-0002-4023-9257"],"primaryAffiliation":["Shanghai Jiao Tong University, Department of Computer Science and Engineering, China"],"primaryHomepage":["http://web.stanford.edu/~lucewu/WWW.html"]},"rawFormalRecordCount2025":51,"signatureAudit":{"completedAt":"2026-10-19","frozen":true,"scope":"对 B 组 39 个数值档案的全部 1074 条原始 2025 正式记录扫描 DBLP author-signature ORCID 和机构；复用既有 59 条 Crossref 核验，补查 6 条新触发记录。重点核查不同 ORCID，以及只有预期机构之外机构的条目。本轮不扩展为所有作者逐篇全文审计。","formalRecordCoverage":51,"orcidCounts":{"https://orcid.org/0000-0003-1533-8576":13},"institutionCounts":{"Shanghai Artificial Intelligence Laboratory":1,"Shanghai Jiao Tong University (SJTU)":42},"caveat":"机构名称可能由 DBLP 自动映射而失真；多 ORCID 也不自动等于异人。只有有原始资料支撑的错归才作确认排除，未解决分支则暂停总数。"},"labName":"Machine Vision and Intelligence Group (MVIG)","labUrl":"https://www.mvig.org/","labEvidence":"MVIG 官方网站使用 Machine Vision and Intelligence Group 名称，列上海交通大学 Cewu Lu，并在招募信息中直接称我们 MVIG 实验室。","labSourceUrl":"https://www.mvig.org/","sourceWarning":false,"excludedOther":[],"excludedHomonyms":[],"unassignedCandidates":[],"knownPreprintMinimum2025":null,"excludedMisattributed":[],"displayNotes":"身份已与原名单机构及公开资料核对确认。2025 年正式记录 51 条（会议 42、期刊 9），所有作者位置均计入，不表示主导或贡献份额；预印本 32 条单列，不加总。","labDisplayNotes":"MVIG 官网写出 Machine Vision and Intelligence Group 全称，列出上海交大卢策吾，并以本组名义招募，据此归组。"},{"index":69,"name":"Ping Luo","nameZh":"罗平","role":"Associate Professor","affiliation":"The University of Hong Kong","affiliationZh":"香港大学","source":"DBLP RDF via official SPARQL; primary-source identity checks","sourceUrl":"https://sparql.dblp.org/","profileUrl":"https://dblp.org/pid/54/4989-2.html","identifier":"54/4989-2","retrievedAt":"2026-10-19","count2025":60,"conference2025":47,"journal2025":13,"preprint2025":52,"status":"confirmed","notes":"","identityEvidence":[{"url":"https://dblp.org/pid/54/4989-2.html","evidence":"DBLP RDF 类型为 Person，消歧后名字为 Ping Luo 0002。机构元数据含：University of Hong Kong, Shanghai AI Laboratory, Department of Computer Science, Hong Kong；Sun Yat-Sen University, School of Software, Guangzhou, China；Lotus Hill Insititue, China；Chinese University of Hong Kong, Department of Information Engineering, Hong Kong"}],"papers":[{"key":"conf/aaai/LaiLCPHP025","url":"https://dblp.org/rec/conf/aaai/LaiLCPHP025","title":"AnalogCoder: Analog Circuit Design via Training-Free Code Generation.","year":2025,"types":["Inproceedings"],"venue":"AAAI","doi":"https://doi.org/10.1609/AAAI.V39I1.32016","eventYear":2025,"numberOfCreators":7,"category":"conference","sources":["https://dblp.org/rec/conf/aaai/LaiLCPHP025","https://doi.org/10.1609/AAAI.V39I1.32016"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/aaai/LaiLCPHP025","documentUrl":null,"type":"Inproceedings"},{"key":"conf/aaai/YangZ000025","url":"https://dblp.org/rec/conf/aaai/YangZ000025","title":"AutoMMLab: Automatically Generating Deployable Models from Language Instructions for Computer Vision Tasks.","year":2025,"types":["Inproceedings"],"venue":"AAAI","doi":"https://doi.org/10.1609/AAAI.V39I21.34358","eventYear":2025,"numberOfCreators":6,"category":"conference","sources":["https://dblp.org/rec/conf/aaai/YangZ000025","https://doi.org/10.1609/AAAI.V39I21.34358"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/aaai/YangZ000025","documentUrl":null,"type":"Inproceedings"},{"key":"conf/aaai/YuYZY00N25","url":"https://dblp.org/rec/conf/aaai/YuYZY00N25","title":"End-to-End Autonomous Driving Through V2X Cooperation.","year":2025,"types":["Inproceedings"],"venue":"AAAI","doi":"https://doi.org/10.1609/AAAI.V39I9.33040","eventYear":2025,"numberOfCreators":7,"category":"conference","sources":["https://dblp.org/rec/conf/aaai/YuYZY00N25","https://doi.org/10.1609/AAAI.V39I9.33040"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/aaai/YuYZY00N25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/acl/ChenSXWGZ025","url":"https://dblp.org/rec/conf/acl/ChenSXWGZ025","title":"EfficientQAT: Efficient Quantization-Aware Training for Large Language Models.","year":2025,"types":["Inproceedings"],"venue":"ACL (1)","doi":"https://doi.org/10.18653/V1/2025.ACL-LONG.498","eventYear":2025,"numberOfCreators":7,"category":"conference","sources":["https://dblp.org/rec/conf/acl/ChenSXWGZ025","https://doi.org/10.18653/V1/2025.ACL-LONG.498"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/acl/ChenSXWGZ025","documentUrl":null,"type":"Inproceedings"},{"key":"conf/acl/HuCC0S025","url":"https://dblp.org/rec/conf/acl/HuCC0S025","title":"HiAgent: Hierarchical Working Memory Management for Solving Long-Horizon Agent Tasks with Large Language Model.","year":2025,"types":["Inproceedings"],"venue":"ACL (1)","doi":"https://doi.org/10.18653/V1/2025.ACL-LONG.1575","eventYear":2025,"numberOfCreators":6,"category":"conference","sources":["https://dblp.org/rec/conf/acl/HuCC0S025","https://doi.org/10.18653/V1/2025.ACL-LONG.1575"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/acl/HuCC0S025","documentUrl":null,"type":"Inproceedings"},{"key":"conf/acl/HuCZLCL00SL25","url":"https://dblp.org/rec/conf/acl/HuCZLCL00SL25","title":"Text2World: Benchmarking Large Language Models for Symbolic World Model Generation.","year":2025,"types":["Inproceedings"],"venue":"ACL (Findings)","doi":"https://doi.org/10.18653/V1/2025.FINDINGS-ACL.1337","eventYear":2025,"numberOfCreators":10,"category":"conference","sources":["https://dblp.org/rec/conf/acl/HuCZLCL00SL25","https://doi.org/10.18653/V1/2025.FINDINGS-ACL.1337"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/acl/HuCZLCL00SL25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/acl/LvLSLLY25","url":"https://dblp.org/rec/conf/acl/LvLSLLY25","title":"Whether LLMs Know If They Know: Identifying Knowledge Boundaries via Debiased Historical In-Context Learning.","year":2025,"types":["Inproceedings"],"venue":"ACL (Findings)","doi":"https://doi.org/10.18653/V1/2025.FINDINGS-ACL.999","eventYear":2025,"numberOfCreators":6,"category":"conference","sources":["https://dblp.org/rec/conf/acl/LvLSLLY25","https://doi.org/10.18653/V1/2025.FINDINGS-ACL.999"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/acl/LvLSLLY25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/cvpr/ChenGZZZYHWLHLZ25","url":"https://dblp.org/rec/conf/cvpr/ChenGZZZYHWLHLZ25","title":"Goku: Flow Based Video Generative Foundation Models.","year":2025,"types":["Inproceedings"],"venue":"CVPR","doi":"https://doi.org/10.1109/CVPR52734.2025.02190","eventYear":2025,"numberOfCreators":22,"category":"conference","sources":["https://dblp.org/rec/conf/cvpr/ChenGZZZYHWLHLZ25","https://doi.org/10.1109/CVPR52734.2025.02190"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/ChenGZZZYHWLHLZ25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/cvpr/ChenMLCPCXH00025","url":"https://dblp.org/rec/conf/cvpr/ChenMLCPCXH00025","title":"G3Flow: Generative 3D Semantic Flow for Pose-aware and Generalizable Object Manipulation.","year":2025,"types":["Inproceedings"],"venue":"CVPR","doi":"https://doi.org/10.1109/CVPR52734.2025.00169","eventYear":2025,"numberOfCreators":11,"category":"conference","sources":["https://dblp.org/rec/conf/cvpr/ChenMLCPCXH00025","https://doi.org/10.1109/CVPR52734.2025.00169"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/ChenMLCPCXH00025","documentUrl":null,"type":"Inproceedings"},{"key":"conf/cvpr/ChenS0SJL25","url":"https://dblp.org/rec/conf/cvpr/ChenS0SJL25","title":"JiSAM: Alleviate Labeling Burden and Corner Case Problems in Autonomous Driving via Minimal Real-World Data.","year":2025,"types":["Inproceedings"],"venue":"CVPR","doi":"https://doi.org/10.1109/CVPR52734.2025.00637","eventYear":2025,"numberOfCreators":6,"category":"conference","sources":["https://dblp.org/rec/conf/cvpr/ChenS0SJL25","https://doi.org/10.1109/CVPR52734.2025.00637"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/ChenS0SJL25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/cvpr/GeXJPTLDJZ25","url":"https://dblp.org/rec/conf/cvpr/GeXJPTLDJZ25","title":"CompGS: Unleashing 2D Compositionality for Compositional Text-to-3D via Dynamically Optimizing 3D Gaussians.","year":2025,"types":["Inproceedings"],"venue":"CVPR","doi":"https://doi.org/10.1109/CVPR52734.2025.01725","eventYear":2025,"numberOfCreators":9,"category":"conference","sources":["https://dblp.org/rec/conf/cvpr/GeXJPTLDJZ25","https://doi.org/10.1109/CVPR52734.2025.01725"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/GeXJPTLDJZ25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/cvpr/LiangMWCSZTLD25","url":"https://dblp.org/rec/conf/cvpr/LiangMWCSZTLD25","title":"DexHandDiff: Interaction-aware Diffusion Planning for Adaptive Dexterous Manipulation.","year":2025,"types":["Inproceedings"],"venue":"CVPR","doi":"https://doi.org/10.1109/CVPR52734.2025.00170","eventYear":2025,"numberOfCreators":9,"category":"conference","sources":["https://dblp.org/rec/conf/cvpr/LiangMWCSZTLD25","https://doi.org/10.1109/CVPR52734.2025.00170"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/LiangMWCSZTLD25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/cvpr/LiuCC0OZLSCL25","url":"https://dblp.org/rec/conf/cvpr/LiuCC0OZLSCL25","title":"MangaNinja: Line Art Colorization with Precise Reference Following.","year":2025,"types":["Inproceedings"],"venue":"CVPR","doi":"https://doi.org/10.1109/CVPR52734.2025.00532","eventYear":2025,"numberOfCreators":10,"category":"conference","sources":["https://dblp.org/rec/conf/cvpr/LiuCC0OZLSCL25","https://doi.org/10.1109/CVPR52734.2025.00532"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/LiuCC0OZLSCL25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/cvpr/MuCCPLGLYZXLXDL25","url":"https://dblp.org/rec/conf/cvpr/MuCCPLGLYZXLXDL25","title":"RoboTwin: Dual-Arm Robot Benchmark with Generative Digital Twins.","year":2025,"types":["Inproceedings"],"venue":"CVPR","doi":"https://doi.org/10.1109/CVPR52734.2025.02575","eventYear":2025,"numberOfCreators":14,"category":"conference","sources":["https://dblp.org/rec/conf/cvpr/MuCCPLGLYZXLXDL25","https://doi.org/10.1109/CVPR52734.2025.02575"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/MuCCPLGLYZXLXDL25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/cvpr/Sun0X00QL025","url":"https://dblp.org/rec/conf/cvpr/Sun0X00QL025","title":"Unsupervised Continual Domain Shift Learning with Multi-Prototype Modeling.","year":2025,"types":["Inproceedings"],"venue":"CVPR","doi":"https://doi.org/10.1109/CVPR52734.2025.00947","eventYear":2025,"numberOfCreators":8,"category":"conference","sources":["https://dblp.org/rec/conf/cvpr/Sun0X00QL025","https://doi.org/10.1109/CVPR52734.2025.00947"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/Sun0X00QL025","documentUrl":null,"type":"Inproceedings"},{"key":"conf/cvpr/WuCWMLPLXYR025","url":"https://dblp.org/rec/conf/cvpr/WuCWMLPLXYR025","title":"Janus: Decoupling Visual Encoding for Unified Multimodal Understanding and Generation.","year":2025,"types":["Inproceedings"],"venue":"CVPR","doi":"https://doi.org/10.1109/CVPR52734.2025.01210","eventYear":2025,"numberOfCreators":11,"category":"conference","sources":["https://dblp.org/rec/conf/cvpr/WuCWMLPLXYR025","https://doi.org/10.1109/CVPR52734.2025.01210"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/WuCWMLPLXYR025","documentUrl":null,"type":"Inproceedings"},{"key":"conf/cvpr/YangZ000025","url":"https://dblp.org/rec/conf/cvpr/YangZ000025","title":"NADER: Neural Architecture Design via Multi-Agent Collaboration.","year":2025,"types":["Inproceedings"],"venue":"CVPR","doi":"https://doi.org/10.1109/CVPR52734.2025.00420","eventYear":2025,"numberOfCreators":6,"category":"conference","sources":["https://dblp.org/rec/conf/cvpr/YangZ000025","https://doi.org/10.1109/CVPR52734.2025.00420"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/YangZ000025","documentUrl":null,"type":"Inproceedings"},{"key":"conf/eccv/ChenGXWYRWLLL24","url":"https://dblp.org/rec/conf/eccv/ChenGXWYRWLLL24","title":"PIXART-Σ: Weak-to-Strong Training of Diffusion Transformer for 4K Text-to-Image Generation.","year":2025,"types":["Inproceedings"],"venue":"ECCV (32)","doi":"https://doi.org/10.1007/978-3-031-73411-3_5","eventYear":2024,"numberOfCreators":10,"category":"conference","sources":["https://dblp.org/rec/conf/eccv/ChenGXWYRWLLL24","https://doi.org/10.1007/978-3-031-73411-3_5"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2024,"sourceUrl":"https://dblp.org/rec/conf/eccv/ChenGXWYRWLLL24","documentUrl":null,"type":"Inproceedings"},{"key":"conf/eccv/JinLLLQL24","url":"https://dblp.org/rec/conf/eccv/JinLLLQL24","title":"You Only Learn One Query: Learning Unified Human Query for Single-Stage Multi-person Multi-task Human-Centric Perception.","year":2025,"types":["Inproceedings"],"venue":"ECCV (18)","doi":"https://doi.org/10.1007/978-3-031-72649-1_8","eventYear":2024,"numberOfCreators":6,"category":"conference","sources":["https://dblp.org/rec/conf/eccv/JinLLLQL24","https://doi.org/10.1007/978-3-031-72649-1_8"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2024,"sourceUrl":"https://dblp.org/rec/conf/eccv/JinLLLQL24","documentUrl":null,"type":"Inproceedings"},{"key":"conf/eccv/JinYXLQWL24","url":"https://dblp.org/rec/conf/eccv/JinYXLQWL24","title":"UniFS: Universal Few-Shot Instance Perception with Point Representations.","year":2025,"types":["Inproceedings"],"venue":"ECCV (29)","doi":"https://doi.org/10.1007/978-3-031-73397-0_27","eventYear":2024,"numberOfCreators":7,"category":"conference","sources":["https://dblp.org/rec/conf/eccv/JinYXLQWL24","https://doi.org/10.1007/978-3-031-73397-0_27"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2024,"sourceUrl":"https://dblp.org/rec/conf/eccv/JinYXLQWL24","documentUrl":null,"type":"Inproceedings"},{"key":"conf/eccv/LiSWXFZYXLL24","url":"https://dblp.org/rec/conf/eccv/LiSWXFZYXLL24","title":"Segment, Lift and Fit: Automatic 3D Shape Labeling from 2D Prompts.","year":2025,"types":["Inproceedings"],"venue":"ECCV (84)","doi":"https://doi.org/10.1007/978-3-031-72907-2_24","eventYear":2024,"numberOfCreators":10,"category":"conference","sources":["https://dblp.org/rec/conf/eccv/LiSWXFZYXLL24","https://doi.org/10.1007/978-3-031-72907-2_24"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2024,"sourceUrl":"https://dblp.org/rec/conf/eccv/LiSWXFZYXLL24","documentUrl":null,"type":"Inproceedings"},{"key":"conf/eccv/MuCPCGZLXL24","url":"https://dblp.org/rec/conf/eccv/MuCPCGZLXL24","title":"RoboTwin: Dual-Arm Robot Benchmark with Generative Digital Twins (Early Version).","year":2025,"types":["Inproceedings"],"venue":"ECCV Workshops (8)","doi":"https://doi.org/10.1007/978-3-031-91813-1_17","eventYear":2024,"numberOfCreators":9,"category":"conference","sources":["https://dblp.org/rec/conf/eccv/MuCPCGZLXL24","https://doi.org/10.1007/978-3-031-91813-1_17"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2024,"sourceUrl":"https://dblp.org/rec/conf/eccv/MuCPCGZLXL24","documentUrl":null,"type":"Inproceedings"},{"key":"conf/eccv/SimaRCCZXBLGL24","url":"https://dblp.org/rec/conf/eccv/SimaRCCZXBLGL24","title":"DriveLM: Driving with Graph Visual Question Answering.","year":2025,"types":["Inproceedings"],"venue":"ECCV (52)","doi":"https://doi.org/10.1007/978-3-031-72943-0_15","eventYear":2024,"numberOfCreators":10,"category":"conference","sources":["https://dblp.org/rec/conf/eccv/SimaRCCZXBLGL24","https://doi.org/10.1007/978-3-031-72943-0_15"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2024,"sourceUrl":"https://dblp.org/rec/conf/eccv/SimaRCCZXBLGL24","documentUrl":null,"type":"Inproceedings"},{"key":"conf/eccv/YaoJXZLQLW24","url":"https://dblp.org/rec/conf/eccv/YaoJXZLQLW24","title":"GKGNet: Group K-Nearest Neighbor Based Graph Convolutional Network for Multi-label Image Recognition.","year":2025,"types":["Inproceedings"],"venue":"ECCV (18)","doi":"https://doi.org/10.1007/978-3-031-72649-1_6","eventYear":2024,"numberOfCreators":8,"category":"conference","sources":["https://dblp.org/rec/conf/eccv/YaoJXZLQLW24","https://doi.org/10.1007/978-3-031-72649-1_6"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2024,"sourceUrl":"https://dblp.org/rec/conf/eccv/YaoJXZLQLW24","documentUrl":null,"type":"Inproceedings"},{"key":"conf/eccv/ZhangSCXSZLCL24","url":"https://dblp.org/rec/conf/eccv/ZhangSCXSZLCL24","title":"GPT4RoI: Instruction Tuning Large Language Model on Region-of-Interest.","year":2025,"types":["Inproceedings"],"venue":"ECCV Workshops (8)","doi":"https://doi.org/10.1007/978-3-031-91813-1_4","eventYear":2024,"numberOfCreators":9,"category":"conference","sources":["https://dblp.org/rec/conf/eccv/ZhangSCXSZLCL24","https://doi.org/10.1007/978-3-031-91813-1_4"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2024,"sourceUrl":"https://dblp.org/rec/conf/eccv/ZhangSCXSZLCL24","documentUrl":null,"type":"Inproceedings"},{"key":"conf/eccv/ZhangZJQLL24","url":"https://dblp.org/rec/conf/eccv/ZhangZJQLL24","title":"When Pedestrian Detection Meets Multi-modal Learning: Generalist Model and Benchmark Dataset.","year":2025,"types":["Inproceedings"],"venue":"ECCV (48)","doi":"https://doi.org/10.1007/978-3-031-73195-2_25","eventYear":2024,"numberOfCreators":6,"category":"conference","sources":["https://dblp.org/rec/conf/eccv/ZhangZJQLL24","https://doi.org/10.1007/978-3-031-73195-2_25"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2024,"sourceUrl":"https://dblp.org/rec/conf/eccv/ZhangZJQLL24","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iccv/HaoYZWWKYFYQMSCZZZSLN25","url":"https://dblp.org/rec/conf/iccv/HaoYZWWKYFYQMSCZZZSLN25","title":"Research Challenges and Progress in the End-to-End V2X Cooperative Autonomous Driving Competition.","year":2025,"types":["Inproceedings"],"venue":"ICCVW","doi":"https://doi.org/10.1109/ICCVW69036.2025.00195","eventYear":2025,"numberOfCreators":19,"category":"conference","sources":["https://dblp.org/rec/conf/iccv/HaoYZWWKYFYQMSCZZZSLN25","https://doi.org/10.1109/ICCVW69036.2025.00195"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/HaoYZWWKYFYQMSCZZZSLN25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iccv/JiZWZCGSCSXHL25","url":"https://dblp.org/rec/conf/iccv/JiZWZCGSCSXHL25","title":"Prompt-A-Video: Prompt your Video Diffusion Model via Preference-Aligned LLM.","year":2025,"types":["Inproceedings"],"venue":"ICCV","doi":"https://doi.org/10.1109/ICCV51701.2025.01740","eventYear":2025,"numberOfCreators":12,"category":"conference","sources":["https://dblp.org/rec/conf/iccv/JiZWZCGSCSXHL25","https://doi.org/10.1109/ICCV51701.2025.01740"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/JiZWZCGSCSXHL25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iccv/LuSLDMLCHZL25","url":"https://dblp.org/rec/conf/iccv/LuSLDMLCHZL25","title":"GUIOdyssey: A Comprehensive Dataset for Cross-App GUI Navigation on Mobile Devices.","year":2025,"types":["Inproceedings"],"venue":"ICCV","doi":"https://doi.org/10.1109/ICCV51701.2025.02080","eventYear":2025,"numberOfCreators":10,"category":"conference","sources":["https://dblp.org/rec/conf/iccv/LuSLDMLCHZL25","https://doi.org/10.1109/ICCV51701.2025.02080"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/LuSLDMLCHZL25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iccv/LuWXJSZLL25","url":"https://dblp.org/rec/conf/iccv/LuWXJSZLL25","title":"Dynamic-DINO: Fine-Grained Mixture of Experts Tuning for Real-Time Open-Vocabulary Object Detection.","year":2025,"types":["Inproceedings"],"venue":"ICCV","doi":"https://doi.org/10.1109/ICCV51701.2025.01938","eventYear":2025,"numberOfCreators":8,"category":"conference","sources":["https://dblp.org/rec/conf/iccv/LuWXJSZLL25","https://doi.org/10.1109/ICCV51701.2025.01938"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/LuWXJSZLL25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iccv/WangKYCWZXLWLZZSLL25","url":"https://dblp.org/rec/conf/iccv/WangKYCWZXLWLZZSLL25","title":"LiT: Delving into a Simple Linear Diffusion Transformer for Image Generation.","year":2025,"types":["Inproceedings"],"venue":"ICCV","doi":"https://doi.org/10.1109/ICCV51701.2025.01491","eventYear":2025,"numberOfCreators":15,"category":"conference","sources":["https://dblp.org/rec/conf/iccv/WangKYCWZXLWLZZSLL25","https://doi.org/10.1109/ICCV51701.2025.01491"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/WangKYCWZXLWLZZSLL25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iclr/JiZWSC0YY025","url":"https://dblp.org/rec/conf/iclr/JiZWSC0YY025","title":"IDA-VLM: Towards Movie Understanding via ID-Aware Large Vision-Language Model.","year":2025,"types":["Inproceedings"],"venue":"ICLR","doi":null,"eventYear":2025,"numberOfCreators":9,"category":"conference","sources":["https://dblp.org/rec/conf/iclr/JiZWSC0YY025"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iclr/JiZWSC0YY025","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iclr/LinLSYZ00Z25","url":"https://dblp.org/rec/conf/iclr/LinLSYZ00Z25","title":"SAMRefiner: Taming Segment Anything Model for Universal Mask Refinement.","year":2025,"types":["Inproceedings"],"venue":"ICLR","doi":null,"eventYear":2025,"numberOfCreators":8,"category":"conference","sources":["https://dblp.org/rec/conf/iclr/LinLSYZ00Z25"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iclr/LinLSYZ00Z25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iclr/MengW0L0YLZD00Z25","url":"https://dblp.org/rec/conf/iclr/MengW0L0YLZD00Z25","title":"MMIU: Multimodal Multi-image Understanding for Evaluating Large Vision-Language Models.","year":2025,"types":["Inproceedings"],"venue":"ICLR","doi":null,"eventYear":2025,"numberOfCreators":13,"category":"conference","sources":["https://dblp.org/rec/conf/iclr/MengW0L0YLZD00Z25"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iclr/MengW0L0YLZD00Z25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iclr/YangZZB00S25","url":"https://dblp.org/rec/conf/iclr/YangZZB00S25","title":"Dynamic Multimodal Evaluation with Flexible Complexity by Vision-Language Bootstrapping.","year":2025,"types":["Inproceedings"],"venue":"ICLR","doi":null,"eventYear":2025,"numberOfCreators":7,"category":"conference","sources":["https://dblp.org/rec/conf/iclr/YangZZB00S25"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iclr/YangZZB00S25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/icml/Liao0Z0Z25","url":"https://dblp.org/rec/conf/icml/Liao0Z0Z25","title":"BOOD: Boundary-based Out-Of-Distribution Data Generation.","year":2025,"types":["Inproceedings"],"venue":"ICML","doi":null,"eventYear":2025,"numberOfCreators":5,"category":"conference","sources":["https://dblp.org/rec/conf/icml/Liao0Z0Z25"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/icml/Liao0Z0Z25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/icml/MengLTLSZ0L025","url":"https://dblp.org/rec/conf/icml/MengLTLSZ0L025","title":"Towards World Simulator: Crafting Physical Commonsense-Based Benchmark for Video Generation.","year":2025,"types":["Inproceedings"],"venue":"ICML","doi":null,"eventYear":2025,"numberOfCreators":9,"category":"conference","sources":["https://dblp.org/rec/conf/icml/MengLTLSZ0L025"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/icml/MengLTLSZ0L025","documentUrl":null,"type":"Inproceedings"},{"key":"conf/icra/LongRSWHLP25","url":"https://dblp.org/rec/conf/icra/LongRSWHLP25","title":"Learning Humanoid Locomotion with Perceptive Internal Model.","year":2025,"types":["Inproceedings"],"venue":"ICRA","doi":"https://doi.org/10.1109/ICRA55743.2025.11128333","eventYear":2025,"numberOfCreators":7,"category":"conference","sources":["https://dblp.org/rec/conf/icra/LongRSWHLP25","https://doi.org/10.1109/ICRA55743.2025.11128333"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/icra/LongRSWHLP25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/kdd/Hu0XSLLLR25","url":"https://dblp.org/rec/conf/kdd/Hu0XSLLLR25","title":"AgentGen: Enhancing Planning Abilities for Large Language Model based Agent via Environment and Task Generation.","year":2025,"types":["Inproceedings"],"venue":"KDD (1)","doi":"https://doi.org/10.1145/3690624.3709321","eventYear":2025,"numberOfCreators":8,"category":"conference","sources":["https://dblp.org/rec/conf/kdd/Hu0XSLLLR25","https://doi.org/10.1145/3690624.3709321"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/kdd/Hu0XSLLLR25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/mm/XuHS0WQYL25","url":"https://dblp.org/rec/conf/mm/XuHS0WQYL25","title":"DiffusionMat: Alpha Matting as Deterministic Sequential Refinement Learning.","year":2025,"types":["Inproceedings"],"venue":"ACM Multimedia","doi":"https://doi.org/10.1145/3746027.3754903","eventYear":2025,"numberOfCreators":8,"category":"conference","sources":["https://dblp.org/rec/conf/mm/XuHS0WQYL25","https://doi.org/10.1145/3746027.3754903"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/mm/XuHS0WQYL25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/naacl/WuLGGLWSL25","url":"https://dblp.org/rec/conf/naacl/WuLGGLWSL25","title":"Plot2Code: A Comprehensive Benchmark for Evaluating Multi-modal Large Language Models in Code Generation from Scientific Plots.","year":2025,"types":["Inproceedings"],"venue":"NAACL (Findings)","doi":"https://doi.org/10.18653/V1/2025.FINDINGS-NAACL.164","eventYear":2025,"numberOfCreators":8,"category":"conference","sources":["https://dblp.org/rec/conf/naacl/WuLGGLWSL25","https://doi.org/10.18653/V1/2025.FINDINGS-NAACL.164"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/naacl/WuLGGLWSL25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/nips/ChenLDWHMWDLSS25","url":"https://dblp.org/rec/conf/nips/ChenLDWHMWDLSS25","title":"OWMM-Agent: Open World Mobile Manipulation With Multi-modal Agentic Data Synthesis.","year":2025,"types":["Inproceedings"],"venue":"NeurIPS","doi":null,"eventYear":2025,"numberOfCreators":11,"category":"conference","sources":["https://dblp.org/rec/conf/nips/ChenLDWHMWDLSS25"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/nips/ChenLDWHMWDLSS25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/nips/ChenPZSLW25","url":"https://dblp.org/rec/conf/nips/ChenPZSLW25","title":"TREND: Unsupervised 3D Representation Learning via Temporal Forecasting for LiDAR Perception.","year":2025,"types":["Inproceedings"],"venue":"NeurIPS","doi":null,"eventYear":2025,"numberOfCreators":6,"category":"conference","sources":["https://dblp.org/rec/conf/nips/ChenPZSLW25"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/nips/ChenPZSLW25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/nips/HuZFNYXSJLZWYGL25","url":"https://dblp.org/rec/conf/nips/HuZFNYXSJLZWYGL25","title":"OWL: Optimized Workforce Learning for General Multi-Agent Assistance in Real-World Task Automation.","year":2025,"types":["Inproceedings"],"venue":"NeurIPS","doi":null,"eventYear":2025,"numberOfCreators":15,"category":"conference","sources":["https://dblp.org/rec/conf/nips/HuZFNYXSJLZWYGL25"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/nips/HuZFNYXSJLZWYGL25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/nips/LiuDCWGHXCLY25","url":"https://dblp.org/rec/conf/nips/LiuDCWGHXCLY25","title":"WorldWeaver: Generating Long-Horizon Video Worlds via Rich Perception.","year":2025,"types":["Inproceedings"],"venue":"NeurIPS","doi":null,"eventYear":2025,"numberOfCreators":10,"category":"conference","sources":["https://dblp.org/rec/conf/nips/LiuDCWGHXCLY25"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/nips/LiuDCWGHXCLY25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/nips/LvLTLYL25","url":"https://dblp.org/rec/conf/nips/LvLTLYL25","title":"SpecEM: Training-Free LLM Ensembling via Iterative Drafting, Verification, and Online Feedback.","year":2025,"types":["Inproceedings"],"venue":"NeurIPS","doi":null,"eventYear":2025,"numberOfCreators":6,"category":"conference","sources":["https://dblp.org/rec/conf/nips/LvLTLYL25"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/nips/LvLTLYL25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/nips/WangLLZSKWLL25","url":"https://dblp.org/rec/conf/nips/WangLLZSKWLL25","title":"FUDOKI: Discrete Flow-based Unified Understanding and Generation via Kinetic-Optimal Velocities.","year":2025,"types":["Inproceedings"],"venue":"NeurIPS","doi":null,"eventYear":2025,"numberOfCreators":9,"category":"conference","sources":["https://dblp.org/rec/conf/nips/WangLLZSKWLL25"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/nips/WangLLZSKWLL25","documentUrl":null,"type":"Inproceedings"},{"key":"journals/chinaf/LiHWLWLWWQ25","url":"https://dblp.org/rec/journals/chinaf/LiHWLWLWWQ25","title":"VideoChat: chat-centric video understanding.","year":2025,"types":["Article"],"venue":"Sci. China Inf. Sci.","doi":"https://doi.org/10.1007/S11432-024-4321-9","numberOfCreators":9,"category":"journal","sources":["https://dblp.org/rec/journals/chinaf/LiHWLWLWWQ25","https://doi.org/10.1007/S11432-024-4321-9"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/chinaf/LiHWLWLWWQ25","documentUrl":null,"type":"Article"},{"key":"journals/csur/SunZXLCQXDLGWWCYRFHYLLL25","url":"https://dblp.org/rec/journals/csur/SunZXLCQXDLGWWCYRFHYLLL25","title":"A Survey of Reasoning with Foundation Models: Concepts, Methodologies, and Outlook.","year":2025,"types":["Article"],"venue":"ACM Comput. Surv.","doi":"https://doi.org/10.1145/3729218","numberOfCreators":34,"category":"journal","sources":["https://dblp.org/rec/journals/csur/SunZXLCQXDLGWWCYRFHYLLL25","https://doi.org/10.1145/3729218"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/csur/SunZXLCQXDLGWWCYRFHYLLL25","documentUrl":null,"type":"Article"},{"key":"journals/cvm/LiuLLLW25","url":"https://dblp.org/rec/journals/cvm/LiuLLLW25","title":"Sem-iNeRF: Camera Pose Refinement by Inverting Neural Radiance Fields with Semantic Feature Consistency.","year":2025,"types":["Article"],"venue":"Comput. Vis. Media","doi":"https://doi.org/10.26599/CVM.2025.9450404","numberOfCreators":5,"category":"journal","sources":["https://dblp.org/rec/journals/cvm/LiuLLLW25","https://doi.org/10.26599/CVM.2025.9450404"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/cvm/LiuLLLW25","documentUrl":null,"type":"Article"},{"key":"journals/ijcv/WangWXQSWL25","url":"https://dblp.org/rec/journals/ijcv/WangWXQSWL25","title":"StyleAdapter: A Unified Stylized Image Generation Model.","year":2025,"types":["Article"],"venue":"Int. J. Comput. Vis.","doi":"https://doi.org/10.1007/S11263-024-02253-X","numberOfCreators":7,"category":"journal","sources":["https://dblp.org/rec/journals/ijcv/WangWXQSWL25","https://doi.org/10.1007/S11263-024-02253-X"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/ijcv/WangWXQSWL25","documentUrl":null,"type":"Article"},{"key":"journals/ijcv/XuHWL25","url":"https://dblp.org/rec/journals/ijcv/XuHWL25","title":"RIGID: Recurrent GAN Inversion and Editing of Real Face Videos and Beyond.","year":2025,"types":["Article"],"venue":"Int. J. Comput. Vis.","doi":"https://doi.org/10.1007/S11263-024-02329-8","numberOfCreators":4,"category":"journal","sources":["https://dblp.org/rec/journals/ijcv/XuHWL25","https://doi.org/10.1007/S11263-024-02329-8"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/ijcv/XuHWL25","documentUrl":null,"type":"Article"},{"key":"journals/pami/XuSZGLLMHQL25","url":"https://dblp.org/rec/journals/pami/XuSZGLLMHQL25","title":"LVLM-EHub: A Comprehensive Evaluation Benchmark for Large Vision-Language Models.","year":2025,"types":["Article"],"venue":"IEEE Trans. Pattern Anal. Mach. Intell.","doi":"https://doi.org/10.1109/TPAMI.2024.3507000","numberOfCreators":10,"category":"journal","sources":["https://dblp.org/rec/journals/pami/XuSZGLLMHQL25","https://doi.org/10.1109/TPAMI.2024.3507000"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/pami/XuSZGLLMHQL25","documentUrl":null,"type":"Article"},{"key":"journals/pami/YanCZYXYZCSSLQCY25","url":"https://dblp.org/rec/journals/pami/YanCZYXYZCSSLQCY25","title":"SPOT: Scalable 3D Pre-Training via Occupancy Prediction for Learning Transferable 3D Representations.","year":2025,"types":["Article"],"venue":"IEEE Trans. Pattern Anal. Mach. Intell.","doi":"https://doi.org/10.1109/TPAMI.2025.3586961","numberOfCreators":14,"category":"journal","sources":["https://dblp.org/rec/journals/pami/YanCZYXYZCSSLQCY25","https://doi.org/10.1109/TPAMI.2025.3586961"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/pami/YanCZYXYZCSSLQCY25","documentUrl":null,"type":"Article"},{"key":"journals/spl/ZhangLQXZ25","url":"https://dblp.org/rec/journals/spl/ZhangLQXZ25","title":"Adaptive Superpixel-Guided Non-Homogeneous Image Dehazing.","year":2025,"types":["Article"],"venue":"IEEE Signal Process. Lett.","doi":"https://doi.org/10.1109/LSP.2025.3527197","numberOfCreators":5,"category":"journal","sources":["https://dblp.org/rec/journals/spl/ZhangLQXZ25","https://doi.org/10.1109/LSP.2025.3527197"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/spl/ZhangLQXZ25","documentUrl":null,"type":"Article"},{"key":"journals/tbd/ShaoLHGXZMHLQL25","url":"https://dblp.org/rec/journals/tbd/ShaoLHGXZMHLQL25","title":"TinyLVLM-eHub: Towards Comprehensive and Efficient Evaluation for Large Vision-Language Models.","year":2025,"types":["Article"],"venue":"IEEE Trans. Big Data","doi":"https://doi.org/10.1109/TBDATA.2025.3536930","numberOfCreators":11,"category":"journal","sources":["https://dblp.org/rec/journals/tbd/ShaoLHGXZMHLQL25","https://doi.org/10.1109/TBDATA.2025.3536930"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/tbd/ShaoLHGXZMHLQL25","documentUrl":null,"type":"Article"},{"key":"journals/tifs/ZhangSLMLQZZ25","url":"https://dblp.org/rec/journals/tifs/ZhangSLMLQZZ25","title":"B-AVIBench: Toward Evaluating the Robustness of Large Vision-Language Model on Black-Box Adversarial Visual-Instructions.","year":2025,"types":["Article"],"venue":"IEEE Trans. Inf. Forensics Secur.","doi":"https://doi.org/10.1109/TIFS.2024.3520306","numberOfCreators":8,"category":"journal","sources":["https://dblp.org/rec/journals/tifs/ZhangSLMLQZZ25","https://doi.org/10.1109/TIFS.2024.3520306"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/tifs/ZhangSLMLQZZ25","documentUrl":null,"type":"Article"},{"key":"journals/tmlr/XiongLHWW0YSWHT25","url":"https://dblp.org/rec/journals/tmlr/XiongLHWW0YSWHT25","title":"Autoregressive Models in Vision: A Survey.","year":2025,"types":["Article"],"venue":"Trans. Mach. Learn. Res.","doi":null,"numberOfCreators":20,"category":"journal","sources":["https://dblp.org/rec/journals/tmlr/XiongLHWW0YSWHT25"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/tmlr/XiongLHWW0YSWHT25","documentUrl":null,"type":"Article"},{"key":"journals/tvcg/LiuLLWLLW25","url":"https://dblp.org/rec/journals/tvcg/LiuLLWLLW25","title":"NeRFBuff: Fast Neural Rendering via Inter-Frame Feature Buffering.","year":2025,"types":["Article"],"venue":"IEEE Trans. Vis. Comput. Graph.","doi":"https://doi.org/10.1109/TVCG.2024.3393715","numberOfCreators":7,"category":"journal","sources":["https://dblp.org/rec/journals/tvcg/LiuLLWLLW25","https://doi.org/10.1109/TVCG.2024.3393715"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/tvcg/LiuLLWLLW25","documentUrl":null,"type":"Article"},{"key":"journals/tvcg/XieZWWWLGLW25","url":"https://dblp.org/rec/journals/tvcg/XieZWWWLGLW25","title":"Tooth Motion Monitoring in Orthodontic Treatment by Mobile Device-Based Multi-View Stereo.","year":2025,"types":["Article"],"venue":"IEEE Trans. Vis. Comput. Graph.","doi":"https://doi.org/10.1109/TVCG.2024.3470992","numberOfCreators":9,"category":"journal","sources":["https://dblp.org/rec/journals/tvcg/XieZWWWLGLW25","https://doi.org/10.1109/TVCG.2024.3470992"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/tvcg/XieZWWWLGLW25","documentUrl":null,"type":"Article"}],"preprints":[{"key":"journals/corr/abs-2501-08332","url":"https://dblp.org/rec/journals/corr/abs-2501-08332","title":"MangaNinja: Line Art Colorization with Precise Reference Following.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2501.08332","numberOfCreators":10,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2501-08332","https://doi.org/10.48550/ARXIV.2501.08332"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2501-08332","documentUrl":null,"type":"Informal","arxivId":"2501.08332","arxivUrl":"https://arxiv.org/abs/2501.08332"},{"key":"journals/corr/abs-2501-12976","url":"https://dblp.org/rec/journals/corr/abs-2501-12976","title":"LiT: Delving into a Simplified Linear Diffusion Transformer for Image Generation.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2501.12976","numberOfCreators":15,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2501-12976","https://doi.org/10.48550/ARXIV.2501.12976"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2501-12976","documentUrl":null,"type":"Informal","arxivId":"2501.12976","arxivUrl":"https://arxiv.org/abs/2501.12976"},{"key":"journals/corr/abs-2502-04896","url":"https://dblp.org/rec/journals/corr/abs-2502-04896","title":"Goku: Flow Based Video Generative Foundation Models.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2502.04896","numberOfCreators":22,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2502-04896","https://doi.org/10.48550/ARXIV.2502.04896"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2502-04896","documentUrl":null,"type":"Informal","arxivId":"2502.04896","arxivUrl":"https://arxiv.org/abs/2502.04896"},{"key":"journals/corr/abs-2502-05179","url":"https://dblp.org/rec/journals/corr/abs-2502-05179","title":"FlashVideo: Flowing Fidelity to Detail for Efficient High-Resolution Video Generation.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2502.05179","numberOfCreators":10,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2502-05179","https://doi.org/10.48550/ARXIV.2502.05179"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2502-05179","documentUrl":null,"type":"Informal","arxivId":"2502.05179","arxivUrl":"https://arxiv.org/abs/2502.05179"},{"key":"journals/corr/abs-2502-06756","url":"https://dblp.org/rec/journals/corr/abs-2502-06756","title":"SAMRefiner: Taming Segment Anything Model for Universal Mask Refinement.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2502.06756","numberOfCreators":8,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2502-06756","https://doi.org/10.48550/ARXIV.2502.06756"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2502-06756","documentUrl":null,"type":"Informal","arxivId":"2502.06756","arxivUrl":"https://arxiv.org/abs/2502.06756"},{"key":"journals/corr/abs-2502-13092","url":"https://dblp.org/rec/journals/corr/abs-2502-13092","title":"Text2World: Benchmarking Large Language Models for Symbolic World Model Generation.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2502.13092","numberOfCreators":10,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2502-13092","https://doi.org/10.48550/ARXIV.2502.13092"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2502-13092","documentUrl":null,"type":"Informal","arxivId":"2502.13092","arxivUrl":"https://arxiv.org/abs/2502.13092"},{"key":"journals/corr/abs-2502-14814","url":"https://dblp.org/rec/journals/corr/abs-2502-14814","title":"VB-Com: Learning Vision-Blind Composite Humanoid Locomotion Against Deficient Perception.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2502.14814","numberOfCreators":7,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2502-14814","https://doi.org/10.48550/ARXIV.2502.14814"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2502-14814","documentUrl":null,"type":"Informal","arxivId":"2502.14814","arxivUrl":"https://arxiv.org/abs/2502.14814"},{"key":"journals/corr/abs-2503-06669","url":"https://dblp.org/rec/journals/corr/abs-2503-06669","title":"AgiBot World Colosseo: A Large-scale Manipulation Platform for Scalable and Intelligent Embodied Systems.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2503.06669","numberOfCreators":51,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2503-06669","https://doi.org/10.48550/ARXIV.2503.06669"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-06669","documentUrl":null,"type":"Informal","arxivId":"2503.06669","arxivUrl":"https://arxiv.org/abs/2503.06669"},{"key":"journals/corr/abs-2503-07365","url":"https://dblp.org/rec/journals/corr/abs-2503-07365","title":"MM-Eureka: Exploring Visual Aha Moment with Rule-based Large-scale Reinforcement Learning.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2503.07365","numberOfCreators":14,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2503-07365","https://doi.org/10.48550/ARXIV.2503.07365"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-07365","documentUrl":null,"type":"Informal","arxivId":"2503.07365","arxivUrl":"https://arxiv.org/abs/2503.07365"},{"key":"journals/corr/abs-2503-08422","url":"https://dblp.org/rec/journals/corr/abs-2503-08422","title":"JiSAM: Alleviate Labeling Burden and Corner Case Problems in Autonomous Driving via Minimal Real-World Data.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2503.08422","numberOfCreators":6,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2503-08422","https://doi.org/10.48550/ARXIV.2503.08422"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-08422","documentUrl":null,"type":"Informal","arxivId":"2503.08422","arxivUrl":"https://arxiv.org/abs/2503.08422"},{"key":"journals/corr/abs-2503-11650","url":"https://dblp.org/rec/journals/corr/abs-2503-11650","title":"Centaur: Robust End-to-End Autonomous Driving with Test-Time Training.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2503.11650","numberOfCreators":8,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2503-11650","https://doi.org/10.48550/ARXIV.2503.11650"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-11650","documentUrl":null,"type":"Informal","arxivId":"2503.11650","arxivUrl":"https://arxiv.org/abs/2503.11650"},{"key":"journals/corr/abs-2504-07963","url":"https://dblp.org/rec/journals/corr/abs-2504-07963","title":"PixelFlow: Pixel-Space Generative Models with Flow.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2504.07963","numberOfCreators":5,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2504-07963","https://doi.org/10.48550/ARXIV.2504.07963"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2504-07963","documentUrl":null,"type":"Informal","arxivId":"2504.07963","arxivUrl":"https://arxiv.org/abs/2504.07963"},{"key":"journals/corr/abs-2504-13059","url":"https://dblp.org/rec/journals/corr/abs-2504-13059","title":"RoboTwin: Dual-Arm Robot Benchmark with Generative Digital Twins.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2504.13059","numberOfCreators":14,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2504-13059","https://doi.org/10.48550/ARXIV.2504.13059"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2504-13059","documentUrl":null,"type":"Informal","arxivId":"2504.13059","arxivUrl":"https://arxiv.org/abs/2504.13059"},{"key":"journals/corr/abs-2505-06111","url":"https://dblp.org/rec/journals/corr/abs-2505-06111","title":"UniVLA: Learning to Act Anywhere with Task-centric Latent Actions.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2505.06111","numberOfCreators":8,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2505-06111","https://doi.org/10.48550/ARXIV.2505.06111"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-06111","documentUrl":null,"type":"Informal","arxivId":"2505.06111","arxivUrl":"https://arxiv.org/abs/2505.06111"},{"key":"journals/corr/abs-2505-07818","url":"https://dblp.org/rec/journals/corr/abs-2505-07818","title":"DanceGRPO: Unleashing GRPO on Visual Generation.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2505.07818","numberOfCreators":11,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2505-07818","https://doi.org/10.48550/ARXIV.2505.07818"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-07818","documentUrl":null,"type":"Informal","arxivId":"2505.07818","arxivUrl":"https://arxiv.org/abs/2505.07818"},{"key":"journals/corr/abs-2505-13427","url":"https://dblp.org/rec/journals/corr/abs-2505-13427","title":"MM-PRM: Enhancing Multimodal Mathematical Reasoning with Scalable Step-Level Supervision.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2505.13427","numberOfCreators":7,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2505-13427","https://doi.org/10.48550/ARXIV.2505.13427"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-13427","documentUrl":null,"type":"Informal","arxivId":"2505.13427","arxivUrl":"https://arxiv.org/abs/2505.13427"},{"key":"journals/corr/abs-2505-14030","url":"https://dblp.org/rec/journals/corr/abs-2505-14030","title":"AutoBio: A Simulation and Benchmark for Robotic Automation in Digital Biology Laboratory.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2505.14030","numberOfCreators":15,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2505-14030","https://doi.org/10.48550/ARXIV.2505.14030"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-14030","documentUrl":null,"type":"Informal","arxivId":"2505.14030","arxivUrl":"https://arxiv.org/abs/2505.14030"},{"key":"journals/corr/abs-2505-14302","url":"https://dblp.org/rec/journals/corr/abs-2505-14302","title":"Scaling Law for Quantization-Aware Training.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2505.14302","numberOfCreators":11,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2505-14302","https://doi.org/10.48550/ARXIV.2505.14302"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-14302","documentUrl":null,"type":"Informal","arxivId":"2505.14302","arxivUrl":"https://arxiv.org/abs/2505.14302"},{"key":"journals/corr/abs-2505-15929","url":"https://dblp.org/rec/journals/corr/abs-2505-15929","title":"PhyX: Does Your Model Have the \"Wits\" for Physical Reasoning?","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2505.15929","numberOfCreators":19,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2505-15929","https://doi.org/10.48550/ARXIV.2505.15929"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-15929","documentUrl":null,"type":"Informal","arxivId":"2505.15929","arxivUrl":"https://arxiv.org/abs/2505.15929"},{"key":"journals/corr/abs-2505-20147","url":"https://dblp.org/rec/journals/corr/abs-2505-20147","title":"FUDOKI: Discrete Flow-based Unified Understanding and Generation via Kinetic-Optimal Velocities.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2505.20147","numberOfCreators":9,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2505-20147","https://doi.org/10.48550/ARXIV.2505.20147"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-20147","documentUrl":null,"type":"Informal","arxivId":"2505.20147","arxivUrl":"https://arxiv.org/abs/2505.20147"},{"key":"journals/corr/abs-2505-22618","url":"https://dblp.org/rec/journals/corr/abs-2505-22618","title":"Fast-dLLM: Training-free Acceleration of Diffusion LLM by Enabling KV Cache and Parallel Decoding.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2505.22618","numberOfCreators":9,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2505-22618","https://doi.org/10.48550/ARXIV.2505.22618"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-22618","documentUrl":null,"type":"Informal","arxivId":"2505.22618","arxivUrl":"https://arxiv.org/abs/2505.22618"},{"key":"journals/corr/abs-2505-23885","url":"https://dblp.org/rec/journals/corr/abs-2505-23885","title":"OWL: Optimized Workforce Learning for General Multi-Agent Assistance in Real-World Task Automation.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2505.23885","numberOfCreators":16,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2505-23885","https://doi.org/10.48550/ARXIV.2505.23885"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-23885","documentUrl":null,"type":"Informal","arxivId":"2505.23885","arxivUrl":"https://arxiv.org/abs/2505.23885"},{"key":"journals/corr/abs-2506-02648","url":"https://dblp.org/rec/journals/corr/abs-2506-02648","title":"Truly Assessing Fluid Intelligence of Large Language Models through Dynamic Reasoning Evaluation.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2506.02648","numberOfCreators":12,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2506-02648","https://doi.org/10.48550/ARXIV.2506.02648"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-02648","documentUrl":null,"type":"Informal","arxivId":"2506.02648","arxivUrl":"https://arxiv.org/abs/2506.02648"},{"key":"journals/corr/abs-2506-04217","url":"https://dblp.org/rec/journals/corr/abs-2506-04217","title":"OWMM-Agent: Open World Mobile Manipulation With Multi-modal Agentic Data Synthesis.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2506.04217","numberOfCreators":11,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2506-04217","https://doi.org/10.48550/ARXIV.2506.04217"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-04217","documentUrl":null,"type":"Informal","arxivId":"2506.04217","arxivUrl":"https://arxiv.org/abs/2506.04217"},{"key":"journals/corr/abs-2506-05240","url":"https://dblp.org/rec/journals/corr/abs-2506-05240","title":"Aligning Latent Spaces with Flow Priors.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2506.05240","numberOfCreators":5,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2506-05240","https://doi.org/10.48550/ARXIV.2506.05240"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-05240","documentUrl":null,"type":"Informal","arxivId":"2506.05240","arxivUrl":"https://arxiv.org/abs/2506.05240"},{"key":"journals/corr/abs-2506-05985","url":"https://dblp.org/rec/journals/corr/abs-2506-05985","title":"Dynamic Mixture of Progressive Parameter-Efficient Expert Library for Lifelong Robot Learning.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2506.05985","numberOfCreators":6,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2506-05985","https://doi.org/10.48550/ARXIV.2506.05985"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-05985","documentUrl":null,"type":"Informal","arxivId":"2506.05985","arxivUrl":"https://arxiv.org/abs/2506.05985"},{"key":"journals/corr/abs-2506-18088","url":"https://dblp.org/rec/journals/corr/abs-2506-18088","title":"RoboTwin 2.0: A Scalable Data Generator and Benchmark with Strong Domain Randomization for Robust Bimanual Robotic Manipulation.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2506.18088","numberOfCreators":26,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2506-18088","https://doi.org/10.48550/ARXIV.2506.18088"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-18088","documentUrl":null,"type":"Informal","arxivId":"2506.18088","arxivUrl":"https://arxiv.org/abs/2506.18088"},{"key":"journals/corr/abs-2506-23351","url":"https://dblp.org/rec/journals/corr/abs-2506-23351","title":"Benchmarking Generalizable Bimanual Manipulation: RoboTwin Dual-Arm Collaboration Challenge at CVPR 2025 MEIS Workshop.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2506.23351","numberOfCreators":16,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2506-23351","https://doi.org/10.48550/ARXIV.2506.23351"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-23351","documentUrl":null,"type":"Informal","arxivId":"2506.23351","arxivUrl":"https://arxiv.org/abs/2506.23351"},{"key":"journals/corr/abs-2507-06219","url":"https://dblp.org/rec/journals/corr/abs-2507-06219","title":"Is Diversity All You Need for Scalable Robotic Manipulation?","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2507.06219","numberOfCreators":10,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2507-06219","https://doi.org/10.48550/ARXIV.2507.06219"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2507-06219","documentUrl":null,"type":"Informal","arxivId":"2507.06219","arxivUrl":"https://arxiv.org/abs/2507.06219"},{"key":"journals/corr/abs-2507-21610","url":"https://dblp.org/rec/journals/corr/abs-2507-21610","title":"Research Challenges and Progress in the End-to-End V2X Cooperative Autonomous Driving Competition.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2507.21610","numberOfCreators":21,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2507-21610","https://doi.org/10.48550/ARXIV.2507.21610"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2507-21610","documentUrl":null,"type":"Informal","arxivId":"2507.21610","arxivUrl":"https://arxiv.org/abs/2507.21610"},{"key":"journals/corr/abs-2508-00350","url":"https://dblp.org/rec/journals/corr/abs-2508-00350","title":"BOOD: Boundary-based Out-Of-Distribution Data Generation.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2508.00350","numberOfCreators":5,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2508-00350","https://doi.org/10.48550/ARXIV.2508.00350"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-00350","documentUrl":null,"type":"Informal","arxivId":"2508.00350","arxivUrl":"https://arxiv.org/abs/2508.00350"},{"key":"journals/corr/abs-2508-02518","url":"https://dblp.org/rec/journals/corr/abs-2508-02518","title":"AnalogCoder-Pro: Unifying Analog Circuit Generation and Optimization via Multi-modal LLMs.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2508.02518","numberOfCreators":8,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2508-02518","https://doi.org/10.48550/ARXIV.2508.02518"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-02518","documentUrl":null,"type":"Informal","arxivId":"2508.02518","arxivUrl":"https://arxiv.org/abs/2508.02518"},{"key":"journals/corr/abs-2508-15720","url":"https://dblp.org/rec/journals/corr/abs-2508-15720","title":"WorldWeaver: Generating Long-Horizon Video Worlds via Rich Perception.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2508.15720","numberOfCreators":10,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2508-15720","https://doi.org/10.48550/ARXIV.2508.15720"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-15720","documentUrl":null,"type":"Informal","arxivId":"2508.15720","arxivUrl":"https://arxiv.org/abs/2508.15720"},{"key":"journals/corr/abs-2508-19699","url":"https://dblp.org/rec/journals/corr/abs-2508-19699","title":"LabelGS: Label-Aware 3D Gaussian Splatting for 3D Scene Segmentation.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2508.19699","numberOfCreators":11,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2508-19699","https://doi.org/10.48550/ARXIV.2508.19699"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-19699","documentUrl":null,"type":"Informal","arxivId":"2508.19699","arxivUrl":"https://arxiv.org/abs/2508.19699"},{"key":"journals/corr/abs-2508-20018","url":"https://dblp.org/rec/journals/corr/abs-2508-20018","title":"SWIRL: A Staged Workflow for Interleaved Reinforcement Learning in Mobile GUI Control.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2508.20018","numberOfCreators":7,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2508-20018","https://doi.org/10.48550/ARXIV.2508.20018"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-20018","documentUrl":null,"type":"Informal","arxivId":"2508.20018","arxivUrl":"https://arxiv.org/abs/2508.20018"},{"key":"journals/corr/abs-2508-20072","url":"https://dblp.org/rec/journals/corr/abs-2508-20072","title":"Discrete Diffusion VLA: Bringing Discrete Diffusion to Action Decoding in Vision-Language-Action Policies.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2508.20072","numberOfCreators":10,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2508-20072","https://doi.org/10.48550/ARXIV.2508.20072"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-20072","documentUrl":null,"type":"Informal","arxivId":"2508.20072","arxivUrl":"https://arxiv.org/abs/2508.20072"},{"key":"journals/corr/abs-2509-03903","url":"https://dblp.org/rec/journals/corr/abs-2509-03903","title":"A Generative Foundation Model for Chest Radiography.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2509.03903","numberOfCreators":15,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2509-03903","https://doi.org/10.48550/ARXIV.2509.03903"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-03903","documentUrl":null,"type":"Informal","arxivId":"2509.03903","arxivUrl":"https://arxiv.org/abs/2509.03903"},{"key":"journals/corr/abs-2509-23922","url":"https://dblp.org/rec/journals/corr/abs-2509-23922","title":"DriveE2E: Closed-Loop Benchmark for End-to-End Autonomous Driving through Real-to-Simulation.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2509.23922","numberOfCreators":7,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2509-23922","https://doi.org/10.48550/ARXIV.2509.23922"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-23922","documentUrl":null,"type":"Informal","arxivId":"2509.23922","arxivUrl":"https://arxiv.org/abs/2509.23922"},{"key":"journals/corr/abs-2509-24695","url":"https://dblp.org/rec/journals/corr/abs-2509-24695","title":"SANA-Video: Efficient Video Generation with Block Linear Diffusion Transformer.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2509.24695","numberOfCreators":20,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2509-24695","https://doi.org/10.48550/ARXIV.2509.24695"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-24695","documentUrl":null,"type":"Informal","arxivId":"2509.24695","arxivUrl":"https://arxiv.org/abs/2509.24695"},{"key":"journals/corr/abs-2509-26328","url":"https://dblp.org/rec/journals/corr/abs-2509-26328","title":"Fast-dLLM v2: Efficient Block-Diffusion LLM.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2509.26328","numberOfCreators":10,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2509-26328","https://doi.org/10.48550/ARXIV.2509.26328"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-26328","documentUrl":null,"type":"Informal","arxivId":"2509.26328","arxivUrl":"https://arxiv.org/abs/2509.26328"},{"key":"journals/corr/abs-2510-00050","url":"https://dblp.org/rec/journals/corr/abs-2510-00050","title":"Object-AVEdit: An Object-level Audio-Visual Editing Model.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2510.00050","numberOfCreators":9,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2510-00050","https://doi.org/10.48550/ARXIV.2510.00050"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-00050","documentUrl":null,"type":"Informal","arxivId":"2510.00050","arxivUrl":"https://arxiv.org/abs/2510.00050"},{"key":"journals/corr/abs-2510-18002","url":"https://dblp.org/rec/journals/corr/abs-2510-18002","title":"Humanoid Goalkeeper: Learning from Position Conditioned Task-Motion Constraints.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2510.18002","numberOfCreators":10,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2510-18002","https://doi.org/10.48550/ARXIV.2510.18002"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-18002","documentUrl":null,"type":"Informal","arxivId":"2510.18002","arxivUrl":"https://arxiv.org/abs/2510.18002"},{"key":"journals/corr/abs-2510-19871","url":"https://dblp.org/rec/journals/corr/abs-2510-19871","title":"From Denoising to Refining: A Corrective Framework for Vision-Language Diffusion Model.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2510.19871","numberOfCreators":7,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2510-19871","https://doi.org/10.48550/ARXIV.2510.19871"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-19871","documentUrl":null,"type":"Informal","arxivId":"2510.19871","arxivUrl":"https://arxiv.org/abs/2510.19871"},{"key":"journals/corr/abs-2510-20774","url":"https://dblp.org/rec/journals/corr/abs-2510-20774","title":"FieldGen: From Teleoperated Pre-Manipulation Trajectories to Field-Guided Data Generation.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2510.20774","numberOfCreators":12,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2510-20774","https://doi.org/10.48550/ARXIV.2510.20774"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-20774","documentUrl":null,"type":"Informal","arxivId":"2510.20774","arxivUrl":"https://arxiv.org/abs/2510.20774"},{"key":"journals/corr/abs-2510-25602","url":"https://dblp.org/rec/journals/corr/abs-2510-25602","title":"INT v.s. FP: A Comprehensive Study of Fine-Grained Low-bit Quantization Formats.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2510.25602","numberOfCreators":13,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2510-25602","https://doi.org/10.48550/ARXIV.2510.25602"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-25602","documentUrl":null,"type":"Informal","arxivId":"2510.25602","arxivUrl":"https://arxiv.org/abs/2510.25602"},{"key":"journals/corr/abs-2511-07934","url":"https://dblp.org/rec/journals/corr/abs-2511-07934","title":"Laytrol: Preserving Pretrained Knowledge in Layout Control for Multimodal Diffusion Transformers.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2511.07934","numberOfCreators":4,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2511-07934","https://doi.org/10.48550/ARXIV.2511.07934"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2511-07934","documentUrl":null,"type":"Informal","arxivId":"2511.07934","arxivUrl":"https://arxiv.org/abs/2511.07934"},{"key":"journals/corr/abs-2511-16901","url":"https://dblp.org/rec/journals/corr/abs-2511-16901","title":"R-AVST: Empowering Video-LLMs with Fine-Grained Spatio-Temporal Reasoning in Complex Audio-Visual Scenarios.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2511.16901","numberOfCreators":6,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2511-16901","https://doi.org/10.48550/ARXIV.2511.16901"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2511-16901","documentUrl":null,"type":"Informal","arxivId":"2511.16901","arxivUrl":"https://arxiv.org/abs/2511.16901"},{"key":"journals/corr/abs-2511-17373","url":"https://dblp.org/rec/journals/corr/abs-2511-17373","title":"Agility Meets Stability: Versatile Humanoid Control with Heterogeneous Data.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2511.17373","numberOfCreators":11,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2511-17373","https://doi.org/10.48550/ARXIV.2511.17373"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2511-17373","documentUrl":null,"type":"Informal","arxivId":"2511.17373","arxivUrl":"https://arxiv.org/abs/2511.17373"},{"key":"journals/corr/abs-2512-00975","url":"https://dblp.org/rec/journals/corr/abs-2512-00975","title":"MM-ACT: Learn from Multimodal Parallel Generation to Act.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2512.00975","numberOfCreators":15,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2512-00975","https://doi.org/10.48550/ARXIV.2512.00975"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-00975","documentUrl":null,"type":"Informal","arxivId":"2512.00975","arxivUrl":"https://arxiv.org/abs/2512.00975"},{"key":"journals/corr/abs-2512-02014","url":"https://dblp.org/rec/journals/corr/abs-2512-02014","title":"TUNA: Taming Unified Visual Representations for Native Unified Multimodal Models.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2512.02014","numberOfCreators":25,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2512-02014","https://doi.org/10.48550/ARXIV.2512.02014"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-02014","documentUrl":null,"type":"Informal","arxivId":"2512.02014","arxivUrl":"https://arxiv.org/abs/2512.02014"},{"key":"journals/corr/abs-2512-14099","url":"https://dblp.org/rec/journals/corr/abs-2512-14099","title":"ViewMask-1-to-3: Multi-View Consistent Image Generation via Multimodal Diffusion Models.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2512.14099","numberOfCreators":6,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2512-14099","https://doi.org/10.48550/ARXIV.2512.14099"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-14099","documentUrl":null,"type":"Informal","arxivId":"2512.14099","arxivUrl":"https://arxiv.org/abs/2512.14099"},{"key":"journals/corr/abs-2512-17909","url":"https://dblp.org/rec/journals/corr/abs-2512-17909","title":"Both Semantics and Reconstruction Matter: Making Representation Encoders Ready for Text-to-Image Generation and Editing.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2512.17909","numberOfCreators":14,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2512-17909","https://doi.org/10.48550/ARXIV.2512.17909"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-17909","documentUrl":null,"type":"Informal","arxivId":"2512.17909","arxivUrl":"https://arxiv.org/abs/2512.17909"}],"excludedFormal":[],"otherRecords":[],"matchedName":"Ping Luo","databaseLabel":"Ping Luo 0002","databaseMetadata":{"type":["https://dblp.org/rdf/schema#Creator","https://dblp.org/rdf/schema#Person"],"label":["Ping Luo 0002"],"affiliation":["University of Hong Kong, Shanghai AI Laboratory, Department of Computer Science, Hong Kong","Sun Yat-Sen University, School of Software, Guangzhou, China","Lotus Hill Insititue, China","Chinese University of Hong Kong, Department of Information Engineering, Hong Kong"],"homepage":["http://luoping.me/","http://personal.ie.cuhk.edu.hk/~pluo/","https://openreview.net/profile?id=~Ping_Luo2"],"orcid":["https://orcid.org/0000-0002-6685-7950"],"primaryAffiliation":["University of Hong Kong, Shanghai AI Laboratory, Department of Computer Science, Hong Kong"],"primaryHomepage":["http://luoping.me/"]},"rawFormalRecordCount2025":60,"signatureAudit":{"completedAt":"2026-10-19","frozen":true,"scope":"对 B 组 39 个数值档案的全部 1074 条原始 2025 正式记录扫描 DBLP author-signature ORCID 和机构；复用既有 59 条 Crossref 核验，补查 6 条新触发记录。重点核查不同 ORCID，以及只有预期机构之外机构的条目。本轮不扩展为所有作者逐篇全文审计。","formalRecordCoverage":60,"orcidCounts":{"https://orcid.org/0000-0002-6685-7950":11},"institutionCounts":{"Beijing Academy of Artificial Intelligence (BAAI)":1,"ShangHai JiAi Genetics & IVF Institute":1,"Shanghai Artificial Intelligence Laboratory":11,"Shanghai Open University":1,"University of Hong Kong (HKU)":35},"caveat":"机构名称可能由 DBLP 自动映射而失真；多 ORCID 也不自动等于异人。只有有原始资料支撑的错归才作确认排除，未解决分支则暂停总数。"},"labName":"HKU-MMLab","labUrl":"https://mmlab.hk/about-us","labEvidence":"MMLab 官方 People 页在 HKU MMLab 分区列 Ping Luo；HKU-MMLab About Us 页亦列本人。与刘希慧条目采用同一组名，不单独编造一个罗平实验室。","labSourceUrl":"https://mmlab.ie.cuhk.edu.hk/people.html","sourceWarning":false,"excludedOther":[],"excludedHomonyms":[],"unassignedCandidates":[],"knownPreprintMinimum2025":null,"excludedMisattributed":[],"displayNotes":"身份已与原名单机构及公开资料核对确认。2025 年正式记录 60 条（会议 47、期刊 13），所有作者位置均计入，不表示主导或贡献份额；预印本 52 条单列，不加总。","labDisplayNotes":"港中文 MMLab 官方 People 页在 HKU MMLab 分区列其姓名，HKU-MMLab 的 About Us 页也列出本人。与刘希慧同组，去重后 90 条。"},{"index":70,"name":"Yuexin Ma","nameZh":"马月昕","role":"Associate Professor","affiliation":"ShanghaiTech University","affiliationZh":"上海科技大学","source":"DBLP RDF via official SPARQL; primary-source identity checks","sourceUrl":"https://sparql.dblp.org/","profileUrl":"https://dblp.org/pid/209/5925.html","identifier":"209/5925","retrievedAt":"2026-10-19","count2025":null,"conference2025":null,"journal2025":null,"preprint2025":null,"status":"unresolved","notes":"author-signature 机构扫描发现 WheatGP（journals/bib/WangZMZLL24）挂入上海科技大学 Yuexin Ma 档案；出版商原文将 Yuexin Ma 单独归为山东农业大学机械与电子工程学院，未见上海科技大学机构，也未见于本人公开发表页。不能在缺少进一步身份确认时认定为本人或径自减一后称完整统计，因此全年总数暂留空，候选论文单列。","identityEvidence":[{"url":"https://dblp.org/pid/209/5925.html","evidence":"DBLP RDF 类型为 Person，消歧后名字为 Yuexin Ma。此档案未提供可用机构元数据，以下以本人/机构/出版商来源补证。"},{"url":"https://yuexinma.me/","evidence":"个人主页为上海科技大学 Yuexin Ma；完整发表页多个标题与 DBLP 相符。"},{"url":"https://yuexinma.me/publications.html","evidence":"此本人或机构页面的正文与所选档案中 39 条 2025 记录标题匹配，其中 24 条为当前计入的正式记录（忽略空格、标点、大小写）。","matchedPaperKeys":["conf/aaai/LuYTSMZ25","conf/aaai/XueRSYZM25","conf/aaai/Yang0PYM25","conf/cvpr/CongWM025","conf/cvpr/LiHXMSZ25","conf/cvpr/LiuLY0HTMW25","conf/cvpr/YanLLFDZZMXWS025","conf/cvpr/ZhongJYM25","conf/eccv/FuYHWMTSLL24","conf/eccv/LinPCZSHZYM24","conf/eccv/PengCQKLSWZM24","conf/eccv/RenHYLSM24","conf/eccv/ShiZYTMY24","conf/iccv/JiSJCXMYW25","conf/iccv/LuTMZ25","conf/iccv/WangYXZTYLYM25","conf/iccv/ZhuZYCYZM25","conf/icra/XiaoWTPM25","conf/icra/YanDSLLLWWWRM25","conf/iros/WangYFWWHMZ25","conf/iros/WuHLZMLCS25","conf/nips/XuDSPHWLLMWK25","conf/nips/ZhongLXYWZSSZM25","conf/siggrapha/ChenXRYLDWLCWLC25","journals/corr/abs-2501-16728","journals/corr/abs-2502-06324","journals/corr/abs-2503-01291","journals/corr/abs-2503-08257","journals/corr/abs-2503-14329","journals/corr/abs-2503-21268","journals/corr/abs-2506-01583","journals/corr/abs-2506-03753","journals/corr/abs-2506-13138","journals/corr/abs-2506-23152","journals/corr/abs-2507-11949","journals/corr/abs-2507-12499","journals/corr/abs-2508-02106","journals/corr/abs-2508-06206","journals/corr/abs-2511-22187"],"matchedFormalPaperKeys":["conf/aaai/LuYTSMZ25","conf/aaai/XueRSYZM25","conf/aaai/Yang0PYM25","conf/cvpr/CongWM025","conf/cvpr/LiHXMSZ25","conf/cvpr/LiuLY0HTMW25","conf/cvpr/YanLLFDZZMXWS025","conf/cvpr/ZhongJYM25","conf/eccv/FuYHWMTSLL24","conf/eccv/LinPCZSHZYM24","conf/eccv/PengCQKLSWZM24","conf/eccv/RenHYLSM24","conf/eccv/ShiZYTMY24","conf/iccv/JiSJCXMYW25","conf/iccv/LuTMZ25","conf/iccv/WangYXZTYLYM25","conf/iccv/ZhuZYCYZM25","conf/icra/XiaoWTPM25","conf/icra/YanDSLLLWWWRM25","conf/iros/WangYFWWHMZ25","conf/iros/WuHLZMLCS25","conf/nips/XuDSPHWLLMWK25","conf/nips/ZhongLXYWZSSZM25","conf/siggrapha/ChenXRYLDWLCWLC25"]},{"url":"https://academic.oup.com/bib/article-pdf/26/2/bbaf191/63002705/bbaf191.pdf","evidence":"出版社原文首页 Yuexin Ma 上标 2，对应山东农业大学机械与电子工程学院农业装备智能化工程研究中心。"},{"url":"https://api.crossref.org/works/10.1093/BIB/BBAF191","evidence":"出版商 Crossref 元数据给出同一山东农业大学机构，未提供可关联到上海科技大学作者的 ORCID。"},{"url":"https://yuexinma.me/publications.html","evidence":"本人公开发表列表与 24 条已收录正式标题匹配，但未找到 WheatGP；列表缺席本身不作为异人定论。"}],"papers":[],"preprints":[],"excludedFormal":[],"otherRecords":[],"matchedName":"Yuexin Ma","databaseLabel":"Yuexin Ma","databaseMetadata":{"type":["https://dblp.org/rdf/schema#Creator","https://dblp.org/rdf/schema#Person"],"label":["Yuexin Ma"]},"rawFormalRecordCount2025":32,"signatureAudit":{"completedAt":"2026-10-19","frozen":true,"scope":"对 B 组 39 个数值档案的全部 1074 条原始 2025 正式记录扫描 DBLP author-signature ORCID 和机构；复用既有 59 条 Crossref 核验，补查 6 条新触发记录。重点核查不同 ORCID，以及只有预期机构之外机构的条目。本轮不扩展为所有作者逐篇全文审计。","formalRecordCoverage":32,"orcidCounts":{"https://orcid.org/0000-0001-7237-988X":2},"institutionCounts":{"Shandong Agricultural University (SDAU)":1,"ShanghaiTech University":23},"caveat":"机构名称可能由 DBLP 自动映射而失真；多 ORCID 也不自动等于异人。只有有原始资料支撑的错归才作确认排除，未解决分支则暂停总数。","decision":{"decision":"unresolved","reason":"author-signature 机构扫描发现 WheatGP（journals/bib/WangZMZLL24）挂入上海科技大学 Yuexin Ma 档案；出版商原文将 Yuexin Ma 单独归为山东农业大学机械与电子工程学院，未见上海科技大学机构，也未见于本人公开发表页。不能在缺少进一步身份确认时认定为本人或径自减一后称完整统计，因此全年总数暂留空，候选论文单列。","flaggedKeys":["journals/bib/WangZMZLL24"],"evidence":[{"url":"https://academic.oup.com/bib/article-pdf/26/2/bbaf191/63002705/bbaf191.pdf","evidence":"出版社原文首页 Yuexin Ma 上标 2，对应山东农业大学机械与电子工程学院农业装备智能化工程研究中心。"},{"url":"https://api.crossref.org/works/10.1093/BIB/BBAF191","evidence":"出版商 Crossref 元数据给出同一山东农业大学机构，未提供可关联到上海科技大学作者的 ORCID。"},{"url":"https://yuexinma.me/publications.html","evidence":"本人公开发表列表与 24 条已收录正式标题匹配，但未找到 WheatGP；列表缺席本身不作为异人定论。"}]}},"sourceWarning":true,"candidatePapers":[{"key":"conf/3dim/WuLLMSH25","url":"https://dblp.org/rec/conf/3dim/WuLLMSH25","title":"FastGrasp: Efficient Grasp Synthesis with Diffusion.","year":2025,"types":["Inproceedings"],"venue":["3DV"],"doi":["https://doi.org/10.1109/3DV66043.2025.00073"],"eventYear":2025,"numberOfCreators":6,"category":"conference","sources":["https://dblp.org/rec/conf/3dim/WuLLMSH25","https://doi.org/10.1109/3DV66043.2025.00073"],"publicationYear":2025},{"key":"conf/aaai/LuYTSMZ25","url":"https://dblp.org/rec/conf/aaai/LuYTSMZ25","title":"Can LVLMs Obtain a Driver's License? A Benchmark Towards Reliable AGI for Autonomous Driving.","year":2025,"types":["Inproceedings"],"venue":["AAAI"],"doi":["https://doi.org/10.1609/AAAI.V39I6.32623"],"eventYear":2025,"numberOfCreators":6,"category":"conference","sources":["https://dblp.org/rec/conf/aaai/LuYTSMZ25","https://doi.org/10.1609/AAAI.V39I6.32623"],"publicationYear":2025},{"key":"conf/aaai/XueRSYZM25","url":"https://dblp.org/rec/conf/aaai/XueRSYZM25","title":"FreeCap: Hybrid Calibration-Free Motion Capture in Open Environments.","year":2025,"types":["Inproceedings"],"venue":["AAAI"],"doi":["https://doi.org/10.1609/AAAI.V39I9.32977"],"eventYear":2025,"numberOfCreators":6,"category":"conference","sources":["https://dblp.org/rec/conf/aaai/XueRSYZM25","https://doi.org/10.1609/AAAI.V39I9.32977"],"publicationYear":2025},{"key":"conf/aaai/Yang0PYM25","url":"https://dblp.org/rec/conf/aaai/Yang0PYM25","title":"UniDemoiré: Towards Universal Image Demoiréing with Data Generation and Synthesis.","year":2025,"types":["Inproceedings"],"venue":["AAAI"],"doi":["https://doi.org/10.1609/AAAI.V39I9.33013"],"eventYear":2025,"numberOfCreators":5,"category":"conference","sources":["https://dblp.org/rec/conf/aaai/Yang0PYM25","https://doi.org/10.1609/AAAI.V39I9.33013"],"publicationYear":2025},{"key":"conf/cvm/SunSLMY25","url":"https://dblp.org/rec/conf/cvm/SunSLMY25","title":"Extreme Two-View Geometry From Object Poses with Diffusion Models.","year":2025,"types":["Inproceedings"],"venue":["CVM (2)"],"doi":["https://doi.org/10.1007/978-981-96-5812-1_16"],"eventYear":2025,"numberOfCreators":5,"category":"conference","sources":["https://dblp.org/rec/conf/cvm/SunSLMY25","https://doi.org/10.1007/978-981-96-5812-1_16"],"publicationYear":2025},{"key":"conf/cvpr/CongWM025","url":"https://dblp.org/rec/conf/cvpr/CongWM025","title":"SemGeoMo: Dynamic Contextual Human Motion Generation with Semantic and Geometric Guidance.","year":2025,"types":["Inproceedings"],"venue":["CVPR"],"doi":["https://doi.org/10.1109/CVPR52734.2025.01636"],"eventYear":2025,"numberOfCreators":4,"category":"conference","sources":["https://dblp.org/rec/conf/cvpr/CongWM025","https://doi.org/10.1109/CVPR52734.2025.01636"],"publicationYear":2025},{"key":"conf/cvpr/LiHXMSZ25","url":"https://dblp.org/rec/conf/cvpr/LiHXMSZ25","title":"OccMamba: Semantic Occupancy Prediction with State Space Models.","year":2025,"types":["Inproceedings"],"venue":["CVPR"],"doi":["https://doi.org/10.1109/CVPR52734.2025.01116"],"eventYear":2025,"numberOfCreators":6,"category":"conference","sources":["https://dblp.org/rec/conf/cvpr/LiHXMSZ25","https://doi.org/10.1109/CVPR52734.2025.01116"],"publicationYear":2025},{"key":"conf/cvpr/LiuLY0HTMW25","url":"https://dblp.org/rec/conf/cvpr/LiuLY0HTMW25","title":"EasyHOI: Unleashing the Power of Large Models for Reconstructing Hand-Object Interactions in the Wild.","year":2025,"types":["Inproceedings"],"venue":["CVPR"],"doi":["https://doi.org/10.1109/CVPR52734.2025.00660"],"eventYear":2025,"numberOfCreators":8,"category":"conference","sources":["https://dblp.org/rec/conf/cvpr/LiuLY0HTMW25","https://doi.org/10.1109/CVPR52734.2025.00660"],"publicationYear":2025},{"key":"conf/cvpr/YanLLFDZZMXWS025","url":"https://dblp.org/rec/conf/cvpr/YanLLFDZZMXWS025","title":"ClimbingCap: Multi-Modal Dataset and Method for Rock Climbing in World Coordinate.","year":2025,"types":["Inproceedings"],"venue":["CVPR"],"doi":["https://doi.org/10.1109/CVPR52734.2025.01149"],"eventYear":2025,"numberOfCreators":12,"category":"conference","sources":["https://dblp.org/rec/conf/cvpr/YanLLFDZZMXWS025","https://doi.org/10.1109/CVPR52734.2025.01149"],"publicationYear":2025},{"key":"conf/cvpr/ZhongJYM25","url":"https://dblp.org/rec/conf/cvpr/ZhongJYM25","title":"DexGrasp Anything: Towards Universal Robotic Dexterous Grasping with Physics Awareness.","year":2025,"types":["Inproceedings"],"venue":["CVPR"],"doi":["https://doi.org/10.1109/CVPR52734.2025.02103"],"eventYear":2025,"numberOfCreators":4,"category":"conference","sources":["https://dblp.org/rec/conf/cvpr/ZhongJYM25","https://doi.org/10.1109/CVPR52734.2025.02103"],"publicationYear":2025},{"key":"conf/eccv/FuYHWMTSLL24","url":"https://dblp.org/rec/conf/eccv/FuYHWMTSLL24","title":"GeoWizard: Unleashing the Diffusion Priors for 3D Geometry Estimation from a Single Image.","year":2025,"types":["Inproceedings"],"venue":["ECCV (22)"],"doi":["https://doi.org/10.1007/978-3-031-72670-5_14"],"eventYear":2024,"numberOfCreators":9,"category":"conference","sources":["https://dblp.org/rec/conf/eccv/FuYHWMTSLL24","https://doi.org/10.1007/978-3-031-72670-5_14"],"publicationYear":2025},{"key":"conf/eccv/LinPCZSHZYM24","url":"https://dblp.org/rec/conf/eccv/LinPCZSHZYM24","title":"WildRefer: 3D Object Localization in Large-Scale Dynamic Scenes with Multi-modal Visual Data and Natural Language.","year":2025,"types":["Inproceedings"],"venue":["ECCV (46)"],"doi":["https://doi.org/10.1007/978-3-031-72952-2_26"],"eventYear":2024,"numberOfCreators":9,"category":"conference","sources":["https://dblp.org/rec/conf/eccv/LinPCZSHZYM24","https://doi.org/10.1007/978-3-031-72952-2_26"],"publicationYear":2025},{"key":"conf/eccv/PengCQKLSWZM24","url":"https://dblp.org/rec/conf/eccv/PengCQKLSWZM24","title":"Learning to Adapt SAM for Segmenting Cross-Domain Point Clouds.","year":2025,"types":["Inproceedings"],"venue":["ECCV (43)"],"doi":["https://doi.org/10.1007/978-3-031-72775-7_4"],"eventYear":2024,"numberOfCreators":9,"category":"conference","sources":["https://dblp.org/rec/conf/eccv/PengCQKLSWZM24","https://doi.org/10.1007/978-3-031-72775-7_4"],"publicationYear":2025},{"key":"conf/eccv/RenHYLSM24","url":"https://dblp.org/rec/conf/eccv/RenHYLSM24","title":"LiveHPS++: Robust and Coherent Motion Capture in Dynamic Free Environment.","year":2025,"types":["Inproceedings"],"venue":["ECCV (29)"],"doi":["https://doi.org/10.1007/978-3-031-73397-0_8"],"eventYear":2024,"numberOfCreators":6,"category":"conference","sources":["https://dblp.org/rec/conf/eccv/RenHYLSM24","https://doi.org/10.1007/978-3-031-73397-0_8"],"publicationYear":2025},{"key":"conf/eccv/ShiZYTMY24","url":"https://dblp.org/rec/conf/eccv/ShiZYTMY24","title":"Part2Object: Hierarchical Unsupervised 3D Instance Segmentation.","year":2025,"types":["Inproceedings"],"venue":["ECCV (18)"],"doi":["https://doi.org/10.1007/978-3-031-72649-1_1"],"eventYear":2024,"numberOfCreators":6,"category":"conference","sources":["https://dblp.org/rec/conf/eccv/ShiZYTMY24","https://doi.org/10.1007/978-3-031-72649-1_1"],"publicationYear":2025},{"key":"conf/iccv/JiSJCXMYW25","url":"https://dblp.org/rec/conf/iccv/JiSJCXMYW25","title":"Towards Immersive Human-X Interaction: A Real-Time Framework for Physically Plausible Motion Synthesis.","year":2025,"types":["Inproceedings"],"venue":["ICCV"],"doi":["https://doi.org/10.1109/ICCV51701.2025.00948"],"eventYear":2025,"numberOfCreators":8,"category":"conference","sources":["https://dblp.org/rec/conf/iccv/JiSJCXMYW25","https://doi.org/10.1109/ICCV51701.2025.00948"],"publicationYear":2025},{"key":"conf/iccv/LuTMZ25","url":"https://dblp.org/rec/conf/iccv/LuTMZ25","title":"ReAL-AD: Towards Human-Like Reasoning in End-to-End Autonomous Driving.","year":2025,"types":["Inproceedings"],"venue":["ICCV"],"doi":["https://doi.org/10.1109/ICCV51701.2025.02579"],"eventYear":2025,"numberOfCreators":4,"category":"conference","sources":["https://dblp.org/rec/conf/iccv/LuTMZ25","https://doi.org/10.1109/ICCV51701.2025.02579"],"publicationYear":2025},{"key":"conf/iccv/WangYXZTYLYM25","url":"https://dblp.org/rec/conf/iccv/WangYXZTYLYM25","title":"DexH2R: A Benchmark for Dynamic Dexterous Grasping in Human-To-Robot Handover.","year":2025,"types":["Inproceedings"],"venue":["ICCV"],"doi":["https://doi.org/10.1109/ICCV51701.2025.01180"],"eventYear":2025,"numberOfCreators":9,"category":"conference","sources":["https://dblp.org/rec/conf/iccv/WangYXZTYLYM25","https://doi.org/10.1109/ICCV51701.2025.01180"],"publicationYear":2025},{"key":"conf/iccv/ZhuZYCYZM25","url":"https://dblp.org/rec/conf/iccv/ZhuZYCYZM25","title":"Evolvinggrasp: Evolutionary Grasp Generation Via Efficient Preference Alignment.","year":2025,"types":["Inproceedings"],"venue":["ICCV"],"doi":["https://doi.org/10.1109/ICCV51701.2025.01085"],"eventYear":2025,"numberOfCreators":7,"category":"conference","sources":["https://dblp.org/rec/conf/iccv/ZhuZYCYZM25","https://doi.org/10.1109/ICCV51701.2025.01085"],"publicationYear":2025},{"key":"conf/iclr/Li0CLDMYLW0Y25","url":"https://dblp.org/rec/conf/iclr/Li0CLDMYLW0Y25","title":"CityAnchor: City-scale 3D Visual Grounding with Multi-modality LLMs.","year":2025,"types":["Inproceedings"],"venue":["ICLR"],"doi":[],"eventYear":2025,"numberOfCreators":11,"category":"conference","sources":["https://dblp.org/rec/conf/iclr/Li0CLDMYLW0Y25"],"publicationYear":2025},{"key":"conf/icml/ZhuPM0YW025","url":"https://dblp.org/rec/conf/icml/ZhuPM0YW025","title":"UniDB: A Unified Diffusion Bridge Framework via Stochastic Optimal Control.","year":2025,"types":["Inproceedings"],"venue":["ICML"],"doi":[],"eventYear":2025,"numberOfCreators":7,"category":"conference","sources":["https://dblp.org/rec/conf/icml/ZhuPM0YW025"],"publicationYear":2025},{"key":"conf/icra/XiaoWTPM25","url":"https://dblp.org/rec/conf/icra/XiaoWTPM25","title":"Optimizing Efficiency of Mixed Traffic Through Reinforcement Learning: A Topology-Independent Approach and Benchmark.","year":2025,"types":["Inproceedings"],"venue":["ICRA"],"doi":["https://doi.org/10.1109/ICRA55743.2025.11127732"],"eventYear":2025,"numberOfCreators":5,"category":"conference","sources":["https://dblp.org/rec/conf/icra/XiaoWTPM25","https://doi.org/10.1109/ICRA55743.2025.11127732"],"publicationYear":2025},{"key":"conf/icra/YanDSLLLWWWRM25","url":"https://dblp.org/rec/conf/icra/YanDSLLLWWWRM25","title":"Renderworld: World Model with Self-Supervised 3D Label.","year":2025,"types":["Inproceedings"],"venue":["ICRA"],"doi":["https://doi.org/10.1109/ICRA55743.2025.11127609"],"eventYear":2025,"numberOfCreators":11,"category":"conference","sources":["https://dblp.org/rec/conf/icra/YanDSLLLWWWRM25","https://doi.org/10.1109/ICRA55743.2025.11127609"],"publicationYear":2025},{"key":"conf/iros/WangYFWWHMZ25","url":"https://dblp.org/rec/conf/iros/WangYFWWHMZ25","title":"STAGE: A Stream-Centric Generative World Model for Long-Horizon Driving-Scene Simulation.","year":2025,"types":["Inproceedings"],"venue":["IROS"],"doi":["https://doi.org/10.1109/IROS60139.2025.11246734"],"eventYear":2025,"numberOfCreators":8,"category":"conference","sources":["https://dblp.org/rec/conf/iros/WangYFWWHMZ25","https://doi.org/10.1109/IROS60139.2025.11246734"],"publicationYear":2025},{"key":"conf/iros/WuHLZMLCS25","url":"https://dblp.org/rec/conf/iros/WuHLZMLCS25","title":"Towards Label-Free 3D Visual Grounding with Vision Foundation Models.","year":2025,"types":["Inproceedings"],"venue":["IROS"],"doi":["https://doi.org/10.1109/IROS60139.2025.11246497"],"eventYear":2025,"numberOfCreators":8,"category":"conference","sources":["https://dblp.org/rec/conf/iros/WuHLZMLCS25","https://doi.org/10.1109/IROS60139.2025.11246497"],"publicationYear":2025},{"key":"conf/nips/XuDSPHWLLMWK25","url":"https://dblp.org/rec/conf/nips/XuDSPHWLLMWK25","title":"🎧MOSPA: Human Motion Generation Driven by Spatial Audio.","year":2025,"types":["Inproceedings"],"venue":["NeurIPS"],"doi":[],"eventYear":2025,"numberOfCreators":11,"category":"conference","sources":["https://dblp.org/rec/conf/nips/XuDSPHWLLMWK25"],"publicationYear":2025},{"key":"conf/nips/ZhongLXYWZSSZM25","url":"https://dblp.org/rec/conf/nips/ZhongLXYWZSSZM25","title":"FreqPolicy: Frequency Autoregressive Visuomotor Policy with Continuous Tokens.","year":2025,"types":["Inproceedings"],"venue":["NeurIPS"],"doi":[],"eventYear":2025,"numberOfCreators":10,"category":"conference","sources":["https://dblp.org/rec/conf/nips/ZhongLXYWZSSZM25"],"publicationYear":2025},{"key":"conf/siggrapha/ChenXRYLDWLCWLC25","url":"https://dblp.org/rec/conf/siggrapha/ChenXRYLDWLCWLC25","title":"SymBridge: A Human-in-the-Loop Cyber-Physical Interactive System for Adaptive Human-Robot Symbiosis.","year":2025,"types":["Inproceedings"],"venue":["SIGGRAPH Asia"],"doi":["https://doi.org/10.1145/3757377.3763915"],"eventYear":2025,"numberOfCreators":17,"category":"conference","sources":["https://dblp.org/rec/conf/siggrapha/ChenXRYLDWLCWLC25","https://doi.org/10.1145/3757377.3763915"],"publicationYear":2025},{"key":"conf/wacv/0001S0MY25","url":"https://dblp.org/rec/conf/wacv/0001S0MY25","title":"Generalizable Single-View Object Pose Estimation by Two-Side Generating and Matching.","year":2025,"types":["Inproceedings"],"venue":["WACV"],"doi":["https://doi.org/10.1109/WACV61041.2025.00063"],"eventYear":2025,"numberOfCreators":5,"category":"conference","sources":["https://dblp.org/rec/conf/wacv/0001S0MY25","https://doi.org/10.1109/WACV61041.2025.00063"],"publicationYear":2025},{"key":"journals/bib/WangZMZLL24","url":"https://dblp.org/rec/journals/bib/WangZMZLL24","title":"WheatGP, a genomic prediction method based on CNN and LSTM.","year":2025,"types":["Article"],"venue":["Briefings Bioinform."],"doi":["https://doi.org/10.1093/BIB/BBAF191"],"numberOfCreators":6,"category":"journal","sources":["https://dblp.org/rec/journals/bib/WangZMZLL24","https://doi.org/10.1093/BIB/BBAF191"],"publicationYear":2025,"eventYear":null},{"key":"journals/tnn/TangMMSGTW25","url":"https://dblp.org/rec/journals/tnn/TangMMSGTW25","title":"Decision Fusion Networks for Image Classification.","year":2025,"types":["Article"],"venue":["IEEE Trans. Neural Networks Learn. Syst."],"doi":["https://doi.org/10.1109/TNNLS.2022.3196129"],"numberOfCreators":7,"category":"journal","sources":["https://dblp.org/rec/journals/tnn/TangMMSGTW25","https://doi.org/10.1109/TNNLS.2022.3196129"],"publicationYear":2025,"eventYear":null},{"key":"journals/tvcg/LiuMYZWCGPYKXZTW25","url":"https://dblp.org/rec/journals/tvcg/LiuMYZWCGPYKXZTW25","title":"A Potential Field Method for Tooth Motion Planning in Orthodontic Treatment.","year":2025,"types":["Article"],"venue":["IEEE Trans. Vis. Comput. Graph."],"doi":["https://doi.org/10.1109/TVCG.2025.3567299"],"numberOfCreators":14,"category":"journal","sources":["https://dblp.org/rec/journals/tvcg/LiuMYZWCGPYKXZTW25","https://doi.org/10.1109/TVCG.2025.3567299"],"publicationYear":2025,"eventYear":null}],"candidatePreprints":[{"key":"journals/corr/abs-2501-00352","url":"https://dblp.org/rec/journals/corr/abs-2501-00352","title":"PanoSLAM: Panoptic 3D Scene Reconstruction via Gaussian SLAM.","year":2025,"types":["Informal"],"venue":["CoRR"],"doi":["https://doi.org/10.48550/ARXIV.2501.00352"],"numberOfCreators":7,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2501-00352","https://doi.org/10.48550/ARXIV.2501.00352"],"publicationYear":2025,"eventYear":null},{"key":"journals/corr/abs-2501-16728","url":"https://dblp.org/rec/journals/corr/abs-2501-16728","title":"Optimizing Efficiency of Mixed Traffic through Reinforcement Learning: A Topology-Independent Approach and Benchmark.","year":2025,"types":["Informal"],"venue":["CoRR"],"doi":["https://doi.org/10.48550/ARXIV.2501.16728"],"numberOfCreators":5,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2501-16728","https://doi.org/10.48550/ARXIV.2501.16728"],"publicationYear":2025,"eventYear":null},{"key":"journals/corr/abs-2502-05749","url":"https://dblp.org/rec/journals/corr/abs-2502-05749","title":"UniDB: A Unified Diffusion Bridge Framework via Stochastic Optimal Control.","year":2025,"types":["Informal"],"venue":["CoRR"],"doi":["https://doi.org/10.48550/ARXIV.2502.05749"],"numberOfCreators":7,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2502-05749","https://doi.org/10.48550/ARXIV.2502.05749"],"publicationYear":2025,"eventYear":null},{"key":"journals/corr/abs-2502-06324","url":"https://dblp.org/rec/journals/corr/abs-2502-06324","title":"UniDemoiré: Towards Universal Image Demoiréing with Data Generation and Synthesis.","year":2025,"types":["Informal"],"venue":["CoRR"],"doi":["https://doi.org/10.48550/ARXIV.2502.06324"],"numberOfCreators":5,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2502-06324","https://doi.org/10.48550/ARXIV.2502.06324"],"publicationYear":2025,"eventYear":null},{"key":"journals/corr/abs-2502-07358","url":"https://dblp.org/rec/journals/corr/abs-2502-07358","title":"SymbioSim: Human-in-the-loop Simulation Platform for Bidirectional Continuing Learning in Human-Robot Interaction.","year":2025,"types":["Informal"],"venue":["CoRR"],"doi":["https://doi.org/10.48550/ARXIV.2502.07358"],"numberOfCreators":15,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2502-07358","https://doi.org/10.48550/ARXIV.2502.07358"],"publicationYear":2025,"eventYear":null},{"key":"journals/corr/abs-2503-01291","url":"https://dblp.org/rec/journals/corr/abs-2503-01291","title":"SemGeoMo: Dynamic Contextual Human Motion Generation with Semantic and Geometric Guidance.","year":2025,"types":["Informal"],"venue":["CoRR"],"doi":["https://doi.org/10.48550/ARXIV.2503.01291"],"numberOfCreators":4,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2503-01291","https://doi.org/10.48550/ARXIV.2503.01291"],"publicationYear":2025,"eventYear":null},{"key":"journals/corr/abs-2503-08257","url":"https://dblp.org/rec/journals/corr/abs-2503-08257","title":"DexGrasp Anything: Towards Universal Robotic Dexterous Grasping with Physics Awareness.","year":2025,"types":["Informal"],"venue":["CoRR"],"doi":["https://doi.org/10.48550/ARXIV.2503.08257"],"numberOfCreators":4,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2503-08257","https://doi.org/10.48550/ARXIV.2503.08257"],"publicationYear":2025,"eventYear":null},{"key":"journals/corr/abs-2503-14329","url":"https://dblp.org/rec/journals/corr/abs-2503-14329","title":"EvolvingGrasp: Evolutionary Grasp Generation via Efficient Preference Alignment.","year":2025,"types":["Informal"],"venue":["CoRR"],"doi":["https://doi.org/10.48550/ARXIV.2503.14329"],"numberOfCreators":7,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2503-14329","https://doi.org/10.48550/ARXIV.2503.14329"],"publicationYear":2025,"eventYear":null},{"key":"journals/corr/abs-2503-21268","url":"https://dblp.org/rec/journals/corr/abs-2503-21268","title":"ClimbingCap: Multi-Modal Dataset and Method for Rock Climbing in World Coordinate.","year":2025,"types":["Informal"],"venue":["CoRR"],"doi":["https://doi.org/10.48550/ARXIV.2503.21268"],"numberOfCreators":12,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2503-21268","https://doi.org/10.48550/ARXIV.2503.21268"],"publicationYear":2025,"eventYear":null},{"key":"journals/corr/abs-2505-21528","url":"https://dblp.org/rec/journals/corr/abs-2505-21528","title":"UniDB++: Fast Sampling of Unified Diffusion Bridge.","year":2025,"types":["Informal"],"venue":["CoRR"],"doi":["https://doi.org/10.48550/ARXIV.2505.21528"],"numberOfCreators":7,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2505-21528","https://doi.org/10.48550/ARXIV.2505.21528"],"publicationYear":2025,"eventYear":null},{"key":"journals/corr/abs-2506-01583","url":"https://dblp.org/rec/journals/corr/abs-2506-01583","title":"FreqPolicy: Frequency Autoregressive Visuomotor Policy with Continuous Tokens.","year":2025,"types":["Informal"],"venue":["CoRR"],"doi":["https://doi.org/10.48550/ARXIV.2506.01583"],"numberOfCreators":10,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2506-01583","https://doi.org/10.48550/ARXIV.2506.01583"],"publicationYear":2025,"eventYear":null},{"key":"journals/corr/abs-2506-03753","url":"https://dblp.org/rec/journals/corr/abs-2506-03753","title":"HUMOF: Human Motion Forecasting in Interactive Social Scenes.","year":2025,"types":["Informal"],"venue":["CoRR"],"doi":["https://doi.org/10.48550/ARXIV.2506.03753"],"numberOfCreators":8,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2506-03753","https://doi.org/10.48550/ARXIV.2506.03753"],"publicationYear":2025,"eventYear":null},{"key":"journals/corr/abs-2506-13138","url":"https://dblp.org/rec/journals/corr/abs-2506-13138","title":"STAGE: A Stream-Centric Generative World Model for Long-Horizon Driving-Scene Simulation.","year":2025,"types":["Informal"],"venue":["CoRR"],"doi":["https://doi.org/10.48550/ARXIV.2506.13138"],"numberOfCreators":8,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2506-13138","https://doi.org/10.48550/ARXIV.2506.13138"],"publicationYear":2025,"eventYear":null},{"key":"journals/corr/abs-2506-23152","url":"https://dblp.org/rec/journals/corr/abs-2506-23152","title":"DexH2R: A Benchmark for Dynamic Dexterous Grasping in Human-to-Robot Handover.","year":2025,"types":["Informal"],"venue":["CoRR"],"doi":["https://doi.org/10.48550/ARXIV.2506.23152"],"numberOfCreators":9,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2506-23152","https://doi.org/10.48550/ARXIV.2506.23152"],"publicationYear":2025,"eventYear":null},{"key":"journals/corr/abs-2507-11949","url":"https://dblp.org/rec/journals/corr/abs-2507-11949","title":"MOSPA: Human Motion Generation Driven by Spatial Audio.","year":2025,"types":["Informal"],"venue":["CoRR"],"doi":["https://doi.org/10.48550/ARXIV.2507.11949"],"numberOfCreators":11,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2507-11949","https://doi.org/10.48550/ARXIV.2507.11949"],"publicationYear":2025,"eventYear":null},{"key":"journals/corr/abs-2507-12499","url":"https://dblp.org/rec/journals/corr/abs-2507-12499","title":"ReAL-AD: Towards Human-Like Reasoning in End-to-End Autonomous Driving.","year":2025,"types":["Informal"],"venue":["CoRR"],"doi":["https://doi.org/10.48550/ARXIV.2507.12499"],"numberOfCreators":4,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2507-12499","https://doi.org/10.48550/ARXIV.2507.12499"],"publicationYear":2025,"eventYear":null},{"key":"journals/corr/abs-2508-02106","url":"https://dblp.org/rec/journals/corr/abs-2508-02106","title":"Towards Immersive Human-X Interaction: A Real-Time Framework for Physically Plausible Motion Synthesis.","year":2025,"types":["Informal"],"venue":["CoRR"],"doi":["https://doi.org/10.48550/ARXIV.2508.02106"],"numberOfCreators":8,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2508-02106","https://doi.org/10.48550/ARXIV.2508.02106"],"publicationYear":2025,"eventYear":null},{"key":"journals/corr/abs-2508-06206","url":"https://dblp.org/rec/journals/corr/abs-2508-06206","title":"Affordance-R1: Reinforcement Learning for Generalizable Affordance Reasoning in Multimodal Large Language Model.","year":2025,"types":["Informal"],"venue":["CoRR"],"doi":["https://doi.org/10.48550/ARXIV.2508.06206"],"numberOfCreators":10,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2508-06206","https://doi.org/10.48550/ARXIV.2508.06206"],"publicationYear":2025,"eventYear":null},{"key":"journals/corr/abs-2511-01767","url":"https://dblp.org/rec/journals/corr/abs-2511-01767","title":"Wonder3D++: Cross-domain Diffusion for High-fidelity 3D Generation from a Single Image.","year":2025,"types":["Informal"],"venue":["CoRR"],"doi":["https://doi.org/10.48550/ARXIV.2511.01767"],"numberOfCreators":10,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2511-01767","https://doi.org/10.48550/ARXIV.2511.01767"],"publicationYear":2025,"eventYear":null},{"key":"journals/corr/abs-2511-22103","url":"https://dblp.org/rec/journals/corr/abs-2511-22103","title":"MoE3D: Mixture of Experts meets Multi-Modal 3D Understanding.","year":2025,"types":["Informal"],"venue":["CoRR"],"doi":["https://doi.org/10.48550/ARXIV.2511.22103"],"numberOfCreators":7,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2511-22103","https://doi.org/10.48550/ARXIV.2511.22103"],"publicationYear":2025,"eventYear":null},{"key":"journals/corr/abs-2511-22187","url":"https://dblp.org/rec/journals/corr/abs-2511-22187","title":"HybridWorldSim: A Scalable and Controllable High-fidelity Simulator for Autonomous Driving.","year":2025,"types":["Informal"],"venue":["CoRR"],"doi":["https://doi.org/10.48550/ARXIV.2511.22187"],"numberOfCreators":20,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2511-22187","https://doi.org/10.48550/ARXIV.2511.22187"],"publicationYear":2025,"eventYear":null}],"candidateFormalRecordCount2025":32,"candidatePreprintRecordCount2025":21,"labName":"4DV Lab","labUrl":"https://yuexinma.me/team.html","labEvidence":"本人主页直接链接的 Team 页面标题为 4DV Lab，并在 Professor 一栏列 Yuexin Ma（马月昕）。本标签只表示公开团队关联，不改变仍为 null 的论文归属结论。","labSourceUrl":"https://yuexinma.me/team.html","excludedOther":[],"excludedHomonyms":[],"unassignedCandidates":[],"knownPreprintMinimum2025":null,"excludedMisattributed":[],"knownMinimum2025":null,"displayNotes":"档案中挂有 WheatGP（journals/bib/WangZMZLL24）。出版商原文将该文作者 Yuexin Ma 列为山东农业大学所属，未见上海科技大学，该文也不在本人的发表页上。进一步确认之前，不能认定为本人，也不宜减去一条后称为完整，因此全年总数暂不给出，这绝非零。","labDisplayNotes":"个人主页链接的 Team 页面标题为 4DV Lab，并列其为 Professor，据此命名；论文数仍为空缺，图中不画柱。"},{"index":71,"name":"Yao Mu","nameZh":"穆尧","role":"Assistant Professor","affiliation":"Shanghai Jiao Tong University","affiliationZh":"上海交通大学","source":"DBLP RDF via official SPARQL; primary-source identity checks","sourceUrl":"https://sparql.dblp.org/","profileUrl":"https://dblp.org/pid/260/0674.html","identifier":"260/0674","retrievedAt":"2026-10-19","count2025":18,"conference2025":17,"journal2025":1,"preprint2025":27,"status":"confirmed","notes":"","identityEvidence":[{"url":"https://dblp.org/pid/260/0674.html","evidence":"DBLP RDF 类型为 Person，消歧后名字为 Yao Mu 0001。机构元数据含：Tsinghua University, School of Vehicle and Mobility, Beijing, China；University of Hong Kong, Department of Computer Science, Hong Kong；Shanghai Jiao Tong University, China"}],"papers":[{"key":"conf/acl/HuCC0S025","url":"https://dblp.org/rec/conf/acl/HuCC0S025","title":"HiAgent: Hierarchical Working Memory Management for Solving Long-Horizon Agent Tasks with Large Language Model.","year":2025,"types":["Inproceedings"],"venue":"ACL (1)","doi":"https://doi.org/10.18653/V1/2025.ACL-LONG.1575","eventYear":2025,"numberOfCreators":6,"category":"conference","sources":["https://dblp.org/rec/conf/acl/HuCC0S025","https://doi.org/10.18653/V1/2025.ACL-LONG.1575"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/acl/HuCC0S025","documentUrl":null,"type":"Inproceedings"},{"key":"conf/acl/HuCZLCL00SL25","url":"https://dblp.org/rec/conf/acl/HuCZLCL00SL25","title":"Text2World: Benchmarking Large Language Models for Symbolic World Model Generation.","year":2025,"types":["Inproceedings"],"venue":"ACL (Findings)","doi":"https://doi.org/10.18653/V1/2025.FINDINGS-ACL.1337","eventYear":2025,"numberOfCreators":10,"category":"conference","sources":["https://dblp.org/rec/conf/acl/HuCZLCL00SL25","https://doi.org/10.18653/V1/2025.FINDINGS-ACL.1337"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/acl/HuCZLCL00SL25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/cvpr/ChenC0YHL0PZJ0Y25","url":"https://dblp.org/rec/conf/cvpr/ChenC0YHL0PZJ0Y25","title":"GraphMimic: Graph-to-Graphs Generative Modeling from Videos for Policy Learning.","year":2025,"types":["Inproceedings"],"venue":"CVPR","doi":"https://doi.org/10.1109/CVPR52734.2025.00171","eventYear":2025,"numberOfCreators":12,"category":"conference","sources":["https://dblp.org/rec/conf/cvpr/ChenC0YHL0PZJ0Y25","https://doi.org/10.1109/CVPR52734.2025.00171"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/ChenC0YHL0PZJ0Y25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/cvpr/ChenMLCPCXH00025","url":"https://dblp.org/rec/conf/cvpr/ChenMLCPCXH00025","title":"G3Flow: Generative 3D Semantic Flow for Pose-aware and Generalizable Object Manipulation.","year":2025,"types":["Inproceedings"],"venue":"CVPR","doi":"https://doi.org/10.1109/CVPR52734.2025.00169","eventYear":2025,"numberOfCreators":11,"category":"conference","sources":["https://dblp.org/rec/conf/cvpr/ChenMLCPCXH00025","https://doi.org/10.1109/CVPR52734.2025.00169"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/ChenMLCPCXH00025","documentUrl":null,"type":"Inproceedings"},{"key":"conf/cvpr/DingJHZW0025","url":"https://dblp.org/rec/conf/cvpr/DingJHZW0025","title":"SwarmDiff: Swarm Robotic Trajectory Planning in Cluttered Environments via Diffusion Transformer.","year":2025,"types":["Inproceedings"],"venue":"CVPR Workshops","doi":null,"eventYear":2025,"numberOfCreators":7,"category":"conference","sources":["https://dblp.org/rec/conf/cvpr/DingJHZW0025"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/DingJHZW0025","documentUrl":null,"type":"Inproceedings"},{"key":"conf/cvpr/JiTSHZZWZ0AXSL025","url":"https://dblp.org/rec/conf/cvpr/JiTSHZZWZ0AXSL025","title":"RoboBrain: A Unified Brain Model for Robotic Manipulation from Abstract to Concrete.","year":2025,"types":["Inproceedings"],"venue":"CVPR","doi":"https://doi.org/10.1109/CVPR52734.2025.00168","eventYear":2025,"numberOfCreators":17,"category":"conference","sources":["https://dblp.org/rec/conf/cvpr/JiTSHZZWZ0AXSL025","https://doi.org/10.1109/CVPR52734.2025.00168"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/JiTSHZZWZ0AXSL025","documentUrl":null,"type":"Inproceedings"},{"key":"conf/cvpr/LiangMWCSZTLD25","url":"https://dblp.org/rec/conf/cvpr/LiangMWCSZTLD25","title":"DexHandDiff: Interaction-aware Diffusion Planning for Adaptive Dexterous Manipulation.","year":2025,"types":["Inproceedings"],"venue":"CVPR","doi":"https://doi.org/10.1109/CVPR52734.2025.00170","eventYear":2025,"numberOfCreators":9,"category":"conference","sources":["https://dblp.org/rec/conf/cvpr/LiangMWCSZTLD25","https://doi.org/10.1109/CVPR52734.2025.00170"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/LiangMWCSZTLD25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/cvpr/MuCCPLGLYZXLXDL25","url":"https://dblp.org/rec/conf/cvpr/MuCCPLGLYZXLXDL25","title":"RoboTwin: Dual-Arm Robot Benchmark with Generative Digital Twins.","year":2025,"types":["Inproceedings"],"venue":"CVPR","doi":"https://doi.org/10.1109/CVPR52734.2025.02575","eventYear":2025,"numberOfCreators":14,"category":"conference","sources":["https://dblp.org/rec/conf/cvpr/MuCCPLGLYZXLXDL25","https://doi.org/10.1109/CVPR52734.2025.02575"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/MuCCPLGLYZXLXDL25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/eccv/MuCPCGZLXL24","url":"https://dblp.org/rec/conf/eccv/MuCPCGZLXL24","title":"RoboTwin: Dual-Arm Robot Benchmark with Generative Digital Twins (Early Version).","year":2025,"types":["Inproceedings"],"venue":"ECCV Workshops (8)","doi":"https://doi.org/10.1007/978-3-031-91813-1_17","eventYear":2024,"numberOfCreators":9,"category":"conference","sources":["https://dblp.org/rec/conf/eccv/MuCPCGZLXL24","https://doi.org/10.1007/978-3-031-91813-1_17"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2024,"sourceUrl":"https://dblp.org/rec/conf/eccv/MuCPCGZLXL24","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iccv/HaoYZWWKYFYQMSCZZZSLN25","url":"https://dblp.org/rec/conf/iccv/HaoYZWWKYFYQMSCZZZSLN25","title":"Research Challenges and Progress in the End-to-End V2X Cooperative Autonomous Driving Competition.","year":2025,"types":["Inproceedings"],"venue":"ICCVW","doi":"https://doi.org/10.1109/ICCVW69036.2025.00195","eventYear":2025,"numberOfCreators":19,"category":"conference","sources":["https://dblp.org/rec/conf/iccv/HaoYZWWKYFYQMSCZZZSLN25","https://doi.org/10.1109/ICCVW69036.2025.00195"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/HaoYZWWKYFYQMSCZZZSLN25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iccv/ZhuZPJM25","url":"https://dblp.org/rec/conf/iccv/ZhuZPJM25","title":"PASG: A Closed-Loop Framework for Automated Geometric Primitive Extraction and Semantic Anchoring in Robotic Manipulation.","year":2025,"types":["Inproceedings"],"venue":"ICCV","doi":"https://doi.org/10.1109/ICCV51701.2025.00837","eventYear":2025,"numberOfCreators":5,"category":"conference","sources":["https://dblp.org/rec/conf/iccv/ZhuZPJM25","https://doi.org/10.1109/ICCV51701.2025.00837"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/ZhuZPJM25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iclr/ChenYZX0HSW0025","url":"https://dblp.org/rec/conf/iclr/ChenYZX0HSW0025","title":"EMOS: Embodiment-aware Heterogeneous Multi-robot Operating System with LLM Agents.","year":2025,"types":["Inproceedings"],"venue":"ICLR","doi":null,"eventYear":2025,"numberOfCreators":10,"category":"conference","sources":["https://dblp.org/rec/conf/iclr/ChenYZX0HSW0025"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iclr/ChenYZX0HSW0025","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iclr/Wen00K25","url":"https://dblp.org/rec/conf/iclr/Wen00K25","title":"M^3PC: Test-time Model Predictive Control using Pretrained Masked Trajectory Model.","year":2025,"types":["Inproceedings"],"venue":"ICLR","doi":null,"eventYear":2025,"numberOfCreators":4,"category":"conference","sources":["https://dblp.org/rec/conf/iclr/Wen00K25"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iclr/Wen00K25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iros/XiongMLFHL25","url":"https://dblp.org/rec/conf/iros/XiongMLFHL25","title":"PACR: Point-Axis Constraint Reasoning for Enhanced Robotic Manipulation with Dexterity and Compliance.","year":2025,"types":["Inproceedings"],"venue":"IROS","doi":"https://doi.org/10.1109/IROS60139.2025.11246460","eventYear":2025,"numberOfCreators":6,"category":"conference","sources":["https://dblp.org/rec/conf/iros/XiongMLFHL25","https://doi.org/10.1109/IROS60139.2025.11246460"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iros/XiongMLFHL25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iros/YuYJCZHYCMLL25","url":"https://dblp.org/rec/conf/iros/YuYJCZHYCMLL25","title":"ArtGS: 3D Gaussian Splatting for Interactive Visual-Physical Modeling and Manipulation of Articulated Objects.","year":2025,"types":["Inproceedings"],"venue":"IROS","doi":"https://doi.org/10.1109/IROS60139.2025.11246522","eventYear":2025,"numberOfCreators":11,"category":"conference","sources":["https://dblp.org/rec/conf/iros/YuYJCZHYCMLL25","https://doi.org/10.1109/IROS60139.2025.11246522"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iros/YuYJCZHYCMLL25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/ivs/WangLCJML25","url":"https://dblp.org/rec/conf/ivs/WangLCJML25","title":"PA-TCP: Interpretable End-to-End Autonomous Driving Through Parallel Adaptive Attention Mechanism and State Representation.","year":2025,"types":["Inproceedings"],"venue":"IV","doi":"https://doi.org/10.1109/IV64158.2025.11097569","eventYear":2025,"numberOfCreators":6,"category":"conference","sources":["https://dblp.org/rec/conf/ivs/WangLCJML25","https://doi.org/10.1109/IV64158.2025.11097569"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/ivs/WangLCJML25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/nips/ChenLDWHMWDLSS25","url":"https://dblp.org/rec/conf/nips/ChenLDWHMWDLSS25","title":"OWMM-Agent: Open World Mobile Manipulation With Multi-modal Agentic Data Synthesis.","year":2025,"types":["Inproceedings"],"venue":"NeurIPS","doi":null,"eventYear":2025,"numberOfCreators":11,"category":"conference","sources":["https://dblp.org/rec/conf/nips/ChenLDWHMWDLSS25"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/nips/ChenLDWHMWDLSS25","documentUrl":null,"type":"Inproceedings"},{"key":"journals/tmlr/XiongLHWW0YSWHT25","url":"https://dblp.org/rec/journals/tmlr/XiongLHWW0YSWHT25","title":"Autoregressive Models in Vision: A Survey.","year":2025,"types":["Article"],"venue":"Trans. Mach. Learn. Res.","doi":null,"numberOfCreators":20,"category":"journal","sources":["https://dblp.org/rec/journals/tmlr/XiongLHWW0YSWHT25"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/tmlr/XiongLHWW0YSWHT25","documentUrl":null,"type":"Article"}],"preprints":[{"key":"journals/corr/abs-2501-09218","url":"https://dblp.org/rec/journals/corr/abs-2501-09218","title":"Interpretable Droplet Digital PCR Assay for Trustworthy Molecular Diagnostics.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2501.09218","numberOfCreators":8,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2501-09218","https://doi.org/10.48550/ARXIV.2501.09218"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2501-09218","documentUrl":null,"type":"Informal","arxivId":"2501.09218","arxivUrl":"https://arxiv.org/abs/2501.09218"},{"key":"journals/corr/abs-2502-13092","url":"https://dblp.org/rec/journals/corr/abs-2502-13092","title":"Text2World: Benchmarking Large Language Models for Symbolic World Model Generation.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2502.13092","numberOfCreators":10,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2502-13092","https://doi.org/10.48550/ARXIV.2502.13092"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2502-13092","documentUrl":null,"type":"Informal","arxivId":"2502.13092","arxivUrl":"https://arxiv.org/abs/2502.13092"},{"key":"journals/corr/abs-2502-21257","url":"https://dblp.org/rec/journals/corr/abs-2502-21257","title":"RoboBrain: A Unified Brain Model for Robotic Manipulation from Abstract to Concrete.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2502.21257","numberOfCreators":17,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2502-21257","https://doi.org/10.48550/ARXIV.2502.21257"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2502-21257","documentUrl":null,"type":"Informal","arxivId":"2502.21257","arxivUrl":"https://arxiv.org/abs/2502.21257"},{"key":"journals/corr/abs-2503-01439","url":"https://dblp.org/rec/journals/corr/abs-2503-01439","title":"AVR: Active Vision-Driven Robotic Precision Manipulation with Viewpoint and Focal Length Optimization.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2503.01439","numberOfCreators":10,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2503-01439","https://doi.org/10.48550/ARXIV.2503.01439"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-01439","documentUrl":null,"type":"Informal","arxivId":"2503.01439","arxivUrl":"https://arxiv.org/abs/2503.01439"},{"key":"journals/corr/abs-2503-06669","url":"https://dblp.org/rec/journals/corr/abs-2503-06669","title":"AgiBot World Colosseo: A Large-scale Manipulation Platform for Scalable and Intelligent Embodied Systems.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2503.06669","numberOfCreators":51,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2503-06669","https://doi.org/10.48550/ARXIV.2503.06669"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-06669","documentUrl":null,"type":"Informal","arxivId":"2503.06669","arxivUrl":"https://arxiv.org/abs/2503.06669"},{"key":"journals/corr/abs-2503-09366","url":"https://dblp.org/rec/journals/corr/abs-2503-09366","title":"Post-interactive Multimodal Trajectory Prediction for Autonomous Driving.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2503.09366","numberOfCreators":6,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2503-09366","https://doi.org/10.48550/ARXIV.2503.09366"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-09366","documentUrl":null,"type":"Informal","arxivId":"2503.09366","arxivUrl":"https://arxiv.org/abs/2503.09366"},{"key":"journals/corr/abs-2503-22942","url":"https://dblp.org/rec/journals/corr/abs-2503-22942","title":"Adaptive Interactive Navigation of Quadruped Robots using Large Language Models.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2503.22942","numberOfCreators":7,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2503-22942","https://doi.org/10.48550/ARXIV.2503.22942"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-22942","documentUrl":null,"type":"Informal","arxivId":"2503.22942","arxivUrl":"https://arxiv.org/abs/2503.22942"},{"key":"journals/corr/abs-2504-03515","url":"https://dblp.org/rec/journals/corr/abs-2504-03515","title":"Dexterous Manipulation through Imitation Learning: A Survey.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2504.03515","numberOfCreators":12,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2504-03515","https://doi.org/10.48550/ARXIV.2504.03515"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2504-03515","documentUrl":null,"type":"Informal","arxivId":"2504.03515","arxivUrl":"https://arxiv.org/abs/2504.03515"},{"key":"journals/corr/abs-2504-13059","url":"https://dblp.org/rec/journals/corr/abs-2504-13059","title":"RoboTwin: Dual-Arm Robot Benchmark with Generative Digital Twins.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2504.13059","numberOfCreators":14,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2504-13059","https://doi.org/10.48550/ARXIV.2504.13059"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2504-13059","documentUrl":null,"type":"Informal","arxivId":"2504.13059","arxivUrl":"https://arxiv.org/abs/2504.13059"},{"key":"journals/corr/abs-2505-14030","url":"https://dblp.org/rec/journals/corr/abs-2505-14030","title":"AutoBio: A Simulation and Benchmark for Robotic Automation in Digital Biology Laboratory.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2505.14030","numberOfCreators":15,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2505-14030","https://doi.org/10.48550/ARXIV.2505.14030"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-14030","documentUrl":null,"type":"Informal","arxivId":"2505.14030","arxivUrl":"https://arxiv.org/abs/2505.14030"},{"key":"journals/corr/abs-2505-15679","url":"https://dblp.org/rec/journals/corr/abs-2505-15679","title":"SwarmDiff: Swarm Robotic Trajectory Planning in Cluttered Environments via Diffusion Transformer.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2505.15679","numberOfCreators":7,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2505-15679","https://doi.org/10.48550/ARXIV.2505.15679"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-15679","documentUrl":null,"type":"Informal","arxivId":"2505.15679","arxivUrl":"https://arxiv.org/abs/2505.15679"},{"key":"journals/corr/abs-2506-04217","url":"https://dblp.org/rec/journals/corr/abs-2506-04217","title":"OWMM-Agent: Open World Mobile Manipulation With Multi-modal Agentic Data Synthesis.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2506.04217","numberOfCreators":11,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2506-04217","https://doi.org/10.48550/ARXIV.2506.04217"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-04217","documentUrl":null,"type":"Informal","arxivId":"2506.04217","arxivUrl":"https://arxiv.org/abs/2506.04217"},{"key":"journals/corr/abs-2506-18088","url":"https://dblp.org/rec/journals/corr/abs-2506-18088","title":"RoboTwin 2.0: A Scalable Data Generator and Benchmark with Strong Domain Randomization for Robust Bimanual Robotic Manipulation.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2506.18088","numberOfCreators":26,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2506-18088","https://doi.org/10.48550/ARXIV.2506.18088"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-18088","documentUrl":null,"type":"Informal","arxivId":"2506.18088","arxivUrl":"https://arxiv.org/abs/2506.18088"},{"key":"journals/corr/abs-2506-23351","url":"https://dblp.org/rec/journals/corr/abs-2506-23351","title":"Benchmarking Generalizable Bimanual Manipulation: RoboTwin Dual-Arm Collaboration Challenge at CVPR 2025 MEIS Workshop.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2506.23351","numberOfCreators":16,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2506-23351","https://doi.org/10.48550/ARXIV.2506.23351"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-23351","documentUrl":null,"type":"Informal","arxivId":"2506.23351","arxivUrl":"https://arxiv.org/abs/2506.23351"},{"key":"journals/corr/abs-2507-02600","url":"https://dblp.org/rec/journals/corr/abs-2507-02600","title":"ArtGS:3D Gaussian Splatting for Interactive Visual-Physical Modeling and Manipulation of Articulated Objects.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2507.02600","numberOfCreators":11,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2507-02600","https://doi.org/10.48550/ARXIV.2507.02600"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2507-02600","documentUrl":null,"type":"Informal","arxivId":"2507.02600","arxivUrl":"https://arxiv.org/abs/2507.02600"},{"key":"journals/corr/abs-2507-20622","url":"https://dblp.org/rec/journals/corr/abs-2507-20622","title":"FMimic: Foundation Models are Fine-grained Action Learners from Human Videos.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2507.20622","numberOfCreators":11,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2507-20622","https://doi.org/10.48550/ARXIV.2507.20622"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2507-20622","documentUrl":null,"type":"Informal","arxivId":"2507.20622","arxivUrl":"https://arxiv.org/abs/2507.20622"},{"key":"journals/corr/abs-2507-21610","url":"https://dblp.org/rec/journals/corr/abs-2507-21610","title":"Research Challenges and Progress in the End-to-End V2X Cooperative Autonomous Driving Competition.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2507.21610","numberOfCreators":21,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2507-21610","https://doi.org/10.48550/ARXIV.2507.21610"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2507-21610","documentUrl":null,"type":"Informal","arxivId":"2507.21610","arxivUrl":"https://arxiv.org/abs/2507.21610"},{"key":"journals/corr/abs-2508-02629","url":"https://dblp.org/rec/journals/corr/abs-2508-02629","title":"HyCodePolicy: Hybrid Language Controllers for Multimodal Monitoring and Decision in Embodied Agents.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2508.02629","numberOfCreators":10,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2508-02629","https://doi.org/10.48550/ARXIV.2508.02629"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-02629","documentUrl":null,"type":"Informal","arxivId":"2508.02629","arxivUrl":"https://arxiv.org/abs/2508.02629"},{"key":"journals/corr/abs-2508-05976","url":"https://dblp.org/rec/journals/corr/abs-2508-05976","title":"PASG: A Closed-Loop Framework for Automated Geometric Primitive Extraction and Semantic Anchoring in Robotic Manipulation.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2508.05976","numberOfCreators":5,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2508-05976","https://doi.org/10.48550/ARXIV.2508.05976"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-05976","documentUrl":null,"type":"Informal","arxivId":"2508.05976","arxivUrl":"https://arxiv.org/abs/2508.05976"},{"key":"journals/corr/abs-2508-20072","url":"https://dblp.org/rec/journals/corr/abs-2508-20072","title":"Discrete Diffusion VLA: Bringing Discrete Diffusion to Action Decoding in Vision-Language-Action Policies.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2508.20072","numberOfCreators":10,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2508-20072","https://doi.org/10.48550/ARXIV.2508.20072"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-20072","documentUrl":null,"type":"Informal","arxivId":"2508.20072","arxivUrl":"https://arxiv.org/abs/2508.20072"},{"key":"journals/corr/abs-2509-09674","url":"https://dblp.org/rec/journals/corr/abs-2509-09674","title":"SimpleVLA-RL: Scaling VLA Training via Reinforcement Learning.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2509.09674","numberOfCreators":21,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2509-09674","https://doi.org/10.48550/ARXIV.2509.09674"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-09674","documentUrl":null,"type":"Informal","arxivId":"2509.09674","arxivUrl":"https://arxiv.org/abs/2509.09674"},{"key":"journals/corr/abs-2509-23823","url":"https://dblp.org/rec/journals/corr/abs-2509-23823","title":"Control Your Robot: A Unified System for Robot Control and Policy Deployment.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2509.23823","numberOfCreators":6,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2509-23823","https://doi.org/10.48550/ARXIV.2509.23823"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-23823","documentUrl":null,"type":"Informal","arxivId":"2509.23823","arxivUrl":"https://arxiv.org/abs/2509.23823"},{"key":"journals/corr/abs-2510-11027","url":"https://dblp.org/rec/journals/corr/abs-2510-11027","title":"Vlaser: Vision-Language-Action Model with Synergistic Embodied Reasoning.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2510.11027","numberOfCreators":18,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2510-11027","https://doi.org/10.48550/ARXIV.2510.11027"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-11027","documentUrl":null,"type":"Informal","arxivId":"2510.11027","arxivUrl":"https://arxiv.org/abs/2510.11027"},{"key":"journals/corr/abs-2510-13778","url":"https://dblp.org/rec/journals/corr/abs-2510-13778","title":"InternVLA-M1: A Spatially Guided Vision-Language-Action Framework for Generalist Robot Policy.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2510.13778","numberOfCreators":29,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2510-13778","https://doi.org/10.48550/ARXIV.2510.13778"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-13778","documentUrl":null,"type":"Informal","arxivId":"2510.13778","arxivUrl":"https://arxiv.org/abs/2510.13778"},{"key":"journals/corr/abs-2510-14300","url":"https://dblp.org/rec/journals/corr/abs-2510-14300","title":"Expertise need not monopolize: Action-Specialized Mixture of Experts for Vision-Language-Action Learning.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2510.14300","numberOfCreators":13,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2510-14300","https://doi.org/10.48550/ARXIV.2510.14300"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-14300","documentUrl":null,"type":"Informal","arxivId":"2510.14300","arxivUrl":"https://arxiv.org/abs/2510.14300"},{"key":"journals/corr/abs-2510-20774","url":"https://dblp.org/rec/journals/corr/abs-2510-20774","title":"FieldGen: From Teleoperated Pre-Manipulation Trajectories to Field-Guided Data Generation.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2510.20774","numberOfCreators":12,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2510-20774","https://doi.org/10.48550/ARXIV.2510.20774"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-20774","documentUrl":null,"type":"Informal","arxivId":"2510.20774","arxivUrl":"https://arxiv.org/abs/2510.20774"},{"key":"journals/corr/abs-2512-00975","url":"https://dblp.org/rec/journals/corr/abs-2512-00975","title":"MM-ACT: Learn from Multimodal Parallel Generation to Act.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2512.00975","numberOfCreators":15,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2512-00975","https://doi.org/10.48550/ARXIV.2512.00975"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-00975","documentUrl":null,"type":"Informal","arxivId":"2512.00975","arxivUrl":"https://arxiv.org/abs/2512.00975"}],"excludedFormal":[],"otherRecords":[],"matchedName":"Yao Mu","databaseLabel":"Yao Mu 0001","databaseMetadata":{"type":["https://dblp.org/rdf/schema#Person","https://dblp.org/rdf/schema#Creator"],"label":["Yao Mu 0001"],"affiliation":["Tsinghua University, School of Vehicle and Mobility, Beijing, China","University of Hong Kong, Department of Computer Science, Hong Kong","Shanghai Jiao Tong University, China"],"homepage":["https://openreview.net/profile?id=~Yao_Mu1"],"orcid":["https://orcid.org/0000-0002-0321-021X"],"primaryAffiliation":["Shanghai Jiao Tong University, China"],"primaryHomepage":["https://openreview.net/profile?id=~Yao_Mu1"]},"rawFormalRecordCount2025":18,"signatureAudit":{"completedAt":"2026-10-19","frozen":true,"scope":"对 B 组 39 个数值档案的全部 1074 条原始 2025 正式记录扫描 DBLP author-signature ORCID 和机构；复用既有 59 条 Crossref 核验，补查 6 条新触发记录。重点核查不同 ORCID，以及只有预期机构之外机构的条目。本轮不扩展为所有作者逐篇全文审计。","formalRecordCoverage":18,"orcidCounts":{},"institutionCounts":{"Artificial Intelligence in Medicine (AIM)":1,"Shanghai Artificial Intelligence Laboratory":2,"Shanghai Jiao Tong University (SJTU)":4,"University of Hong Kong (HKU)":8},"caveat":"机构名称可能由 DBLP 自动映射而失真；多 ORCID 也不自动等于异人。只有有原始资料支撑的错归才作确认排除，未解决分支则暂停总数。"},"labName":"ScaleLab","labUrl":"https://scalelab-sjtu.github.io/","labEvidence":"本人当前主页明确写 Welcome to ScaleLab@SJTU，并直接提供实验室链接；上海交通大学官方穆尧教师页也列实验室主页。未采用其博士阶段 HKU MMLab 作为当前组。","labSourceUrl":"https://yaomarkmu.github.io/","sourceWarning":false,"excludedOther":[],"excludedHomonyms":[],"unassignedCandidates":[],"knownPreprintMinimum2025":null,"excludedMisattributed":[],"displayNotes":"身份已与原名单机构及公开资料核对确认。2025 年正式记录 18 条（会议 17、期刊 1），所有作者位置均计入，不表示主导或贡献份额；预印本 27 条单列，不加总。","labDisplayNotes":"本人主页写明欢迎加入 ScaleLab@SJTU 并附链接，上海交大官方教师页也列出该实验室主页，据此归组；不采用其博士阶段所在的港大 MMLab。"},{"index":72,"name":"Wenjie Pei","nameZh":"裴文杰","role":"Professor","affiliation":"Harbin Institute of Technology, Shenzhen","affiliationZh":"哈尔滨工业大学（深圳）","source":"DBLP RDF via official SPARQL; primary-source identity checks","sourceUrl":"https://sparql.dblp.org/","profileUrl":"https://dblp.org/pid/08/9704.html","identifier":"08/9704","retrievedAt":"2026-10-19","count2025":12,"conference2025":10,"journal2025":2,"preprint2025":7,"status":"confirmed","notes":"","identityEvidence":[{"url":"https://dblp.org/pid/08/9704.html","evidence":"DBLP RDF 类型为 Person，消歧后名字为 Wenjie Pei。此档案未提供可用机构元数据，以下以本人/机构/出版商来源补证。"},{"url":"https://wenjiepei.github.io/","evidence":"个人主页为哈尔滨工业大学（深圳）Wenjie Pei，个人论文列表与 DBLP 标题匹配。"},{"url":"https://wenjiepei.github.io/","evidence":"此本人或机构页面的正文与所选档案中 15 条 2025 记录标题匹配，其中 10 条为当前计入的正式记录（忽略空格、标点、大小写）。","matchedPaperKeys":["conf/cvpr/FangLWZYLP25","conf/cvpr/SunZJ0YLP25","conf/eccv/SunLTPC24","conf/eccv/WuFLZCLP24","conf/eccv/WuTLLP24","conf/iccv/LiuSXGCP25","conf/iccv/NingTSLHPJ25","conf/iccv/PeiTLTY25","conf/nips/WangCYLP25","journals/corr/abs-2503-08387","journals/corr/abs-2504-11879","journals/corr/abs-2506-23120","journals/corr/abs-2507-16310","journals/corr/abs-2510-20217","journals/tnn/XuPWPLX25"],"matchedFormalPaperKeys":["conf/cvpr/FangLWZYLP25","conf/cvpr/SunZJ0YLP25","conf/eccv/SunLTPC24","conf/eccv/WuFLZCLP24","conf/eccv/WuTLLP24","conf/iccv/LiuSXGCP25","conf/iccv/NingTSLHPJ25","conf/iccv/PeiTLTY25","conf/nips/WangCYLP25","journals/tnn/XuPWPLX25"]}],"papers":[{"key":"conf/cvpr/FangLWZYLP25","url":"https://dblp.org/rec/conf/cvpr/FangLWZYLP25","title":"Recognition-Synergistic Scene Text Editing.","year":2025,"types":["Inproceedings"],"venue":"CVPR","doi":"https://doi.org/10.1109/CVPR52734.2025.01223","eventYear":2025,"numberOfCreators":7,"category":"conference","sources":["https://dblp.org/rec/conf/cvpr/FangLWZYLP25","https://doi.org/10.1109/CVPR52734.2025.01223"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/FangLWZYLP25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/cvpr/SunZJ0YLP25","url":"https://dblp.org/rec/conf/cvpr/SunZJ0YLP25","title":"Learning Compatible Multi-Prize Subnetworks for Asymmetric Retrieval.","year":2025,"types":["Inproceedings"],"venue":"CVPR","doi":"https://doi.org/10.1109/CVPR52734.2025.01421","eventYear":2025,"numberOfCreators":7,"category":"conference","sources":["https://dblp.org/rec/conf/cvpr/SunZJ0YLP25","https://doi.org/10.1109/CVPR52734.2025.01421"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/SunZJ0YLP25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/eccv/SunLTPC24","url":"https://dblp.org/rec/conf/eccv/SunLTPC24","title":"AnyControl: Create Your Artwork with Versatile Control on Text-to-Image Generation.","year":2025,"types":["Inproceedings"],"venue":"ECCV (11)","doi":"https://doi.org/10.1007/978-3-031-73247-8_6","eventYear":2024,"numberOfCreators":5,"category":"conference","sources":["https://dblp.org/rec/conf/eccv/SunLTPC24","https://doi.org/10.1007/978-3-031-73247-8_6"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2024,"sourceUrl":"https://dblp.org/rec/conf/eccv/SunLTPC24","documentUrl":null,"type":"Inproceedings"},{"key":"conf/eccv/WuFLZCLP24","url":"https://dblp.org/rec/conf/eccv/WuFLZCLP24","title":"WeCromCL: Weakly Supervised Cross-Modality Contrastive Learning for Transcription-Only Supervised Text Spotting.","year":2025,"types":["Inproceedings"],"venue":"ECCV (31)","doi":"https://doi.org/10.1007/978-3-031-72751-1_17","eventYear":2024,"numberOfCreators":7,"category":"conference","sources":["https://dblp.org/rec/conf/eccv/WuFLZCLP24","https://doi.org/10.1007/978-3-031-72751-1_17"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2024,"sourceUrl":"https://dblp.org/rec/conf/eccv/WuFLZCLP24","documentUrl":null,"type":"Inproceedings"},{"key":"conf/eccv/WuTLLP24","url":"https://dblp.org/rec/conf/eccv/WuTLLP24","title":"UniVoxel: Fast Inverse Rendering by Unified Voxelization of Scene Representation.","year":2025,"types":["Inproceedings"],"venue":"ECCV (71)","doi":"https://doi.org/10.1007/978-3-031-73209-6_21","eventYear":2024,"numberOfCreators":5,"category":"conference","sources":["https://dblp.org/rec/conf/eccv/WuTLLP24","https://doi.org/10.1007/978-3-031-73209-6_21"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2024,"sourceUrl":"https://dblp.org/rec/conf/eccv/WuTLLP24","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iccv/LiuSXGCP25","url":"https://dblp.org/rec/conf/iccv/LiuSXGCP25","title":"MotionShot: Adaptive Motion Transfer Across Arbitrary Objects for Text-to-Video Generation.","year":2025,"types":["Inproceedings"],"venue":"ICCV","doi":"https://doi.org/10.1109/ICCV51701.2025.01103","eventYear":2025,"numberOfCreators":6,"category":"conference","sources":["https://dblp.org/rec/conf/iccv/LiuSXGCP25","https://doi.org/10.1109/ICCV51701.2025.01103"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/LiuSXGCP25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iccv/NingTSLHPJ25","url":"https://dblp.org/rec/conf/iccv/NingTSLHPJ25","title":"Enhancing Spatial Reasoning in Multimodal Large Language Models Through Reasoning-Based Segmentation.","year":2025,"types":["Inproceedings"],"venue":"ICCV","doi":"https://doi.org/10.1109/ICCV51701.2025.00736","eventYear":2025,"numberOfCreators":7,"category":"conference","sources":["https://dblp.org/rec/conf/iccv/NingTSLHPJ25","https://doi.org/10.1109/ICCV51701.2025.00736"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/NingTSLHPJ25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iccv/PeiTLTY25","url":"https://dblp.org/rec/conf/iccv/PeiTLTY25","title":"D2 ST-Adapter: Disentangled-and-Deformable Spatio-Temporal Adapter for Few-Shot Action Recognition.","year":2025,"types":["Inproceedings"],"venue":"ICCV","doi":"https://doi.org/10.1109/ICCV51701.2025.01053","eventYear":2025,"numberOfCreators":5,"category":"conference","sources":["https://dblp.org/rec/conf/iccv/PeiTLTY25","https://doi.org/10.1109/ICCV51701.2025.01053"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/PeiTLTY25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/nips/WangCYLP25","url":"https://dblp.org/rec/conf/nips/WangCYLP25","title":"EditInfinity: Image Editing with Binary-Quantized Generative Models.","year":2025,"types":["Inproceedings"],"venue":"NeurIPS","doi":null,"eventYear":2025,"numberOfCreators":5,"category":"conference","sources":["https://dblp.org/rec/conf/nips/WangCYLP25"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/nips/WangCYLP25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/prcv/ChenPLL24","url":"https://dblp.org/rec/conf/prcv/ChenPLL24","title":"Frequency Adapter and Spatial Prompt Network for All-in-One Blind Image Restoration.","year":2025,"types":["Inproceedings"],"venue":"PRCV (8)","doi":"https://doi.org/10.1007/978-981-97-8685-5_12","eventYear":2024,"numberOfCreators":4,"category":"conference","sources":["https://dblp.org/rec/conf/prcv/ChenPLL24","https://doi.org/10.1007/978-981-97-8685-5_12"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2024,"sourceUrl":"https://dblp.org/rec/conf/prcv/ChenPLL24","documentUrl":null,"type":"Inproceedings"},{"key":"journals/tnn/XuPWPLX25","url":"https://dblp.org/rec/journals/tnn/XuPWPLX25","title":"CORE: CORrelation-Guided Feature Enhancement for Few-Shot Image Classification.","year":2025,"types":["Article"],"venue":"IEEE Trans. Neural Networks Learn. Syst.","doi":"https://doi.org/10.1109/TNNLS.2024.3355774","numberOfCreators":6,"category":"journal","sources":["https://dblp.org/rec/journals/tnn/XuPWPLX25","https://doi.org/10.1109/TNNLS.2024.3355774"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/tnn/XuPWPLX25","documentUrl":null,"type":"Article"},{"key":"journals/tnn/ZhouMPWWH25","url":"https://dblp.org/rec/journals/tnn/ZhouMPWWH25","title":"Reliability-Guided Hierarchical Memory Network for Scribble-Supervised Video Object Segmentation.","year":2025,"types":["Article"],"venue":"IEEE Trans. Neural Networks Learn. Syst.","doi":"https://doi.org/10.1109/TNNLS.2024.3389008","numberOfCreators":6,"category":"journal","sources":["https://dblp.org/rec/journals/tnn/ZhouMPWWH25","https://doi.org/10.1109/TNNLS.2024.3389008"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/tnn/ZhouMPWWH25","documentUrl":null,"type":"Article"}],"preprints":[{"key":"journals/corr/abs-2503-08387","url":"https://dblp.org/rec/journals/corr/abs-2503-08387","title":"Recognition-Synergistic Scene Text Editing.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2503.08387","numberOfCreators":7,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2503-08387","https://doi.org/10.48550/ARXIV.2503.08387"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-08387","documentUrl":null,"type":"Informal","arxivId":"2503.08387","arxivUrl":"https://arxiv.org/abs/2503.08387"},{"key":"journals/corr/abs-2503-14824","url":"https://dblp.org/rec/journals/corr/abs-2503-14824","title":"Prototype Perturbation for Relaxing Alignment Constraints in Backward-Compatible Learning.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2503.14824","numberOfCreators":5,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2503-14824","https://doi.org/10.48550/ARXIV.2503.14824"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-14824","documentUrl":null,"type":"Informal","arxivId":"2503.14824","arxivUrl":"https://arxiv.org/abs/2503.14824"},{"key":"journals/corr/abs-2504-11879","url":"https://dblp.org/rec/journals/corr/abs-2504-11879","title":"Learning Compatible Multi-Prize Subnetworks for Asymmetric Retrieval.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2504.11879","numberOfCreators":7,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2504-11879","https://doi.org/10.48550/ARXIV.2504.11879"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2504-11879","documentUrl":null,"type":"Informal","arxivId":"2504.11879","arxivUrl":"https://arxiv.org/abs/2504.11879"},{"key":"journals/corr/abs-2506-07358","url":"https://dblp.org/rec/journals/corr/abs-2506-07358","title":"Lightweight Joint Audio-Visual Deepfake Detection via Single-Stream Multi-Modal Learning Framework.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2506.07358","numberOfCreators":5,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2506-07358","https://doi.org/10.48550/ARXIV.2506.07358"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-07358","documentUrl":null,"type":"Informal","arxivId":"2506.07358","arxivUrl":"https://arxiv.org/abs/2506.07358"},{"key":"journals/corr/abs-2506-23120","url":"https://dblp.org/rec/journals/corr/abs-2506-23120","title":"Enhancing Spatial Reasoning in Multimodal Large Language Models through Reasoning-based Segmentation.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2506.23120","numberOfCreators":7,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2506-23120","https://doi.org/10.48550/ARXIV.2506.23120"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-23120","documentUrl":null,"type":"Informal","arxivId":"2506.23120","arxivUrl":"https://arxiv.org/abs/2506.23120"},{"key":"journals/corr/abs-2507-16310","url":"https://dblp.org/rec/journals/corr/abs-2507-16310","title":"MotionShot: Adaptive Motion Transfer across Arbitrary Objects for Text-to-Video Generation.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2507.16310","numberOfCreators":6,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2507-16310","https://doi.org/10.48550/ARXIV.2507.16310"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2507-16310","documentUrl":null,"type":"Informal","arxivId":"2507.16310","arxivUrl":"https://arxiv.org/abs/2507.16310"},{"key":"journals/corr/abs-2510-20217","url":"https://dblp.org/rec/journals/corr/abs-2510-20217","title":"EditInfinity: Image Editing with Binary-Quantized Generative Models.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2510.20217","numberOfCreators":5,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2510-20217","https://doi.org/10.48550/ARXIV.2510.20217"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-20217","documentUrl":null,"type":"Informal","arxivId":"2510.20217","arxivUrl":"https://arxiv.org/abs/2510.20217"}],"excludedFormal":[],"otherRecords":[],"matchedName":"Wenjie Pei","databaseLabel":"Wenjie Pei","databaseMetadata":{"type":["https://dblp.org/rdf/schema#Creator","https://dblp.org/rdf/schema#Person"],"label":["Wenjie Pei"],"orcid":["https://orcid.org/0000-0001-8117-2696"]},"rawFormalRecordCount2025":12,"signatureAudit":{"completedAt":"2026-10-19","frozen":true,"scope":"对 B 组 39 个数值档案的全部 1074 条原始 2025 正式记录扫描 DBLP author-signature ORCID 和机构；复用既有 59 条 Crossref 核验，补查 6 条新触发记录。重点核查不同 ORCID，以及只有预期机构之外机构的条目。本轮不扩展为所有作者逐篇全文审计。","formalRecordCoverage":12,"orcidCounts":{"https://orcid.org/0000-0001-8117-2696":3},"institutionCounts":{"Harbin Institute of Technology (HIT)":11,"Peng Cheng Laboratory":4},"caveat":"机构名称可能由 DBLP 自动映射而失真；多 ORCID 也不自动等于异人。只有有原始资料支撑的错归才作确认排除，未解决分支则暂停总数。"},"labName":null,"labUrl":null,"labEvidence":"本人主页提到的 Pattern Recognition and Computer Vision Lab、Tencent Youtu X-Lab 等是既往学习或工作经历，未核实当前实验室名。","labSourceUrl":"https://wenjiepei.github.io/","sourceWarning":false,"excludedOther":[],"excludedHomonyms":[],"unassignedCandidates":[],"knownPreprintMinimum2025":null,"excludedMisattributed":[],"displayNotes":"身份已与原名单机构及公开资料核对确认。2025 年正式记录 12 条（会议 10、期刊 2），所有作者位置均计入；预印本 7 条单列，不加总。","labDisplayNotes":"个人主页提到的 Pattern Recognition and Computer Vision Lab、Tencent Youtu X-Lab 是既往经历；当前实验室名称未能核实。"},{"index":73,"name":"Evan Yifan Peng","nameZh":"彭祎帆","role":"Assistant Professor","affiliation":"The University of Hong Kong","affiliationZh":"香港大学","source":"DBLP RDF via official SPARQL; primary-source identity checks","sourceUrl":"https://sparql.dblp.org/","profileUrl":"https://dblp.org/pid/123/7941.html","identifier":"123/7941","retrievedAt":"2026-10-19","count2025":11,"conference2025":6,"journal2025":5,"preprint2025":4,"status":"confirmed","notes":"名单英文 Evan Yifan Peng，对应 DBLP Yifan Peng 0001；以香港大学机构及 evanpeng 官方个人主页消歧。","identityEvidence":[{"url":"https://dblp.org/pid/123/7941.html","evidence":"DBLP RDF 类型为 Person，消歧后名字为 Yifan Peng 0001。机构元数据含：University of British Columbia (UBC), Imager Lab, Vancouver, BC, Canada；Stanford University, Stanford, CA, USA；University of Hong Kong, Computational Imaging & Mixed Representation Laboratory, Pokfulam, Hong Kong；King Abdullah University of Science and Technology (KAUST), Visual Computing Center, Thuwal, Saudi Arabia"},{"url":"https://www.eee.hku.hk/~evanpeng/","evidence":"DBLP Yifan Peng 0001 的个人主页 URL 为香港大学 evanpeng，机构为 HKU Computational Imaging & Mixed Representation Laboratory；对应名单的 Evan Yifan Peng。"}],"papers":[{"key":"conf/cvpr/LiuO0AH025","url":"https://dblp.org/rec/conf/cvpr/LiuO0AH025","title":"Learned Binocular-Encoding Optics for RGBD Imaging Using Joint Stereo and Focus Cues.","year":2025,"types":["Inproceedings"],"venue":"CVPR","doi":"https://doi.org/10.1109/CVPR52734.2025.01476","eventYear":2025,"numberOfCreators":6,"category":"conference","sources":["https://dblp.org/rec/conf/cvpr/LiuO0AH025","https://doi.org/10.1109/CVPR52734.2025.01476"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/LiuO0AH025","documentUrl":null,"type":"Inproceedings"},{"key":"conf/cvpr/Wu0H025","url":"https://dblp.org/rec/conf/cvpr/Wu0H025","title":"Glossy Object Reconstruction with Cost-effective Polarized Acquisition.","year":2025,"types":["Inproceedings"],"venue":"CVPR","doi":"https://doi.org/10.1109/CVPR52734.2025.00048","eventYear":2025,"numberOfCreators":4,"category":"conference","sources":["https://dblp.org/rec/conf/cvpr/Wu0H025","https://doi.org/10.1109/CVPR52734.2025.00048"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/Wu0H025","documentUrl":null,"type":"Inproceedings"},{"key":"conf/ismar/LiBZSXP25","url":"https://dblp.org/rec/conf/ismar/LiBZSXP25","title":"Enhanced Velocity Field Modeling for Gaussian Video Reconstruction.","year":2025,"types":["Inproceedings"],"venue":"ISMAR","doi":"https://doi.org/10.1109/ISMAR67309.2025.00042","eventYear":2025,"numberOfCreators":6,"category":"conference","sources":["https://dblp.org/rec/conf/ismar/LiBZSXP25","https://doi.org/10.1109/ISMAR67309.2025.00042"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/ismar/LiBZSXP25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/siggrapha/ShenQLH025","url":"https://dblp.org/rec/conf/siggrapha/ShenQLH025","title":"S3 Imagery: Specular Shading from Scratch-Anisotropy.","year":2025,"types":["Inproceedings"],"venue":"SIGGRAPH Asia","doi":"https://doi.org/10.1145/3757377.3763928","eventYear":2025,"numberOfCreators":5,"category":"conference","sources":["https://dblp.org/rec/conf/siggrapha/ShenQLH025","https://doi.org/10.1145/3757377.3763928"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/siggrapha/ShenQLH025","documentUrl":null,"type":"Inproceedings"},{"key":"conf/siggrapha/ShengHZH0LZZ0W025","url":"https://dblp.org/rec/conf/siggrapha/ShengHZH0LZZ0W025","title":"NeLiF: Neural Lighting Function Generation for Real-Time Indoor Rendering.","year":2025,"types":["Inproceedings"],"venue":"SIGGRAPH Asia","doi":"https://doi.org/10.1145/3757377.3763958","eventYear":2025,"numberOfCreators":12,"category":"conference","sources":["https://dblp.org/rec/conf/siggrapha/ShengHZH0LZZ0W025","https://doi.org/10.1145/3757377.3763958"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/siggrapha/ShengHZH0LZZ0W025","documentUrl":null,"type":"Inproceedings"},{"key":"conf/siggrapha/ZhouML025","url":"https://dblp.org/rec/conf/siggrapha/ZhouML025","title":"Empowering Head-up AR: Leveraging Holographic Display Engine, Geometry Optical Combiner, and Learned Calibration.","year":2025,"types":["Inproceedings"],"venue":"SIGGRAPH Asia Emerging Technologies","doi":"https://doi.org/10.1145/3757373.3763776","eventYear":2025,"numberOfCreators":4,"category":"conference","sources":["https://dblp.org/rec/conf/siggrapha/ZhouML025","https://doi.org/10.1145/3757373.3763776"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/siggrapha/ZhouML025","documentUrl":null,"type":"Inproceedings"},{"key":"journals/tog/DaiZDXPDSYLLX25","url":"https://dblp.org/rec/journals/tog/DaiZDXPDSYLLX25","title":"4D Gaussian Videos with Motion Layering.","year":2025,"types":["Article"],"venue":"ACM Trans. Graph.","doi":"https://doi.org/10.1145/3731189","numberOfCreators":11,"category":"journal","sources":["https://dblp.org/rec/journals/tog/DaiZDXPDSYLLX25","https://doi.org/10.1145/3731189"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/tog/DaiZDXPDSYLLX25","documentUrl":null,"type":"Article"},{"key":"journals/tog/LiuHPW25","url":"https://dblp.org/rec/journals/tog/LiuHPW25","title":"A Fully-statistical Wave Scattering Model for Heterogeneous Surfaces.","year":2025,"types":["Article"],"venue":"ACM Trans. Graph.","doi":"https://doi.org/10.1145/3730828","numberOfCreators":4,"category":"journal","sources":["https://dblp.org/rec/journals/tog/LiuHPW25","https://doi.org/10.1145/3730828"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/tog/LiuHPW25","documentUrl":null,"type":"Article"},{"key":"journals/tog/WuYZYPPWH25","url":"https://dblp.org/rec/journals/tog/WuYZYPPWH25","title":"MoFlow: Motion-Guided Flows for Recurrent Rendered Frame Prediction.","year":2025,"types":["Article"],"venue":"ACM Trans. Graph.","doi":"https://doi.org/10.1145/3730400","numberOfCreators":8,"category":"journal","sources":["https://dblp.org/rec/journals/tog/WuYZYPPWH25","https://doi.org/10.1145/3730400"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/tog/WuYZYPPWH25","documentUrl":null,"type":"Article"},{"key":"journals/tvcg/DaiTYPZQ25","url":"https://dblp.org/rec/journals/tvcg/DaiTYPZQ25","title":"GO-NeRF: Generating Objects in Neural Radiance Fields for Virtual Reality Content Creation.","year":2025,"types":["Article"],"venue":"IEEE Trans. Vis. Comput. Graph.","doi":"https://doi.org/10.1109/TVCG.2025.3549558","numberOfCreators":6,"category":"journal","sources":["https://dblp.org/rec/journals/tvcg/DaiTYPZQ25","https://doi.org/10.1109/TVCG.2025.3549558"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/tvcg/DaiTYPZQ25","documentUrl":null,"type":"Article"},{"key":"journals/tvcg/XiaMTMZY025","url":"https://dblp.org/rec/journals/tvcg/XiaMTMZY025","title":"Multi-illumination-interfered Neural Holography with Expanded Eyebox.","year":2025,"types":["Article"],"venue":"IEEE Trans. Vis. Comput. Graph.","doi":"https://doi.org/10.1109/TVCG.2025.3616793","numberOfCreators":7,"category":"journal","sources":["https://dblp.org/rec/journals/tvcg/XiaMTMZY025","https://doi.org/10.1109/TVCG.2025.3616793"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/tvcg/XiaMTMZY025","documentUrl":null,"type":"Article"}],"preprints":[{"key":"journals/corr/abs-2504-07025","url":"https://dblp.org/rec/journals/corr/abs-2504-07025","title":"Glossy Object Reconstruction with Cost-effective Polarized Acquisition.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2504.07025","numberOfCreators":4,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2504-07025","https://doi.org/10.48550/ARXIV.2504.07025"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2504-07025","documentUrl":null,"type":"Informal","arxivId":"2504.07025","arxivUrl":"https://arxiv.org/abs/2504.07025"},{"key":"journals/corr/abs-2507-22523","url":"https://dblp.org/rec/journals/corr/abs-2507-22523","title":"Learned Off-aperture Encoding for Wide Field-of-view RGBD Imaging.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2507.22523","numberOfCreators":7,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2507-22523","https://doi.org/10.48550/ARXIV.2507.22523"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2507-22523","documentUrl":null,"type":"Informal","arxivId":"2507.22523","arxivUrl":"https://arxiv.org/abs/2507.22523"},{"key":"journals/corr/abs-2507-23704","url":"https://dblp.org/rec/journals/corr/abs-2507-23704","title":"Enhanced Velocity Field Modeling for Gaussian Video Reconstruction.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2507.23704","numberOfCreators":6,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2507-23704","https://doi.org/10.48550/ARXIV.2507.23704"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2507-23704","documentUrl":null,"type":"Informal","arxivId":"2507.23704","arxivUrl":"https://arxiv.org/abs/2507.23704"},{"key":"journals/corr/abs-2508-18071","url":"https://dblp.org/rec/journals/corr/abs-2508-18071","title":"EventTracer: Fast Path Tracing-based Event Stream Rendering.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2508.18071","numberOfCreators":6,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2508-18071","https://doi.org/10.48550/ARXIV.2508.18071"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-18071","documentUrl":null,"type":"Informal","arxivId":"2508.18071","arxivUrl":"https://arxiv.org/abs/2508.18071"}],"excludedFormal":[],"otherRecords":[],"matchedName":"Yifan Peng","databaseLabel":"Yifan Peng 0001","databaseMetadata":{"type":["https://dblp.org/rdf/schema#Person","https://dblp.org/rdf/schema#Creator"],"label":["Yifan Peng 0001"],"affiliation":["University of British Columbia (UBC), Imager Lab, Vancouver, BC, Canada","Stanford University, Stanford, CA, USA","University of Hong Kong, Computational Imaging & Mixed Representation Laboratory, Pokfulam, Hong Kong","King Abdullah University of Science and Technology (KAUST), Visual Computing Center, Thuwal, Saudi Arabia"],"homepage":["https://www.eee.hku.hk/~evanpeng/"],"orcid":["https://orcid.org/0000-0003-0667-2599"],"primaryAffiliation":["University of Hong Kong, Computational Imaging & Mixed Representation Laboratory, Pokfulam, Hong Kong"],"primaryHomepage":["https://www.eee.hku.hk/~evanpeng/"]},"rawFormalRecordCount2025":11,"signatureAudit":{"completedAt":"2026-10-19","frozen":true,"scope":"对 B 组 39 个数值档案的全部 1074 条原始 2025 正式记录扫描 DBLP author-signature ORCID 和机构；复用既有 59 条 Crossref 核验，补查 6 条新触发记录。重点核查不同 ORCID，以及只有预期机构之外机构的条目。本轮不扩展为所有作者逐篇全文审计。","formalRecordCoverage":11,"orcidCounts":{"https://orcid.org/0000-0003-0667-2599":7},"institutionCounts":{"University of Hong Kong (HKU)":11},"caveat":"机构名称可能由 DBLP 自动映射而失真；多 ORCID 也不自动等于异人。只有有原始资料支撑的错归才作确认排除，未解决分支则暂停总数。"},"labName":"Computational Imaging & Mixed Representation Laboratory (WeLight@HKU)","labUrl":"https://hku.welight.fun/","labEvidence":"香港大学本人主页明确写 leading the Computational Imaging & Mixed Representation Laboratory, aka., WeLight@HKU；当前页面导航直接链接 hku.welight.fun。","labSourceUrl":"https://web.ece.hku.hk/~evanpeng/","sourceWarning":false,"excludedOther":[],"excludedHomonyms":[],"unassignedCandidates":[],"knownPreprintMinimum2025":null,"excludedMisattributed":[],"displayNotes":"原名单英文名为 Evan Yifan Peng，对应 DBLP 的 Yifan Peng 0001，已通过港大机构信息与本人官方主页消歧。计入 11 条（会议 6、期刊 5）；预印本 4 条单列，不加总。","labDisplayNotes":"港大本人主页写明其领导 Computational Imaging & Mixed Representation Laboratory（WeLight@HKU），并链接组站，据此归组。"},{"index":74,"name":"Sida Peng","nameZh":"彭思达","role":"ZJU100 Young Professor","affiliation":"Zhejiang University","affiliationZh":"浙江大学","source":"DBLP RDF via official SPARQL; primary-source identity checks","sourceUrl":"https://sparql.dblp.org/","profileUrl":"https://dblp.org/pid/232/3246.html","identifier":"232/3246","retrievedAt":"2026-10-19","count2025":33,"conference2025":30,"journal2025":3,"preprint2025":21,"status":"confirmed","notes":"","identityEvidence":[{"url":"https://dblp.org/pid/232/3246.html","evidence":"DBLP RDF 类型为 Person，消歧后名字为 Sida Peng。此档案未提供可用机构元数据，以下以本人/机构/出版商来源补证。"},{"url":"https://pengsida.net/","evidence":"个人主页为浙江大学 Sida Peng，个人论文列表与 DBLP 记录匹配。"},{"url":"https://pengsida.net/","evidence":"此本人或机构页面的正文与所选档案中 15 条 2025 记录标题匹配，其中 11 条为当前计入的正式记录（忽略空格、标点、大小写）。","matchedPaperKeys":["conf/cvpr/GuoZPLYXWZB25","conf/cvpr/LinPCPSLBFZK25","conf/cvpr/WangYXSZCBPZ25","conf/cvpr/Yan0LJGWZLB0P25","conf/cvpr/ZhouFPYZCXZ25","conf/eccv/ChenPYLPLZ24","conf/eccv/XuSWCYPSW24","conf/iccv/SunYWXLWZBZP25","conf/iccv/TanHPGZSHSBZ25","journals/corr/abs-2501-07556","journals/corr/abs-2503-14483","journals/corr/abs-2507-11540","journals/corr/abs-2512-22745","journals/pami/GaoYKPLT25","journals/tog/HuYLWDDZJBZP25"],"matchedFormalPaperKeys":["conf/cvpr/GuoZPLYXWZB25","conf/cvpr/LinPCPSLBFZK25","conf/cvpr/WangYXSZCBPZ25","conf/cvpr/Yan0LJGWZLB0P25","conf/cvpr/ZhouFPYZCXZ25","conf/eccv/ChenPYLPLZ24","conf/eccv/XuSWCYPSW24","conf/iccv/SunYWXLWZBZP25","conf/iccv/TanHPGZSHSBZ25","journals/pami/GaoYKPLT25","journals/tog/HuYLWDDZJBZP25"]}],"papers":[{"key":"conf/cvm/SuPKHH25","url":"https://dblp.org/rec/conf/cvm/SuPKHH25","title":"MTScan: Material Transfer from Partial Scans to CAD Models.","year":2025,"types":["Inproceedings"],"venue":"CVM (2)","doi":"https://doi.org/10.1007/978-981-96-5812-1_8","eventYear":2025,"numberOfCreators":5,"category":"conference","sources":["https://dblp.org/rec/conf/cvm/SuPKHH25","https://doi.org/10.1007/978-981-96-5812-1_8"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/cvm/SuPKHH25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/cvpr/GuoZPLYXWZB25","url":"https://dblp.org/rec/conf/cvpr/GuoZPLYXWZB25","title":"Multi-view Reconstruction via SfM-guided Monocular Depth Estimation.","year":2025,"types":["Inproceedings"],"venue":"CVPR","doi":"https://doi.org/10.1109/CVPR52734.2025.00497","eventYear":2025,"numberOfCreators":9,"category":"conference","sources":["https://dblp.org/rec/conf/cvpr/GuoZPLYXWZB25","https://doi.org/10.1109/CVPR52734.2025.00497"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/GuoZPLYXWZB25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/cvpr/LinPCPSLBFZK25","url":"https://dblp.org/rec/conf/cvpr/LinPCPSLBFZK25","title":"Prompting Depth Anything for 4K Resolution Accurate Metric Depth Estimation.","year":2025,"types":["Inproceedings"],"venue":"CVPR","doi":"https://doi.org/10.1109/CVPR52734.2025.01591","eventYear":2025,"numberOfCreators":10,"category":"conference","sources":["https://dblp.org/rec/conf/cvpr/LinPCPSLBFZK25","https://doi.org/10.1109/CVPR52734.2025.01591"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/LinPCPSLBFZK25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/cvpr/WangYXSZCBPZ25","url":"https://dblp.org/rec/conf/cvpr/WangYXSZCBPZ25","title":"FreeTimeGS: Free Gaussian Primitives at Anytime Anywhere for Dynamic Scene Reconstruction.","year":2025,"types":["Inproceedings"],"venue":"CVPR","doi":"https://doi.org/10.1109/CVPR52734.2025.02026","eventYear":2025,"numberOfCreators":9,"category":"conference","sources":["https://dblp.org/rec/conf/cvpr/WangYXSZCBPZ25","https://doi.org/10.1109/CVPR52734.2025.02026"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/WangYXSZCBPZ25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/cvpr/XieCXXJSPBZ25","url":"https://dblp.org/rec/conf/cvpr/XieCXXJSPBZ25","title":"EnvGS: Modeling View-Dependent Appearance with Environment Gaussian.","year":2025,"types":["Inproceedings"],"venue":"CVPR","doi":"https://doi.org/10.1109/CVPR52734.2025.00539","eventYear":2025,"numberOfCreators":9,"category":"conference","sources":["https://dblp.org/rec/conf/cvpr/XieCXXJSPBZ25","https://doi.org/10.1109/CVPR52734.2025.00539"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/XieCXXJSPBZ25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/cvpr/Yan0LJGWZLB0P25","url":"https://dblp.org/rec/conf/cvpr/Yan0LJGWZLB0P25","title":"StreetCrafter: Street View Synthesis with Controllable Video Diffusion Models.","year":2025,"types":["Inproceedings"],"venue":"CVPR","doi":"https://doi.org/10.1109/CVPR52734.2025.00085","eventYear":2025,"numberOfCreators":11,"category":"conference","sources":["https://dblp.org/rec/conf/cvpr/Yan0LJGWZLB0P25","https://doi.org/10.1109/CVPR52734.2025.00085"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/Yan0LJGWZLB0P25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/cvpr/ZhouFPYZCXZ25","url":"https://dblp.org/rec/conf/cvpr/ZhouFPYZCXZ25","title":"LiDAR-RT: Gaussian-based Ray Tracing for Dynamic LiDAR Re-simulation.","year":2025,"types":["Inproceedings"],"venue":"CVPR","doi":"https://doi.org/10.1109/CVPR52734.2025.00151","eventYear":2025,"numberOfCreators":8,"category":"conference","sources":["https://dblp.org/rec/conf/cvpr/ZhouFPYZCXZ25","https://doi.org/10.1109/CVPR52734.2025.00151"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/ZhouFPYZCXZ25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/eccv/ChenPYLPLZ24","url":"https://dblp.org/rec/conf/eccv/ChenPYLPLZ24","title":"IntrinsicAnything: Learning Diffusion Priors for Inverse Rendering Under Unknown Illumination.","year":2025,"types":["Inproceedings"],"venue":"ECCV (60)","doi":"https://doi.org/10.1007/978-3-031-73027-6_26","eventYear":2024,"numberOfCreators":7,"category":"conference","sources":["https://dblp.org/rec/conf/eccv/ChenPYLPLZ24","https://doi.org/10.1007/978-3-031-73027-6_26"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2024,"sourceUrl":"https://dblp.org/rec/conf/eccv/ChenPYLPLZ24","documentUrl":null,"type":"Inproceedings"},{"key":"conf/eccv/DongFHXWPD24","url":"https://dblp.org/rec/conf/eccv/DongFHXWPD24","title":"TELA: Text to Layer-Wise 3D Clothed Human Generation.","year":2025,"types":["Inproceedings"],"venue":"ECCV (25)","doi":"https://doi.org/10.1007/978-3-031-72698-9_2","eventYear":2024,"numberOfCreators":7,"category":"conference","sources":["https://dblp.org/rec/conf/eccv/DongFHXWPD24","https://doi.org/10.1007/978-3-031-72698-9_2"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2024,"sourceUrl":"https://dblp.org/rec/conf/eccv/DongFHXWPD24","documentUrl":null,"type":"Inproceedings"},{"key":"conf/eccv/GuoZPWSHZ24","url":"https://dblp.org/rec/conf/eccv/GuoZPWSHZ24","title":"SAM-Guided Graph Cut for 3D Instance Segmentation.","year":2025,"types":["Inproceedings"],"venue":"ECCV (48)","doi":"https://doi.org/10.1007/978-3-031-73195-2_14","eventYear":2024,"numberOfCreators":7,"category":"conference","sources":["https://dblp.org/rec/conf/eccv/GuoZPWSHZ24","https://doi.org/10.1007/978-3-031-73195-2_14"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2024,"sourceUrl":"https://dblp.org/rec/conf/eccv/GuoZPWSHZ24","documentUrl":null,"type":"Inproceedings"},{"key":"conf/eccv/HeCPHLHYOH24","url":"https://dblp.org/rec/conf/eccv/HeCPHLHYOH24","title":"GVGEN: Text-to-3D Generation with Volumetric Representation.","year":2025,"types":["Inproceedings"],"venue":"ECCV (8)","doi":"https://doi.org/10.1007/978-3-031-73242-3_26","eventYear":2024,"numberOfCreators":9,"category":"conference","sources":["https://dblp.org/rec/conf/eccv/HeCPHLHYOH24","https://doi.org/10.1007/978-3-031-73242-3_26"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2024,"sourceUrl":"https://dblp.org/rec/conf/eccv/HeCPHLHYOH24","documentUrl":null,"type":"Inproceedings"},{"key":"conf/eccv/HuZLLPZFY24","url":"https://dblp.org/rec/conf/eccv/HuZLLPZFY24","title":"CPT-VR: Improving Surface Rendering via Closest Point Transform with View-Reflection Appearance.","year":2025,"types":["Inproceedings"],"venue":"ECCV (73)","doi":"https://doi.org/10.1007/978-3-031-73464-9_14","eventYear":2024,"numberOfCreators":8,"category":"conference","sources":["https://dblp.org/rec/conf/eccv/HuZLLPZFY24","https://doi.org/10.1007/978-3-031-73464-9_14"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2024,"sourceUrl":"https://dblp.org/rec/conf/eccv/HuZLLPZFY24","documentUrl":null,"type":"Inproceedings"},{"key":"conf/eccv/LiuLLYPCQHLO24","url":"https://dblp.org/rec/conf/eccv/LiuLLYPCQHLO24","title":"UniDream: Unifying Diffusion Priors for Relightable Text-to-3D Generation.","year":2025,"types":["Inproceedings"],"venue":"ECCV (5)","doi":"https://doi.org/10.1007/978-3-031-72652-1_5","eventYear":2024,"numberOfCreators":10,"category":"conference","sources":["https://dblp.org/rec/conf/eccv/LiuLLYPCQHLO24","https://doi.org/10.1007/978-3-031-72652-1_5"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2024,"sourceUrl":"https://dblp.org/rec/conf/eccv/LiuLLYPCQHLO24","documentUrl":null,"type":"Inproceedings"},{"key":"conf/eccv/XuSWCYPSW24","url":"https://dblp.org/rec/conf/eccv/XuSWCYPSW24","title":"GRM: Large Gaussian Reconstruction Model for Efficient 3D Reconstruction and Generation.","year":2025,"types":["Inproceedings"],"venue":"ECCV (15)","doi":"https://doi.org/10.1007/978-3-031-72633-0_1","eventYear":2024,"numberOfCreators":8,"category":"conference","sources":["https://dblp.org/rec/conf/eccv/XuSWCYPSW24","https://doi.org/10.1007/978-3-031-72633-0_1"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2024,"sourceUrl":"https://dblp.org/rec/conf/eccv/XuSWCYPSW24","documentUrl":null,"type":"Inproceedings"},{"key":"conf/eccv/YanLZWSZLZP24","url":"https://dblp.org/rec/conf/eccv/YanLZWSZLZP24","title":"Street Gaussians: Modeling Dynamic Urban Scenes with Gaussian Splatting.","year":2025,"types":["Inproceedings"],"venue":"ECCV (73)","doi":"https://doi.org/10.1007/978-3-031-73464-9_10","eventYear":2024,"numberOfCreators":9,"category":"conference","sources":["https://dblp.org/rec/conf/eccv/YanLZWSZLZP24","https://doi.org/10.1007/978-3-031-73464-9_10"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2024,"sourceUrl":"https://dblp.org/rec/conf/eccv/YanLZWSZLZP24","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iccv/CaoWFBZP25","url":"https://dblp.org/rec/conf/iccv/CaoWFBZP25","title":"UniVerse: Unleashing the Scene Prior of Video Diffusion Models for Robust Radiance Field Reconstruction.","year":2025,"types":["Inproceedings"],"venue":"ICCV","doi":"https://doi.org/10.1109/ICCV51701.2025.02509","eventYear":2025,"numberOfCreators":6,"category":"conference","sources":["https://dblp.org/rec/conf/iccv/CaoWFBZP25","https://doi.org/10.1109/ICCV51701.2025.02509"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/CaoWFBZP25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iccv/ChenWTMHOZBP25","url":"https://dblp.org/rec/conf/iccv/ChenWTMHOZBP25","title":"EgoAgent: A Joint Predictive Agent Model in Egocentric Worlds.","year":2025,"types":["Inproceedings"],"venue":"ICCV","doi":"https://doi.org/10.1109/ICCV51701.2025.00655","eventYear":2025,"numberOfCreators":9,"category":"conference","sources":["https://dblp.org/rec/conf/iccv/ChenWTMHOZBP25","https://doi.org/10.1109/ICCV51701.2025.00655"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/ChenWTMHOZBP25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iccv/GuoPSSHWDHKPZ25","url":"https://dblp.org/rec/conf/iccv/GuoPSSHWDHKPZ25","title":"Motion-2-To-3: Leveraging 2D Motion Data for 3D Motion Generations.","year":2025,"types":["Inproceedings"],"venue":"ICCV","doi":"https://doi.org/10.1109/ICCV51701.2025.01327","eventYear":2025,"numberOfCreators":11,"category":"conference","sources":["https://dblp.org/rec/conf/iccv/GuoPSSHWDHKPZ25","https://doi.org/10.1109/ICCV51701.2025.01327"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/GuoPSSHWDHKPZ25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iccv/HeXXZP25","url":"https://dblp.org/rec/conf/iccv/HeXXZP25","title":"ERNet: Efficient Non-Rigid Registration Network for Point Sequences.","year":2025,"types":["Inproceedings"],"venue":"ICCV","doi":"https://doi.org/10.1109/ICCV51701.2025.02521","eventYear":2025,"numberOfCreators":5,"category":"conference","sources":["https://dblp.org/rec/conf/iccv/HeXXZP25","https://doi.org/10.1109/ICCV51701.2025.02521"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/HeXXZP25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iccv/JinPWXXYSBZ25","url":"https://dblp.org/rec/conf/iccv/JinPWXXYSBZ25","title":"Diffuman4D: 4D Consistent Human View Synthesis From Sparse-View Videos With Spatio-Temporal Diffusion Models.","year":2025,"types":["Inproceedings"],"venue":"ICCV","doi":"https://doi.org/10.1109/ICCV51701.2025.01028","eventYear":2025,"numberOfCreators":9,"category":"conference","sources":["https://dblp.org/rec/conf/iccv/JinPWXXYSBZ25","https://doi.org/10.1109/ICCV51701.2025.01028"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/JinPWXXYSBZ25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iccv/SunYWXLWZBZP25","url":"https://dblp.org/rec/conf/iccv/SunYWXLWZBZP25","title":"Hierarchy UGP: Hierarchy Unified Gaussian Primitive for Large-Scale Dynamic Scene Reconstruction.","year":2025,"types":["Inproceedings"],"venue":"ICCV","doi":"https://doi.org/10.1109/ICCV51701.2025.02436","eventYear":2025,"numberOfCreators":10,"category":"conference","sources":["https://dblp.org/rec/conf/iccv/SunYWXLWZBZP25","https://doi.org/10.1109/ICCV51701.2025.02436"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/SunYWXLWZBZP25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iccv/TanHPGZSHSBZ25","url":"https://dblp.org/rec/conf/iccv/TanHPGZSHSBZ25","title":"ReTracker: Exploring Image Matching for Robust Online Any Point Tracking.","year":2025,"types":["Inproceedings"],"venue":"ICCV","doi":"https://doi.org/10.1109/ICCV51701.2025.00410","eventYear":2025,"numberOfCreators":10,"category":"conference","sources":["https://dblp.org/rec/conf/iccv/TanHPGZSHSBZ25","https://doi.org/10.1109/ICCV51701.2025.00410"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/TanHPGZSHSBZ25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iccv/WangWGPQBZH25","url":"https://dblp.org/rec/conf/iccv/WangWGPQBZH25","title":"Precise Action-to-Video Generation Through Visual Action Prompts.","year":2025,"types":["Inproceedings"],"venue":"ICCV","doi":"https://doi.org/10.1109/ICCV51701.2025.01181","eventYear":2025,"numberOfCreators":8,"category":"conference","sources":["https://dblp.org/rec/conf/iccv/WangWGPQBZH25","https://doi.org/10.1109/ICCV51701.2025.01181"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/WangWGPQBZH25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iccv/XiaoLPFPZFZPW25","url":"https://dblp.org/rec/conf/iccv/XiaoLPFPZFZPW25","title":"MotionStreamer: Streaming Motion Generation via Diffusion-Based Autoregressive Model in Causal Latent Space.","year":2025,"types":["Inproceedings"],"venue":"ICCV","doi":"https://doi.org/10.1109/ICCV51701.2025.00940","eventYear":2025,"numberOfCreators":10,"category":"conference","sources":["https://dblp.org/rec/conf/iccv/XiaoLPFPZFZPW25","https://doi.org/10.1109/ICCV51701.2025.00940"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/XiaoLPFPZFZPW25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iccv/YuHZYYHSZZP25","url":"https://dblp.org/rec/conf/iccv/YuHZYYHSZZP25","title":"BoxDreamer: Dreaming Box Corners for Generalizable Object Pose Estimation.","year":2025,"types":["Inproceedings"],"venue":"ICCV","doi":"https://doi.org/10.1109/ICCV51701.2025.00875","eventYear":2025,"numberOfCreators":10,"category":"conference","sources":["https://dblp.org/rec/conf/iccv/YuHZYYHSZZP25","https://doi.org/10.1109/ICCV51701.2025.00875"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/YuHZYYHSZZP25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iclr/CenPPSSB0H25","url":"https://dblp.org/rec/conf/iclr/CenPPSSB0H25","title":"Ready-to-React: Online Reaction Policy for Two-Character Interaction Generation.","year":2025,"types":["Inproceedings"],"venue":"ICLR","doi":null,"eventYear":2025,"numberOfCreators":8,"category":"conference","sources":["https://dblp.org/rec/conf/iclr/CenPPSSB0H25"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iclr/CenPPSSB0H25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iclr/FuLWPXSY0ZL25","url":"https://dblp.org/rec/conf/iclr/FuLWPXSY0ZL25","title":"3DTrajMaster: Mastering 3D Trajectory for Multi-Entity Motion in Video Generation.","year":2025,"types":["Inproceedings"],"venue":"ICLR","doi":null,"eventYear":2025,"numberOfCreators":10,"category":"conference","sources":["https://dblp.org/rec/conf/iclr/FuLWPXSY0ZL25"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iclr/FuLWPXSY0ZL25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iclr/WangZPHGSB025","url":"https://dblp.org/rec/conf/iclr/WangZPHGSB025","title":"UniRestore3D: A Scalable Framework For General Shape Restoration.","year":2025,"types":["Inproceedings"],"venue":"ICLR","doi":null,"eventYear":2025,"numberOfCreators":8,"category":"conference","sources":["https://dblp.org/rec/conf/iclr/WangZPHGSB025"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iclr/WangZPHGSB025","documentUrl":null,"type":"Inproceedings"},{"key":"conf/ijcai/TangWCWPXO25","url":"https://dblp.org/rec/conf/ijcai/TangWCWPXO25","title":"Human-Centric Foundation Models: Perception, Generation and Agentic Modeling.","year":2025,"types":["Inproceedings"],"venue":"IJCAI","doi":"https://doi.org/10.24963/IJCAI.2025/1185","eventYear":2025,"numberOfCreators":7,"category":"conference","sources":["https://dblp.org/rec/conf/ijcai/TangWCWPXO25","https://doi.org/10.24963/IJCAI.2025/1185"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/ijcai/TangWCWPXO25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/nips/XuLLWYZPCSWCYPY25","url":"https://dblp.org/rec/conf/nips/XuLLWYZPCSWCYPY25","title":"Pixel-Perfect Depth with Semantics-Prompted Diffusion Transformers.","year":2025,"types":["Inproceedings"],"venue":"NeurIPS","doi":null,"eventYear":2025,"numberOfCreators":14,"category":"conference","sources":["https://dblp.org/rec/conf/nips/XuLLWYZPCSWCYPY25"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/nips/XuLLWYZPCSWCYPY25","documentUrl":null,"type":"Inproceedings"},{"key":"journals/cg/ShenTuZXSCPZ25","url":"https://dblp.org/rec/journals/cg/ShenTuZXSCPZ25","title":"Dyn-E: Local appearance editing of dynamic neural radiance fields.","year":2025,"types":["Article"],"venue":"Comput. Graph.","doi":"https://doi.org/10.1016/J.CAG.2024.104140","numberOfCreators":7,"category":"journal","sources":["https://dblp.org/rec/journals/cg/ShenTuZXSCPZ25","https://doi.org/10.1016/J.CAG.2024.104140"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/cg/ShenTuZXSCPZ25","documentUrl":null,"type":"Article"},{"key":"journals/pami/GaoYKPLT25","url":"https://dblp.org/rec/journals/pami/GaoYKPLT25","title":"MPS-NeRF: Generalizable 3D Human Rendering From Multiview Images.","year":2025,"types":["Article"],"venue":"IEEE Trans. Pattern Anal. Mach. Intell.","doi":"https://doi.org/10.1109/TPAMI.2022.3205910","numberOfCreators":6,"category":"journal","sources":["https://dblp.org/rec/journals/pami/GaoYKPLT25","https://doi.org/10.1109/TPAMI.2022.3205910"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/pami/GaoYKPLT25","documentUrl":null,"type":"Article"},{"key":"journals/tog/HuYLWDDZJBZP25","url":"https://dblp.org/rec/journals/tog/HuYLWDDZJBZP25","title":"Split4D: Decomposed 4D Scene Reconstruction Without Video Segmentation.","year":2025,"types":["Article"],"venue":"ACM Trans. Graph.","doi":"https://doi.org/10.1145/3763343","numberOfCreators":11,"category":"journal","sources":["https://dblp.org/rec/journals/tog/HuYLWDDZJBZP25","https://doi.org/10.1145/3763343"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/tog/HuYLWDDZJBZP25","documentUrl":null,"type":"Article"}],"preprints":[{"key":"journals/corr/abs-2501-07556","url":"https://dblp.org/rec/journals/corr/abs-2501-07556","title":"MatchAnything: Universal Cross-Modality Image Matching with Large-Scale Pre-Training.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2501.07556","numberOfCreators":7,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2501-07556","https://doi.org/10.48550/ARXIV.2501.07556"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2501-07556","documentUrl":null,"type":"Informal","arxivId":"2501.07556","arxivUrl":"https://arxiv.org/abs/2501.07556"},{"key":"journals/corr/abs-2502-05857","url":"https://dblp.org/rec/journals/corr/abs-2502-05857","title":"Acquisition through My Eyes and Steps: A Joint Predictive Agent Model in Egocentric Worlds.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2502.05857","numberOfCreators":9,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2502-05857","https://doi.org/10.48550/ARXIV.2502.05857"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2502-05857","documentUrl":null,"type":"Informal","arxivId":"2502.05857","arxivUrl":"https://arxiv.org/abs/2502.05857"},{"key":"journals/corr/abs-2502-08556","url":"https://dblp.org/rec/journals/corr/abs-2502-08556","title":"Human-Centric Foundation Models: Perception, Generation and Agentic Modeling.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2502.08556","numberOfCreators":7,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2502-08556","https://doi.org/10.48550/ARXIV.2502.08556"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2502-08556","documentUrl":null,"type":"Informal","arxivId":"2502.08556","arxivUrl":"https://arxiv.org/abs/2502.08556"},{"key":"journals/corr/abs-2502-20370","url":"https://dblp.org/rec/journals/corr/abs-2502-20370","title":"Ready-to-React: Online Reaction Policy for Two-Character Interaction Generation.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2502.20370","numberOfCreators":8,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2502-20370","https://doi.org/10.48550/ARXIV.2502.20370"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2502-20370","documentUrl":null,"type":"Informal","arxivId":"2502.20370","arxivUrl":"https://arxiv.org/abs/2502.20370"},{"key":"journals/corr/abs-2503-03222","url":"https://dblp.org/rec/journals/corr/abs-2503-03222","title":"Mocap-2-to-3: Lifting 2D Diffusion-Based Pretrained Models for 3D Motion Capture.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2503.03222","numberOfCreators":7,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2503-03222","https://doi.org/10.48550/ARXIV.2503.03222"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-03222","documentUrl":null,"type":"Informal","arxivId":"2503.03222","arxivUrl":"https://arxiv.org/abs/2503.03222"},{"key":"journals/corr/abs-2503-14483","url":"https://dblp.org/rec/journals/corr/abs-2503-14483","title":"Multi-view Reconstruction via SfM-guided Monocular Depth Estimation.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2503.14483","numberOfCreators":9,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2503-14483","https://doi.org/10.48550/ARXIV.2503.14483"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-14483","documentUrl":null,"type":"Informal","arxivId":"2503.14483","arxivUrl":"https://arxiv.org/abs/2503.14483"},{"key":"journals/corr/abs-2503-15451","url":"https://dblp.org/rec/journals/corr/abs-2503-15451","title":"MotionStreamer: Streaming Motion Generation via Diffusion-based Autoregressive Model in Causal Latent Space.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2503.15451","numberOfCreators":10,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2503-15451","https://doi.org/10.48550/ARXIV.2503.15451"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-15451","documentUrl":null,"type":"Informal","arxivId":"2503.15451","arxivUrl":"https://arxiv.org/abs/2503.15451"},{"key":"journals/corr/abs-2504-00437","url":"https://dblp.org/rec/journals/corr/abs-2504-00437","title":"ADGaussian: Generalizable Gaussian Splatting for Autonomous Driving with Multi-modal Inputs.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2504.00437","numberOfCreators":5,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2504-00437","https://doi.org/10.48550/ARXIV.2504.00437"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2504-00437","documentUrl":null,"type":"Informal","arxivId":"2504.00437","arxivUrl":"https://arxiv.org/abs/2504.00437"},{"key":"journals/corr/abs-2504-07955","url":"https://dblp.org/rec/journals/corr/abs-2504-07955","title":"BoxDreamer: Dreaming Box Corners for Generalizable Object Pose Estimation.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2504.07955","numberOfCreators":10,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2504-07955","https://doi.org/10.48550/ARXIV.2504.07955"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2504-07955","documentUrl":null,"type":"Informal","arxivId":"2504.07955","arxivUrl":"https://arxiv.org/abs/2504.07955"},{"key":"journals/corr/abs-2504-11443","url":"https://dblp.org/rec/journals/corr/abs-2504-11443","title":"Early Impacts of M365 Copilot.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2504.11443","numberOfCreators":4,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2504-11443","https://doi.org/10.48550/ARXIV.2504.11443"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2504-11443","documentUrl":null,"type":"Informal","arxivId":"2504.11443","arxivUrl":"https://arxiv.org/abs/2504.11443"},{"key":"journals/corr/abs-2506-05348","url":"https://dblp.org/rec/journals/corr/abs-2506-05348","title":"FreeTimeGS: Free Gaussian Primitives at Anytime and Anywhere for Dynamic Scene Reconstruction.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2506.05348","numberOfCreators":9,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2506-05348","https://doi.org/10.48550/ARXIV.2506.05348"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-05348","documentUrl":null,"type":"Informal","arxivId":"2506.05348","arxivUrl":"https://arxiv.org/abs/2506.05348"},{"key":"journals/corr/abs-2507-11540","url":"https://dblp.org/rec/journals/corr/abs-2507-11540","title":"Towards Depth Foundation Model: Recent Trends in Vision-Based Depth Estimation.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2507.11540","numberOfCreators":16,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2507-11540","https://doi.org/10.48550/ARXIV.2507.11540"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2507-11540","documentUrl":null,"type":"Informal","arxivId":"2507.11540","arxivUrl":"https://arxiv.org/abs/2507.11540"},{"key":"journals/corr/abs-2507-13344","url":"https://dblp.org/rec/journals/corr/abs-2507-13344","title":"Diffuman4D: 4D Consistent Human View Synthesis from Sparse-View Videos with Spatio-Temporal Diffusion Models.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2507.13344","numberOfCreators":9,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2507-13344","https://doi.org/10.48550/ARXIV.2507.13344"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2507-13344","documentUrl":null,"type":"Informal","arxivId":"2507.13344","arxivUrl":"https://arxiv.org/abs/2507.13344"},{"key":"journals/corr/abs-2508-13104","url":"https://dblp.org/rec/journals/corr/abs-2508-13104","title":"Precise Action-to-Video Generation Through Visual Action Prompts.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2508.13104","numberOfCreators":8,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2508-13104","https://doi.org/10.48550/ARXIV.2508.13104"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-13104","documentUrl":null,"type":"Informal","arxivId":"2508.13104","arxivUrl":"https://arxiv.org/abs/2508.13104"},{"key":"journals/corr/abs-2509-07978","url":"https://dblp.org/rec/journals/corr/abs-2509-07978","title":"One View, Many Worlds: Single-Image to 3D Object Meets Generative Domain Randomization for One-Shot 6D Pose Estimation.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2509.07978","numberOfCreators":8,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2509-07978","https://doi.org/10.48550/ARXIV.2509.07978"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-07978","documentUrl":null,"type":"Informal","arxivId":"2509.07978","arxivUrl":"https://arxiv.org/abs/2509.07978"},{"key":"journals/corr/abs-2510-01669","url":"https://dblp.org/rec/journals/corr/abs-2510-01669","title":"UniVerse: Unleashing the Scene Prior of Video Diffusion Models for Robust Radiance Field Reconstruction.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2510.01669","numberOfCreators":6,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2510-01669","https://doi.org/10.48550/ARXIV.2510.01669"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-01669","documentUrl":null,"type":"Informal","arxivId":"2510.01669","arxivUrl":"https://arxiv.org/abs/2510.01669"},{"key":"journals/corr/abs-2510-07316","url":"https://dblp.org/rec/journals/corr/abs-2510-07316","title":"Pixel-Perfect Depth with Semantics-Prompted Diffusion Transformers.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2510.07316","numberOfCreators":14,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2510-07316","https://doi.org/10.48550/ARXIV.2510.07316"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-07316","documentUrl":null,"type":"Informal","arxivId":"2510.07316","arxivUrl":"https://arxiv.org/abs/2510.07316"},{"key":"journals/corr/abs-2510-15800","url":"https://dblp.org/rec/journals/corr/abs-2510-15800","title":"ERNet: Efficient Non-Rigid Registration Network for Point Sequences.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2510.15800","numberOfCreators":5,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2510-15800","https://doi.org/10.48550/ARXIV.2510.15800"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-15800","documentUrl":null,"type":"Informal","arxivId":"2510.15800","arxivUrl":"https://arxiv.org/abs/2510.15800"},{"key":"journals/corr/abs-2511-14223","url":"https://dblp.org/rec/journals/corr/abs-2511-14223","title":"StreamingTalker: Audio-driven 3D Facial Animation with Autoregressive Diffusion Model.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2511.14223","numberOfCreators":9,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2511-14223","https://doi.org/10.48550/ARXIV.2511.14223"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2511-14223","documentUrl":null,"type":"Informal","arxivId":"2511.14223","arxivUrl":"https://arxiv.org/abs/2511.14223"},{"key":"journals/corr/abs-2512-20617","url":"https://dblp.org/rec/journals/corr/abs-2512-20617","title":"SpatialTree: How Spatial Abilities Branch Out in MLLMs.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2512.20617","numberOfCreators":8,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2512-20617","https://doi.org/10.48550/ARXIV.2512.20617"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-20617","documentUrl":null,"type":"Informal","arxivId":"2512.20617","arxivUrl":"https://arxiv.org/abs/2512.20617"},{"key":"journals/corr/abs-2512-22745","url":"https://dblp.org/rec/journals/corr/abs-2512-22745","title":"Split4D: Decomposed 4D Scene Reconstruction Without Video Segmentation.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2512.22745","numberOfCreators":11,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2512-22745","https://doi.org/10.48550/ARXIV.2512.22745"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-22745","documentUrl":null,"type":"Informal","arxivId":"2512.22745","arxivUrl":"https://arxiv.org/abs/2512.22745"}],"excludedFormal":[],"otherRecords":[],"matchedName":"Sida Peng","databaseLabel":"Sida Peng","databaseMetadata":{"type":["https://dblp.org/rdf/schema#Person","https://dblp.org/rdf/schema#Creator"],"label":["Sida Peng"]},"rawFormalRecordCount2025":33,"signatureAudit":{"completedAt":"2026-10-19","frozen":true,"scope":"对 B 组 39 个数值档案的全部 1074 条原始 2025 正式记录扫描 DBLP author-signature ORCID 和机构；复用既有 59 条 Crossref 核验，补查 6 条新触发记录。重点核查不同 ORCID，以及只有预期机构之外机构的条目。本轮不扩展为所有作者逐篇全文审计。","formalRecordCoverage":33,"orcidCounts":{"https://orcid.org/0000-0001-6546-4525":4},"institutionCounts":{"ETH Zurich":1,"Zhejiang University (ZJU)":29,"Zhejiang University of Science and Technology (ZUST)":1},"caveat":"机构名称可能由 DBLP 自动映射而失真；多 ORCID 也不自动等于异人。只有有原始资料支撑的错归才作确认排除，未解决分支则暂停总数。"},"labName":null,"labUrl":null,"labEvidence":"本人主页提到 our lab 及申请入口，但未明确组名；没有从项目 GitHub 名称反推实验室名称。","labSourceUrl":"https://pengsida.net/","sourceWarning":false,"excludedOther":[],"excludedHomonyms":[],"unassignedCandidates":[],"knownPreprintMinimum2025":null,"excludedMisattributed":[],"displayNotes":"身份已与原名单机构及公开资料核对确认。2025 年正式记录 33 条（会议 30、期刊 3），所有作者位置均计入，不表示主导或贡献份额；预印本 21 条单列，不加总。","labDisplayNotes":"个人主页提到 our lab 及申请入口，但未写组名；不从项目 GitHub 的名称反推实验室名称。"},{"index":75,"name":"Xiaojuan Qi","nameZh":"齐晓娟","role":"Associate Professor","affiliation":"The University of Hong Kong","affiliationZh":"香港大学","source":"DBLP RDF via official SPARQL; primary-source identity checks","sourceUrl":"https://sparql.dblp.org/","profileUrl":"https://dblp.org/pid/176/1445-1.html","identifier":"176/1445-1","retrievedAt":"2026-10-19","count2025":43,"conference2025":37,"journal2025":6,"preprint2025":39,"status":"confirmed","notes":"","identityEvidence":[{"url":"https://dblp.org/pid/176/1445-1.html","evidence":"DBLP RDF 类型为 Person，消歧后名字为 Xiaojuan Qi 0001。机构元数据含：University of Hong Kong, Department of Electrical and Electronic Engineering, Pokfulam, Hong Kong；Chinese University of Hong Kong, Sha Tin, Hong Kong"}],"papers":[{"key":"conf/cvpr/0004ZCP025","url":"https://dblp.org/rec/conf/cvpr/0004ZCP025","title":"A Data-Centric Revisit of Pre-Trained Vision Models for Robot Learning.","year":2025,"types":["Inproceedings"],"venue":"CVPR","doi":"https://doi.org/10.1109/CVPR52734.2025.01134","eventYear":2025,"numberOfCreators":5,"category":"conference","sources":["https://dblp.org/rec/conf/cvpr/0004ZCP025","https://doi.org/10.1109/CVPR52734.2025.01134"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/0004ZCP025","documentUrl":null,"type":"Inproceedings"},{"key":"conf/cvpr/HanHSZSZZ0L025","url":"https://dblp.org/rec/conf/cvpr/HanHSZSZZ0L025","title":"VideoEspresso: A Large-Scale Chain-of-Thought Dataset for Fine-Grained Video Reasoning via Core Frame Selection.","year":2025,"types":["Inproceedings"],"venue":"CVPR","doi":"https://doi.org/10.1109/CVPR52734.2025.02438","eventYear":2025,"numberOfCreators":10,"category":"conference","sources":["https://dblp.org/rec/conf/cvpr/HanHSZSZZ0L025","https://doi.org/10.1109/CVPR52734.2025.02438"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/HanHSZSZZ0L025","documentUrl":null,"type":"Inproceedings"},{"key":"conf/cvpr/HuangLSYLCQ25","url":"https://dblp.org/rec/conf/cvpr/HuangLSYLCQ25","title":"Deformable Radial Kernel Splatting.","year":2025,"types":["Inproceedings"],"venue":"CVPR","doi":"https://doi.org/10.1109/CVPR52734.2025.02004","eventYear":2025,"numberOfCreators":7,"category":"conference","sources":["https://dblp.org/rec/conf/cvpr/HuangLSYLCQ25","https://doi.org/10.1109/CVPR52734.2025.02004"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/HuangLSYLCQ25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/cvpr/LiGLZDCZTZW0Z0Z25","url":"https://dblp.org/rec/conf/cvpr/LiGLZDCZTZW0Z0Z25","title":"UniScene: Unified Occupancy-centric Driving Scene Generation.","year":2025,"types":["Inproceedings"],"venue":"CVPR","doi":"https://doi.org/10.1109/CVPR52734.2025.01118","eventYear":2025,"numberOfCreators":17,"category":"conference","sources":["https://dblp.org/rec/conf/cvpr/LiGLZDCZTZW0Z0Z25","https://doi.org/10.1109/CVPR52734.2025.01118"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/LiGLZDCZTZW0Z0Z25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/cvpr/YuWK0CLL025","url":"https://dblp.org/rec/conf/cvpr/YuWK0CLL025","title":"ObjectMover: Generative Object Movement with Video Prior.","year":2025,"types":["Inproceedings"],"venue":"CVPR","doi":"https://doi.org/10.1109/CVPR52734.2025.01647","eventYear":2025,"numberOfCreators":8,"category":"conference","sources":["https://dblp.org/rec/conf/cvpr/YuWK0CLL025","https://doi.org/10.1109/CVPR52734.2025.01647"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/YuWK0CLL025","documentUrl":null,"type":"Inproceedings"},{"key":"conf/cvpr/Zhao0LMY025","url":"https://dblp.org/rec/conf/cvpr/Zhao0LMY025","title":"Learning from Neighbors: Category Extrapolation for Long-Tail Learning.","year":2025,"types":["Inproceedings"],"venue":"CVPR","doi":"https://doi.org/10.1109/CVPR52734.2025.02838","eventYear":2025,"numberOfCreators":6,"category":"conference","sources":["https://dblp.org/rec/conf/cvpr/Zhao0LMY025","https://doi.org/10.1109/CVPR52734.2025.02838"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/Zhao0LMY025","documentUrl":null,"type":"Inproceedings"},{"key":"conf/dac/LiYFWDLSYWQZW25","url":"https://dblp.org/rec/conf/dac/LiYFWDLSYWQZW25","title":"Efficient Edge Vision Transformer Accelerator with Decoupled Chunk Attention and Hybrid Computing-In-Memory.","year":2025,"types":["Inproceedings"],"venue":"DAC","doi":"https://doi.org/10.1109/DAC63849.2025.11132426","eventYear":2025,"numberOfCreators":12,"category":"conference","sources":["https://dblp.org/rec/conf/dac/LiYFWDLSYWQZW25","https://doi.org/10.1109/DAC63849.2025.11132426"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/dac/LiYFWDLSYWQZW25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/dac/LinLLYHLSCQW25","url":"https://dblp.org/rec/conf/dac/LinLLYHLSCQW25","title":"Guarder: A Stable and Lightweight Reconfigurable RRAM-based PIM Accelerator for DNN IP Protection.","year":2025,"types":["Inproceedings"],"venue":"DAC","doi":"https://doi.org/10.1109/DAC63849.2025.11133133","eventYear":2025,"numberOfCreators":10,"category":"conference","sources":["https://dblp.org/rec/conf/dac/LinLLYHLSCQW25","https://doi.org/10.1109/DAC63849.2025.11133133"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/dac/LinLLYHLSCQW25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/eccv/LiuLLYPCQHLO24","url":"https://dblp.org/rec/conf/eccv/LiuLLYPCQHLO24","title":"UniDream: Unifying Diffusion Priors for Relightable Text-to-3D Generation.","year":2025,"types":["Inproceedings"],"venue":"ECCV (5)","doi":"https://doi.org/10.1007/978-3-031-72652-1_5","eventYear":2024,"numberOfCreators":10,"category":"conference","sources":["https://dblp.org/rec/conf/eccv/LiuLLYPCQHLO24","https://doi.org/10.1007/978-3-031-72652-1_5"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2024,"sourceUrl":"https://dblp.org/rec/conf/eccv/LiuLLYPCQHLO24","documentUrl":null,"type":"Inproceedings"},{"key":"conf/eccv/LiuWZCQ24","url":"https://dblp.org/rec/conf/eccv/LiuWZCQ24","title":"Can OOD Object Detectors Learn from Foundation Models?","year":2025,"types":["Inproceedings"],"venue":"ECCV (12)","doi":"https://doi.org/10.1007/978-3-031-73254-6_13","eventYear":2024,"numberOfCreators":5,"category":"conference","sources":["https://dblp.org/rec/conf/eccv/LiuWZCQ24","https://doi.org/10.1007/978-3-031-73254-6_13"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2024,"sourceUrl":"https://dblp.org/rec/conf/eccv/LiuWZCQ24","documentUrl":null,"type":"Inproceedings"},{"key":"conf/eccv/MaJWYQ24","url":"https://dblp.org/rec/conf/eccv/MaJWYQ24","title":"Groma: Localized Visual Tokenization for Grounding Multimodal Large Language Models.","year":2025,"types":["Inproceedings"],"venue":"ECCV (6)","doi":"https://doi.org/10.1007/978-3-031-72658-3_24","eventYear":2024,"numberOfCreators":5,"category":"conference","sources":["https://dblp.org/rec/conf/eccv/MaJWYQ24","https://doi.org/10.1007/978-3-031-72658-3_24"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2024,"sourceUrl":"https://dblp.org/rec/conf/eccv/MaJWYQ24","documentUrl":null,"type":"Inproceedings"},{"key":"conf/eccv/MaZCQYLLLQSH24","url":"https://dblp.org/rec/conf/eccv/MaZCQYLLLQSH24","title":"EA-VTR: Event-Aware Video-Text Retrieval.","year":2025,"types":["Inproceedings"],"venue":"ECCV (52)","doi":"https://doi.org/10.1007/978-3-031-72943-0_5","eventYear":2024,"numberOfCreators":11,"category":"conference","sources":["https://dblp.org/rec/conf/eccv/MaZCQYLLLQSH24","https://doi.org/10.1007/978-3-031-72943-0_5"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2024,"sourceUrl":"https://dblp.org/rec/conf/eccv/MaZCQYLLLQSH24","documentUrl":null,"type":"Inproceedings"},{"key":"conf/eccv/WuSCZWLQ24","url":"https://dblp.org/rec/conf/eccv/WuSCZWLQ24","title":"3D-Aware Text-Driven Talking Avatar Generation.","year":2025,"types":["Inproceedings"],"venue":"ECCV (88)","doi":"https://doi.org/10.1007/978-3-031-73223-2_23","eventYear":2024,"numberOfCreators":7,"category":"conference","sources":["https://dblp.org/rec/conf/eccv/WuSCZWLQ24","https://doi.org/10.1007/978-3-031-73223-2_23"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2024,"sourceUrl":"https://dblp.org/rec/conf/eccv/WuSCZWLQ24","documentUrl":null,"type":"Inproceedings"},{"key":"conf/eccv/YangDBQX24","url":"https://dblp.org/rec/conf/eccv/YangDBQX24","title":"V-IRL: Grounding Virtual Intelligence in Real Life.","year":2025,"types":["Inproceedings"],"venue":"ECCV (45)","doi":"https://doi.org/10.1007/978-3-031-72995-9_3","eventYear":2024,"numberOfCreators":5,"category":"conference","sources":["https://dblp.org/rec/conf/eccv/YangDBQX24","https://doi.org/10.1007/978-3-031-72995-9_3"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2024,"sourceUrl":"https://dblp.org/rec/conf/eccv/YangDBQX24","documentUrl":null,"type":"Inproceedings"},{"key":"conf/emnlp/LuZYGZQLH25","url":"https://dblp.org/rec/conf/emnlp/LuZYGZQLH25","title":"Mitigating Hallucinations in Large Vision-Language Models by Self-Injecting Hallucinations.","year":2025,"types":["Inproceedings"],"venue":"EMNLP (Findings)","doi":"https://doi.org/10.18653/V1/2025.FINDINGS-EMNLP.746","eventYear":2025,"numberOfCreators":8,"category":"conference","sources":["https://dblp.org/rec/conf/emnlp/LuZYGZQLH25","https://doi.org/10.18653/V1/2025.FINDINGS-EMNLP.746"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/emnlp/LuZYGZQLH25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iccv/ChangLLLHTWZQ25","url":"https://dblp.org/rec/conf/iccv/ChangLLLHTWZQ25","title":"How Far are AI-Generated Videos from Simulating the 3D Visual World: A Learned 3D Evaluation Approach.","year":2025,"types":["Inproceedings"],"venue":"ICCV","doi":"https://doi.org/10.1109/ICCV51701.2025.00960","eventYear":2025,"numberOfCreators":9,"category":"conference","sources":["https://dblp.org/rec/conf/iccv/ChangLLLHTWZQ25","https://doi.org/10.1109/ICCV51701.2025.00960"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/ChangLLLHTWZQ25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iccv/ChenLFLCZFQW25","url":"https://dblp.org/rec/conf/iccv/ChenLFLCZFQW25","title":"Aligning Effective Tokens with Video Anomaly in Large Language Models.","year":2025,"types":["Inproceedings"],"venue":"ICCV","doi":"https://doi.org/10.1109/ICCV51701.2025.02107","eventYear":2025,"numberOfCreators":9,"category":"conference","sources":["https://dblp.org/rec/conf/iccv/ChenLFLCZFQW25","https://doi.org/10.1109/ICCV51701.2025.02107"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/ChenLFLCZFQW25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iccv/GuoDCCLZLTQLZ25","url":"https://dblp.org/rec/conf/iccv/GuoDCCLZLTQLZ25","title":"DiST-4D: Disentangled Spatiotemporal Diffusion with Metric Depth for 4D Driving Scene Generation.","year":2025,"types":["Inproceedings"],"venue":"ICCV","doi":"https://doi.org/10.1109/ICCV51701.2025.02528","eventYear":2025,"numberOfCreators":11,"category":"conference","sources":["https://dblp.org/rec/conf/iccv/GuoDCCLZLTQLZ25","https://doi.org/10.1109/ICCV51701.2025.02528"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/GuoDCCLZLTQLZ25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iccv/WenZEDQ25","url":"https://dblp.org/rec/conf/iccv/WenZEDQ25","title":"\"Principal Components\" Enable a New Language of Images.","year":2025,"types":["Inproceedings"],"venue":"ICCV","doi":"https://doi.org/10.1109/ICCV51701.2025.01545","eventYear":2025,"numberOfCreators":5,"category":"conference","sources":["https://dblp.org/rec/conf/iccv/WenZEDQ25","https://doi.org/10.1109/ICCV51701.2025.01545"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/WenZEDQ25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iccv/WuTCZLYQJ25","url":"https://dblp.org/rec/conf/iccv/WuTCZLYQJ25","title":"Mixture-of-Scores: Robust Image-Text Data Valuation via Three Lines of Code.","year":2025,"types":["Inproceedings"],"venue":"ICCV","doi":"https://doi.org/10.1109/ICCV51701.2025.02281","eventYear":2025,"numberOfCreators":8,"category":"conference","sources":["https://dblp.org/rec/conf/iccv/WuTCZLYQJ25","https://doi.org/10.1109/ICCV51701.2025.02281"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/WuTCZLYQJ25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iccv/XiePLHHQ25","url":"https://dblp.org/rec/conf/iccv/XiePLHHQ25","title":"2D Instance Editing in 3D Space.","year":2025,"types":["Inproceedings"],"venue":"ICCVW","doi":"https://doi.org/10.1109/ICCVW69036.2025.00208","eventYear":2025,"numberOfCreators":6,"category":"conference","sources":["https://dblp.org/rec/conf/iccv/XiePLHHQ25","https://doi.org/10.1109/ICCVW69036.2025.00208"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/XiePLHHQ25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iccv/ZhaoLWTQ25","url":"https://dblp.org/rec/conf/iccv/ZhaoLWTQ25","title":"Equipping Vision Foundation Model with Mixture of Experts for Out-of-Distribution Detection.","year":2025,"types":["Inproceedings"],"venue":"ICCV","doi":"https://doi.org/10.1109/ICCV51701.2025.00171","eventYear":2025,"numberOfCreators":5,"category":"conference","sources":["https://dblp.org/rec/conf/iccv/ZhaoLWTQ25","https://doi.org/10.1109/ICCV51701.2025.00171"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/ZhaoLWTQ25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iccv/ZhengWZDWZQ25","url":"https://dblp.org/rec/conf/iccv/ZhengWZDWZQ25","title":"Holistic Tokenizer for Autoregressive Image Generation.","year":2025,"types":["Inproceedings"],"venue":"ICCV","doi":"https://doi.org/10.1109/ICCV51701.2025.01571","eventYear":2025,"numberOfCreators":7,"category":"conference","sources":["https://dblp.org/rec/conf/iccv/ZhengWZDWZQ25","https://doi.org/10.1109/ICCV51701.2025.01571"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/ZhengWZDWZQ25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iclr/0003TXFDF0025","url":"https://dblp.org/rec/conf/iclr/0003TXFDF0025","title":"SVG: 3D Stereoscopic Video Generation via Denoising Frame Matrix.","year":2025,"types":["Inproceedings"],"venue":"ICLR","doi":null,"eventYear":2025,"numberOfCreators":8,"category":"conference","sources":["https://dblp.org/rec/conf/iclr/0003TXFDF0025"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iclr/0003TXFDF0025","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iclr/HuangLLHTZ00025","url":"https://dblp.org/rec/conf/iclr/HuangLLHTZ00025","title":"Mixture Compressor for Mixture-of-Experts LLMs Gains More.","year":2025,"types":["Inproceedings"],"venue":"ICLR","doi":null,"eventYear":2025,"numberOfCreators":9,"category":"conference","sources":["https://dblp.org/rec/conf/iclr/HuangLLHTZ00025"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iclr/HuangLLHTZ00025","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iclr/TanWHZ025","url":"https://dblp.org/rec/conf/iclr/TanWHZ025","title":"Data Pruning by Information Maximization.","year":2025,"types":["Inproceedings"],"venue":"ICLR","doi":null,"eventYear":2025,"numberOfCreators":5,"category":"conference","sources":["https://dblp.org/rec/conf/iclr/TanWHZ025"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iclr/TanWHZ025","documentUrl":null,"type":"Inproceedings"},{"key":"conf/icml/0042QL0L0BMZ025","url":"https://dblp.org/rec/conf/icml/0042QL0L0BMZ025","title":"SliM-LLM: Salience-Driven Mixed-Precision Quantization for Large Language Models.","year":2025,"types":["Inproceedings"],"venue":"ICML","doi":null,"eventYear":2025,"numberOfCreators":10,"category":"conference","sources":["https://dblp.org/rec/conf/icml/0042QL0L0BMZ025"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/icml/0042QL0L0BMZ025","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iros/DingQZJYYQW25","url":"https://dblp.org/rec/conf/iros/DingQZJYYQW25","title":"Bunny-VisionPro: Real-Time Bimanual Dexterous Teleoperation for Imitation Learning.","year":2025,"types":["Inproceedings"],"venue":"IROS","doi":"https://doi.org/10.1109/IROS60139.2025.11247017","eventYear":2025,"numberOfCreators":8,"category":"conference","sources":["https://dblp.org/rec/conf/iros/DingQZJYYQW25","https://doi.org/10.1109/IROS60139.2025.11247017"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iros/DingQZJYYQW25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/nips/ChenHSHYZLMKQLY25","url":"https://dblp.org/rec/conf/nips/ChenHSHYZLMKQLY25","title":"Scaling RL to Long Videos.","year":2025,"types":["Inproceedings"],"venue":"NeurIPS","doi":null,"eventYear":2025,"numberOfCreators":14,"category":"conference","sources":["https://dblp.org/rec/conf/nips/ChenHSHYZLMKQLY25"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/nips/ChenHSHYZLMKQLY25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/nips/MaJWYYYPQ25","url":"https://dblp.org/rec/conf/nips/MaJWYYYPQ25","title":"UniTok: a Unified Tokenizer for Visual Generation and Understanding.","year":2025,"types":["Inproceedings"],"venue":"NeurIPS","doi":null,"eventYear":2025,"numberOfCreators":8,"category":"conference","sources":["https://dblp.org/rec/conf/nips/MaJWYYYPQ25"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/nips/MaJWYYYPQ25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/nips/TanWWZCSSQ25","url":"https://dblp.org/rec/conf/nips/TanWWZCSSQ25","title":"Understanding Data Influence in Reinforcement Finetuning.","year":2025,"types":["Inproceedings"],"venue":"NeurIPS","doi":null,"eventYear":2025,"numberOfCreators":8,"category":"conference","sources":["https://dblp.org/rec/conf/nips/TanWWZCSSQ25"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/nips/TanWWZCSSQ25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/nips/WuTLZQYJ25","url":"https://dblp.org/rec/conf/nips/WuTLZQYJ25","title":"DLoFT: Gradient-Decoupled Fine-Tuning for Generalizable Long Chain-of-Thought Reasoning.","year":2025,"types":["Inproceedings"],"venue":"NeurIPS","doi":null,"eventYear":2025,"numberOfCreators":7,"category":"conference","sources":["https://dblp.org/rec/conf/nips/WuTLZQYJ25"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/nips/WuTLZQYJ25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/nips/WuYLHWZWQ25","url":"https://dblp.org/rec/conf/nips/WuYLHWZWQ25","title":"EAG3R: Event-Augmented 3D Geometry Estimation for Dynamic and Extreme-Lighting Scenes.","year":2025,"types":["Inproceedings"],"venue":"NeurIPS","doi":null,"eventYear":2025,"numberOfCreators":8,"category":"conference","sources":["https://dblp.org/rec/conf/nips/WuYLHWZWQ25"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/nips/WuYLHWZWQ25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/nips/XiaoSCLCGHLQS25","url":"https://dblp.org/rec/conf/nips/XiaoSCLCGHLQS25","title":"MindOmni: Unleashing Reasoning Generation in Vision Language Models with RGPO.","year":2025,"types":["Inproceedings"],"venue":"NeurIPS","doi":null,"eventYear":2025,"numberOfCreators":10,"category":"conference","sources":["https://dblp.org/rec/conf/nips/XiaoSCLCGHLQS25"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/nips/XiaoSCLCGHLQS25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/nips/ZhengWZMWYZQ25","url":"https://dblp.org/rec/conf/nips/ZhengWZMWYZQ25","title":"Vision Foundation Models as Effective Visual Tokenizers for Autoregressive Generation.","year":2025,"types":["Inproceedings"],"venue":"NeurIPS","doi":null,"eventYear":2025,"numberOfCreators":8,"category":"conference","sources":["https://dblp.org/rec/conf/nips/ZhengWZMWYZQ25"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/nips/ZhengWZMWYZQ25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/siggrapha/YuanYSGCLQ25","url":"https://dblp.org/rec/conf/siggrapha/YuanYSGCLQ25","title":"SeqTex: Generate Mesh Textures in Video Sequence.","year":2025,"types":["Inproceedings"],"venue":"SIGGRAPH Asia","doi":"https://doi.org/10.1145/3757377.3763863","eventYear":2025,"numberOfCreators":7,"category":"conference","sources":["https://dblp.org/rec/conf/siggrapha/YuanYSGCLQ25","https://doi.org/10.1145/3757377.3763863"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/siggrapha/YuanYSGCLQ25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/uist/ZhaoJZCCDJQQN25","url":"https://dblp.org/rec/conf/uist/ZhaoJZCCDJQQN25","title":"NoteIt: A System Converting Instructional Videos to Interactable Notes Through Multimodal Video Understanding.","year":2025,"types":["Inproceedings"],"venue":"UIST","doi":"https://doi.org/10.1145/3746059.3747626","eventYear":2025,"numberOfCreators":10,"category":"conference","sources":["https://dblp.org/rec/conf/uist/ZhaoJZCCDJQQN25","https://doi.org/10.1145/3746059.3747626"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/uist/ZhaoJZCCDJQQN25","documentUrl":null,"type":"Inproceedings"},{"key":"journals/access/WangWLQS25","url":"https://dblp.org/rec/journals/access/WangWLQS25","title":"SpikeMOT: Event-Based Multi-Object Tracking With Sparse Motion Features.","year":2025,"types":["Article"],"venue":"IEEE Access","doi":"https://doi.org/10.1109/ACCESS.2024.3523411","numberOfCreators":5,"category":"journal","sources":["https://dblp.org/rec/journals/access/WangWLQS25","https://doi.org/10.1109/ACCESS.2024.3523411"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/access/WangWLQS25","documentUrl":null,"type":"Article"},{"key":"journals/aisy/HuangFWWQZ25","url":"https://dblp.org/rec/journals/aisy/HuangFWWQZ25","title":"Improving Long-Term Glucose Prediction Accuracy with Uncertainty-Estimated ProbSparse-Transformer.","year":2025,"types":["Article"],"venue":"Adv. Intell. Syst.","doi":"https://doi.org/10.1002/AISY.202500235","numberOfCreators":6,"category":"journal","sources":["https://dblp.org/rec/journals/aisy/HuangFWWQZ25","https://doi.org/10.1002/AISY.202500235"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/aisy/HuangFWWQZ25","documentUrl":null,"type":"Article"},{"key":"journals/aisy/HuangPBCQZ25","url":"https://dblp.org/rec/journals/aisy/HuangPBCQZ25","title":"Artificial Intelligence-Enhanced, Closed-Loop Wearable Systems Toward Next-Generation Diabetes Management.","year":2025,"types":["Article"],"venue":"Adv. Intell. Syst.","doi":"https://doi.org/10.1002/AISY.202400822","numberOfCreators":6,"category":"journal","sources":["https://dblp.org/rec/journals/aisy/HuangPBCQZ25","https://doi.org/10.1002/AISY.202400822"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/aisy/HuangPBCQZ25","documentUrl":null,"type":"Article"},{"key":"journals/ncs/LinWLWSHZYZZWWCJZLXQWSL25","url":"https://dblp.org/rec/journals/ncs/LinWLWSHZYZZWWCJZLXQWSL25","title":"Resistive memory-based zero-shot liquid state machine for multimodal event data learning.","year":2025,"types":["Article"],"venue":"Nat. Comput. Sci.","doi":"https://doi.org/10.1038/S43588-024-00751-Z","numberOfCreators":22,"category":"journal","sources":["https://dblp.org/rec/journals/ncs/LinWLWSHZYZZWWCJZLXQWSL25","https://doi.org/10.1038/S43588-024-00751-Z"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/ncs/LinWLWSHZYZZWWCJZLXQWSL25","documentUrl":null,"type":"Article"},{"key":"journals/ncs/XuWHLZYQWXSLML25","url":"https://dblp.org/rec/journals/ncs/XuWHLZYQWXSLML25","title":"Efficient modeling of ionic and electronic interactions by a resistive memory-based reservoir graph neural network.","year":2025,"types":["Article"],"venue":"Nat. Comput. Sci.","doi":"https://doi.org/10.1038/S43588-025-00844-3","numberOfCreators":13,"category":"journal","sources":["https://dblp.org/rec/journals/ncs/XuWHLZYQWXSLML25","https://doi.org/10.1038/S43588-025-00844-3"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/ncs/XuWHLZYQWXSLML25","documentUrl":null,"type":"Article"},{"key":"journals/tvcg/DaiTYPZQ25","url":"https://dblp.org/rec/journals/tvcg/DaiTYPZQ25","title":"GO-NeRF: Generating Objects in Neural Radiance Fields for Virtual Reality Content Creation.","year":2025,"types":["Article"],"venue":"IEEE Trans. Vis. Comput. Graph.","doi":"https://doi.org/10.1109/TVCG.2025.3549558","numberOfCreators":6,"category":"journal","sources":["https://dblp.org/rec/journals/tvcg/DaiTYPZQ25","https://doi.org/10.1109/TVCG.2025.3549558"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/tvcg/DaiTYPZQ25","documentUrl":null,"type":"Article"}],"preprints":[{"key":"journals/corr/abs-2502-20321","url":"https://dblp.org/rec/journals/corr/abs-2502-20321","title":"UniTok: A Unified Tokenizer for Visual Generation and Understanding.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2502.20321","numberOfCreators":8,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2502-20321","https://doi.org/10.48550/ARXIV.2502.20321"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2502-20321","documentUrl":null,"type":"Informal","arxivId":"2502.20321","arxivUrl":"https://arxiv.org/abs/2502.20321"},{"key":"journals/corr/abs-2503-06960","url":"https://dblp.org/rec/journals/corr/abs-2503-06960","title":"A Data-Centric Revisit of Pre-Trained Vision Models for Robot Learning.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2503.06960","numberOfCreators":5,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2503-06960","https://doi.org/10.48550/ARXIV.2503.06960"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-06960","documentUrl":null,"type":"Informal","arxivId":"2503.06960","arxivUrl":"https://arxiv.org/abs/2503.06960"},{"key":"journals/corr/abs-2503-08037","url":"https://dblp.org/rec/journals/corr/abs-2503-08037","title":"ObjectMover: Generative Object Movement with Video Prior.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2503.08037","numberOfCreators":8,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2503-08037","https://doi.org/10.48550/ARXIV.2503.08037"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-08037","documentUrl":null,"type":"Informal","arxivId":"2503.08037","arxivUrl":"https://arxiv.org/abs/2503.08037"},{"key":"journals/corr/abs-2503-08038","url":"https://dblp.org/rec/journals/corr/abs-2503-08038","title":"Generalized Kullback-Leibler Divergence Loss.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2503.08038","numberOfCreators":8,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2503-08038","https://doi.org/10.48550/ARXIV.2503.08038"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-08038","documentUrl":null,"type":"Informal","arxivId":"2503.08038","arxivUrl":"https://arxiv.org/abs/2503.08038"},{"key":"journals/corr/abs-2503-08685","url":"https://dblp.org/rec/journals/corr/abs-2503-08685","title":"\"Principal Components\" Enable A New Language of Images.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2503.08685","numberOfCreators":5,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2503-08685","https://doi.org/10.48550/ARXIV.2503.08685"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-08685","documentUrl":null,"type":"Informal","arxivId":"2503.08685","arxivUrl":"https://arxiv.org/abs/2503.08685"},{"key":"journals/corr/abs-2503-10604","url":"https://dblp.org/rec/journals/corr/abs-2503-10604","title":"MuDG: Taming Multi-modal Diffusion with Gaussian Splatting for Urban Scene Reconstruction.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2503.10604","numberOfCreators":9,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2503-10604","https://doi.org/10.48550/ARXIV.2503.10604"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-10604","documentUrl":null,"type":"Informal","arxivId":"2503.10604","arxivUrl":"https://arxiv.org/abs/2503.10604"},{"key":"journals/corr/abs-2503-12015","url":"https://dblp.org/rec/journals/corr/abs-2503-12015","title":"QDM: Quadtree-Based Region-Adaptive Sparse Diffusion Models for Efficient Image Super-Resolution.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2503.12015","numberOfCreators":5,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2503-12015","https://doi.org/10.48550/ARXIV.2503.12015"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-12015","documentUrl":null,"type":"Informal","arxivId":"2503.12015","arxivUrl":"https://arxiv.org/abs/2503.12015"},{"key":"journals/corr/abs-2503-15208","url":"https://dblp.org/rec/journals/corr/abs-2503-15208","title":"DiST-4D: Disentangled Spatiotemporal Diffusion with Metric Depth for 4D Driving Scene Generation.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2503.15208","numberOfCreators":11,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2503-15208","https://doi.org/10.48550/ARXIV.2503.15208"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-15208","documentUrl":null,"type":"Informal","arxivId":"2503.15208","arxivUrl":"https://arxiv.org/abs/2503.15208"},{"key":"journals/corr/abs-2505-13031","url":"https://dblp.org/rec/journals/corr/abs-2505-13031","title":"MindOmni: Unleashing Reasoning Generation in Vision Language Models with RGPO.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2505.13031","numberOfCreators":10,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2505-13031","https://doi.org/10.48550/ARXIV.2505.13031"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-13031","documentUrl":null,"type":"Informal","arxivId":"2505.13031","arxivUrl":"https://arxiv.org/abs/2505.13031"},{"key":"journals/corr/abs-2505-24521","url":"https://dblp.org/rec/journals/corr/abs-2505-24521","title":"UniGeo: Taming Video Diffusion for Unified Consistent Geometry Estimation.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2505.24521","numberOfCreators":8,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2505-24521","https://doi.org/10.48550/ARXIV.2505.24521"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-24521","documentUrl":null,"type":"Informal","arxivId":"2505.24521","arxivUrl":"https://arxiv.org/abs/2505.24521"},{"key":"journals/corr/abs-2506-01701","url":"https://dblp.org/rec/journals/corr/abs-2506-01701","title":"Data Pruning by Information Maximization.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2506.01701","numberOfCreators":5,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2506-01701","https://doi.org/10.48550/ARXIV.2506.01701"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-01701","documentUrl":null,"type":"Informal","arxivId":"2506.01701","arxivUrl":"https://arxiv.org/abs/2506.01701"},{"key":"journals/corr/abs-2506-13151","url":"https://dblp.org/rec/journals/corr/abs-2506-13151","title":"Reconfigurable Digital RRAM Logic Enables In-Situ Pruning and Learning for Edge AI.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2506.13151","numberOfCreators":13,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2506-13151","https://doi.org/10.48550/ARXIV.2506.13151"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-13151","documentUrl":null,"type":"Informal","arxivId":"2506.13151","arxivUrl":"https://arxiv.org/abs/2506.13151"},{"key":"journals/corr/abs-2507-01027","url":"https://dblp.org/rec/journals/corr/abs-2507-01027","title":"DBellQuant: Breaking the Bell with Double-Bell Transformation for LLMs Post Training Binarization.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2507.01027","numberOfCreators":6,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2507-01027","https://doi.org/10.48550/ARXIV.2507.01027"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2507-01027","documentUrl":null,"type":"Informal","arxivId":"2507.01027","arxivUrl":"https://arxiv.org/abs/2507.01027"},{"key":"journals/corr/abs-2507-02358","url":"https://dblp.org/rec/journals/corr/abs-2507-02358","title":"Hita: Holistic Tokenizer for Autoregressive Image Generation.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2507.02358","numberOfCreators":7,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2507-02358","https://doi.org/10.48550/ARXIV.2507.02358"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2507-02358","documentUrl":null,"type":"Informal","arxivId":"2507.02358","arxivUrl":"https://arxiv.org/abs/2507.02358"},{"key":"journals/corr/abs-2507-04285","url":"https://dblp.org/rec/journals/corr/abs-2507-04285","title":"SeqTex: Generate Mesh Textures in Video Sequence.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2507.04285","numberOfCreators":7,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2507-04285","https://doi.org/10.48550/ARXIV.2507.04285"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2507-04285","documentUrl":null,"type":"Informal","arxivId":"2507.04285","arxivUrl":"https://arxiv.org/abs/2507.04285"},{"key":"journals/corr/abs-2507-05819","url":"https://dblp.org/rec/journals/corr/abs-2507-05819","title":"2D Instance Editing in 3D Space.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2507.05819","numberOfCreators":6,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2507-05819","https://doi.org/10.48550/ARXIV.2507.05819"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2507-05819","documentUrl":null,"type":"Informal","arxivId":"2507.05819","arxivUrl":"https://arxiv.org/abs/2507.05819"},{"key":"journals/corr/abs-2507-07966","url":"https://dblp.org/rec/journals/corr/abs-2507-07966","title":"Scaling RL to Long Videos.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2507.07966","numberOfCreators":14,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2507-07966","https://doi.org/10.48550/ARXIV.2507.07966"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2507-07966","documentUrl":null,"type":"Informal","arxivId":"2507.07966","arxivUrl":"https://arxiv.org/abs/2507.07966"},{"key":"journals/corr/abs-2507-08441","url":"https://dblp.org/rec/journals/corr/abs-2507-08441","title":"Vision Foundation Models as Effective Visual Tokenizers for Autoregressive Image Generation.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2507.08441","numberOfCreators":8,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2507-08441","https://doi.org/10.48550/ARXIV.2507.08441"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2507-08441","documentUrl":null,"type":"Informal","arxivId":"2507.08441","arxivUrl":"https://arxiv.org/abs/2507.08441"},{"key":"journals/corr/abs-2507-10548","url":"https://dblp.org/rec/journals/corr/abs-2507-10548","title":"EmbRACE-3K: Embodied Reasoning and Action in Complex Environments.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2507.10548","numberOfCreators":9,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2507-10548","https://doi.org/10.48550/ARXIV.2507.10548"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2507-10548","documentUrl":null,"type":"Informal","arxivId":"2507.10548","arxivUrl":"https://arxiv.org/abs/2507.10548"},{"key":"journals/corr/abs-2507-12384","url":"https://dblp.org/rec/journals/corr/abs-2507-12384","title":"Trustworthy Tree-based Machine Learning by MoS2 Flash-based Analog CAM with Inherent Soft Boundaries.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2507.12384","numberOfCreators":8,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2507-12384","https://doi.org/10.48550/ARXIV.2507.12384"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2507-12384","documentUrl":null,"type":"Informal","arxivId":"2507.12384","arxivUrl":"https://arxiv.org/abs/2507.12384"},{"key":"journals/corr/abs-2507-14503","url":"https://dblp.org/rec/journals/corr/abs-2507-14503","title":"Generative Distribution Distillation.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2507.14503","numberOfCreators":9,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2507-14503","https://doi.org/10.48550/ARXIV.2507.14503"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2507-14503","documentUrl":null,"type":"Informal","arxivId":"2507.14503","arxivUrl":"https://arxiv.org/abs/2507.14503"},{"key":"journals/corr/abs-2508-06350","url":"https://dblp.org/rec/journals/corr/abs-2508-06350","title":"Aligning Effective Tokens with Video Anomaly in Large Language Models.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2508.06350","numberOfCreators":9,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2508-06350","https://doi.org/10.48550/ARXIV.2508.06350"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-06350","documentUrl":null,"type":"Informal","arxivId":"2508.06350","arxivUrl":"https://arxiv.org/abs/2508.06350"},{"key":"journals/corr/abs-2508-08048","url":"https://dblp.org/rec/journals/corr/abs-2508-08048","title":"S^2VG: 3D Stereoscopic and Spatial Video Generation via Denoising Frame Matrix.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2508.08048","numberOfCreators":9,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2508-08048","https://doi.org/10.48550/ARXIV.2508.08048"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-08048","documentUrl":null,"type":"Informal","arxivId":"2508.08048","arxivUrl":"https://arxiv.org/abs/2508.08048"},{"key":"journals/corr/abs-2508-11256","url":"https://dblp.org/rec/journals/corr/abs-2508-11256","title":"Generalized Decoupled Learning for Enhancing Open-Vocabulary Dense Perception.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2508.11256","numberOfCreators":7,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2508-11256","https://doi.org/10.48550/ARXIV.2508.11256"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-11256","documentUrl":null,"type":"Informal","arxivId":"2508.11256","arxivUrl":"https://arxiv.org/abs/2508.11256"},{"key":"journals/corr/abs-2508-14395","url":"https://dblp.org/rec/journals/corr/abs-2508-14395","title":"NoteIt: A System Converting Instructional Videos to Interactable Notes Through Multimodal Video Understanding.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2508.14395","numberOfCreators":10,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2508-14395","https://doi.org/10.48550/ARXIV.2508.14395"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-14395","documentUrl":null,"type":"Informal","arxivId":"2508.14395","arxivUrl":"https://arxiv.org/abs/2508.14395"},{"key":"journals/corr/abs-2508-14648","url":"https://dblp.org/rec/journals/corr/abs-2508-14648","title":"Understanding Data Influence with Differential Approximation.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2508.14648","numberOfCreators":8,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2508-14648","https://doi.org/10.48550/ARXIV.2508.14648"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-14648","documentUrl":null,"type":"Informal","arxivId":"2508.14648","arxivUrl":"https://arxiv.org/abs/2508.14648"},{"key":"journals/corr/abs-2509-03516","url":"https://dblp.org/rec/journals/corr/abs-2509-03516","title":"Easier Painting Than Thinking: Can Text-to-Image Models Set the Stage, but Not Direct the Play?","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2509.03516","numberOfCreators":10,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2509-03516","https://doi.org/10.48550/ARXIV.2509.03516"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-03516","documentUrl":null,"type":"Informal","arxivId":"2509.03516","arxivUrl":"https://arxiv.org/abs/2509.03516"},{"key":"journals/corr/abs-2509-11287","url":"https://dblp.org/rec/journals/corr/abs-2509-11287","title":"Mitigating Hallucinations in Large Vision-Language Models by Self-Injecting Hallucinations.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2509.11287","numberOfCreators":8,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2509-11287","https://doi.org/10.48550/ARXIV.2509.11287"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-11287","documentUrl":null,"type":"Informal","arxivId":"2509.11287","arxivUrl":"https://arxiv.org/abs/2509.11287"},{"key":"journals/corr/abs-2509-12812","url":"https://dblp.org/rec/journals/corr/abs-2509-12812","title":"Efficient lattice field theory simulation using adaptive normalizing flow on a resistive memory-based neural differential equation solver.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2509.12812","numberOfCreators":9,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2509-12812","https://doi.org/10.48550/ARXIV.2509.12812"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-12812","documentUrl":null,"type":"Informal","arxivId":"2509.12812","arxivUrl":"https://arxiv.org/abs/2509.12812"},{"key":"journals/corr/abs-2510-10584","url":"https://dblp.org/rec/journals/corr/abs-2510-10584","title":"Equipping Vision Foundation Model with Mixture of Experts for Out-of-Distribution Detection.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2510.10584","numberOfCreators":5,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2510-10584","https://doi.org/10.48550/ARXIV.2510.10584"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-10584","documentUrl":null,"type":"Informal","arxivId":"2510.10584","arxivUrl":"https://arxiv.org/abs/2510.10584"},{"key":"journals/corr/abs-2510-10962","url":"https://dblp.org/rec/journals/corr/abs-2510-10962","title":"MC#: Mixture Compressor for Mixture-of-Experts Large Models.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2510.10962","numberOfCreators":9,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2510-10962","https://doi.org/10.48550/ARXIV.2510.10962"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-10962","documentUrl":null,"type":"Informal","arxivId":"2510.10962","arxivUrl":"https://arxiv.org/abs/2510.10962"},{"key":"journals/corr/abs-2510-11696","url":"https://dblp.org/rec/journals/corr/abs-2510-11696","title":"QeRL: Beyond Efficiency - Quantization-enhanced Reinforcement Learning for LLMs.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2510.11696","numberOfCreators":14,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2510-11696","https://doi.org/10.48550/ARXIV.2510.11696"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-11696","documentUrl":null,"type":"Informal","arxivId":"2510.11696","arxivUrl":"https://arxiv.org/abs/2510.11696"},{"key":"journals/corr/abs-2511-22609","url":"https://dblp.org/rec/journals/corr/abs-2511-22609","title":"MG-Nav: Dual-Scale Visual Navigation via Sparse Spatial Memory.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2511.22609","numberOfCreators":8,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2511-22609","https://doi.org/10.48550/ARXIV.2511.22609"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2511-22609","documentUrl":null,"type":"Informal","arxivId":"2511.22609","arxivUrl":"https://arxiv.org/abs/2511.22609"},{"key":"journals/corr/abs-2512-00771","url":"https://dblp.org/rec/journals/corr/abs-2512-00771","title":"EAG3R: Event-Augmented 3D Geometry Estimation for Dynamic and Extreme-Lighting Scenes.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2512.00771","numberOfCreators":8,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2512-00771","https://doi.org/10.48550/ARXIV.2512.00771"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-00771","documentUrl":null,"type":"Informal","arxivId":"2512.00771","arxivUrl":"https://arxiv.org/abs/2512.00771"},{"key":"journals/corr/abs-2512-04519","url":"https://dblp.org/rec/journals/corr/abs-2512-04519","title":"VideoSSM: Autoregressive Long Video Generation with Hybrid State-Space Memory.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2512.04519","numberOfCreators":11,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2512-04519","https://doi.org/10.48550/ARXIV.2512.04519"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-04519","documentUrl":null,"type":"Informal","arxivId":"2512.04519","arxivUrl":"https://arxiv.org/abs/2512.04519"},{"key":"journals/corr/abs-2512-04786","url":"https://dblp.org/rec/journals/corr/abs-2512-04786","title":"LaFiTe: A Generative Latent Field for 3D Native Texturing.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2512.04786","numberOfCreators":9,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2512-04786","https://doi.org/10.48550/ARXIV.2512.04786"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-04786","documentUrl":null,"type":"Informal","arxivId":"2512.04786","arxivUrl":"https://arxiv.org/abs/2512.04786"},{"key":"journals/corr/abs-2512-09364","url":"https://dblp.org/rec/journals/corr/abs-2512-09364","title":"ASSIST-3D: Adapted Scene Synthesis for Class-Agnostic 3D Instance Segmentation.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2512.09364","numberOfCreators":6,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2512-09364","https://doi.org/10.48550/ARXIV.2512.09364"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-09364","documentUrl":null,"type":"Informal","arxivId":"2512.09364","arxivUrl":"https://arxiv.org/abs/2512.09364"},{"key":"journals/corr/abs-2512-20557","url":"https://dblp.org/rec/journals/corr/abs-2512-20557","title":"Learning to Reason in 4D: Dynamic Spatial Understanding for Vision Language Models.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2512.20557","numberOfCreators":7,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2512-20557","https://doi.org/10.48550/ARXIV.2512.20557"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-20557","documentUrl":null,"type":"Informal","arxivId":"2512.20557","arxivUrl":"https://arxiv.org/abs/2512.20557"},{"key":"journals/corr/abs-2512-22374","url":"https://dblp.org/rec/journals/corr/abs-2512-22374","title":"Self-Evaluation Unlocks Any-Step Text-to-Image Generation.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2512.22374","numberOfCreators":9,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2512-22374","https://doi.org/10.48550/ARXIV.2512.22374"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-22374","documentUrl":null,"type":"Informal","arxivId":"2512.22374","arxivUrl":"https://arxiv.org/abs/2512.22374"}],"excludedFormal":[],"otherRecords":[],"matchedName":"Xiaojuan Qi","databaseLabel":"Xiaojuan Qi 0001","databaseMetadata":{"type":["https://dblp.org/rdf/schema#Person","https://dblp.org/rdf/schema#Creator"],"label":["Xiaojuan Qi 0001"],"affiliation":["University of Hong Kong, Department of Electrical and Electronic Engineering, Pokfulam, Hong Kong","Chinese University of Hong Kong, Sha Tin, Hong Kong"],"homepage":["https://xjqi.github.io/"],"orcid":["https://orcid.org/0000-0002-4285-1626"],"primaryAffiliation":["University of Hong Kong, Department of Electrical and Electronic Engineering, Pokfulam, Hong Kong"],"primaryHomepage":["https://xjqi.github.io/"]},"rawFormalRecordCount2025":43,"signatureAudit":{"completedAt":"2026-10-19","frozen":true,"scope":"对 B 组 39 个数值档案的全部 1074 条原始 2025 正式记录扫描 DBLP author-signature ORCID 和机构；复用既有 59 条 Crossref 核验，补查 6 条新触发记录。重点核查不同 ORCID，以及只有预期机构之外机构的条目。本轮不扩展为所有作者逐篇全文审计。","formalRecordCoverage":43,"orcidCounts":{"https://orcid.org/0000-0002-4285-1626":7},"institutionCounts":{"University of Hong Kong (HKU)":31},"caveat":"机构名称可能由 DBLP 自动映射而失真；多 ORCID 也不自动等于异人。只有有原始资料支撑的错归才作确认排除，未解决分支则暂停总数。"},"labName":"Computer Vision and Machine Intelligence Lab (CVMI Lab)","labUrl":"https://cvmi.hku.hk/","labEvidence":"本人 cvmi.html 页面明确给出 Computer Vision and Machine Intelligence Lab 名称；香港大学 CVMI 官方 Team 页面列 Xiaojuan Qi 为 Principal Investigator。","labSourceUrl":"https://cvmi.hku.hk/wp-content/uploads/cvmi/team.html","sourceWarning":false,"excludedOther":[],"excludedHomonyms":[],"unassignedCandidates":[],"knownPreprintMinimum2025":null,"excludedMisattributed":[],"displayNotes":"身份已与原名单机构及公开资料核对确认。2025 年正式记录 43 条（会议 37、期刊 6），所有作者位置均计入，不表示主导或贡献份额；预印本 39 条单列，不加总。","labDisplayNotes":"港大 CVMI Lab 官方团队页列其为 PI，本人页面写出实验室全称，据此归组。"},{"index":76,"name":"Shiguang Shan","nameZh":"山世光","role":"Researcher","affiliation":"Institute of Computing Technology, Chinese Academy of Sciences","affiliationZh":"中科院计算所","source":"DBLP RDF via official SPARQL; primary-source identity checks","sourceUrl":"https://sparql.dblp.org/","profileUrl":"https://dblp.org/pid/s/ShiguangShan.html","identifier":"s/ShiguangShan","retrievedAt":"2026-10-19","count2025":48,"conference2025":29,"journal2025":19,"preprint2025":33,"status":"confirmed","notes":"","identityEvidence":[{"url":"https://dblp.org/pid/s/ShiguangShan.html","evidence":"DBLP RDF 类型为 Person，消歧后名字为 Shiguang Shan。机构元数据含：Chinese Academy of Sciences, Institute of Computing Technology, Beijing, China"}],"papers":[{"key":"conf/cvpr/GuoLZZS25","url":"https://dblp.org/rec/conf/cvpr/GuoLZZS25","title":"Face Forgery Video Detection via Temporal Forgery Cue Unraveling.","year":2025,"types":["Inproceedings"],"venue":"CVPR","doi":"https://doi.org/10.1109/CVPR52734.2025.00693","eventYear":2025,"numberOfCreators":5,"category":"conference","sources":["https://dblp.org/rec/conf/cvpr/GuoLZZS25","https://doi.org/10.1109/CVPR52734.2025.00693"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/GuoLZZS25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/cvpr/LiH0S025","url":"https://dblp.org/rec/conf/cvpr/LiH0S025","title":"UniPose: A Unified Multimodal Framework for Human Pose Comprehension, Generation and Editing.","year":2025,"types":["Inproceedings"],"venue":"CVPR","doi":"https://doi.org/10.1109/CVPR52734.2025.02589","eventYear":2025,"numberOfCreators":5,"category":"conference","sources":["https://dblp.org/rec/conf/cvpr/LiH0S025","https://doi.org/10.1109/CVPR52734.2025.02589"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/LiH0S025","documentUrl":null,"type":"Inproceedings"},{"key":"conf/eccv/HuLCMSC24","url":"https://dblp.org/rec/conf/eccv/HuLCMSC24","title":"An Information Theoretical View for Out-of-Distribution Detection.","year":2025,"types":["Inproceedings"],"venue":"ECCV (55)","doi":"https://doi.org/10.1007/978-3-031-73001-6_24","eventYear":2024,"numberOfCreators":6,"category":"conference","sources":["https://dblp.org/rec/conf/eccv/HuLCMSC24","https://doi.org/10.1007/978-3-031-73001-6_24"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2024,"sourceUrl":"https://dblp.org/rec/conf/eccv/HuLCMSC24","documentUrl":null,"type":"Inproceedings"},{"key":"conf/eccv/PanTWS24","url":"https://dblp.org/rec/conf/eccv/PanTWS24","title":"Tokenize Anything via Prompting.","year":2025,"types":["Inproceedings"],"venue":"ECCV (47)","doi":"https://doi.org/10.1007/978-3-031-72970-6_19","eventYear":2024,"numberOfCreators":4,"category":"conference","sources":["https://dblp.org/rec/conf/eccv/PanTWS24","https://doi.org/10.1007/978-3-031-72970-6_19"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2024,"sourceUrl":"https://dblp.org/rec/conf/eccv/PanTWS24","documentUrl":null,"type":"Inproceedings"},{"key":"conf/eccv/WangZSC24","url":"https://dblp.org/rec/conf/eccv/WangZSC24","title":"T2IShield: Defending Against Backdoors on Text-to-Image Diffusion Models.","year":2025,"types":["Inproceedings"],"venue":"ECCV (85)","doi":"https://doi.org/10.1007/978-3-031-73013-9_7","eventYear":2024,"numberOfCreators":4,"category":"conference","sources":["https://dblp.org/rec/conf/eccv/WangZSC24","https://doi.org/10.1007/978-3-031-73013-9_7"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2024,"sourceUrl":"https://dblp.org/rec/conf/eccv/WangZSC24","documentUrl":null,"type":"Inproceedings"},{"key":"conf/eccv/ZhangKSC24","url":"https://dblp.org/rec/conf/eccv/ZhangKSC24","title":"PreLAR: World Model Pre-training with Learnable Action Representation.","year":2025,"types":["Inproceedings"],"venue":"ECCV (23)","doi":"https://doi.org/10.1007/978-3-031-73337-6_11","eventYear":2024,"numberOfCreators":4,"category":"conference","sources":["https://dblp.org/rec/conf/eccv/ZhangKSC24","https://doi.org/10.1007/978-3-031-73337-6_11"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2024,"sourceUrl":"https://dblp.org/rec/conf/eccv/ZhangKSC24","documentUrl":null,"type":"Inproceedings"},{"key":"conf/emnlp/WangZYHSZ25","url":"https://dblp.org/rec/conf/emnlp/WangZYHSZ25","title":"Evaluating Cognitive-Behavioral Fixation via Multimodal User Viewing Patterns on Social Media.","year":2025,"types":["Inproceedings"],"venue":"EMNLP","doi":"https://doi.org/10.18653/V1/2025.EMNLP-MAIN.987","eventYear":2025,"numberOfCreators":6,"category":"conference","sources":["https://dblp.org/rec/conf/emnlp/WangZYHSZ25","https://doi.org/10.18653/V1/2025.EMNLP-MAIN.987"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/emnlp/WangZYHSZ25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/fgr/HanH0S25","url":"https://dblp.org/rec/conf/fgr/HanH0S25","title":"Dual-Branch Partial Annotation Learning for Facial Attributes Recognition.","year":2025,"types":["Inproceedings"],"venue":"FG","doi":"https://doi.org/10.1109/FG61629.2025.11099151","eventYear":2025,"numberOfCreators":4,"category":"conference","sources":["https://dblp.org/rec/conf/fgr/HanH0S25","https://doi.org/10.1109/FG61629.2025.11099151"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/fgr/HanH0S25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/fgr/LuoYS025","url":"https://dblp.org/rec/conf/fgr/LuoYS025","title":"Dynamic Visual Speaking Patterns: You Are the Way You Speak.","year":2025,"types":["Inproceedings"],"venue":"FG","doi":"https://doi.org/10.1109/FG61629.2025.11099168","eventYear":2025,"numberOfCreators":4,"category":"conference","sources":["https://dblp.org/rec/conf/fgr/LuoYS025","https://doi.org/10.1109/FG61629.2025.11099168"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/fgr/LuoYS025","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iccv/CaiHWSC25","url":"https://dblp.org/rec/conf/iccv/CaiHWSC25","title":"EfficientMT: Efficient Temporal Adaptation for Motion Transfer in Text-To-Video Diffusion Models.","year":2025,"types":["Inproceedings"],"venue":"ICCV","doi":"https://doi.org/10.1109/ICCV51701.2025.00986","eventYear":2025,"numberOfCreators":5,"category":"conference","sources":["https://dblp.org/rec/conf/iccv/CaiHWSC25","https://doi.org/10.1109/ICCV51701.2025.00986"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/CaiHWSC25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iccv/LiuGCLSC25","url":"https://dblp.org/rec/conf/iccv/LiuGCLSC25","title":"G2PDiffusion: Cross-Species Genotype-to-Phenotype Prediction Via Evolutionary Diffusion.","year":2025,"types":["Inproceedings"],"venue":"ICCV","doi":"https://doi.org/10.1109/ICCV51701.2025.01925","eventYear":2025,"numberOfCreators":6,"category":"conference","sources":["https://dblp.org/rec/conf/iccv/LiuGCLSC25","https://doi.org/10.1109/ICCV51701.2025.01925"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/LiuGCLSC25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iccv/QiuKZS25","url":"https://dblp.org/rec/conf/iccv/QiuKZS25","title":"Benchmarking Multimodal Large Language Models Against Image Corruptions.","year":2025,"types":["Inproceedings"],"venue":"ICCV","doi":"https://doi.org/10.1109/ICCV51701.2025.00843","eventYear":2025,"numberOfCreators":4,"category":"conference","sources":["https://dblp.org/rec/conf/iccv/QiuKZS25","https://doi.org/10.1109/ICCV51701.2025.00843"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/QiuKZS25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iccv/WangYSC25","url":"https://dblp.org/rec/conf/iccv/WangYSC25","title":"CogCM: Cognition-Inspired Contextual Modeling for Audio-Visual Speech Enhancement.","year":2025,"types":["Inproceedings"],"venue":"ICCV","doi":"https://doi.org/10.1109/ICCV51701.2025.01988","eventYear":2025,"numberOfCreators":4,"category":"conference","sources":["https://dblp.org/rec/conf/iccv/WangYSC25","https://doi.org/10.1109/ICCV51701.2025.01988"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/WangYSC25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iccv/XueKSC25","url":"https://dblp.org/rec/conf/iccv/XueKSC25","title":"Feature Decomposition-Recomposition in Large Vision-Language Model for Few-Shot Class-Incremental Learning.","year":2025,"types":["Inproceedings"],"venue":"ICCV","doi":"https://doi.org/10.1109/ICCV51701.2025.00302","eventYear":2025,"numberOfCreators":4,"category":"conference","sources":["https://dblp.org/rec/conf/iccv/XueKSC25","https://doi.org/10.1109/ICCV51701.2025.00302"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/XueKSC25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iccv/YuanYSC25","url":"https://dblp.org/rec/conf/iccv/YuanYSC25","title":"Not Only Vision: Evolve Visual Speech Recognition via Peripheral Information.","year":2025,"types":["Inproceedings"],"venue":"ICCV","doi":"https://doi.org/10.1109/ICCV51701.2025.00296","eventYear":2025,"numberOfCreators":4,"category":"conference","sources":["https://dblp.org/rec/conf/iccv/YuanYSC25","https://doi.org/10.1109/ICCV51701.2025.00296"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/YuanYSC25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iccv/ZhaoHTCS25","url":"https://dblp.org/rec/conf/iccv/ZhaoHTCS25","title":"HIS-GPT: Towards 3D Human-In-Scene Multimodal Understanding.","year":2025,"types":["Inproceedings"],"venue":"ICCV","doi":"https://doi.org/10.1109/ICCV51701.2025.00411","eventYear":2025,"numberOfCreators":5,"category":"conference","sources":["https://dblp.org/rec/conf/iccv/ZhaoHTCS25","https://doi.org/10.1109/ICCV51701.2025.00411"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/ZhaoHTCS25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iclr/DengPDLCLSQW25","url":"https://dblp.org/rec/conf/iclr/DengPDLCLSQW25","title":"Autoregressive Video Generation without Vector Quantization.","year":2025,"types":["Inproceedings"],"venue":"ICLR","doi":null,"eventYear":2025,"numberOfCreators":9,"category":"conference","sources":["https://dblp.org/rec/conf/iclr/DengPDLCLSQW25"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iclr/DengPDLCLSQW25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iclr/XuHS025","url":"https://dblp.org/rec/conf/iclr/XuHS025","title":"CtrLoRA: An Extensible and Efficient Framework for Controllable Image Generation.","year":2025,"types":["Inproceedings"],"venue":"ICLR","doi":null,"eventYear":2025,"numberOfCreators":4,"category":"conference","sources":["https://dblp.org/rec/conf/iclr/XuHS025"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iclr/XuHS025","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iclr/ZhangWL0YS025","url":"https://dblp.org/rec/conf/iclr/ZhangWL0YS025","title":"Dysca: A Dynamic and Scalable Benchmark for Evaluating Perception Ability of LVLMs.","year":2025,"types":["Inproceedings"],"venue":"ICLR","doi":null,"eventYear":2025,"numberOfCreators":7,"category":"conference","sources":["https://dblp.org/rec/conf/iclr/ZhangWL0YS025"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iclr/ZhangWL0YS025","documentUrl":null,"type":"Inproceedings"},{"key":"conf/icml/0022H0S025","url":"https://dblp.org/rec/conf/icml/0022H0S025","title":"MATS: An Audio Language Model under Text-only Supervision.","year":2025,"types":["Inproceedings"],"venue":"ICML","doi":null,"eventYear":2025,"numberOfCreators":5,"category":"conference","sources":["https://dblp.org/rec/conf/icml/0022H0S025"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/icml/0022H0S025","documentUrl":null,"type":"Inproceedings"},{"key":"conf/icpr/XuKJBSC24","url":"https://dblp.org/rec/conf/icpr/XuKJBSC24","title":"Collaborative Domain Alignment for Multi-source Domain Adaptation.","year":2025,"types":["Inproceedings"],"venue":"ICPR (27)","doi":"https://doi.org/10.1007/978-3-031-78398-2_13","eventYear":2024,"numberOfCreators":6,"category":"conference","sources":["https://dblp.org/rec/conf/icpr/XuKJBSC24","https://doi.org/10.1007/978-3-031-78398-2_13"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2024,"sourceUrl":"https://dblp.org/rec/conf/icpr/XuKJBSC24","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iros/LiangKSC25","url":"https://dblp.org/rec/conf/iros/LiangKSC25","title":"Task-Oriented Token Pruning for Efficient Object Detection and Segmentation.","year":2025,"types":["Inproceedings"],"venue":"IROS","doi":"https://doi.org/10.1109/IROS60139.2025.11246298","eventYear":2025,"numberOfCreators":4,"category":"conference","sources":["https://dblp.org/rec/conf/iros/LiangKSC25","https://doi.org/10.1109/IROS60139.2025.11246298"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iros/LiangKSC25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/mm/YanCM0WWS25","url":"https://dblp.org/rec/conf/mm/YanCM0WWS25","title":"SHALE: A Scalable Benchmark for Fine-grained Hallucination Evaluation in LVLMs.","year":2025,"types":["Inproceedings"],"venue":"ACM Multimedia","doi":"https://doi.org/10.1145/3746027.3758308","eventYear":2025,"numberOfCreators":7,"category":"conference","sources":["https://dblp.org/rec/conf/mm/YanCM0WWS25","https://doi.org/10.1145/3746027.3758308"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/mm/YanCM0WWS25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/nips/LiZCHSC25","url":"https://dblp.org/rec/conf/nips/LiZCHSC25","title":"un2CLIP: Improving CLIP's Visual Detail Capturing Ability via Inverting unCLIP.","year":2025,"types":["Inproceedings"],"venue":"NeurIPS","doi":null,"eventYear":2025,"numberOfCreators":6,"category":"conference","sources":["https://dblp.org/rec/conf/nips/LiZCHSC25"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/nips/LiZCHSC25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/nips/LiangHHCSC25","url":"https://dblp.org/rec/conf/nips/LiangHHCSC25","title":"Revisiting Logit Distributions for Reliable Out-of-Distribution Detection.","year":2025,"types":["Inproceedings"],"venue":"NeurIPS","doi":null,"eventYear":2025,"numberOfCreators":6,"category":"conference","sources":["https://dblp.org/rec/conf/nips/LiangHHCSC25"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/nips/LiangHHCSC25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/nips/LiuCGCTSC25","url":"https://dblp.org/rec/conf/nips/LiuCGCTSC25","title":"ProtInvTree: Deliberate Protein Inverse Folding with Reward-guided Tree Search.","year":2025,"types":["Inproceedings"],"venue":"NeurIPS","doi":null,"eventYear":2025,"numberOfCreators":7,"category":"conference","sources":["https://dblp.org/rec/conf/nips/LiuCGCTSC25"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/nips/LiuCGCTSC25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/nips/YangCHSC25","url":"https://dblp.org/rec/conf/nips/YangCHSC25","title":"KnowMol: Advancing Molecular Large Language Models with Multi-Level Chemical Knowledge.","year":2025,"types":["Inproceedings"],"venue":"NeurIPS","doi":null,"eventYear":2025,"numberOfCreators":5,"category":"conference","sources":["https://dblp.org/rec/conf/nips/YangCHSC25"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/nips/YangCHSC25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/repss/YangZYLGDSZHL25","url":"https://dblp.org/rec/conf/repss/YangZYLGDSZHL25","title":"The 4th Vision-based Remote Physiological Signal Sensing (RePSS) Challenge & Workshop.","year":2025,"types":["Inproceedings"],"venue":"RePSS@IJCAI","doi":null,"eventYear":2025,"numberOfCreators":10,"category":"conference","sources":["https://dblp.org/rec/conf/repss/YangZYLGDSZHL25"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/repss/YangZYLGDSZHL25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/wacv/ZhangHKS25","url":"https://dblp.org/rec/conf/wacv/ZhangHKS25","title":"Precise Integral in NeRFs: Overcoming the Approximation Errors of Numerical Quadrature.","year":2025,"types":["Inproceedings"],"venue":"WACV","doi":"https://doi.org/10.1109/WACV61041.2025.00041","eventYear":2025,"numberOfCreators":4,"category":"conference","sources":["https://dblp.org/rec/conf/wacv/ZhangHKS25","https://doi.org/10.1109/WACV61041.2025.00041"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/wacv/ZhangHKS25","documentUrl":null,"type":"Inproceedings"},{"key":"journals/chinaf/PanTWLS25","url":"https://dblp.org/rec/journals/chinaf/PanTWLS25","title":"Consistent multimodal pre-training for visual tokenization.","year":2025,"types":["Article"],"venue":"Sci. China Inf. Sci.","doi":"https://doi.org/10.1007/S11432-024-4603-X","numberOfCreators":5,"category":"journal","sources":["https://dblp.org/rec/journals/chinaf/PanTWLS25","https://doi.org/10.1007/S11432-024-4603-X"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/chinaf/PanTWLS25","documentUrl":null,"type":"Article"},{"key":"journals/pami/LiCSC25","url":"https://dblp.org/rec/journals/pami/LiCSC25","title":"PIT: A Plug-and-Play Image Translator for Making Off-the-Shelf Models Adapt to Corruptions.","year":2025,"types":["Article"],"venue":"IEEE Trans. Pattern Anal. Mach. Intell.","doi":"https://doi.org/10.1109/TPAMI.2025.3598147","numberOfCreators":4,"category":"journal","sources":["https://dblp.org/rec/journals/pami/LiCSC25","https://doi.org/10.1109/TPAMI.2025.3598147"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/pami/LiCSC25","documentUrl":null,"type":"Article"},{"key":"journals/pami/LiSCSS25","url":"https://dblp.org/rec/journals/pami/LiSCSS25","title":"Instance-Consistent Fair Face Recognition.","year":2025,"types":["Article"],"venue":"IEEE Trans. Pattern Anal. Mach. Intell.","doi":"https://doi.org/10.1109/TPAMI.2025.3545781","numberOfCreators":5,"category":"journal","sources":["https://dblp.org/rec/journals/pami/LiSCSS25","https://doi.org/10.1109/TPAMI.2025.3545781"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/pami/LiSCSS25","documentUrl":null,"type":"Article"},{"key":"journals/pami/LongZS25","url":"https://dblp.org/rec/journals/pami/LongZS25","title":"Generalized Face Liveness Detection via De-Fake Face Generator.","year":2025,"types":["Article"],"venue":"IEEE Trans. Pattern Anal. Mach. Intell.","doi":"https://doi.org/10.1109/TPAMI.2024.3507101","numberOfCreators":3,"category":"journal","sources":["https://dblp.org/rec/journals/pami/LongZS25","https://doi.org/10.1109/TPAMI.2024.3507101"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/pami/LongZS25","documentUrl":null,"type":"Article"},{"key":"journals/pami/XieHSC25","url":"https://dblp.org/rec/journals/pami/XieHSC25","title":"Natural Adversarial Mask for Face Identity Protection in Physical World.","year":2025,"types":["Article"],"venue":"IEEE Trans. Pattern Anal. Mach. Intell.","doi":"https://doi.org/10.1109/TPAMI.2024.3522994","numberOfCreators":4,"category":"journal","sources":["https://dblp.org/rec/journals/pami/XieHSC25","https://doi.org/10.1109/TPAMI.2024.3522994"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/pami/XieHSC25","documentUrl":null,"type":"Article"},{"key":"journals/pami/ZhangYCZHSG25","url":"https://dblp.org/rec/journals/pami/ZhangYCZHSG25","title":"StylizedGS: Controllable Stylization for 3D Gaussian Splatting.","year":2025,"types":["Article"],"venue":"IEEE Trans. Pattern Anal. Mach. Intell.","doi":"https://doi.org/10.1109/TPAMI.2025.3604010","numberOfCreators":7,"category":"journal","sources":["https://dblp.org/rec/journals/pami/ZhangYCZHSG25","https://doi.org/10.1109/TPAMI.2025.3604010"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/pami/ZhangYCZHSG25","documentUrl":null,"type":"Article"},{"key":"journals/pr/ShiZJBS25","url":"https://dblp.org/rec/journals/pr/ShiZJBS25","title":"Real face foundation representation learning for generalized deepfake detection.","year":2025,"types":["Article"],"venue":"Pattern Recognit.","doi":"https://doi.org/10.1016/J.PATCOG.2024.111299","numberOfCreators":5,"category":"journal","sources":["https://dblp.org/rec/journals/pr/ShiZJBS25","https://doi.org/10.1016/J.PATCOG.2024.111299"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/pr/ShiZJBS25","documentUrl":null,"type":"Article"},{"key":"journals/pr/SunHSH25","url":"https://dblp.org/rec/journals/pr/SunHSH25","title":"Leveraging face-prior knowledge for general face representation learning.","year":2025,"types":["Article"],"venue":"Pattern Recognit.","doi":"https://doi.org/10.1016/J.PATCOG.2025.111784","numberOfCreators":4,"category":"journal","sources":["https://dblp.org/rec/journals/pr/SunHSH25","https://doi.org/10.1016/J.PATCOG.2025.111784"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/pr/SunHSH25","documentUrl":null,"type":"Article"},{"key":"journals/pr/YuanZS25","url":"https://dblp.org/rec/journals/pr/YuanZS25","title":"Exp-VQA: Fine-grained facial expression analysis via visual question answering.","year":2025,"types":["Article"],"venue":"Pattern Recognit.","doi":"https://doi.org/10.1016/J.PATCOG.2025.111783","numberOfCreators":3,"category":"journal","sources":["https://dblp.org/rec/journals/pr/YuanZS25","https://doi.org/10.1016/J.PATCOG.2025.111783"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/pr/YuanZS25","documentUrl":null,"type":"Article"},{"key":"journals/prl/HuCSC25","url":"https://dblp.org/rec/journals/prl/HuCSC25","title":"Inference Calibration of Vision-Language Foundation Models for Zero-Shot and Few-Shot Learning.","year":2025,"types":["Article"],"venue":"Pattern Recognit. Lett.","doi":"https://doi.org/10.1016/J.PATREC.2025.03.010","numberOfCreators":4,"category":"journal","sources":["https://dblp.org/rec/journals/prl/HuCSC25","https://doi.org/10.1016/J.PATREC.2025.03.010"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/prl/HuCSC25","documentUrl":null,"type":"Article"},{"key":"journals/taffco/ChenLSWH25","url":"https://dblp.org/rec/journals/taffco/ChenLSWH25","title":"From Static to Dynamic: Adapting Landmark-Aware Image Models for Facial Expression Recognition in Videos.","year":2025,"types":["Article"],"venue":"IEEE Trans. Affect. Comput.","doi":"https://doi.org/10.1109/TAFFC.2024.3453443","numberOfCreators":5,"category":"journal","sources":["https://dblp.org/rec/journals/taffco/ChenLSWH25","https://doi.org/10.1109/TAFFC.2024.3453443"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/taffco/ChenLSWH25","documentUrl":null,"type":"Article"},{"key":"journals/taffco/LiuWLCCTCS25","url":"https://dblp.org/rec/journals/taffco/LiuWLCCTCS25","title":"Leveraging Eye Movement for Instructing Robust Video-Based Facial Expression Recognition.","year":2025,"types":["Article"],"venue":"IEEE Trans. Affect. Comput.","doi":"https://doi.org/10.1109/TAFFC.2025.3599859","numberOfCreators":8,"category":"journal","sources":["https://dblp.org/rec/journals/taffco/LiuWLCCTCS25","https://doi.org/10.1109/TAFFC.2025.3599859"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/taffco/LiuWLCCTCS25","documentUrl":null,"type":"Article"},{"key":"journals/taffco/ZengYQCSGHLZLSC25","url":"https://dblp.org/rec/journals/taffco/ZengYQCSGHLZLSC25","title":"Multi-View Facial Expressions Analysis of Autistic Children in Social Play.","year":2025,"types":["Article"],"venue":"IEEE Trans. Affect. Comput.","doi":"https://doi.org/10.1109/TAFFC.2025.3557458","numberOfCreators":12,"category":"journal","sources":["https://dblp.org/rec/journals/taffco/ZengYQCSGHLZLSC25","https://doi.org/10.1109/TAFFC.2025.3557458"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/taffco/ZengYQCSGHLZLSC25","documentUrl":null,"type":"Article"},{"key":"journals/tase/KanZLZFLSC25","url":"https://dblp.org/rec/journals/tase/KanZLZFLSC25","title":"eLabrador: A Wearable Navigation System for Visually Impaired Individuals.","year":2025,"types":["Article"],"venue":"IEEE Trans Autom. Sci. Eng.","doi":"https://doi.org/10.1109/TASE.2025.3541055","numberOfCreators":8,"category":"journal","sources":["https://dblp.org/rec/journals/tase/KanZLZFLSC25","https://doi.org/10.1109/TASE.2025.3541055"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/tase/KanZLZFLSC25","documentUrl":null,"type":"Article"},{"key":"journals/tifs/LongZS25","url":"https://dblp.org/rec/journals/tifs/LongZS25","title":"Confidence Aware Learning for Reliable Face Anti-Spoofing.","year":2025,"types":["Article"],"venue":"IEEE Trans. Inf. Forensics Secur.","doi":"https://doi.org/10.1109/TIFS.2025.3564878","numberOfCreators":3,"category":"journal","sources":["https://dblp.org/rec/journals/tifs/LongZS25","https://doi.org/10.1109/TIFS.2025.3564878"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/tifs/LongZS25","documentUrl":null,"type":"Article"},{"key":"journals/tifs/ZhangWHLWS25","url":"https://dblp.org/rec/journals/tifs/ZhangWHLWS25","title":"Collaboratively Self-Supervised Video Representation Learning for Action Recognition.","year":2025,"types":["Article"],"venue":"IEEE Trans. Inf. Forensics Secur.","doi":"https://doi.org/10.1109/TIFS.2025.3531772","numberOfCreators":6,"category":"journal","sources":["https://dblp.org/rec/journals/tifs/ZhangWHLWS25","https://doi.org/10.1109/TIFS.2025.3531772"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/tifs/ZhangWHLWS25","documentUrl":null,"type":"Article"},{"key":"journals/tip/LiLCDZZSG25","url":"https://dblp.org/rec/journals/tip/LiLCDZZSG25","title":"Decoupled Doubly Contrastive Learning for Cross-Domain Facial Action Unit Detection.","year":2025,"types":["Article"],"venue":"IEEE Trans. Image Process.","doi":"https://doi.org/10.1109/TIP.2025.3546479","numberOfCreators":8,"category":"journal","sources":["https://dblp.org/rec/journals/tip/LiLCDZZSG25","https://doi.org/10.1109/TIP.2025.3546479"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/tip/LiLCDZZSG25","documentUrl":null,"type":"Article"},{"key":"journals/tip/YuanZSC25","url":"https://dblp.org/rec/journals/tip/YuanZSC25","title":"FullLoRA: Efficiently Boosting the Robustness of Pretrained Vision Transformers.","year":2025,"types":["Article"],"venue":"IEEE Trans. Image Process.","doi":"https://doi.org/10.1109/TIP.2025.3587598","numberOfCreators":4,"category":"journal","sources":["https://dblp.org/rec/journals/tip/YuanZSC25","https://doi.org/10.1109/TIP.2025.3587598"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/tip/YuanZSC25","documentUrl":null,"type":"Article"},{"key":"journals/tmm/ZhaoHCGMSC25","url":"https://dblp.org/rec/journals/tmm/ZhaoHCGMSC25","title":"Clothes-Changing Person Re-Identification With Feasibility-Aware Intermediary Matching.","year":2025,"types":["Article"],"venue":"IEEE Trans. Multim.","doi":"https://doi.org/10.1109/TMM.2025.3535357","numberOfCreators":7,"category":"journal","sources":["https://dblp.org/rec/journals/tmm/ZhaoHCGMSC25","https://doi.org/10.1109/TMM.2025.3535357"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/tmm/ZhaoHCGMSC25","documentUrl":null,"type":"Article"}],"preprints":[{"key":"journals/corr/abs-2502-04684","url":"https://dblp.org/rec/journals/corr/abs-2502-04684","title":"G2PDiffusion: Genotype-to-Phenotype Prediction with Diffusion Models.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2502.04684","numberOfCreators":6,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2502-04684","https://doi.org/10.48550/ARXIV.2502.04684"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2502-04684","documentUrl":null,"type":"Informal","arxivId":"2502.04684","arxivUrl":"https://arxiv.org/abs/2502.04684"},{"key":"journals/corr/abs-2502-13433","url":"https://dblp.org/rec/journals/corr/abs-2502-13433","title":"MATS: An Audio Language Model under Text-only Supervision.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2502.13433","numberOfCreators":5,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2502-13433","https://doi.org/10.48550/ARXIV.2502.13433"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2502-13433","documentUrl":null,"type":"Informal","arxivId":"2502.13433","arxivUrl":"https://arxiv.org/abs/2502.13433"},{"key":"journals/corr/abs-2503-06236","url":"https://dblp.org/rec/journals/corr/abs-2503-06236","title":"Dynamically evolving segment anything model with continuous learning for medical image segmentation.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2503.06236","numberOfCreators":6,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2503-06236","https://doi.org/10.48550/ARXIV.2503.06236"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-06236","documentUrl":null,"type":"Informal","arxivId":"2503.06236","arxivUrl":"https://arxiv.org/abs/2503.06236"},{"key":"journals/corr/abs-2503-08977","url":"https://dblp.org/rec/journals/corr/abs-2503-08977","title":"Decoupled Doubly Contrastive Learning for Cross Domain Facial Action Unit Detection.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2503.08977","numberOfCreators":8,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2503-08977","https://doi.org/10.48550/ARXIV.2503.08977"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-08977","documentUrl":null,"type":"Informal","arxivId":"2503.08977","arxivUrl":"https://arxiv.org/abs/2503.08977"},{"key":"journals/corr/abs-2503-12955","url":"https://dblp.org/rec/journals/corr/abs-2503-12955","title":"HIS-GPT: Towards 3D Human-In-Scene Multimodal Understanding.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2503.12955","numberOfCreators":5,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2503-12955","https://doi.org/10.48550/ARXIV.2503.12955"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-12955","documentUrl":null,"type":"Informal","arxivId":"2503.12955","arxivUrl":"https://arxiv.org/abs/2503.12955"},{"key":"journals/corr/abs-2503-16566","url":"https://dblp.org/rec/journals/corr/abs-2503-16566","title":"REVAL: A Comprehension Evaluation on Reliability and Values of Large Vision-Language Models.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2503.16566","numberOfCreators":9,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2503-16566","https://doi.org/10.48550/ARXIV.2503.16566"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-16566","documentUrl":null,"type":"Informal","arxivId":"2503.16566","arxivUrl":"https://arxiv.org/abs/2503.16566"},{"key":"journals/corr/abs-2503-17724","url":"https://dblp.org/rec/journals/corr/abs-2503-17724","title":"Towards Invisible Backdoor Attack on Text-to-Image Diffusion Model.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2503.17724","numberOfCreators":4,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2503-17724","https://doi.org/10.48550/ARXIV.2503.17724"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-17724","documentUrl":null,"type":"Informal","arxivId":"2503.17724","arxivUrl":"https://arxiv.org/abs/2503.17724"},{"key":"journals/corr/abs-2503-19369","url":"https://dblp.org/rec/journals/corr/abs-2503-19369","title":"EfficientMT: Efficient Temporal Adaptation for Motion Transfer in Text-to-Video Diffusion Models.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2503.19369","numberOfCreators":5,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2503-19369","https://doi.org/10.48550/ARXIV.2503.19369"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-19369","documentUrl":null,"type":"Informal","arxivId":"2503.19369","arxivUrl":"https://arxiv.org/abs/2503.19369"},{"key":"journals/corr/abs-2504-17253","url":"https://dblp.org/rec/journals/corr/abs-2504-17253","title":"DIVE: Inverting Conditional Diffusion Models for Discriminative Tasks.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2504.17253","numberOfCreators":5,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2504-17253","https://doi.org/10.48550/ARXIV.2504.17253"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2504-17253","documentUrl":null,"type":"Informal","arxivId":"2504.17253","arxivUrl":"https://arxiv.org/abs/2504.17253"},{"key":"journals/corr/abs-2504-20518","url":"https://dblp.org/rec/journals/corr/abs-2504-20518","title":"Dynamic Attention Analysis for Backdoor Detection in Text-to-Image Diffusion Models.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2504.20518","numberOfCreators":4,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2504-20518","https://doi.org/10.48550/ARXIV.2504.20518"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2504-20518","documentUrl":null,"type":"Informal","arxivId":"2504.20518","arxivUrl":"https://arxiv.org/abs/2504.20518"},{"key":"journals/corr/abs-2505-17659","url":"https://dblp.org/rec/journals/corr/abs-2505-17659","title":"Plan-R1: Safe and Feasible Trajectory Planning as Language Modeling.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2505.17659","numberOfCreators":4,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2505-17659","https://doi.org/10.48550/ARXIV.2505.17659"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-17659","documentUrl":null,"type":"Informal","arxivId":"2505.17659","arxivUrl":"https://arxiv.org/abs/2505.17659"},{"key":"journals/corr/abs-2505-19084","url":"https://dblp.org/rec/journals/corr/abs-2505-19084","title":"Jodi: Unification of Visual Generation and Understanding via Joint Modeling.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2505.19084","numberOfCreators":5,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2505-19084","https://doi.org/10.48550/ARXIV.2505.19084"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-19084","documentUrl":null,"type":"Informal","arxivId":"2505.19084","arxivUrl":"https://arxiv.org/abs/2505.19084"},{"key":"journals/corr/abs-2505-24517","url":"https://dblp.org/rec/journals/corr/abs-2505-24517","title":"un2CLIP: Improving CLIP's Visual Detail Capturing Ability via Inverting unCLIP.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2505.24517","numberOfCreators":6,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2505-24517","https://doi.org/10.48550/ARXIV.2505.24517"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-24517","documentUrl":null,"type":"Informal","arxivId":"2505.24517","arxivUrl":"https://arxiv.org/abs/2505.24517"},{"key":"journals/corr/abs-2506-00925","url":"https://dblp.org/rec/journals/corr/abs-2506-00925","title":"ProtInvTree: Deliberate Protein Inverse Folding with Reward-guided Tree Search.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2506.00925","numberOfCreators":7,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2506-00925","https://doi.org/10.48550/ARXIV.2506.00925"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-00925","documentUrl":null,"type":"Informal","arxivId":"2506.00925","arxivUrl":"https://arxiv.org/abs/2506.00925"},{"key":"journals/corr/abs-2507-19024","url":"https://dblp.org/rec/journals/corr/abs-2507-19024","title":"A Survey of Multimodal Hallucination Evaluation and Detection.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2507.19024","numberOfCreators":7,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2507-19024","https://doi.org/10.48550/ARXIV.2507.19024"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2507-19024","documentUrl":null,"type":"Informal","arxivId":"2507.19024","arxivUrl":"https://arxiv.org/abs/2507.19024"},{"key":"journals/corr/abs-2508-09584","url":"https://dblp.org/rec/journals/corr/abs-2508-09584","title":"SHALE: A Scalable Benchmark for Fine-grained Hallucination Evaluation in LVLMs.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2508.09584","numberOfCreators":7,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2508-09584","https://doi.org/10.48550/ARXIV.2508.09584"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-09584","documentUrl":null,"type":"Informal","arxivId":"2508.09584","arxivUrl":"https://arxiv.org/abs/2508.09584"},{"key":"journals/corr/abs-2508-10268","url":"https://dblp.org/rec/journals/corr/abs-2508-10268","title":"Pose-Robust Calibration Strategy for Point-of-Gaze Estimation on Mobile Phones.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2508.10268","numberOfCreators":3,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2508-10268","https://doi.org/10.48550/ARXIV.2508.10268"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-10268","documentUrl":null,"type":"Informal","arxivId":"2508.10268","arxivUrl":"https://arxiv.org/abs/2508.10268"},{"key":"journals/corr/abs-2508-13692","url":"https://dblp.org/rec/journals/corr/abs-2508-13692","title":"HumanPCR: Probing MLLM Capabilities in Diverse Human-Centric Scenes.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2508.13692","numberOfCreators":12,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2508-13692","https://doi.org/10.48550/ARXIV.2508.13692"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-13692","documentUrl":null,"type":"Informal","arxivId":"2508.13692","arxivUrl":"https://arxiv.org/abs/2508.13692"},{"key":"journals/corr/abs-2509-04823","url":"https://dblp.org/rec/journals/corr/abs-2509-04823","title":"Evaluating Cognitive-Behavioral Fixation via Multimodal User Viewing Patterns on Social Media.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2509.04823","numberOfCreators":6,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2509-04823","https://doi.org/10.48550/ARXIV.2509.04823"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-04823","documentUrl":null,"type":"Informal","arxivId":"2509.04823","arxivUrl":"https://arxiv.org/abs/2509.04823"},{"key":"journals/corr/abs-2509-16031","url":"https://dblp.org/rec/journals/corr/abs-2509-16031","title":"GLip: A Global-Local Integrated Progressive Framework for Robust Visual Speech Recognition.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2509.16031","numberOfCreators":4,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2509-16031","https://doi.org/10.48550/ARXIV.2509.16031"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-16031","documentUrl":null,"type":"Informal","arxivId":"2509.16031","arxivUrl":"https://arxiv.org/abs/2509.16031"},{"key":"journals/corr/abs-2509-23635","url":"https://dblp.org/rec/journals/corr/abs-2509-23635","title":"MotionVerse: A Unified Multimodal Framework for Motion Comprehension, Generation and Editing.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2509.23635","numberOfCreators":5,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2509-23635","https://doi.org/10.48550/ARXIV.2509.23635"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-23635","documentUrl":null,"type":"Informal","arxivId":"2509.23635","arxivUrl":"https://arxiv.org/abs/2509.23635"},{"key":"journals/corr/abs-2510-19484","url":"https://dblp.org/rec/journals/corr/abs-2510-19484","title":"KnowMol: Advancing Molecular Large Language Models with Multi-Level Chemical Knowledge.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2510.19484","numberOfCreators":5,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2510-19484","https://doi.org/10.48550/ARXIV.2510.19484"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-19484","documentUrl":null,"type":"Informal","arxivId":"2510.19484","arxivUrl":"https://arxiv.org/abs/2510.19484"},{"key":"journals/corr/abs-2510-20134","url":"https://dblp.org/rec/journals/corr/abs-2510-20134","title":"Revisiting Logit Distributions for Reliable Out-of-Distribution Detection.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2510.20134","numberOfCreators":6,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2510-20134","https://doi.org/10.48550/ARXIV.2510.20134"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-20134","documentUrl":null,"type":"Informal","arxivId":"2510.20134","arxivUrl":"https://arxiv.org/abs/2510.20134"},{"key":"journals/corr/abs-2510-24717","url":"https://dblp.org/rec/journals/corr/abs-2510-24717","title":"Uniform Discrete Diffusion with Metric Path for Video Generation.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2510.24717","numberOfCreators":11,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2510-24717","https://doi.org/10.48550/ARXIV.2510.24717"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-24717","documentUrl":null,"type":"Informal","arxivId":"2510.24717","arxivUrl":"https://arxiv.org/abs/2510.24717"},{"key":"journals/corr/abs-2511-13420","url":"https://dblp.org/rec/journals/corr/abs-2511-13420","title":"VOPE: Revisiting Hallucination of Vision-Language Models in Voluntary Imagination Task.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2511.13420","numberOfCreators":4,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2511-13420","https://doi.org/10.48550/ARXIV.2511.13420"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2511-13420","documentUrl":null,"type":"Informal","arxivId":"2511.13420","arxivUrl":"https://arxiv.org/abs/2511.13420"},{"key":"journals/corr/abs-2511-20223","url":"https://dblp.org/rec/journals/corr/abs-2511-20223","title":"V-Attack: Targeting Disentangled Value Features for Controllable Adversarial Attacks on LVLMs.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2511.20223","numberOfCreators":5,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2511-20223","https://doi.org/10.48550/ARXIV.2511.20223"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2511-20223","documentUrl":null,"type":"Informal","arxivId":"2511.20223","arxivUrl":"https://arxiv.org/abs/2511.20223"},{"key":"journals/corr/abs-2512-00343","url":"https://dblp.org/rec/journals/corr/abs-2512-00343","title":"Assimilation Matters: Model-level Backdoor Detection in Vision-Language Pretrained Models.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2512.00343","numberOfCreators":4,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2512-00343","https://doi.org/10.48550/ARXIV.2512.00343"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-00343","documentUrl":null,"type":"Informal","arxivId":"2512.00343","arxivUrl":"https://arxiv.org/abs/2512.00343"},{"key":"journals/corr/abs-2512-06885","url":"https://dblp.org/rec/journals/corr/abs-2512-06885","title":"JoPano: Unified Panorama Generation via Joint Modeling.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2512.06885","numberOfCreators":6,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2512-06885","https://doi.org/10.48550/ARXIV.2512.06885"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-06885","documentUrl":null,"type":"Informal","arxivId":"2512.06885","arxivUrl":"https://arxiv.org/abs/2512.06885"},{"key":"journals/corr/abs-2512-14320","url":"https://dblp.org/rec/journals/corr/abs-2512-14320","title":"Semantic Mismatch and Perceptual Degradation: A New Perspective on Image Editing Immunity.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2512.14320","numberOfCreators":5,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2512-14320","https://doi.org/10.48550/ARXIV.2512.14320"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-14320","documentUrl":null,"type":"Informal","arxivId":"2512.14320","arxivUrl":"https://arxiv.org/abs/2512.14320"},{"key":"journals/corr/abs-2512-14333","url":"https://dblp.org/rec/journals/corr/abs-2512-14333","title":"Dual Attention Guided Defense Against Malicious Edits.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2512.14333","numberOfCreators":4,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2512-14333","https://doi.org/10.48550/ARXIV.2512.14333"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-14333","documentUrl":null,"type":"Informal","arxivId":"2512.14333","arxivUrl":"https://arxiv.org/abs/2512.14333"},{"key":"journals/corr/abs-2512-14341","url":"https://dblp.org/rec/journals/corr/abs-2512-14341","title":"Towards Transferable Defense Against Malicious Image Edits.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2512.14341","numberOfCreators":4,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2512-14341","https://doi.org/10.48550/ARXIV.2512.14341"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-14341","documentUrl":null,"type":"Informal","arxivId":"2512.14341","arxivUrl":"https://arxiv.org/abs/2512.14341"},{"key":"journals/corr/abs-2512-19022","url":"https://dblp.org/rec/journals/corr/abs-2512-19022","title":"Steering Vision-Language Pre-trained Models for Incremental Face Presentation Attack Detection.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2512.19022","numberOfCreators":5,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2512-19022","https://doi.org/10.48550/ARXIV.2512.19022"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-19022","documentUrl":null,"type":"Informal","arxivId":"2512.19022","arxivUrl":"https://arxiv.org/abs/2512.19022"},{"key":"journals/corr/abs-2512-23953","url":"https://dblp.org/rec/journals/corr/abs-2512-23953","title":"T2VAttack: Adversarial Attack on Text-to-Video Diffusion Models.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2512.23953","numberOfCreators":6,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2512-23953","https://doi.org/10.48550/ARXIV.2512.23953"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-23953","documentUrl":null,"type":"Informal","arxivId":"2512.23953","arxivUrl":"https://arxiv.org/abs/2512.23953"}],"excludedFormal":[],"otherRecords":[{"key":"data/11/LiMZYSC25","url":"https://dblp.org/rec/data/11/LiMZYSC25","title":"T2VAttackBench: A High-Quality Dataset for Adversarial Attack on Text-to-Video Diffusion Models.","year":2025,"types":["Data"],"venue":[],"doi":["https://doi.org/10.21227/GAQ8-K852"],"numberOfCreators":6,"category":"excluded","sources":["https://dblp.org/rec/data/11/LiMZYSC25","https://doi.org/10.21227/GAQ8-K852"],"publicationYear":2025,"eventYear":null}],"matchedName":"Shiguang Shan","databaseLabel":"Shiguang Shan","databaseMetadata":{"type":["https://dblp.org/rdf/schema#Creator","https://dblp.org/rdf/schema#Person"],"label":["Shiguang Shan"],"affiliation":["Chinese Academy of Sciences, Institute of Computing Technology, Beijing, China"],"homepage":["https://openreview.net/profile?id=~Shiguang_Shan2","http://www.jdl.ac.cn/user/sgshan/index_en.htm"],"orcid":["https://orcid.org/0000-0002-8348-392X"],"primaryAffiliation":["Chinese Academy of Sciences, Institute of Computing Technology, Beijing, China"],"primaryHomepage":["http://www.jdl.ac.cn/user/sgshan/index_en.htm"]},"rawFormalRecordCount2025":48,"signatureAudit":{"completedAt":"2026-10-19","frozen":true,"scope":"对 B 组 39 个数值档案的全部 1074 条原始 2025 正式记录扫描 DBLP author-signature ORCID 和机构；复用既有 59 条 Crossref 核验，补查 6 条新触发记录。重点核查不同 ORCID，以及只有预期机构之外机构的条目。本轮不扩展为所有作者逐篇全文审计。","formalRecordCoverage":48,"orcidCounts":{"https://orcid.org/0000-0002-8348-392X":18},"institutionCounts":{"Chinese Academy of Sciences (CAS)":36,"Institute of Computing Technology (ICT)":38,"Peng Cheng Laboratory":3,"University of the Chinese Academy of Sciences (UCAS)":35},"caveat":"机构名称可能由 DBLP 自动映射而失真；多 ORCID 也不自动等于异人。只有有原始资料支撑的错归才作确认排除，未解决分支则暂停总数。"},"labName":"Visual Information Processing and Learning (VIPL)","labUrl":"https://vipl.ict.ac.cn/en/","labEvidence":"中科院计算所 VIPL 官方团队域名内的山世光本人页列其教授身份，团队首页明确 Visual Information Processing and Learning。只表示团队关联，不推断这个较大团队的完整产量。","labSourceUrl":"https://vipl.ict.ac.cn/people/_sgshan/","sourceWarning":false,"excludedOther":[],"excludedHomonyms":[],"unassignedCandidates":[],"knownPreprintMinimum2025":null,"excludedMisattributed":[],"displayNotes":"身份已与原名单机构及公开资料核对确认。2025 年正式记录 48 条（会议 29、期刊 19），所有作者位置均计入，不表示主导或贡献份额；预印本 33 条单列，不加总。","labDisplayNotes":"中科院计算所 VIPL 官方站点的本人页列其为教授，据此归组。VIPL 是规模较大的研究团队，分组只含本人参与的记录。"},{"index":77,"name":"Chunhua Shen","nameZh":"沈春华","role":"Qiushi Chair Professor","affiliation":"Zhejiang University","affiliationZh":"浙江大学","source":"DBLP RDF via official SPARQL; primary-source identity checks","sourceUrl":"https://sparql.dblp.org/","profileUrl":"https://dblp.org/pid/56/1673.html","identifier":"56/1673","retrievedAt":"2026-10-19","count2025":30,"conference2025":23,"journal2025":7,"preprint2025":34,"status":"confirmed","notes":"DBLP 的 primaryAffiliation 含历史机构；以原签名名单机构和本人履历交叉核对，未据旧机构另选同名者。","identityEvidence":[{"url":"https://dblp.org/pid/56/1673.html","evidence":"DBLP RDF 类型为 Person，消歧后名字为 Chunhua Shen。机构元数据含：University of Adelaide, School of Computer Science, Adelaide, Australia"},{"url":"https://cshen.github.io/","evidence":"个人主页为浙江大学 Chunhua Shen，说明此前 Adelaide 经历；DBLP 保留旧机构。"},{"url":"https://cshen.github.io/paper.html","evidence":"个人发表页直接链接 DBLP 56/1673，并与多个 2025 标题匹配。"},{"url":"https://cshen.github.io/paper.html","evidence":"此本人或机构页面的正文与所选档案中 41 条 2025 记录标题匹配，其中 24 条为当前计入的正式记录（忽略空格、标点、大小写）。","matchedPaperKeys":["conf/cvpr/0001LZXF0LSS25","conf/cvpr/ZhuTCZGLYS25","conf/eccv/ChenWYYCS24","conf/eccv/ChuSZS24","conf/iccv/ChanLLLSZ25","conf/iccv/GaoBLCS25","conf/iccv/LiuYJZCXFWLS25","conf/iccv/ZhangGTXCLS25","conf/iccv/ZhuOSP25","conf/iccv/ZhuWZCZLCSPH25","conf/iclr/0015WZOCG0SS25","conf/iclr/BoMSB0MZ0S25","conf/iclr/ChenLJZRC0S25","conf/iclr/JiaoMJY0S25","conf/iclr/XuGLFXZ0S25","conf/iclr/YangH0S00LO025","conf/iclr/ZhaoL0C000S25","conf/icml/00120S25","conf/nips/ZhaoSLZZZCHS25","conf/nips/ZhongZDHZLWCS25","journals/corr/abs-2502-17157","journals/corr/abs-2502-18538","journals/corr/abs-2503-06486","journals/corr/abs-2503-08625","journals/corr/abs-2503-18945","journals/corr/abs-2505-20256","journals/corr/abs-2505-21457","journals/corr/abs-2507-15602","journals/corr/abs-2508-09138","journals/corr/abs-2508-14811","journals/corr/abs-2509-05296","journals/corr/abs-2509-12201","journals/corr/abs-2510-05057","journals/corr/abs-2510-10524","journals/corr/abs-2510-24717","journals/corr/abs-2511-12691","journals/corr/abs-2512-07951","journals/ijcv/LiuWZCHS25","journals/ijcv/LiuZCWFWLVS25","journals/ijcv/WuLHSSCLGZ25","journals/pami/LiuHYDWLSJB25"],"matchedFormalPaperKeys":["conf/cvpr/0001LZXF0LSS25","conf/cvpr/ZhuTCZGLYS25","conf/eccv/ChenWYYCS24","conf/eccv/ChuSZS24","conf/iccv/ChanLLLSZ25","conf/iccv/GaoBLCS25","conf/iccv/LiuYJZCXFWLS25","conf/iccv/ZhangGTXCLS25","conf/iccv/ZhuOSP25","conf/iccv/ZhuWZCZLCSPH25","conf/iclr/0015WZOCG0SS25","conf/iclr/BoMSB0MZ0S25","conf/iclr/ChenLJZRC0S25","conf/iclr/JiaoMJY0S25","conf/iclr/XuGLFXZ0S25","conf/iclr/YangH0S00LO025","conf/iclr/ZhaoL0C000S25","conf/icml/00120S25","conf/nips/ZhaoSLZZZCHS25","conf/nips/ZhongZDHZLWCS25","journals/ijcv/LiuWZCHS25","journals/ijcv/LiuZCWFWLVS25","journals/ijcv/WuLHSSCLGZ25","journals/pami/LiuHYDWLSJB25"]},{"url":"https://www.ijcai.org/proceedings/2025/0143.pdf","evidence":"Seeing the Unseen 原文的 Chunhua Shen 机构为浙江工业大学、邮箱 chhshen@zjut.edu.cn。"},{"url":"https://homepage.zjut.edu.cn/csshen/","evidence":"浙江工业大学官方沈春华主页直接指向本人 cshen.github.io，因此异机构是实际任职/合作背景，并非另一个同名者；保留该文。"}],"papers":[{"key":"conf/aaai/YanLLCCLDYZS25","url":"https://dblp.org/rec/conf/aaai/YanLLCCLDYZS25","title":"TG-LLaVA: Text Guided LLaVA via Learnable Latent Embeddings.","year":2025,"types":["Inproceedings"],"venue":"AAAI","doi":"https://doi.org/10.1609/AAAI.V39I9.32982","eventYear":2025,"numberOfCreators":10,"category":"conference","sources":["https://dblp.org/rec/conf/aaai/YanLLCCLDYZS25","https://doi.org/10.1609/AAAI.V39I9.32982"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/aaai/YanLLCCLDYZS25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/cvpr/0001LZXF0LSS25","url":"https://dblp.org/rec/conf/cvpr/0001LZXF0LSS25","title":"MovieBench: A Hierarchical Movie Level Dataset for Long Video Generation.","year":2025,"types":["Inproceedings"],"venue":"CVPR","doi":"https://doi.org/10.1109/CVPR52734.2025.02699","eventYear":2025,"numberOfCreators":9,"category":"conference","sources":["https://dblp.org/rec/conf/cvpr/0001LZXF0LSS25","https://doi.org/10.1109/CVPR52734.2025.02699"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/0001LZXF0LSS25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/cvpr/ZhuTCZGLYS25","url":"https://dblp.org/rec/conf/cvpr/ZhuTCZGLYS25","title":"SegAgent: Exploring Pixel Understanding Capabilities in MLLMs by Imitating Human Annotator Trajectories.","year":2025,"types":["Inproceedings"],"venue":"CVPR","doi":"https://doi.org/10.1109/CVPR52734.2025.00349","eventYear":2025,"numberOfCreators":8,"category":"conference","sources":["https://dblp.org/rec/conf/cvpr/ZhuTCZGLYS25","https://doi.org/10.1109/CVPR52734.2025.00349"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/ZhuTCZGLYS25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/eccv/ChenWYYCS24","url":"https://dblp.org/rec/conf/eccv/ChenWYYCS24","title":"FreeCompose: Generic Zero-Shot Image Composition with Diffusion Prior.","year":2025,"types":["Inproceedings"],"venue":"ECCV (17)","doi":"https://doi.org/10.1007/978-3-031-72643-9_5","eventYear":2024,"numberOfCreators":6,"category":"conference","sources":["https://dblp.org/rec/conf/eccv/ChenWYYCS24","https://doi.org/10.1007/978-3-031-72643-9_5"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2024,"sourceUrl":"https://dblp.org/rec/conf/eccv/ChenWYYCS24","documentUrl":null,"type":"Inproceedings"},{"key":"conf/eccv/ChuSZS24","url":"https://dblp.org/rec/conf/eccv/ChuSZS24","title":"VisionLLaMA: A Unified LLaMA Backbone for Vision Tasks.","year":2025,"types":["Inproceedings"],"venue":"ECCV (66)","doi":"https://doi.org/10.1007/978-3-031-72848-8_1","eventYear":2024,"numberOfCreators":4,"category":"conference","sources":["https://dblp.org/rec/conf/eccv/ChuSZS24","https://doi.org/10.1007/978-3-031-72848-8_1"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2024,"sourceUrl":"https://dblp.org/rec/conf/eccv/ChuSZS24","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iccv/ChanLLLSZ25","url":"https://dblp.org/rec/conf/iccv/ChanLLLSZ25","title":"SMStracker: Tri-Path Score Mask Sigma Fusion for Multi-Modal Tracking.","year":2025,"types":["Inproceedings"],"venue":"ICCV","doi":"https://doi.org/10.1109/ICCV51701.2025.00453","eventYear":2025,"numberOfCreators":6,"category":"conference","sources":["https://dblp.org/rec/conf/iccv/ChanLLLSZ25","https://doi.org/10.1109/ICCV51701.2025.00453"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/ChanLLLSZ25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iccv/GaoBLCS25","url":"https://dblp.org/rec/conf/iccv/GaoBLCS25","title":"SurfaceSplat: Connecting Surface Reconstruction and Gaussian Splatting.","year":2025,"types":["Inproceedings"],"venue":"ICCV","doi":"https://doi.org/10.1109/ICCV51701.2025.02649","eventYear":2025,"numberOfCreators":5,"category":"conference","sources":["https://dblp.org/rec/conf/iccv/GaoBLCS25","https://doi.org/10.1109/ICCV51701.2025.02649"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/GaoBLCS25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iccv/LiuYJZCXFWLS25","url":"https://dblp.org/rec/conf/iccv/LiuYJZCXFWLS25","title":"Unified Open-World Segmentation with Multi-Modal Prompts.","year":2025,"types":["Inproceedings"],"venue":"ICCV","doi":"https://doi.org/10.1109/ICCV51701.2025.02002","eventYear":2025,"numberOfCreators":10,"category":"conference","sources":["https://dblp.org/rec/conf/iccv/LiuYJZCXFWLS25","https://doi.org/10.1109/ICCV51701.2025.02002"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/LiuYJZCXFWLS25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iccv/ZhangGTXCLS25","url":"https://dblp.org/rec/conf/iccv/ZhangGTXCLS25","title":"POMATO: Marrying Pointmap Matching with Temporal Motions for Dynamic 3D Reconstruction.","year":2025,"types":["Inproceedings"],"venue":"ICCV","doi":"https://doi.org/10.1109/ICCV51701.2025.00538","eventYear":2025,"numberOfCreators":7,"category":"conference","sources":["https://dblp.org/rec/conf/iccv/ZhangGTXCLS25","https://doi.org/10.1109/ICCV51701.2025.00538"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/ZhangGTXCLS25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iccv/ZhuOSP25","url":"https://dblp.org/rec/conf/iccv/ZhuOSP25","title":"Fine-Grained Abnormality Prompt Learning for Zero-Shot Anomaly Detection.","year":2025,"types":["Inproceedings"],"venue":"ICCV","doi":"https://doi.org/10.1109/ICCV51701.2025.02065","eventYear":2025,"numberOfCreators":4,"category":"conference","sources":["https://dblp.org/rec/conf/iccv/ZhuOSP25","https://doi.org/10.1109/ICCV51701.2025.02065"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/ZhuOSP25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iccv/ZhuWZCZLCSPH25","url":"https://dblp.org/rec/conf/iccv/ZhuWZCZLCSPH25","title":"AETHER: Geometric-Aware Unified World Modeling.","year":2025,"types":["Inproceedings"],"venue":"ICCV","doi":"https://doi.org/10.1109/ICCV51701.2025.00799","eventYear":2025,"numberOfCreators":10,"category":"conference","sources":["https://dblp.org/rec/conf/iccv/ZhuWZCZLCSPH25","https://doi.org/10.1109/ICCV51701.2025.00799"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/ZhuWZCZLCSPH25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iclr/0015WZOCG0SS25","url":"https://dblp.org/rec/conf/iclr/0015WZOCG0SS25","title":"Framer: Interactive Frame Interpolation.","year":2025,"types":["Inproceedings"],"venue":"ICLR","doi":null,"eventYear":2025,"numberOfCreators":9,"category":"conference","sources":["https://dblp.org/rec/conf/iclr/0015WZOCG0SS25"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iclr/0015WZOCG0SS25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iclr/BoMSB0MZ0S25","url":"https://dblp.org/rec/conf/iclr/BoMSB0MZ0S25","title":"Revisiting Convolution Architecture in the Realm of DNA Foundation Models.","year":2025,"types":["Inproceedings"],"venue":"ICLR","doi":null,"eventYear":2025,"numberOfCreators":9,"category":"conference","sources":["https://dblp.org/rec/conf/iclr/BoMSB0MZ0S25"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iclr/BoMSB0MZ0S25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iclr/ChenLJZRC0S25","url":"https://dblp.org/rec/conf/iclr/ChenLJZRC0S25","title":"PerturboLLaVA: Reducing Multimodal Hallucinations with Perturbative Visual Training.","year":2025,"types":["Inproceedings"],"venue":"ICLR","doi":null,"eventYear":2025,"numberOfCreators":8,"category":"conference","sources":["https://dblp.org/rec/conf/iclr/ChenLJZRC0S25"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iclr/ChenLJZRC0S25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iclr/JiaoMJY0S25","url":"https://dblp.org/rec/conf/iclr/JiaoMJY0S25","title":"Boltzmann-Aligned Inverse Folding Model as a Predictor of Mutational Effects on Protein-Protein Interactions.","year":2025,"types":["Inproceedings"],"venue":"ICLR","doi":null,"eventYear":2025,"numberOfCreators":6,"category":"conference","sources":["https://dblp.org/rec/conf/iclr/JiaoMJY0S25"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iclr/JiaoMJY0S25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iclr/XuGLFXZ0S25","url":"https://dblp.org/rec/conf/iclr/XuGLFXZ0S25","title":"What Matters When Repurposing Diffusion Models for General Dense Perception Tasks?","year":2025,"types":["Inproceedings"],"venue":"ICLR","doi":null,"eventYear":2025,"numberOfCreators":8,"category":"conference","sources":["https://dblp.org/rec/conf/iclr/XuGLFXZ0S25"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iclr/XuGLFXZ0S25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iclr/YangH0S00LO025","url":"https://dblp.org/rec/conf/iclr/YangH0S00LO025","title":"Depth Any Video with Scalable Synthetic Data.","year":2025,"types":["Inproceedings"],"venue":"ICLR","doi":null,"eventYear":2025,"numberOfCreators":9,"category":"conference","sources":["https://dblp.org/rec/conf/iclr/YangH0S00LO025"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iclr/YangH0S00LO025","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iclr/ZhaoL0C000S25","url":"https://dblp.org/rec/conf/iclr/ZhaoL0C000S25","title":"MovieDreamer: Hierarchical Generation for Coherent Long Visual Sequences.","year":2025,"types":["Inproceedings"],"venue":"ICLR","doi":null,"eventYear":2025,"numberOfCreators":8,"category":"conference","sources":["https://dblp.org/rec/conf/iclr/ZhaoL0C000S25"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iclr/ZhaoL0C000S25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/icml/00120S25","url":"https://dblp.org/rec/conf/icml/00120S25","title":"Physics Aware Neural Networks for Unsupervised Binding Energy Prediction.","year":2025,"types":["Inproceedings"],"venue":"ICML","doi":null,"eventYear":2025,"numberOfCreators":3,"category":"conference","sources":["https://dblp.org/rec/conf/icml/00120S25"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/icml/00120S25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/ijcai/JingLCXBGS25","url":"https://dblp.org/rec/conf/ijcai/JingLCXBGS25","title":"Seeing the Unseen: Composing Outliers for Compositional Zero-Shot Learning.","year":2025,"types":["Inproceedings"],"venue":"IJCAI","doi":"https://doi.org/10.24963/IJCAI.2025/143","eventYear":2025,"numberOfCreators":7,"category":"conference","sources":["https://dblp.org/rec/conf/ijcai/JingLCXBGS25","https://doi.org/10.24963/IJCAI.2025/143"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/ijcai/JingLCXBGS25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/nips/ZhaoSLZZZCHS25","url":"https://dblp.org/rec/conf/nips/ZhaoSLZZZCHS25","title":"DICEPTION: A Generalist Diffusion Model for Visual Perceptual Tasks.","year":2025,"types":["Inproceedings"],"venue":"NeurIPS","doi":null,"eventYear":2025,"numberOfCreators":9,"category":"conference","sources":["https://dblp.org/rec/conf/nips/ZhaoSLZZZCHS25"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/nips/ZhaoSLZZZCHS25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/nips/ZhongZDHZLWCS25","url":"https://dblp.org/rec/conf/nips/ZhongZDHZLWCS25","title":"Omni-R1: Reinforcement Learning for Omnimodal Reasoning via Two-System Collaboration.","year":2025,"types":["Inproceedings"],"venue":"NeurIPS","doi":null,"eventYear":2025,"numberOfCreators":9,"category":"conference","sources":["https://dblp.org/rec/conf/nips/ZhongZDHZLWCS25"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/nips/ZhongZDHZLWCS25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/siggraph/GeXXKLHX0S25","url":"https://dblp.org/rec/conf/siggraph/GeXXKLHX0S25","title":"Generative Video Matting.","year":2025,"types":["Inproceedings"],"venue":"SIGGRAPH (Conference Paper Track)","doi":"https://doi.org/10.1145/3721238.3730642","eventYear":2025,"numberOfCreators":9,"category":"conference","sources":["https://dblp.org/rec/conf/siggraph/GeXXKLHX0S25","https://doi.org/10.1145/3721238.3730642"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/siggraph/GeXXKLHX0S25","documentUrl":null,"type":"Inproceedings"},{"key":"journals/ijcv/LiuWZCHS25","url":"https://dblp.org/rec/journals/ijcv/LiuWZCHS25","title":"Masked Channel Modeling for Bootstrapping Visual Pre-training.","year":2025,"types":["Article"],"venue":"Int. J. Comput. Vis.","doi":"https://doi.org/10.1007/S11263-024-02204-6","numberOfCreators":6,"category":"journal","sources":["https://dblp.org/rec/journals/ijcv/LiuWZCHS25","https://doi.org/10.1007/S11263-024-02204-6"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/ijcv/LiuWZCHS25","documentUrl":null,"type":"Article"},{"key":"journals/ijcv/LiuZCWFWLVS25","url":"https://dblp.org/rec/journals/ijcv/LiuZCWFWLVS25","title":"Segment Anything in Context with Vision Foundation Models.","year":2025,"types":["Article"],"venue":"Int. J. Comput. Vis.","doi":"https://doi.org/10.1007/S11263-025-02517-0","numberOfCreators":9,"category":"journal","sources":["https://dblp.org/rec/journals/ijcv/LiuZCWFWLVS25","https://doi.org/10.1007/S11263-025-02517-0"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/ijcv/LiuZCWFWLVS25","documentUrl":null,"type":"Article"},{"key":"journals/ijcv/WangZCCZS25","url":"https://dblp.org/rec/journals/ijcv/WangZCCZS25","title":"AutoStory: Generating Diverse Storytelling Images with Minimal Human Efforts.","year":2025,"types":["Article"],"venue":"Int. J. Comput. Vis.","doi":"https://doi.org/10.1007/S11263-024-02309-Y","numberOfCreators":6,"category":"journal","sources":["https://dblp.org/rec/journals/ijcv/WangZCCZS25","https://doi.org/10.1007/S11263-024-02309-Y"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/ijcv/WangZCCZS25","documentUrl":null,"type":"Article"},{"key":"journals/ijcv/WuLHSSCLGZ25","url":"https://dblp.org/rec/journals/ijcv/WuLHSSCLGZ25","title":"Paragraph-to-Image Generation with Information-Enriched Diffusion Model.","year":2025,"types":["Article"],"venue":"Int. J. Comput. Vis.","doi":"https://doi.org/10.1007/S11263-025-02435-1","numberOfCreators":9,"category":"journal","sources":["https://dblp.org/rec/journals/ijcv/WuLHSSCLGZ25","https://doi.org/10.1007/S11263-025-02435-1"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/ijcv/WuLHSSCLGZ25","documentUrl":null,"type":"Article"},{"key":"journals/pami/LiuHYDWLSJB25","url":"https://dblp.org/rec/journals/pami/LiuHYDWLSJB25","title":"VimTS: A Unified Video and Image Text Spotter for Enhancing the Cross-Domain Generalization.","year":2025,"types":["Article"],"venue":"IEEE Trans. Pattern Anal. Mach. Intell.","doi":"https://doi.org/10.1109/TPAMI.2025.3528950","numberOfCreators":9,"category":"journal","sources":["https://dblp.org/rec/journals/pami/LiuHYDWLSJB25","https://doi.org/10.1109/TPAMI.2025.3528950"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/pami/LiuHYDWLSJB25","documentUrl":null,"type":"Article"},{"key":"journals/pami/WangLJWZS25","url":"https://dblp.org/rec/journals/pami/WangLJWZS25","title":"Learning Dual-Stream Conditional Concepts in Compositional Zero-Shot Learning.","year":2025,"types":["Article"],"venue":"IEEE Trans. Pattern Anal. Mach. Intell.","doi":"https://doi.org/10.1109/TPAMI.2025.3597668","numberOfCreators":6,"category":"journal","sources":["https://dblp.org/rec/journals/pami/WangLJWZS25","https://doi.org/10.1109/TPAMI.2025.3597668"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/pami/WangLJWZS25","documentUrl":null,"type":"Article"},{"key":"journals/pami/ZhuYWHZHZSQHO25","url":"https://dblp.org/rec/journals/pami/ZhuYWHZHZSQHO25","title":"PonderV2: Improved 3D Representation With a Universal Pre-Training Paradigm.","year":2025,"types":["Article"],"venue":"IEEE Trans. Pattern Anal. Mach. Intell.","doi":"https://doi.org/10.1109/TPAMI.2025.3561598","numberOfCreators":11,"category":"journal","sources":["https://dblp.org/rec/journals/pami/ZhuYWHZHZSQHO25","https://doi.org/10.1109/TPAMI.2025.3561598"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/pami/ZhuYWHZHZSQHO25","documentUrl":null,"type":"Article"}],"preprints":[{"key":"journals/corr/abs-2502-05503","url":"https://dblp.org/rec/journals/corr/abs-2502-05503","title":"A Physical Coherence Benchmark for Evaluating Video Generation Models via Optical Flow-guided Frame Prediction.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2502.05503","numberOfCreators":5,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2502-05503","https://doi.org/10.48550/ARXIV.2502.05503"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2502-05503","documentUrl":null,"type":"Informal","arxivId":"2502.05503","arxivUrl":"https://arxiv.org/abs/2502.05503"},{"key":"journals/corr/abs-2502-17157","url":"https://dblp.org/rec/journals/corr/abs-2502-17157","title":"DICEPTION: A Generalist Diffusion Model for Visual Perceptual Tasks.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2502.17157","numberOfCreators":8,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2502-17157","https://doi.org/10.48550/ARXIV.2502.17157"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2502-17157","documentUrl":null,"type":"Informal","arxivId":"2502.17157","arxivUrl":"https://arxiv.org/abs/2502.17157"},{"key":"journals/corr/abs-2502-18538","url":"https://dblp.org/rec/journals/corr/abs-2502-18538","title":"Revisiting Convolution Architecture in the Realm of DNA Foundation Models.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2502.18538","numberOfCreators":9,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2502-18538","https://doi.org/10.48550/ARXIV.2502.18538"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2502-18538","documentUrl":null,"type":"Informal","arxivId":"2502.18538","arxivUrl":"https://arxiv.org/abs/2502.18538"},{"key":"journals/corr/abs-2503-06486","url":"https://dblp.org/rec/journals/corr/abs-2503-06486","title":"PerturboLLaVA: Reducing Multimodal Hallucinations with Perturbative Visual Training.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2503.06486","numberOfCreators":8,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2503-06486","https://doi.org/10.48550/ARXIV.2503.06486"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-06486","documentUrl":null,"type":"Informal","arxivId":"2503.06486","arxivUrl":"https://arxiv.org/abs/2503.06486"},{"key":"journals/corr/abs-2503-08625","url":"https://dblp.org/rec/journals/corr/abs-2503-08625","title":"SegAgent: Exploring Pixel Understanding Capabilities in MLLMs by Imitating Human Annotator Trajectories.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2503.08625","numberOfCreators":8,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2503-08625","https://doi.org/10.48550/ARXIV.2503.08625"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-08625","documentUrl":null,"type":"Informal","arxivId":"2503.08625","arxivUrl":"https://arxiv.org/abs/2503.08625"},{"key":"journals/corr/abs-2503-18533","url":"https://dblp.org/rec/journals/corr/abs-2503-18533","title":"MMCR: Advancing Visual Language Model in Multimodal Multi-Turn Contextual Reasoning.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2503.18533","numberOfCreators":7,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2503-18533","https://doi.org/10.48550/ARXIV.2503.18533"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-18533","documentUrl":null,"type":"Informal","arxivId":"2503.18533","arxivUrl":"https://arxiv.org/abs/2503.18533"},{"key":"journals/corr/abs-2503-18945","url":"https://dblp.org/rec/journals/corr/abs-2503-18945","title":"Aether: Geometric-Aware Unified World Modeling.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2503.18945","numberOfCreators":11,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2503-18945","https://doi.org/10.48550/ARXIV.2503.18945"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-18945","documentUrl":null,"type":"Informal","arxivId":"2503.18945","arxivUrl":"https://arxiv.org/abs/2503.18945"},{"key":"journals/corr/abs-2504-05692","url":"https://dblp.org/rec/journals/corr/abs-2504-05692","title":"POMATO: Marrying Pointmap Matching with Temporal Motion for Dynamic 3D Reconstruction.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2504.05692","numberOfCreators":7,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2504-05692","https://doi.org/10.48550/ARXIV.2504.05692"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2504-05692","documentUrl":null,"type":"Informal","arxivId":"2504.05692","arxivUrl":"https://arxiv.org/abs/2504.05692"},{"key":"journals/corr/abs-2505-20256","url":"https://dblp.org/rec/journals/corr/abs-2505-20256","title":"Omni-R1: Reinforcement Learning for Omnimodal Reasoning via Two-System Collaboration.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2505.20256","numberOfCreators":9,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2505-20256","https://doi.org/10.48550/ARXIV.2505.20256"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-20256","documentUrl":null,"type":"Informal","arxivId":"2505.20256","arxivUrl":"https://arxiv.org/abs/2505.20256"},{"key":"journals/corr/abs-2505-21457","url":"https://dblp.org/rec/journals/corr/abs-2505-21457","title":"Active-O3: Empowering Multimodal Large Language Models with Active Perception via GRPO.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2505.21457","numberOfCreators":11,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2505-21457","https://doi.org/10.48550/ARXIV.2505.21457"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-21457","documentUrl":null,"type":"Informal","arxivId":"2505.21457","arxivUrl":"https://arxiv.org/abs/2505.21457"},{"key":"journals/corr/abs-2506-05327","url":"https://dblp.org/rec/journals/corr/abs-2506-05327","title":"Revisiting Depth Representations for Feed-Forward 3D Gaussian Splatting.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2506.05327","numberOfCreators":7,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2506-05327","https://doi.org/10.48550/ARXIV.2506.05327"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-05327","documentUrl":null,"type":"Informal","arxivId":"2506.05327","arxivUrl":"https://arxiv.org/abs/2506.05327"},{"key":"journals/corr/abs-2506-19348","url":"https://dblp.org/rec/journals/corr/abs-2506-19348","title":"Training-Free Motion Customization for Distilled Video Generators with Adaptive Test-Time Distillation.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2506.19348","numberOfCreators":7,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2506-19348","https://doi.org/10.48550/ARXIV.2506.19348"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-19348","documentUrl":null,"type":"Informal","arxivId":"2506.19348","arxivUrl":"https://arxiv.org/abs/2506.19348"},{"key":"journals/corr/abs-2507-13347","url":"https://dblp.org/rec/journals/corr/abs-2507-13347","title":"π3: Scalable Permutation-Equivariant Visual Geometry Learning.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2507.13347","numberOfCreators":10,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2507-13347","https://doi.org/10.48550/ARXIV.2507.13347"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2507-13347","documentUrl":null,"type":"Informal","arxivId":"2507.13347","arxivUrl":"https://arxiv.org/abs/2507.13347"},{"key":"journals/corr/abs-2507-15602","url":"https://dblp.org/rec/journals/corr/abs-2507-15602","title":"SurfaceSplat: Connecting Surface Reconstruction and Gaussian Splatting.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2507.15602","numberOfCreators":5,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2507-15602","https://doi.org/10.48550/ARXIV.2507.15602"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2507-15602","documentUrl":null,"type":"Informal","arxivId":"2507.15602","arxivUrl":"https://arxiv.org/abs/2507.15602"},{"key":"journals/corr/abs-2508-01591","url":"https://dblp.org/rec/journals/corr/abs-2508-01591","title":"Self-Navigated Residual Mamba for Universal Industrial Anomaly Detection.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2508.01591","numberOfCreators":7,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2508-01591","https://doi.org/10.48550/ARXIV.2508.01591"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-01591","documentUrl":null,"type":"Informal","arxivId":"2508.01591","arxivUrl":"https://arxiv.org/abs/2508.01591"},{"key":"journals/corr/abs-2508-07905","url":"https://dblp.org/rec/journals/corr/abs-2508-07905","title":"Generative Video Matting.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2508.07905","numberOfCreators":9,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2508-07905","https://doi.org/10.48550/ARXIV.2508.07905"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-07905","documentUrl":null,"type":"Informal","arxivId":"2508.07905","arxivUrl":"https://arxiv.org/abs/2508.07905"},{"key":"journals/corr/abs-2508-08240","url":"https://dblp.org/rec/journals/corr/abs-2508-08240","title":"ODYSSEY: Open-World Quadrupeds Exploration and Manipulation for Long-Horizon Tasks.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2508.08240","numberOfCreators":10,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2508-08240","https://doi.org/10.48550/ARXIV.2508.08240"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-08240","documentUrl":null,"type":"Informal","arxivId":"2508.08240","arxivUrl":"https://arxiv.org/abs/2508.08240"},{"key":"journals/corr/abs-2508-09138","url":"https://dblp.org/rec/journals/corr/abs-2508-09138","title":"Time Is a Feature: Exploiting Temporal Dynamics in Diffusion Language Models.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2508.09138","numberOfCreators":9,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2508-09138","https://doi.org/10.48550/ARXIV.2508.09138"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-09138","documentUrl":null,"type":"Informal","arxivId":"2508.09138","arxivUrl":"https://arxiv.org/abs/2508.09138"},{"key":"journals/corr/abs-2508-14811","url":"https://dblp.org/rec/journals/corr/abs-2508-14811","title":"Tinker: Diffusion's Gift to 3D-Multi-View Consistent Editing From Sparse Inputs without Per-Scene Optimization.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2508.14811","numberOfCreators":6,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2508-14811","https://doi.org/10.48550/ARXIV.2508.14811"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-14811","documentUrl":null,"type":"Informal","arxivId":"2508.14811","arxivUrl":"https://arxiv.org/abs/2508.14811"},{"key":"journals/corr/abs-2509-05296","url":"https://dblp.org/rec/journals/corr/abs-2509-05296","title":"WinT3R: Window-Based Streaming Reconstruction with Camera Token Pool.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2509.05296","numberOfCreators":10,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2509-05296","https://doi.org/10.48550/ARXIV.2509.05296"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-05296","documentUrl":null,"type":"Informal","arxivId":"2509.05296","arxivUrl":"https://arxiv.org/abs/2509.05296"},{"key":"journals/corr/abs-2509-12201","url":"https://dblp.org/rec/journals/corr/abs-2509-12201","title":"OmniWorld: A Multi-Domain and Multi-Modal Dataset for 4D World Modeling.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2509.12201","numberOfCreators":19,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2509-12201","https://doi.org/10.48550/ARXIV.2509.12201"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-12201","documentUrl":null,"type":"Informal","arxivId":"2509.12201","arxivUrl":"https://arxiv.org/abs/2509.12201"},{"key":"journals/corr/abs-2509-23736","url":"https://dblp.org/rec/journals/corr/abs-2509-23736","title":"HieraTok: Multi-Scale Visual Tokenizer Improves Image Reconstruction and Generation.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2509.23736","numberOfCreators":9,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2509-23736","https://doi.org/10.48550/ARXIV.2509.23736"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-23736","documentUrl":null,"type":"Informal","arxivId":"2509.23736","arxivUrl":"https://arxiv.org/abs/2509.23736"},{"key":"journals/corr/abs-2509-23738","url":"https://dblp.org/rec/journals/corr/abs-2509-23738","title":"GUI-Shepherd: Reliable Process Reward and Verification for Long-Sequence GUI Tasks.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2509.23738","numberOfCreators":12,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2509-23738","https://doi.org/10.48550/ARXIV.2509.23738"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-23738","documentUrl":null,"type":"Informal","arxivId":"2509.23738","arxivUrl":"https://arxiv.org/abs/2509.23738"},{"key":"journals/corr/abs-2510-02902","url":"https://dblp.org/rec/journals/corr/abs-2510-02902","title":"DMark: Order-Agnostic Watermarking for Diffusion Large Language Models.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2510.02902","numberOfCreators":8,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2510-02902","https://doi.org/10.48550/ARXIV.2510.02902"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-02902","documentUrl":null,"type":"Informal","arxivId":"2510.02902","arxivUrl":"https://arxiv.org/abs/2510.02902"},{"key":"journals/corr/abs-2510-03895","url":"https://dblp.org/rec/journals/corr/abs-2510-03895","title":"NoTVLA: Narrowing of Dense Action Trajectories for Generalizable Robot Manipulation.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2510.03895","numberOfCreators":11,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2510-03895","https://doi.org/10.48550/ARXIV.2510.03895"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-03895","documentUrl":null,"type":"Informal","arxivId":"2510.03895","arxivUrl":"https://arxiv.org/abs/2510.03895"},{"key":"journals/corr/abs-2510-03896","url":"https://dblp.org/rec/journals/corr/abs-2510-03896","title":"Bridge Thinking and Acting: Unleashing Physical Potential of VLM with Generalizable Action Expert.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2510.03896","numberOfCreators":10,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2510-03896","https://doi.org/10.48550/ARXIV.2510.03896"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-03896","documentUrl":null,"type":"Informal","arxivId":"2510.03896","arxivUrl":"https://arxiv.org/abs/2510.03896"},{"key":"journals/corr/abs-2510-05057","url":"https://dblp.org/rec/journals/corr/abs-2510-05057","title":"StaMo: Unsupervised Learning of Generalizable Robot Motion from Compact State Representation.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2510.05057","numberOfCreators":9,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2510-05057","https://doi.org/10.48550/ARXIV.2510.05057"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-05057","documentUrl":null,"type":"Informal","arxivId":"2510.05057","arxivUrl":"https://arxiv.org/abs/2510.05057"},{"key":"journals/corr/abs-2510-07286","url":"https://dblp.org/rec/journals/corr/abs-2510-07286","title":"Evolutionary Profiles for Protein Fitness Prediction.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2510.07286","numberOfCreators":8,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2510-07286","https://doi.org/10.48550/ARXIV.2510.07286"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-07286","documentUrl":null,"type":"Informal","arxivId":"2510.07286","arxivUrl":"https://arxiv.org/abs/2510.07286"},{"key":"journals/corr/abs-2510-10524","url":"https://dblp.org/rec/journals/corr/abs-2510-10524","title":"Unified Open-World Segmentation with Multi-Modal Prompts.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2510.10524","numberOfCreators":10,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2510-10524","https://doi.org/10.48550/ARXIV.2510.10524"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-10524","documentUrl":null,"type":"Informal","arxivId":"2510.10524","arxivUrl":"https://arxiv.org/abs/2510.10524"},{"key":"journals/corr/abs-2510-11726","url":"https://dblp.org/rec/journals/corr/abs-2510-11726","title":"scPPDM: A Diffusion Model for Single-Cell Drug-Response Prediction.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2510.11726","numberOfCreators":6,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2510-11726","https://doi.org/10.48550/ARXIV.2510.11726"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-11726","documentUrl":null,"type":"Informal","arxivId":"2510.11726","arxivUrl":"https://arxiv.org/abs/2510.11726"},{"key":"journals/corr/abs-2510-24717","url":"https://dblp.org/rec/journals/corr/abs-2510-24717","title":"Uniform Discrete Diffusion with Metric Path for Video Generation.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2510.24717","numberOfCreators":11,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2510-24717","https://doi.org/10.48550/ARXIV.2510.24717"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-24717","documentUrl":null,"type":"Informal","arxivId":"2510.24717","arxivUrl":"https://arxiv.org/abs/2510.24717"},{"key":"journals/corr/abs-2511-12691","url":"https://dblp.org/rec/journals/corr/abs-2511-12691","title":"R2Seg: Training-Free OOD Medical Tumor Segmentation via Anatomical Reasoning and Statistical Rejection.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2511.12691","numberOfCreators":8,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2511-12691","https://doi.org/10.48550/ARXIV.2511.12691"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2511-12691","documentUrl":null,"type":"Informal","arxivId":"2511.12691","arxivUrl":"https://arxiv.org/abs/2511.12691"},{"key":"journals/corr/abs-2512-00748","url":"https://dblp.org/rec/journals/corr/abs-2512-00748","title":"Probabilistic Modeling of Multi-rater Medical Image Segmentation for Diversity and Personalization.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2512.00748","numberOfCreators":5,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2512-00748","https://doi.org/10.48550/ARXIV.2512.00748"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-00748","documentUrl":null,"type":"Informal","arxivId":"2512.00748","arxivUrl":"https://arxiv.org/abs/2512.00748"},{"key":"journals/corr/abs-2512-07951","url":"https://dblp.org/rec/journals/corr/abs-2512-07951","title":"Preserving Source Video Realism: High-Fidelity Face Swapping for Cinematic Quality.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2512.07951","numberOfCreators":10,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2512-07951","https://doi.org/10.48550/ARXIV.2512.07951"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-07951","documentUrl":null,"type":"Informal","arxivId":"2512.07951","arxivUrl":"https://arxiv.org/abs/2512.07951"}],"excludedFormal":[],"otherRecords":[],"matchedName":"Chunhua Shen","databaseLabel":"Chunhua Shen","databaseMetadata":{"type":["https://dblp.org/rdf/schema#Person","https://dblp.org/rdf/schema#Creator"],"label":["Chunhua Shen"],"affiliation":["University of Adelaide, School of Computer Science, Adelaide, Australia"],"homepage":["https://www.adelaide.edu.au/directory/chunhua.shen","https://cs.adelaide.edu.au/~chhshen/","https://researchers.adelaide.edu.au/profile/chunhua.shen"],"orcid":["https://orcid.org/0000-0002-8648-8718"],"primaryAffiliation":["University of Adelaide, School of Computer Science, Adelaide, Australia"],"primaryHomepage":["https://cs.adelaide.edu.au/~chhshen/"]},"rawFormalRecordCount2025":30,"signatureAudit":{"completedAt":"2026-10-19","frozen":true,"scope":"对 B 组 39 个数值档案的全部 1074 条原始 2025 正式记录扫描 DBLP author-signature ORCID 和机构；复用既有 59 条 Crossref 核验，补查 6 条新触发记录。重点核查不同 ORCID，以及只有预期机构之外机构的条目。本轮不扩展为所有作者逐篇全文审计。","formalRecordCoverage":30,"orcidCounts":{"https://orcid.org/0000-0002-8648-8718":4},"institutionCounts":{"University of Adelaide":1,"Zhejiang University (ZJU)":17,"Zhejiang University of Technology (ZJUT)":2},"caveat":"机构名称可能由 DBLP 自动映射而失真；多 ORCID 也不自动等于异人。只有有原始资料支撑的错归才作确认排除，未解决分支则暂停总数。","decision":{"decision":"retain","evidence":[{"url":"https://www.ijcai.org/proceedings/2025/0143.pdf","evidence":"Seeing the Unseen 原文的 Chunhua Shen 机构为浙江工业大学、邮箱 chhshen@zjut.edu.cn。"},{"url":"https://homepage.zjut.edu.cn/csshen/","evidence":"浙江工业大学官方沈春华主页直接指向本人 cshen.github.io，因此异机构是实际任职/合作背景，并非另一个同名者；保留该文。"}]}},"labName":"计算机辅助设计与图形系统全国重点实验室","labUrl":null,"labEvidence":"本人主页明确列其现任该全国重点实验室副主任。只确认关联，未获得本轮可核验的独立实验室 URL，也不将其个人合作记录称为整个重点实验室产量。","labSourceUrl":"https://cshen.github.io/","sourceWarning":false,"excludedOther":[],"excludedHomonyms":[],"unassignedCandidates":[],"knownPreprintMinimum2025":null,"excludedMisattributed":[],"displayNotes":"DBLP 的机构字段含历史机构，已按原名单机构与本人履历交叉核对，未依据旧机构另选同名者。计入 30 条（会议 23、期刊 7）；预印本 34 条单列，不加总。","labDisplayNotes":"个人主页列其现任 CAD&CG 全国重点实验室副主任。与崔兆鹏、章国锋、周晓巍按共同的上级实验室合为一组，去重后 112 条；该分组只含四人的记录，不代表重点实验室的产量。"},{"index":78,"name":"Lv Sheng","nameZh":"盛律","role":"Professor","affiliation":"Beihang University","affiliationZh":"北京航空航天大学","source":"DBLP RDF via official SPARQL; primary-source identity checks","sourceUrl":"https://sparql.dblp.org/","profileUrl":"https://dblp.org/pid/132/1772.html","identifier":"132/1772","retrievedAt":"2026-10-19","count2025":17,"conference2025":12,"journal2025":5,"preprint2025":17,"status":"confirmed","notes":"保留原名单英文 Lv Sheng；匹配本人使用的 Lu Sheng（盛律），不是 DBLP 中另一个 Lv Sheng 389/4812。","identityEvidence":[{"url":"https://dblp.org/pid/132/1772.html","evidence":"DBLP RDF 类型为 Person，消歧后名字为 Lu Sheng。此档案未提供可用机构元数据，以下以本人/机构/出版商来源补证。"},{"url":"https://lucassheng.github.io/","evidence":"本人主页明确 Lu Sheng · 盛律、北京航空航天大学，并直接链接 DBLP 132/1772；原签名名单 Lv Sheng 为与本人不一致的英文拼写。"},{"url":"https://soft.buaa.edu.cn/teachershouw.jsp?urltype=news.NewsContentUrl&wbtreeid=1330&wbnewsid=9851","evidence":"北航官方教师页面确认中文姓名盛律及机构。"},{"url":"https://lucassheng.github.io/","evidence":"此本人或机构页面的正文与所选档案中 5 条 2025 记录标题匹配，其中 5 条为当前计入的正式记录（忽略空格、标点、大小写）。","matchedPaperKeys":["conf/cvpr/HuangGAY0ZLLCS25","conf/cvpr/WenH0CS25","conf/cvpr/ZhouSC0W0S025","conf/iccv/HuangGWYMCS25","journals/tip/FanHWCYS25"],"matchedFormalPaperKeys":["conf/cvpr/HuangGAY0ZLLCS25","conf/cvpr/WenH0CS25","conf/cvpr/ZhouSC0W0S025","conf/iccv/HuangGWYMCS25","journals/tip/FanHWCYS25"]}],"papers":[{"key":"conf/cvpr/HuangGAY0ZLLCS25","url":"https://dblp.org/rec/conf/cvpr/HuangGAY0ZLLCS25","title":"MIDI: Multi-Instance Diffusion for Single Image to 3D Scene Generation.","year":2025,"types":["Inproceedings"],"venue":"CVPR","doi":"https://doi.org/10.1109/CVPR52734.2025.02202","eventYear":2025,"numberOfCreators":10,"category":"conference","sources":["https://dblp.org/rec/conf/cvpr/HuangGAY0ZLLCS25","https://doi.org/10.1109/CVPR52734.2025.02202"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/HuangGAY0ZLLCS25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/cvpr/LiSHDQLSS25","url":"https://dblp.org/rec/conf/cvpr/LiSHDQLSS25","title":"T2ISafety: Benchmark for Assessing Fairness, Toxicity, and Privacy in Image Generation.","year":2025,"types":["Inproceedings"],"venue":"CVPR","doi":"https://doi.org/10.1109/CVPR52734.2025.01249","eventYear":2025,"numberOfCreators":8,"category":"conference","sources":["https://dblp.org/rec/conf/cvpr/LiSHDQLSS25","https://doi.org/10.1109/CVPR52734.2025.01249"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/LiSHDQLSS25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/cvpr/WenH0CS25","url":"https://dblp.org/rec/conf/cvpr/WenH0CS25","title":"Ouroboros3D: Image-to-3D Generation via 3D-aware Recursive Diffusion.","year":2025,"types":["Inproceedings"],"venue":"CVPR","doi":"https://doi.org/10.1109/CVPR52734.2025.02015","eventYear":2025,"numberOfCreators":5,"category":"conference","sources":["https://dblp.org/rec/conf/cvpr/WenH0CS25","https://doi.org/10.1109/CVPR52734.2025.02015"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/WenH0CS25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/cvpr/ZhouSC0W0S025","url":"https://dblp.org/rec/conf/cvpr/ZhouSC0W0S025","title":"Code-as-Monitor: Constraint-aware Visual Programming for Reactive and Proactive Robotic Failure Detection.","year":2025,"types":["Inproceedings"],"venue":"CVPR","doi":"https://doi.org/10.1109/CVPR52734.2025.00649","eventYear":2025,"numberOfCreators":8,"category":"conference","sources":["https://dblp.org/rec/conf/cvpr/ZhouSC0W0S025","https://doi.org/10.1109/CVPR52734.2025.00649"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/ZhouSC0W0S025","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iccv/HuangGWYMCS25","url":"https://dblp.org/rec/conf/iccv/HuangGWYMCS25","title":"Mv-Adapter: Multi-View Consistent Image Generation Made Easy.","year":2025,"types":["Inproceedings"],"venue":"ICCV","doi":"https://doi.org/10.1109/ICCV51701.2025.01520","eventYear":2025,"numberOfCreators":7,"category":"conference","sources":["https://dblp.org/rec/conf/iccv/HuangGWYMCS25","https://doi.org/10.1109/ICCV51701.2025.01520"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/HuangGWYMCS25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/icml/QinSYWZLYLSS0Z25","url":"https://dblp.org/rec/conf/icml/QinSYWZLYLSS0Z25","title":"WorldSimBench: Towards Video Generation Models as World Simulators.","year":2025,"types":["Inproceedings"],"venue":"ICML","doi":null,"eventYear":2025,"numberOfCreators":12,"category":"conference","sources":["https://dblp.org/rec/conf/icml/QinSYWZLYLSS0Z25"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/icml/QinSYWZLYLSS0Z25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iros/ChenSLHQZYOSQLS25","url":"https://dblp.org/rec/conf/iros/ChenSLHQZYOSQLS25","title":"RH20T-P: A Primitive-Level Robotic Manipulation Dataset towards Composable Generalization Agents in Real-world Scenarios.","year":2025,"types":["Inproceedings"],"venue":"IROS","doi":"https://doi.org/10.1109/IROS60139.2025.11246228","eventYear":2025,"numberOfCreators":12,"category":"conference","sources":["https://dblp.org/rec/conf/iros/ChenSLHQZYOSQLS25","https://doi.org/10.1109/IROS60139.2025.11246228"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iros/ChenSLHQZYOSQLS25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iros/ZhouQYSHZSS25","url":"https://dblp.org/rec/conf/iros/ZhouQYSHZSS25","title":"Chain-of-Imagination for Reliable Instruction Following in Decision Making.","year":2025,"types":["Inproceedings"],"venue":"IROS","doi":"https://doi.org/10.1109/IROS60139.2025.11246335","eventYear":2025,"numberOfCreators":8,"category":"conference","sources":["https://dblp.org/rec/conf/iros/ZhouQYSHZSS25","https://doi.org/10.1109/IROS60139.2025.11246335"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iros/ZhouQYSHZSS25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/mm/Fan0CHWS25","url":"https://dblp.org/rec/conf/mm/Fan0CHWS25","title":"Multi-Agent Amodal Completion: Direct Synthesis with Fine-Grained Semantic Guidance.","year":2025,"types":["Inproceedings"],"venue":"ACM Multimedia","doi":"https://doi.org/10.1145/3746027.3755225","eventYear":2025,"numberOfCreators":6,"category":"conference","sources":["https://dblp.org/rec/conf/mm/Fan0CHWS25","https://doi.org/10.1145/3746027.3755225"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/mm/Fan0CHWS25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/nips/HeCSYSS25","url":"https://dblp.org/rec/conf/nips/HeCSYSS25","title":"Systematic Reward Gap Optimization for Mitigating VLM Hallucinations.","year":2025,"types":["Inproceedings"],"venue":"NeurIPS","doi":null,"eventYear":2025,"numberOfCreators":6,"category":"conference","sources":["https://dblp.org/rec/conf/nips/HeCSYSS25"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/nips/HeCSYSS25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/nips/ZhouACHRZWWHSZ25","url":"https://dblp.org/rec/conf/nips/ZhouACHRZWWHSZ25","title":"RoboRefer: Towards Spatial Referring with Reasoning in Vision-Language Models for Robotics.","year":2025,"types":["Inproceedings"],"venue":"NeurIPS","doi":null,"eventYear":2025,"numberOfCreators":11,"category":"conference","sources":["https://dblp.org/rec/conf/nips/ZhouACHRZWWHSZ25"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/nips/ZhouACHRZWWHSZ25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/siggrapha/HuangFSGCS25","url":"https://dblp.org/rec/conf/siggrapha/HuangFSGCS25","title":"AnimaX: Animating the Inanimate in 3D with Joint Video-Pose Diffusion Models.","year":2025,"types":["Inproceedings"],"venue":"SIGGRAPH Asia","doi":"https://doi.org/10.1145/3757377.3763885","eventYear":2025,"numberOfCreators":6,"category":"conference","sources":["https://dblp.org/rec/conf/siggrapha/HuangFSGCS25","https://doi.org/10.1145/3757377.3763885"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/siggrapha/HuangFSGCS25","documentUrl":null,"type":"Inproceedings"},{"key":"journals/ieeejas/XiongWCSXLXCHT25","url":"https://dblp.org/rec/journals/ieeejas/XiongWCSXLXCHT25","title":"DeepSeek: Paradigm Shifts and Technical Evolution in Large AI Models.","year":2025,"types":["Article"],"venue":"IEEE CAA J. Autom. Sinica","doi":"https://doi.org/10.1109/JAS.2025.125495","numberOfCreators":10,"category":"journal","sources":["https://dblp.org/rec/journals/ieeejas/XiongWCSXLXCHT25","https://doi.org/10.1109/JAS.2025.125495"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/ieeejas/XiongWCSXLXCHT25","documentUrl":null,"type":"Article"},{"key":"journals/ijcv/ZhangSZHYWSQSL25","url":"https://dblp.org/rec/journals/ijcv/ZhangSZHYWSQSL25","title":"Bamboo: Building Mega-Scale Vision Dataset Continually with Human-Machine Synergy.","year":2025,"types":["Article"],"venue":"Int. J. Comput. Vis.","doi":"https://doi.org/10.1007/S11263-025-02450-2","numberOfCreators":10,"category":"journal","sources":["https://dblp.org/rec/journals/ijcv/ZhangSZHYWSQSL25","https://doi.org/10.1007/S11263-025-02450-2"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/ijcv/ZhangSZHYWSQSL25","documentUrl":null,"type":"Article"},{"key":"journals/tip/FanHWCYS25","url":"https://dblp.org/rec/journals/tip/FanHWCYS25","title":"Parts2Whole: Generalizable Multi-Part Portrait Customization.","year":2025,"types":["Article"],"venue":"IEEE Trans. Image Process.","doi":"https://doi.org/10.1109/TIP.2025.3597037","numberOfCreators":6,"category":"journal","sources":["https://dblp.org/rec/journals/tip/FanHWCYS25","https://doi.org/10.1109/TIP.2025.3597037"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/tip/FanHWCYS25","documentUrl":null,"type":"Article"},{"key":"journals/tip/WangLZXZYSX25","url":"https://dblp.org/rec/journals/tip/WangLZXZYSX25","title":"Diffusion Model is Secretly a Training-Free Open Vocabulary Semantic Segmenter.","year":2025,"types":["Article"],"venue":"IEEE Trans. Image Process.","doi":"https://doi.org/10.1109/TIP.2025.3551648","numberOfCreators":8,"category":"journal","sources":["https://dblp.org/rec/journals/tip/WangLZXZYSX25","https://doi.org/10.1109/TIP.2025.3551648"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/tip/WangLZXZYSX25","documentUrl":null,"type":"Article"},{"key":"journals/tnn/XuYZSRST25","url":"https://dblp.org/rec/journals/tnn/XuYZSRST25","title":"Boundary-Based Active Domain Adaptation for Semantic Segmentation Under Adverse Conditions.","year":2025,"types":["Article"],"venue":"IEEE Trans. Neural Networks Learn. Syst.","doi":"https://doi.org/10.1109/TNNLS.2025.3544204","numberOfCreators":7,"category":"journal","sources":["https://dblp.org/rec/journals/tnn/XuYZSRST25","https://doi.org/10.1109/TNNLS.2025.3544204"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/tnn/XuYZSRST25","documentUrl":null,"type":"Article"}],"preprints":[{"key":"journals/corr/abs-2501-12612","url":"https://dblp.org/rec/journals/corr/abs-2501-12612","title":"T2ISafety: Benchmark for Assessing Fairness, Toxicity, and Privacy in Image Generation.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2501.12612","numberOfCreators":8,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2501-12612","https://doi.org/10.48550/ARXIV.2501.12612"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2501-12612","documentUrl":null,"type":"Informal","arxivId":"2501.12612","arxivUrl":"https://arxiv.org/abs/2501.12612"},{"key":"journals/corr/abs-2503-05127","url":"https://dblp.org/rec/journals/corr/abs-2503-05127","title":"HexPlane Representation for 3D Semantic Scene Understanding.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2503.05127","numberOfCreators":6,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2503-05127","https://doi.org/10.48550/ARXIV.2503.05127"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-05127","documentUrl":null,"type":"Informal","arxivId":"2503.05127","arxivUrl":"https://arxiv.org/abs/2503.05127"},{"key":"journals/corr/abs-2503-12590","url":"https://dblp.org/rec/journals/corr/abs-2503-12590","title":"Personalize Anything for Free with Diffusion Transformer.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2503.12590","numberOfCreators":5,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2503-12590","https://doi.org/10.48550/ARXIV.2503.12590"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-12590","documentUrl":null,"type":"Informal","arxivId":"2503.12590","arxivUrl":"https://arxiv.org/abs/2503.12590"},{"key":"journals/corr/abs-2506-04308","url":"https://dblp.org/rec/journals/corr/abs-2506-04308","title":"RoboRefer: Towards Spatial Referring with Reasoning in Vision-Language Models for Robotics.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2506.04308","numberOfCreators":11,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2506-04308","https://doi.org/10.48550/ARXIV.2506.04308"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-04308","documentUrl":null,"type":"Informal","arxivId":"2506.04308","arxivUrl":"https://arxiv.org/abs/2506.04308"},{"key":"journals/corr/abs-2506-09740","url":"https://dblp.org/rec/journals/corr/abs-2506-09740","title":"ELBO-T2IAlign: A Generic ELBO-Based Method for Calibrating Pixel-level Text-Image Alignment in Diffusion Models.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2506.09740","numberOfCreators":8,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2506-09740","https://doi.org/10.48550/ARXIV.2506.09740"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-09740","documentUrl":null,"type":"Informal","arxivId":"2506.09740","arxivUrl":"https://arxiv.org/abs/2506.09740"},{"key":"journals/corr/abs-2506-16402","url":"https://dblp.org/rec/journals/corr/abs-2506-16402","title":"IS-Bench: Evaluating Interactive Safety of VLM-Driven Embodied Agents in Daily Household Tasks.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2506.16402","numberOfCreators":8,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2506-16402","https://doi.org/10.48550/ARXIV.2506.16402"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-16402","documentUrl":null,"type":"Informal","arxivId":"2506.16402","arxivUrl":"https://arxiv.org/abs/2506.16402"},{"key":"journals/corr/abs-2506-18315","url":"https://dblp.org/rec/journals/corr/abs-2506-18315","title":"Use Property-Based Testing to Bridge LLM Code Generation and Validation.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2506.18315","numberOfCreators":6,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2506-18315","https://doi.org/10.48550/ARXIV.2506.18315"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-18315","documentUrl":null,"type":"Informal","arxivId":"2506.18315","arxivUrl":"https://arxiv.org/abs/2506.18315"},{"key":"journals/corr/abs-2506-19851","url":"https://dblp.org/rec/journals/corr/abs-2506-19851","title":"AnimaX: Animating the Inanimate in 3D with Joint Video-Pose Diffusion Models.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2506.19851","numberOfCreators":6,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2506-19851","https://doi.org/10.48550/ARXIV.2506.19851"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-19851","documentUrl":null,"type":"Informal","arxivId":"2506.19851","arxivUrl":"https://arxiv.org/abs/2506.19851"},{"key":"journals/corr/abs-2507-09955","url":"https://dblp.org/rec/journals/corr/abs-2507-09955","title":"DeepSeek: Paradigm Shifts and Technical Evolution in Large AI Models.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2507.09955","numberOfCreators":10,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2507-09955","https://doi.org/10.48550/ARXIV.2507.09955"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2507-09955","documentUrl":null,"type":"Informal","arxivId":"2507.09955","arxivUrl":"https://arxiv.org/abs/2507.09955"},{"key":"journals/corr/abs-2508-19247","url":"https://dblp.org/rec/journals/corr/abs-2508-19247","title":"VoxHammer: Training-Free Precise and Coherent 3D Editing in Native 3D Space.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2508.19247","numberOfCreators":7,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2508-19247","https://doi.org/10.48550/ARXIV.2508.19247"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-19247","documentUrl":null,"type":"Informal","arxivId":"2508.19247","arxivUrl":"https://arxiv.org/abs/2508.19247"},{"key":"journals/corr/abs-2509-17757","url":"https://dblp.org/rec/journals/corr/abs-2509-17757","title":"Multi-Agent Amodal Completion: Direct Synthesis with Fine-Grained Semantic Guidance.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2509.17757","numberOfCreators":6,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2509-17757","https://doi.org/10.48550/ARXIV.2509.17757"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-17757","documentUrl":null,"type":"Informal","arxivId":"2509.17757","arxivUrl":"https://arxiv.org/abs/2509.17757"},{"key":"journals/corr/abs-2510-07181","url":"https://dblp.org/rec/journals/corr/abs-2510-07181","title":"TIGeR: Tool-Integrated Geometric Reasoning in Vision-Language Models for Robotics.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2510.07181","numberOfCreators":9,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2510-07181","https://doi.org/10.48550/ARXIV.2510.07181"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-07181","documentUrl":null,"type":"Informal","arxivId":"2510.07181","arxivUrl":"https://arxiv.org/abs/2510.07181"},{"key":"journals/corr/abs-2511-13488","url":"https://dblp.org/rec/journals/corr/abs-2511-13488","title":"InterMoE: Individual-Specific 3D Human Interaction Generation via Dynamic Temporal-Selective MoE.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2511.13488","numberOfCreators":5,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2511-13488","https://doi.org/10.48550/ARXIV.2511.13488"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2511-13488","documentUrl":null,"type":"Informal","arxivId":"2511.13488","arxivUrl":"https://arxiv.org/abs/2511.13488"},{"key":"journals/corr/abs-2511-22659","url":"https://dblp.org/rec/journals/corr/abs-2511-22659","title":"Geometrically-Constrained Agent for Spatial Reasoning.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2511.22659","numberOfCreators":9,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2511-22659","https://doi.org/10.48550/ARXIV.2511.22659"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2511-22659","documentUrl":null,"type":"Informal","arxivId":"2511.22659","arxivUrl":"https://arxiv.org/abs/2511.22659"},{"key":"journals/corr/abs-2512-13660","url":"https://dblp.org/rec/journals/corr/abs-2512-13660","title":"RoboTracer: Mastering Spatial Trace with Reasoning in Vision-Language Models for Robotics.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2512.13660","numberOfCreators":13,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2512-13660","https://doi.org/10.48550/ARXIV.2512.13660"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-13660","documentUrl":null,"type":"Informal","arxivId":"2512.13660","arxivUrl":"https://arxiv.org/abs/2512.13660"},{"key":"journals/corr/abs-2512-20936","url":"https://dblp.org/rec/journals/corr/abs-2512-20936","title":"Reasoning-Driven Amodal Completion: Collaborative Agents and Perceptual Evaluation.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2512.20936","numberOfCreators":4,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2512-20936","https://doi.org/10.48550/ARXIV.2512.20936"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-20936","documentUrl":null,"type":"Informal","arxivId":"2512.20936","arxivUrl":"https://arxiv.org/abs/2512.20936"},{"key":"journals/corr/abs-2512-23573","url":"https://dblp.org/rec/journals/corr/abs-2512-23573","title":"ProGuard: Towards Proactive Multimodal Safeguard.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2512.23573","numberOfCreators":5,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2512-23573","https://doi.org/10.48550/ARXIV.2512.23573"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-23573","documentUrl":null,"type":"Informal","arxivId":"2512.23573","arxivUrl":"https://arxiv.org/abs/2512.23573"}],"excludedFormal":[],"otherRecords":[],"matchedName":"Lu Sheng","databaseLabel":"Lu Sheng","databaseMetadata":{"type":["https://dblp.org/rdf/schema#Person","https://dblp.org/rdf/schema#Creator"],"label":["Lu Sheng"],"orcid":["https://orcid.org/0000-0002-8525-9163"]},"rawFormalRecordCount2025":17,"signatureAudit":{"completedAt":"2026-10-19","frozen":true,"scope":"对 B 组 39 个数值档案的全部 1074 条原始 2025 正式记录扫描 DBLP author-signature ORCID 和机构；复用既有 59 条 Crossref 核验，补查 6 条新触发记录。重点核查不同 ORCID，以及只有预期机构之外机构的条目。本轮不扩展为所有作者逐篇全文审计。","formalRecordCoverage":17,"orcidCounts":{"https://orcid.org/0000-0002-8525-9163":6},"institutionCounts":{"Beihang University (BUAA)":14,"Software (Spain)":1},"caveat":"机构名称可能由 DBLP 自动映射而失真；多 ORCID 也不自动等于异人。只有有原始资料支撑的错归才作确认排除，未解决分支则暂停总数。"},"labName":null,"labUrl":null,"labEvidence":"本人主页提到 MMLab@CUHK 是 2017–2019 博士后经历，未明确其当前北航实验室名称。","labSourceUrl":"https://soft.buaa.edu.cn/info/1016/1974.htm","sourceWarning":false,"excludedOther":[],"excludedHomonyms":[],"unassignedCandidates":[],"knownPreprintMinimum2025":null,"excludedMisattributed":[],"displayNotes":"原名单写作 Lv Sheng，本人使用 Lu Sheng（盛律），据此匹配；不是 DBLP 中的另一位 Lv Sheng（389/4812）。计入 17 条（会议 12、期刊 5）；预印本 17 条单列，不加总。","labDisplayNotes":"个人主页提到的 MMLab@CUHK 是 2017–2019 年的博士后经历；未见当前在北航的实验室名称。"},{"index":79,"name":"Boxin Shi","nameZh":"施柏鑫","role":"Tenured Associate Professor","affiliation":"Peking University","affiliationZh":"北京大学","source":"DBLP RDF via official SPARQL; primary-source identity checks","sourceUrl":"https://sparql.dblp.org/","profileUrl":"https://dblp.org/pid/69/783.html","identifier":"69/783","retrievedAt":"2026-10-19","count2025":43,"conference2025":32,"journal2025":11,"preprint2025":24,"status":"confirmed","notes":"排除 1 条数据库形式上属于期刊/会议的记录，逐条原因见 excludedFormal。","identityEvidence":[{"url":"https://dblp.org/pid/69/783.html","evidence":"DBLP RDF 类型为 Person，消歧后名字为 Boxin Shi。此档案未提供可用机构元数据，以下以本人/机构/出版商来源补证。"},{"url":"https://camera.pku.edu.cn/team","evidence":"北京大学 Camera Lab 官方团队页列 Boxin Shi / 施柏鑫，匹配签名机构及姓名。"},{"url":"https://camera.pku.edu.cn/publication","evidence":"该实验室官方发表页将 Boxin Shi 的最新论文列表链接至 DBLP legacy author URL Shi:Boxin，与所选个人资料相符。"}],"papers":[{"key":"conf/aaai/HuangLLQSX25","url":"https://dblp.org/rec/conf/aaai/HuangLLQSX25","title":"Zero-Shot Low-Light Image Enhancement via Latent Diffusion Models.","year":2025,"types":["Inproceedings"],"venue":"AAAI","doi":"https://doi.org/10.1609/AAAI.V39I4.32398","eventYear":2025,"numberOfCreators":6,"category":"conference","sources":["https://dblp.org/rec/conf/aaai/HuangLLQSX25","https://doi.org/10.1609/AAAI.V39I4.32398"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/aaai/HuangLLQSX25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/aaai/XiaZZXS25","url":"https://dblp.org/rec/conf/aaai/XiaZZXS25","title":"PlaNet: Learning to Mitigate Atmospheric Turbulence in Planetary Images.","year":2025,"types":["Inproceedings"],"venue":"AAAI","doi":"https://doi.org/10.1609/AAAI.V39I8.32927","eventYear":2025,"numberOfCreators":5,"category":"conference","sources":["https://dblp.org/rec/conf/aaai/XiaZZXS25","https://doi.org/10.1609/AAAI.V39I8.32927"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/aaai/XiaZZXS25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/aaai/ZhouXS25","url":"https://dblp.org/rec/conf/aaai/ZhouXS25","title":"Polarization Guided Mask-Free Shadow Removal.","year":2025,"types":["Inproceedings"],"venue":"AAAI","doi":"https://doi.org/10.1609/AAAI.V39I10.33164","eventYear":2025,"numberOfCreators":3,"category":"conference","sources":["https://dblp.org/rec/conf/aaai/ZhouXS25","https://doi.org/10.1609/AAAI.V39I10.33164"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/aaai/ZhouXS25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/cvpr/0016ADSWSTPGLYL25","url":"https://dblp.org/rec/conf/cvpr/0016ADSWSTPGLYL25","title":"NTIRE 2025 Challenge on Event-Based Image Deblurring: Methods and Results.","year":2025,"types":["Inproceedings"],"venue":"CVPR Workshops","doi":null,"eventYear":2025,"numberOfCreators":88,"category":"conference","sources":["https://dblp.org/rec/conf/cvpr/0016ADSWSTPGLYL25"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/0016ADSWSTPGLYL25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/cvpr/CaiWXS25","url":"https://dblp.org/rec/conf/cvpr/CaiWXS25","title":"PhyS-EdiT: Physics-aware Semantic Image Editing with Text Description.","year":2025,"types":["Inproceedings"],"venue":"CVPR","doi":"https://doi.org/10.1109/CVPR52734.2025.00737","eventYear":2025,"numberOfCreators":4,"category":"conference","sources":["https://dblp.org/rec/conf/cvpr/CaiWXS25","https://doi.org/10.1109/CVPR52734.2025.00737"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/CaiWXS25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/cvpr/GaoDLTC0S25","url":"https://dblp.org/rec/conf/cvpr/GaoDLTC0S25","title":"Unified Reconstruction of Static and Dynamic Scenes from Events.","year":2025,"types":["Inproceedings"],"venue":"CVPR","doi":"https://doi.org/10.1109/CVPR52734.2025.02599","eventYear":2025,"numberOfCreators":7,"category":"conference","sources":["https://dblp.org/rec/conf/cvpr/GaoDLTC0S25","https://doi.org/10.1109/CVPR52734.2025.02599"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/GaoDLTC0S25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/cvpr/TangF0TLCHCWS25","url":"https://dblp.org/rec/conf/cvpr/TangF0TLCHCWS25","title":"SpecTRe-GS: Modeling Highly Specular Surfaces with Reflected Nearby Objects by Tracing Rays in 3D Gaussian Splatting.","year":2025,"types":["Inproceedings"],"venue":"CVPR","doi":"https://doi.org/10.1109/CVPR52734.2025.01504","eventYear":2025,"numberOfCreators":10,"category":"conference","sources":["https://dblp.org/rec/conf/cvpr/TangF0TLCHCWS25","https://doi.org/10.1109/CVPR52734.2025.01504"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/TangF0TLCHCWS25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/cvpr/WengZZHJ0S25","url":"https://dblp.org/rec/conf/cvpr/WengZZHJ0S25","title":"VIRES: Video Instance Repainting via Sketch and Text Guided Generation.","year":2025,"types":["Inproceedings"],"venue":"CVPR","doi":"https://doi.org/10.1109/CVPR52734.2025.02646","eventYear":2025,"numberOfCreators":7,"category":"conference","sources":["https://dblp.org/rec/conf/cvpr/WengZZHJ0S25","https://doi.org/10.1109/CVPR52734.2025.02646"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/WengZZHJ0S25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/cvpr/Yu0SS25","url":"https://dblp.org/rec/conf/cvpr/Yu0SS25","title":"EventPSR: Surface Normal and Reflectance Estimation from Photometric Stereo Using an Event Camera.","year":2025,"types":["Inproceedings"],"venue":"CVPR","doi":"https://doi.org/10.1109/CVPR52734.2025.01067","eventYear":2025,"numberOfCreators":4,"category":"conference","sources":["https://dblp.org/rec/conf/cvpr/Yu0SS25","https://doi.org/10.1109/CVPR52734.2025.01067"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/Yu0SS25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/cvpr/YuLW0SSS25","url":"https://dblp.org/rec/conf/cvpr/YuLW0SSS25","title":"Active Hyperspectral Imaging Using an Event Camera.","year":2025,"types":["Inproceedings"],"venue":"CVPR","doi":"https://doi.org/10.1109/CVPR52734.2025.00095","eventYear":2025,"numberOfCreators":7,"category":"conference","sources":["https://dblp.org/rec/conf/cvpr/YuLW0SSS25","https://doi.org/10.1109/CVPR52734.2025.00095"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/YuLW0SSS25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/cvpr/ZhouZL0MSS25","url":"https://dblp.org/rec/conf/cvpr/ZhouZL0MSS25","title":"PIDSR: Complementary Polarized Image Demosaicing and Super-Resolution.","year":2025,"types":["Inproceedings"],"venue":"CVPR","doi":"https://doi.org/10.1109/CVPR52734.2025.01499","eventYear":2025,"numberOfCreators":7,"category":"conference","sources":["https://dblp.org/rec/conf/cvpr/ZhouZL0MSS25","https://doi.org/10.1109/CVPR52734.2025.01499"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/ZhouZL0MSS25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/eccv/HongZWLS24","url":"https://dblp.org/rec/conf/eccv/HongZWLS24","title":"L-DiffER: Single Image Reflection Removal with Language-Based Diffusion Model.","year":2025,"types":["Inproceedings"],"venue":"ECCV (20)","doi":"https://doi.org/10.1007/978-3-031-72661-3_4","eventYear":2024,"numberOfCreators":5,"category":"conference","sources":["https://dblp.org/rec/conf/eccv/HongZWLS24","https://doi.org/10.1007/978-3-031-72661-3_4"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2024,"sourceUrl":"https://dblp.org/rec/conf/eccv/HongZWLS24","documentUrl":null,"type":"Inproceedings"},{"key":"conf/eccv/LuoSLW24","url":"https://dblp.org/rec/conf/eccv/LuoSLW24","title":"Imaging Interiors: An Implicit Solution to Electromagnetic Inverse Scattering Problems.","year":2025,"types":["Inproceedings"],"venue":"ECCV (7)","doi":"https://doi.org/10.1007/978-3-031-72667-5_20","eventYear":2024,"numberOfCreators":4,"category":"conference","sources":["https://dblp.org/rec/conf/eccv/LuoSLW24","https://doi.org/10.1007/978-3-031-72667-5_20"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2024,"sourceUrl":"https://dblp.org/rec/conf/eccv/LuoSLW24","documentUrl":null,"type":"Inproceedings"},{"key":"conf/eccv/YangHCFYS24","url":"https://dblp.org/rec/conf/eccv/YangHCFYS24","title":"Real-Data-Driven 2000 FPS Color Video from Mosaicked Chromatic Spikes.","year":2025,"types":["Inproceedings"],"venue":"ECCV (12)","doi":"https://doi.org/10.1007/978-3-031-73254-6_18","eventYear":2024,"numberOfCreators":6,"category":"conference","sources":["https://dblp.org/rec/conf/eccv/YangHCFYS24","https://doi.org/10.1007/978-3-031-73254-6_18"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2024,"sourceUrl":"https://dblp.org/rec/conf/eccv/YangHCFYS24","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iccad/WeiTFSWL25","url":"https://dblp.org/rec/conf/iccad/WeiTFSWL25","title":"No Redundancy, No Stall: Lightweight Streaming 3D Gaussian Splatting for Real-time Rendering.","year":2025,"types":["Inproceedings"],"venue":"ICCAD","doi":"https://doi.org/10.1109/ICCAD66269.2025.11240950","eventYear":2025,"numberOfCreators":6,"category":"conference","sources":["https://dblp.org/rec/conf/iccad/WeiTFSWL25","https://doi.org/10.1109/ICCAD66269.2025.11240950"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iccad/WeiTFSWL25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iccv/HanTGLLSJM25","url":"https://dblp.org/rec/conf/iccv/HanTGLLSJM25","title":"PolGS: Polarimetric Gaussian Splatting for Fast Reflective Surface Reconstruction.","year":2025,"types":["Inproceedings"],"venue":"ICCV","doi":"https://doi.org/10.1109/ICCV51701.2025.02606","eventYear":2025,"numberOfCreators":8,"category":"conference","sources":["https://dblp.org/rec/conf/iccv/HanTGLLSJM25","https://doi.org/10.1109/ICCV51701.2025.02606"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/HanTGLLSJM25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iccv/LiangYYZRDS25","url":"https://dblp.org/rec/conf/iccv/LiangYYZRDS25","title":"EventUPS: Uncalibrated Photometric Stereo Using an Event Camera.","year":2025,"types":["Inproceedings"],"venue":"ICCV","doi":"https://doi.org/10.1109/ICCV51701.2025.00705","eventYear":2025,"numberOfCreators":7,"category":"conference","sources":["https://dblp.org/rec/conf/iccv/LiangYYZRDS25","https://doi.org/10.1109/ICCV51701.2025.00705"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/LiangYYZRDS25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iccv/TengLYZCRS25","url":"https://dblp.org/rec/conf/iccv/TengLYZCRS25","title":"Monochromatic Event Guided Image Deblurring with Event-Triggering-Aware Decomposition.","year":2025,"types":["Inproceedings"],"venue":"ICCVW","doi":"https://doi.org/10.1109/ICCVW69036.2025.00409","eventYear":2025,"numberOfCreators":7,"category":"conference","sources":["https://dblp.org/rec/conf/iccv/TengLYZCRS25","https://doi.org/10.1109/ICCVW69036.2025.00409"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/TengLYZCRS25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iccv/WangDSW25","url":"https://dblp.org/rec/conf/iccv/WangDSW25","title":"Asynchronous Event Error-Minimizing Noise for Safeguarding Event Dataset.","year":2025,"types":["Inproceedings"],"venue":"ICCV","doi":"https://doi.org/10.1109/ICCV51701.2025.00945","eventYear":2025,"numberOfCreators":4,"category":"conference","sources":["https://dblp.org/rec/conf/iccv/WangDSW25","https://doi.org/10.1109/ICCV51701.2025.00945"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/WangDSW25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iccv/XuZSXW25","url":"https://dblp.org/rec/conf/iccv/XuZSXW25","title":"AdaptiveAE: An Adaptive Exposure Strategy for HDR Capturing in Dynamic Scenes.","year":2025,"types":["Inproceedings"],"venue":"ICCV","doi":"https://doi.org/10.1109/ICCV51701.2025.02335","eventYear":2025,"numberOfCreators":5,"category":"conference","sources":["https://dblp.org/rec/conf/iccv/XuZSXW25","https://doi.org/10.1109/ICCV51701.2025.02335"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/XuZSXW25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iccv/YangLHXCYS25","url":"https://dblp.org/rec/conf/iccv/YangLHXCYS25","title":"SpikeDiff: Zero-Shot High-Quality Video Reconstruction from Chromatic Spike Camera and Sub-Millisecond Spike Streams.","year":2025,"types":["Inproceedings"],"venue":"ICCV","doi":"https://doi.org/10.1109/ICCV51701.2025.00741","eventYear":2025,"numberOfCreators":7,"category":"conference","sources":["https://dblp.org/rec/conf/iccv/YangLHXCYS25","https://doi.org/10.1109/ICCV51701.2025.00741"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/YangLHXCYS25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iccv/YangZZWZRS25","url":"https://dblp.org/rec/conf/iccv/YangZZWZRS25","title":"Event-Guided HDR Reconstruction with Diffusion Priors.","year":2025,"types":["Inproceedings"],"venue":"ICCV","doi":"https://doi.org/10.1109/ICCV51701.2025.01096","eventYear":2025,"numberOfCreators":7,"category":"conference","sources":["https://dblp.org/rec/conf/iccv/YangZZWZRS25","https://doi.org/10.1109/ICCV51701.2025.01096"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/YangZZWZRS25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iccv/ZhangLGLMS25","url":"https://dblp.org/rec/conf/iccv/ZhangLGLMS25","title":"PolarAnything: Diffusion-based Polarimetric Image Synthesis.","year":2025,"types":["Inproceedings"],"venue":"ICCV","doi":"https://doi.org/10.1109/ICCV51701.2025.02456","eventYear":2025,"numberOfCreators":6,"category":"conference","sources":["https://dblp.org/rec/conf/iccv/ZhangLGLMS25","https://doi.org/10.1109/ICCV51701.2025.02456"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/ZhangLGLMS25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iccv/ZhouDXXS25","url":"https://dblp.org/rec/conf/iccv/ZhouDXXS25","title":"Event-Based Visual Vibrometry.","year":2025,"types":["Inproceedings"],"venue":"ICCV","doi":"https://doi.org/10.1109/ICCV51701.2025.02287","eventYear":2025,"numberOfCreators":5,"category":"conference","sources":["https://dblp.org/rec/conf/iccv/ZhouDXXS25","https://doi.org/10.1109/ICCV51701.2025.02287"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/ZhouDXXS25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iccv/ZhouYLGSS25","url":"https://dblp.org/rec/conf/iccv/ZhouYLGSS25","title":"Polarimetric Neural Field via Unified Complex-Valued Wave Representation.","year":2025,"types":["Inproceedings"],"venue":"ICCV","doi":"https://doi.org/10.1109/ICCV51701.2025.02380","eventYear":2025,"numberOfCreators":6,"category":"conference","sources":["https://dblp.org/rec/conf/iccv/ZhouYLGSS25","https://doi.org/10.1109/ICCV51701.2025.02380"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/ZhouYLGSS25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/iccv/ZhuFZCZXS25","url":"https://dblp.org/rec/conf/iccv/ZhuFZCZXS25","title":"BokehDiff: Neural Lens Blur with One-Step Diffusion.","year":2025,"types":["Inproceedings"],"venue":"ICCV","doi":"https://doi.org/10.1109/ICCV51701.2025.00887","eventYear":2025,"numberOfCreators":7,"category":"conference","sources":["https://dblp.org/rec/conf/iccv/ZhuFZCZXS25","https://doi.org/10.1109/ICCV51701.2025.00887"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/ZhuFZCZXS25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/mm/00010ZSS25","url":"https://dblp.org/rec/conf/mm/00010ZSS25","title":"EDeF-Net: Spatio-temporal Association Network for Flicker Removal in Event Streams.","year":2025,"types":["Inproceedings"],"venue":"ACM Multimedia","doi":"https://doi.org/10.1145/3746027.3754995","eventYear":2025,"numberOfCreators":5,"category":"conference","sources":["https://dblp.org/rec/conf/mm/00010ZSS25","https://doi.org/10.1145/3746027.3754995"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/mm/00010ZSS25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/nips/LiDHZXS25","url":"https://dblp.org/rec/conf/nips/LiDHZXS25","title":"Dense Metric Depth Estimation via Event-based Differential Focus Volume Prompting.","year":2025,"types":["Inproceedings"],"venue":"NeurIPS","doi":null,"eventYear":2025,"numberOfCreators":6,"category":"conference","sources":["https://dblp.org/rec/conf/nips/LiDHZXS25"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/nips/LiDHZXS25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/nips/LouLTWS25","url":"https://dblp.org/rec/conf/nips/LouLTWS25","title":"V2V: Scaling Event-Based Vision through Efficient Video-to-Voxel Simulation.","year":2025,"types":["Inproceedings"],"venue":"NeurIPS","doi":null,"eventYear":2025,"numberOfCreators":5,"category":"conference","sources":["https://dblp.org/rec/conf/nips/LouLTWS25"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/nips/LouLTWS25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/nips/WengZCLSW25","url":"https://dblp.org/rec/conf/nips/WengZCLSW25","title":"Audio-Sync Video Generation with Multi-Stream Temporal Control.","year":2025,"types":["Inproceedings"],"venue":"NeurIPS","doi":null,"eventYear":2025,"numberOfCreators":6,"category":"conference","sources":["https://dblp.org/rec/conf/nips/WengZCLSW25"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/nips/WengZCLSW25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/nips/XiaWYLZTJJS25","url":"https://dblp.org/rec/conf/nips/XiaWYLZTJJS25","title":"PanoWan: Lifting Diffusion Video Generation Models to 360° with Latitude/Longitude-aware Mechanisms.","year":2025,"types":["Inproceedings"],"venue":"NeurIPS","doi":null,"eventYear":2025,"numberOfCreators":9,"category":"conference","sources":["https://dblp.org/rec/conf/nips/XiaWYLZTJJS25"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/nips/XiaWYLZTJJS25","documentUrl":null,"type":"Inproceedings"},{"key":"conf/wacv/Yin000S25","url":"https://dblp.org/rec/conf/wacv/Yin000S25","title":"Spk2ImgMamba: Spiking Camera Image Reconstruction with Multi-Scale State Space Models.","year":2025,"types":["Inproceedings"],"venue":"WACV","doi":"https://doi.org/10.1109/WACV61041.2025.00905","eventYear":2025,"numberOfCreators":5,"category":"conference","sources":["https://dblp.org/rec/conf/wacv/Yin000S25","https://doi.org/10.1109/WACV61041.2025.00905"],"publicationYear":2025,"yearOfPublication":2025,"yearOfEvent":2025,"sourceUrl":"https://dblp.org/rec/conf/wacv/Yin000S25","documentUrl":null,"type":"Inproceedings"},{"key":"journals/aisy/RenDDZGSZG25","url":"https://dblp.org/rec/journals/aisy/RenDDZGSZG25","title":"GelLight: Illumination Design, Modeling, and Optimization for Camera-Based Tactile Sensor.","year":2025,"types":["Article"],"venue":"Adv. Intell. Syst.","doi":"https://doi.org/10.1002/AISY.202400596","numberOfCreators":8,"category":"journal","sources":["https://dblp.org/rec/journals/aisy/RenDDZGSZG25","https://doi.org/10.1002/AISY.202400596"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/aisy/RenDDZGSZG25","documentUrl":null,"type":"Article"},{"key":"journals/ijcv/LinWZSYHXY25","url":"https://dblp.org/rec/journals/ijcv/LinWZSYHXY25","title":"Self-supervised Shutter Unrolling with Events.","year":2025,"types":["Article"],"venue":"Int. J. Comput. Vis.","doi":"https://doi.org/10.1007/S11263-025-02364-Z","numberOfCreators":8,"category":"journal","sources":["https://dblp.org/rec/journals/ijcv/LinWZSYHXY25","https://doi.org/10.1007/S11263-025-02364-Z"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/ijcv/LinWZSYHXY25","documentUrl":null,"type":"Article"},{"key":"journals/ijcv/ZhouTZXSS25","url":"https://dblp.org/rec/journals/ijcv/ZhouTZXSS25","title":"Learning to Deblur Polarized Images.","year":2025,"types":["Article"],"venue":"Int. J. Comput. Vis.","doi":"https://doi.org/10.1007/S11263-025-02459-7","numberOfCreators":6,"category":"journal","sources":["https://dblp.org/rec/journals/ijcv/ZhouTZXSS25","https://doi.org/10.1007/S11263-025-02459-7"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/ijcv/ZhouTZXSS25","documentUrl":null,"type":"Article"},{"key":"journals/pami/DuanLYLTZMS25","url":"https://dblp.org/rec/journals/pami/DuanLYLTZMS25","title":"EventAid: Benchmarking Event-Aided Image/Video Enhancement Algorithms With Real-Captured Hybrid Dataset.","year":2025,"types":["Article"],"venue":"IEEE Trans. Pattern Anal. Mach. Intell.","doi":"https://doi.org/10.1109/TPAMI.2025.3568333","numberOfCreators":8,"category":"journal","sources":["https://dblp.org/rec/journals/pami/DuanLYLTZMS25","https://doi.org/10.1109/TPAMI.2025.3568333"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/pami/DuanLYLTZMS25","documentUrl":null,"type":"Article"},{"key":"journals/pami/JuSWLJK25","url":"https://dblp.org/rec/journals/pami/JuSWLJK25","title":"Revisiting One-Stage Deep Uncalibrated Photometric Stereo via Fourier Embedding.","year":2025,"types":["Article"],"venue":"IEEE Trans. Pattern Anal. Mach. Intell.","doi":"https://doi.org/10.1109/TPAMI.2025.3557245","numberOfCreators":6,"category":"journal","sources":["https://dblp.org/rec/journals/pami/JuSWLJK25","https://doi.org/10.1109/TPAMI.2025.3557245"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/pami/JuSWLJK25","documentUrl":null,"type":"Article"},{"key":"journals/pami/LuoRSGLW25","url":"https://dblp.org/rec/journals/pami/LuoRSGLW25","title":"The NeRF Signature: Codebook-Aided Watermarking for Neural Radiance Fields.","year":2025,"types":["Article"],"venue":"IEEE Trans. Pattern Anal. Mach. Intell.","doi":"https://doi.org/10.1109/TPAMI.2025.3550166","numberOfCreators":6,"category":"journal","sources":["https://dblp.org/rec/journals/pami/LuoRSGLW25","https://doi.org/10.1109/TPAMI.2025.3550166"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/pami/LuoRSGLW25","documentUrl":null,"type":"Article"},{"key":"journals/pami/WeiLDSJPCZ25","url":"https://dblp.org/rec/journals/pami/WeiLDSJPCZ25","title":"Revisiting Supervised Learning-Based Photometric Stereo Networks.","year":2025,"types":["Article"],"venue":"IEEE Trans. Pattern Anal. Mach. Intell.","doi":"https://doi.org/10.1109/TPAMI.2025.3557498","numberOfCreators":8,"category":"journal","sources":["https://dblp.org/rec/journals/pami/WeiLDSJPCZ25","https://doi.org/10.1109/TPAMI.2025.3557498"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/pami/WeiLDSJPCZ25","documentUrl":null,"type":"Article"},{"key":"journals/pami/WengGZWLS25","url":"https://dblp.org/rec/journals/pami/WengGZWLS25","title":"OpenCIR: Conditional Image Repainting With Open Condition Mixture.","year":2025,"types":["Article"],"venue":"IEEE Trans. Pattern Anal. Mach. Intell.","doi":"https://doi.org/10.1109/TPAMI.2025.3597936","numberOfCreators":6,"category":"journal","sources":["https://dblp.org/rec/journals/pami/WengGZWLS25","https://doi.org/10.1109/TPAMI.2025.3597936"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/pami/WengGZWLS25","documentUrl":null,"type":"Article"},{"key":"journals/tcsv/FanGDXS25","url":"https://dblp.org/rec/journals/tcsv/FanGDXS25","title":"Self-Supervised Learning for Rolling Shutter Temporal Super-Resolution.","year":2025,"types":["Article"],"venue":"IEEE Trans. Circuits Syst. Video Technol.","doi":"https://doi.org/10.1109/TCSVT.2024.3462520","numberOfCreators":5,"category":"journal","sources":["https://dblp.org/rec/journals/tcsv/FanGDXS25","https://doi.org/10.1109/TCSVT.2024.3462520"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/tcsv/FanGDXS25","documentUrl":null,"type":"Article"},{"key":"journals/tcsv/HuangLLSXC25","url":"https://dblp.org/rec/journals/tcsv/HuangLLSXC25","title":"Detail-Preserving Diffusion Models for Low-Light Image Enhancement.","year":2025,"types":["Article"],"venue":"IEEE Trans. Circuits Syst. Video Technol.","doi":"https://doi.org/10.1109/TCSVT.2024.3502801","numberOfCreators":6,"category":"journal","sources":["https://dblp.org/rec/journals/tcsv/HuangLLSXC25","https://doi.org/10.1109/TCSVT.2024.3502801"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/tcsv/HuangLLSXC25","documentUrl":null,"type":"Article"},{"key":"journals/tcsv/WuZWSL25","url":"https://dblp.org/rec/journals/tcsv/WuZWSL25","title":"SweepEvGS: Event-Based 3D Gaussian Splatting for Macro and Micro Radiance Field Rendering From a Single Sweep.","year":2025,"types":["Article"],"venue":"IEEE Trans. Circuits Syst. Video Technol.","doi":"https://doi.org/10.1109/TCSVT.2025.3583735","numberOfCreators":5,"category":"journal","sources":["https://dblp.org/rec/journals/tcsv/WuZWSL25","https://doi.org/10.1109/TCSVT.2025.3583735"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/tcsv/WuZWSL25","documentUrl":null,"type":"Article"}],"preprints":[{"key":"journals/corr/abs-2502-19125","url":"https://dblp.org/rec/journals/corr/abs-2502-19125","title":"The NeRF Signature: Codebook-Aided Watermarking for Neural Radiance Fields.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2502.19125","numberOfCreators":6,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2502-19125","https://doi.org/10.48550/ARXIV.2502.19125"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2502-19125","documentUrl":null,"type":"Informal","arxivId":"2502.19125","arxivUrl":"https://arxiv.org/abs/2502.19125"},{"key":"journals/corr/abs-2504-07758","url":"https://dblp.org/rec/journals/corr/abs-2504-07758","title":"PIDSR: Complementary Polarized Image Demosaicing and Super-Resolution.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2504.07758","numberOfCreators":7,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2504-07758","https://doi.org/10.48550/ARXIV.2504.07758"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2504-07758","documentUrl":null,"type":"Informal","arxivId":"2504.07758","arxivUrl":"https://arxiv.org/abs/2504.07758"},{"key":"journals/corr/abs-2504-12401","url":"https://dblp.org/rec/journals/corr/abs-2504-12401","title":"NTIRE 2025 Challenge on Event-Based Image Deblurring: Methods and Results.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2504.12401","numberOfCreators":88,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2504-12401","https://doi.org/10.48550/ARXIV.2504.12401"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2504-12401","documentUrl":null,"type":"Informal","arxivId":"2504.12401","arxivUrl":"https://arxiv.org/abs/2504.12401"},{"key":"journals/corr/abs-2505-16797","url":"https://dblp.org/rec/journals/corr/abs-2505-16797","title":"V2V: Scaling Event-Based Vision through Efficient Video-to-Voxel Simulation.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2505.16797","numberOfCreators":5,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2505-16797","https://doi.org/10.48550/ARXIV.2505.16797"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-16797","documentUrl":null,"type":"Informal","arxivId":"2505.16797","arxivUrl":"https://arxiv.org/abs/2505.16797"},{"key":"journals/corr/abs-2505-18699","url":"https://dblp.org/rec/journals/corr/abs-2505-18699","title":"Affective Image Editing: Shaping Emotional Factors via Text Descriptions.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2505.18699","numberOfCreators":7,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2505-18699","https://doi.org/10.48550/ARXIV.2505.18699"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-18699","documentUrl":null,"type":"Informal","arxivId":"2505.18699","arxivUrl":"https://arxiv.org/abs/2505.18699"},{"key":"journals/corr/abs-2505-22016","url":"https://dblp.org/rec/journals/corr/abs-2505-22016","title":"PanoWan: Lifting Diffusion Video Generation Models to 360° with Latitude/Longitude-aware Mechanisms.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2505.22016","numberOfCreators":9,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2505-22016","https://doi.org/10.48550/ARXIV.2505.22016"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-22016","documentUrl":null,"type":"Informal","arxivId":"2505.22016","arxivUrl":"https://arxiv.org/abs/2505.22016"},{"key":"journals/corr/abs-2505-22394","url":"https://dblp.org/rec/journals/corr/abs-2505-22394","title":"PacTure: Efficient PBR Texture Generation on Packed Views with Visual Autoregressive Models.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2505.22394","numberOfCreators":5,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2505-22394","https://doi.org/10.48550/ARXIV.2505.22394"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-22394","documentUrl":null,"type":"Informal","arxivId":"2505.22394","arxivUrl":"https://arxiv.org/abs/2505.22394"},{"key":"journals/corr/abs-2506-08003","url":"https://dblp.org/rec/journals/corr/abs-2506-08003","title":"Audio-Sync Video Generation with Multi-Stream Temporal Control.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2506.08003","numberOfCreators":6,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2506-08003","https://doi.org/10.48550/ARXIV.2506.08003"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-08003","documentUrl":null,"type":"Informal","arxivId":"2506.08003","arxivUrl":"https://arxiv.org/abs/2506.08003"},{"key":"journals/corr/abs-2506-18882","url":"https://dblp.org/rec/journals/corr/abs-2506-18882","title":"Light of Normals: Unified Feature Representation for Universal Photometric Stereo.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2506.18882","numberOfCreators":14,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2506-18882","https://doi.org/10.48550/ARXIV.2506.18882"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-18882","documentUrl":null,"type":"Informal","arxivId":"2506.18882","arxivUrl":"https://arxiv.org/abs/2506.18882"},{"key":"journals/corr/abs-2507-05728","url":"https://dblp.org/rec/journals/corr/abs-2507-05728","title":"Asynchronous Event Error-Minimizing Noise for Safeguarding Event Dataset.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2507.05728","numberOfCreators":4,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2507-05728","https://doi.org/10.48550/ARXIV.2507.05728"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2507-05728","documentUrl":null,"type":"Informal","arxivId":"2507.05728","arxivUrl":"https://arxiv.org/abs/2507.05728"},{"key":"journals/corr/abs-2507-11931","url":"https://dblp.org/rec/journals/corr/abs-2507-11931","title":"Dark-EvGS: Event Camera as an Eye for Radiance Field in the Dark.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2507.11931","numberOfCreators":6,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2507-11931","https://doi.org/10.48550/ARXIV.2507.11931"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2507-11931","documentUrl":null,"type":"Informal","arxivId":"2507.11931","arxivUrl":"https://arxiv.org/abs/2507.11931"},{"key":"journals/corr/abs-2507-17268","url":"https://dblp.org/rec/journals/corr/abs-2507-17268","title":"PolarAnything: Diffusion-based Polarimetric Image Synthesis.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2507.17268","numberOfCreators":6,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2507-17268","https://doi.org/10.48550/ARXIV.2507.17268"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2507-17268","documentUrl":null,"type":"Informal","arxivId":"2507.17268","arxivUrl":"https://arxiv.org/abs/2507.17268"},{"key":"journals/corr/abs-2507-18060","url":"https://dblp.org/rec/journals/corr/abs-2507-18060","title":"BokehDiff: Neural Lens Blur with One-Step Diffusion.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2507.18060","numberOfCreators":7,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2507-18060","https://doi.org/10.48550/ARXIV.2507.18060"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2507-18060","documentUrl":null,"type":"Informal","arxivId":"2507.18060","arxivUrl":"https://arxiv.org/abs/2507.18060"},{"key":"journals/corr/abs-2507-21572","url":"https://dblp.org/rec/journals/corr/abs-2507-21572","title":"No Redundancy, No Stall: Lightweight Streaming 3D Gaussian Splatting for Real-time Rendering.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2507.21572","numberOfCreators":6,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2507-21572","https://doi.org/10.48550/ARXIV.2507.21572"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2507-21572","documentUrl":null,"type":"Informal","arxivId":"2507.21572","arxivUrl":"https://arxiv.org/abs/2507.21572"},{"key":"journals/corr/abs-2508-10582","url":"https://dblp.org/rec/journals/corr/abs-2508-10582","title":"EvTurb: Event Camera Guided Turbulence Removal.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2508.10582","numberOfCreators":5,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2508-10582","https://doi.org/10.48550/ARXIV.2508.10582"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-10582","documentUrl":null,"type":"Informal","arxivId":"2508.10582","arxivUrl":"https://arxiv.org/abs/2508.10582"},{"key":"journals/corr/abs-2508-13503","url":"https://dblp.org/rec/journals/corr/abs-2508-13503","title":"AdaptiveAE: An Adaptive Exposure Strategy for HDR Capturing in Dynamic Scenes.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2508.13503","numberOfCreators":5,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2508-13503","https://doi.org/10.48550/ARXIV.2508.13503"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-13503","documentUrl":null,"type":"Informal","arxivId":"2508.13503","arxivUrl":"https://arxiv.org/abs/2508.13503"},{"key":"journals/corr/abs-2509-19726","url":"https://dblp.org/rec/journals/corr/abs-2509-19726","title":"PolGS: Polarimetric Gaussian Splatting for Fast Reflective Surface Reconstruction.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2509.19726","numberOfCreators":8,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2509-19726","https://doi.org/10.48550/ARXIV.2509.19726"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-19726","documentUrl":null,"type":"Informal","arxivId":"2509.19726","arxivUrl":"https://arxiv.org/abs/2509.19726"},{"key":"journals/corr/abs-2510-16791","url":"https://dblp.org/rec/journals/corr/abs-2510-16791","title":"Personalized Image Filter: Mastering Your Photographic Style.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2510.16791","numberOfCreators":7,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2510-16791","https://doi.org/10.48550/ARXIV.2510.16791"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-16791","documentUrl":null,"type":"Informal","arxivId":"2510.16791","arxivUrl":"https://arxiv.org/abs/2510.16791"},{"key":"journals/corr/abs-2511-18287","url":"https://dblp.org/rec/journals/corr/abs-2511-18287","title":"TRIDENT: A Trimodal Cascade Generative Framework for Drug and RNA-Conditioned Cellular Morphology Synthesis.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2511.18287","numberOfCreators":6,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2511-18287","https://doi.org/10.48550/ARXIV.2511.18287"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2511-18287","documentUrl":null,"type":"Informal","arxivId":"2511.18287","arxivUrl":"https://arxiv.org/abs/2511.18287"},{"key":"journals/corr/abs-2512-03044","url":"https://dblp.org/rec/journals/corr/abs-2512-03044","title":"Video2Act: A Dual-System Video Diffusion Policy with Robotic Spatio-Motional Modeling.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2512.03044","numberOfCreators":10,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2512-03044","https://doi.org/10.48550/ARXIV.2512.03044"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-03044","documentUrl":null,"type":"Informal","arxivId":"2512.03044","arxivUrl":"https://arxiv.org/abs/2512.03044"},{"key":"journals/corr/abs-2512-10571","url":"https://dblp.org/rec/journals/corr/abs-2512-10571","title":"Audio-sync Video Instance Editing with Granularity-Aware Mask Refiner.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2512.10571","numberOfCreators":6,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2512-10571","https://doi.org/10.48550/ARXIV.2512.10571"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-10571","documentUrl":null,"type":"Informal","arxivId":"2512.10571","arxivUrl":"https://arxiv.org/abs/2512.10571"},{"key":"journals/corr/abs-2512-11510","url":"https://dblp.org/rec/journals/corr/abs-2512-11510","title":"Reconstruction as a Bridge for Event-Based Visual Question Answering.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2512.11510","numberOfCreators":7,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2512-11510","https://doi.org/10.48550/ARXIV.2512.11510"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-11510","documentUrl":null,"type":"Informal","arxivId":"2512.11510","arxivUrl":"https://arxiv.org/abs/2512.11510"},{"key":"journals/corr/abs-2512-12372","url":"https://dblp.org/rec/journals/corr/abs-2512-12372","title":"STAGE: Storyboard-Anchored Generation for Cinematic Multi-shot Narrative.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2512.12372","numberOfCreators":6,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2512-12372","https://doi.org/10.48550/ARXIV.2512.12372"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-12372","documentUrl":null,"type":"Informal","arxivId":"2512.12372","arxivUrl":"https://arxiv.org/abs/2512.12372"},{"key":"journals/corr/abs-2512-17376","url":"https://dblp.org/rec/journals/corr/abs-2512-17376","title":"Towards Deeper Emotional Reflection: Crafting Affective Image Filters with Generative Priors.","year":2025,"types":["Informal"],"venue":"CoRR","doi":"https://doi.org/10.48550/ARXIV.2512.17376","numberOfCreators":5,"category":"preprint","sources":["https://dblp.org/rec/journals/corr/abs-2512-17376","https://doi.org/10.48550/ARXIV.2512.17376"],"publicationYear":2025,"eventYear":null,"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-17376","documentUrl":null,"type":"Informal","arxivId":"2512.17376","arxivUrl":"https://arxiv.org/abs/2512.17376"}],"excludedFormal":[{"key":"journals/pami/ShiVHH25","url":"https://dblp.org/rec/journals/pami/ShiVHH25","title":"Guest Editorial: Introduction to the Special Section on Computational Photography.","year":2025,"types":["Article"],"venue":"IEEE Trans. Pattern Anal. Mach. Intell.","doi":"https://doi.org/10.1109/TPAMI.2025.3584422","numberOfCreators":4,"category":"journal","sources":["https://dblp.org/rec/journals/pami/ShiVHH25","https://doi.org/10.1109/TPAMI.2025.3584422"],"publicationYear":2025,"eventYear":null,"exclusionReason":"标题为 Guest Editorial；不计研究论文。","exclusionReasonCode":"non_research_front_matter","exclusionSources":["https://dblp.org/rec/journals/pami/ShiVHH25"],"yearOfPublication":2025,"yearOfEvent":null,"sourceUrl":"https://dblp.org/rec/journals/pami/ShiVHH25","documentUrl":null,"type":"Article"}],"otherRecords":[],"matchedName":"Boxin Shi","databaseLabel":"Boxin Shi","databaseMetadata":{"type":["https://dblp.org/rdf/schema#Person","https://dblp.org/rdf/schema#Creator"],"label":["Boxin Shi"],"orcid":["https://orcid.org/0000-0001-6749-0364"]},"rawFormalRecordCount2025":44,"signatureAudit":{"completedAt":"2026-10-19","frozen":true,"scope":"对 B 组 39 个数值档案的全部 1074 条原始 2025 正式记录扫描 DBLP author-signature ORCID 和机构；复用既有 59 条 Crossref 核验，补查 6 条新触发记录。重点核查不同 ORCID，以及只有预期机构之外机构的条目。本轮不扩展为所有作者逐篇全文审计。","formalRecordCoverage":44,"orcidCounts":{"https://orcid.org/0000-0001-6749-0364":23},"institutionCounts":{"Peking University (PKU)":36},"caveat":"机构名称可能由 DBLP 自动映射而失真；多 ORCID 也不自动等于异人。只有有原始资料支撑的错归才作确认排除，未解决分支则暂停总数。"},"labName":"Camera Intelligence Lab","labUrl":"https://camera.pku.edu.cn/","labEvidence":"北京大学官方团队页将 Boxin Shi / 施柏鑫列为 Principal Investigator，并明确写其 leads the Camera Intelligence Lab；此前北京大学教师页也说明其带领 Camera Intelligence Group。","labSourceUrl":"https://camera.pku.edu.cn/team","sourceWarning":false,"excludedOther":[],"excludedHomonyms":[],"unassignedCandidates":[],"knownPreprintMinimum2025":null,"excludedMisattributed":[],"displayNotes":"身份已确认。另排除 1 条形式上属于期刊或会议的记录，逐条原因见排除记录。计入 43 条（会议 32、期刊 11），所有作者位置均计入；预印本 24 条单列，不加总。","labDisplayNotes":"北大官方团队页列其为 PI，并写明其领导 Camera Intelligence Lab，据此归组。"},{"index":80,"name":"Jie Song","nameZh":"宋杰","affiliation":"The Hong Kong University of Science and Technology (Guangzhou)","source":"DBLP Knowledge Graph official SPARQL API","profileUrl":"https://dblp.org/pid/09/4756-6","identifier":"09/4756-6","identityEvidence":[{"url":"https://dblp.org/pid/09/4756-6","evidence":"DBLP curated profile affiliations: ETH Zurich, Switzerland."},{"url":"https://facultyprofiles.hkust-gz.edu.cn/faculty-personal-page/SONG-Jie/jsongroas","evidence":"School profile identifies 宋杰, HKUST(GZ), PhD ETH Zurich 2021; DBLP candidate is Jie Song 0006, ETH Zurich."},{"url":"https://eth-ait.github.io/ODHSR/","evidence":"2025 CVPR project lists Jie Song with ETH / HKUST(GZ) / HKUST affiliations; title is in selected DBLP profile."}],"count2025":11,"conference2025":10,"journal2025":1,"preprint2025":9,"status":"verified","notes":"Counts are DBLP indexed coauthored records, not first-author counts, laboratory totals, unique scientific discoveries, or quality assessments. DBLP yearOfPublication=2025; yearOfEvent retained and can differ. Conference workshops are included. Preprints are separate and may overlap formal versions.","papers":[{"key":"conf/cvpr/ZhangKX0O25","title":"ODHSR: Online Dense 3D Reconstruction of Humans and Scenes from Monocular Videos.","year":2025,"yearOfEvent":2025,"venue":"CVPR","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/CVPR52734.2025.02033"],"source":"https://dblp.org/rec/conf/cvpr/ZhangKX0O25","documentPage":"https://openaccess.thecvf.com/content/CVPR2025/html/Zhang_ODHSR_Online_Dense_3D_Reconstruction_of_Humans_and_Scenes_from_CVPR_2025_paper.html","type":"Inproceedings","doi":"https://doi.org/10.1109/CVPR52734.2025.02033","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/ZhangKX0O25","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Zhang_ODHSR_Online_Dense_3D_Reconstruction_of_Humans_and_Scenes_from_CVPR_2025_paper.html"},{"key":"conf/cvpr/ZhengXZ025","title":"GauSTAR: Gaussian Surface Tracking and Reconstruction.","year":2025,"yearOfEvent":2025,"venue":"CVPR","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/CVPR52734.2025.01542"],"source":"https://dblp.org/rec/conf/cvpr/ZhengXZ025","documentPage":"https://openaccess.thecvf.com/content/CVPR2025/html/Zheng_GauSTAR_Gaussian_Surface_Tracking_and_Reconstruction_CVPR_2025_paper.html","type":"Inproceedings","doi":"https://doi.org/10.1109/CVPR52734.2025.01542","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/ZhengXZ025","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Zheng_GauSTAR_Gaussian_Surface_Tracking_and_Reconstruction_CVPR_2025_paper.html"},{"key":"conf/eccv/GuoJKZVSH24","title":"ReLoo: Reconstructing Humans Dressed in Loose Garments from Monocular Video in the Wild.","year":2025,"yearOfEvent":2024,"venue":"ECCV (9)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1007/978-3-031-72673-6_2"],"source":"https://dblp.org/rec/conf/eccv/GuoJKZVSH24","documentPage":"https://doi.org/10.1007/978-3-031-72673-6_2","type":"Inproceedings","doi":"https://doi.org/10.1007/978-3-031-72673-6_2","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/eccv/GuoJKZVSH24","documentUrl":"https://doi.org/10.1007/978-3-031-72673-6_2"},{"key":"conf/eccv/JiangBMZEOPHKS24","title":"WorldPose: A World Cup Dataset for Global 3D Human Pose Estimation.","year":2025,"yearOfEvent":2024,"venue":"ECCV (19)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1007/978-3-031-72655-2_20"],"source":"https://dblp.org/rec/conf/eccv/JiangBMZEOPHKS24","documentPage":"https://doi.org/10.1007/978-3-031-72655-2_20","type":"Inproceedings","doi":"https://doi.org/10.1007/978-3-031-72655-2_20","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/eccv/JiangBMZEOPHKS24","documentUrl":"https://doi.org/10.1007/978-3-031-72655-2_20"},{"key":"conf/eccv/LuDSH24","title":"AvatarPose: Avatar-Guided 3D Pose Estimation of Close Human Interaction from Sparse Multi-view Videos.","year":2025,"yearOfEvent":2024,"venue":"ECCV (53)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1007/978-3-031-73668-1_13"],"source":"https://dblp.org/rec/conf/eccv/LuDSH24","documentPage":"https://doi.org/10.1007/978-3-031-73668-1_13","type":"Inproceedings","doi":"https://doi.org/10.1007/978-3-031-73668-1_13","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/eccv/LuDSH24","documentUrl":"https://doi.org/10.1007/978-3-031-73668-1_13"},{"key":"conf/eccv/XueGZWJHKSH24","title":"HSR: Holistic 3D Human-Scene Reconstruction from Monocular Videos.","year":2025,"yearOfEvent":2024,"venue":"ECCV (72)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1007/978-3-031-73220-1_25"],"source":"https://dblp.org/rec/conf/eccv/XueGZWJHKSH24","documentPage":"https://doi.org/10.1007/978-3-031-73220-1_25","type":"Inproceedings","doi":"https://doi.org/10.1007/978-3-031-73220-1_25","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/eccv/XueGZWJHKSH24","documentUrl":"https://doi.org/10.1007/978-3-031-73220-1_25"},{"key":"conf/eccv/ZhangCFHS24","title":"GraspXL: Generating Grasping Motions for Diverse Objects at Scale.","year":2025,"yearOfEvent":2024,"venue":"ECCV (26)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1007/978-3-031-73347-5_22"],"source":"https://dblp.org/rec/conf/eccv/ZhangCFHS24","documentPage":"https://doi.org/10.1007/978-3-031-73347-5_22","type":"Inproceedings","doi":"https://doi.org/10.1007/978-3-031-73347-5_22","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/eccv/ZhangCFHS24","documentUrl":"https://doi.org/10.1007/978-3-031-73347-5_22"},{"key":"conf/iccv/DongDSBG25","title":"MoGA: 3D Generative Avatar Prior for Monocular Gaussian Avatar Reconstruction.","year":2025,"yearOfEvent":2025,"venue":"ICCV","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/ICCV51701.2025.01236"],"source":"https://dblp.org/rec/conf/iccv/DongDSBG25","documentPage":"https://doi.org/10.1109/ICCV51701.2025.01236","type":"Inproceedings","doi":"https://doi.org/10.1109/ICCV51701.2025.01236","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/DongDSBG25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.01236"},{"key":"conf/iccv/WangHPGFS25","title":"MagicHOI: Leveraging 3D Priors for Accurate Hand-Object Reconstruction from Short Monocular Video Clips.","year":2025,"yearOfEvent":2025,"venue":"ICCV","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/ICCV51701.2025.00563"],"source":"https://dblp.org/rec/conf/iccv/WangHPGFS25","documentPage":"https://doi.org/10.1109/ICCV51701.2025.00563","type":"Inproceedings","doi":"https://doi.org/10.1109/ICCV51701.2025.00563","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/WangHPGFS25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.00563"},{"key":"conf/siggrapha/JiangHK025","title":"PriorAvatar: Efficient and Robust Avatar Creation from Monocular Video Using Learned Priors.","year":2025,"yearOfEvent":2025,"venue":"SIGGRAPH Asia","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1145/3757377.3763978"],"source":"https://dblp.org/rec/conf/siggrapha/JiangHK025","documentPage":"https://doi.org/10.1145/3757377.3763978","type":"Inproceedings","doi":"https://doi.org/10.1145/3757377.3763978","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/siggrapha/JiangHK025","documentUrl":"https://doi.org/10.1145/3757377.3763978"},{"key":"journals/ral/HuangZWCS25","title":"FunGrasp: Functional Grasping for Diverse Dexterous Hands.","year":2025,"yearOfEvent":null,"venue":"IEEE Robotics Autom. Lett.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1109/LRA.2025.3561573"],"source":"https://dblp.org/rec/journals/ral/HuangZWCS25","documentPage":"https://doi.org/10.1109/LRA.2025.3561573","type":"Article","doi":"https://doi.org/10.1109/LRA.2025.3561573","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/ral/HuangZWCS25","documentUrl":"https://doi.org/10.1109/LRA.2025.3561573"}],"preprints":[{"key":"journals/corr/abs-2501-02771","title":"WorldPose: A World Cup Dataset for Global 3D Human Pose Estimation.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2501.02771"],"source":"https://dblp.org/rec/journals/corr/abs-2501-02771","documentPage":"https://doi.org/10.48550/ARXIV.2501.02771","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2501.02771","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2501-02771","documentUrl":"https://doi.org/10.48550/ARXIV.2501.02771","arxivId":"2501.02771","arxivUrl":"https://arxiv.org/abs/2501.02771"},{"key":"journals/corr/abs-2501-10283","title":"GSTAR: Gaussian Surface Tracking and Reconstruction.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2501.10283"],"source":"https://dblp.org/rec/journals/corr/abs-2501-10283","documentPage":"https://doi.org/10.48550/ARXIV.2501.10283","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2501.10283","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2501-10283","documentUrl":"https://doi.org/10.48550/ARXIV.2501.10283","arxivId":"2501.10283","arxivUrl":"https://arxiv.org/abs/2501.10283"},{"key":"journals/corr/abs-2501-12289","title":"Regressor-Guided Image Editing Regulates Emotional Response to Reduce Online Engagement.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2501.12289"],"source":"https://dblp.org/rec/journals/corr/abs-2501-12289","documentPage":"https://doi.org/10.48550/ARXIV.2501.12289","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2501.12289","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2501-12289","documentUrl":"https://doi.org/10.48550/ARXIV.2501.12289","arxivId":"2501.12289","arxivUrl":"https://arxiv.org/abs/2501.12289"},{"key":"journals/corr/abs-2504-01358","title":"3D Gaussian Inverse Rendering with Approximated Global Illumination.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2504.01358"],"source":"https://dblp.org/rec/journals/corr/abs-2504-01358","documentPage":"https://doi.org/10.48550/ARXIV.2504.01358","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2504.01358","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2504-01358","documentUrl":"https://doi.org/10.48550/ARXIV.2504.01358","arxivId":"2504.01358","arxivUrl":"https://arxiv.org/abs/2504.01358"},{"key":"journals/corr/abs-2504-05287","title":"RobustDexGrasp: Robust Dexterous Grasping of General Objects from Single-view Perception.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2504.05287"],"source":"https://dblp.org/rec/journals/corr/abs-2504-05287","documentPage":"https://doi.org/10.48550/ARXIV.2504.05287","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2504.05287","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2504-05287","documentUrl":"https://doi.org/10.48550/ARXIV.2504.05287","arxivId":"2504.05287","arxivUrl":"https://arxiv.org/abs/2504.05287"},{"key":"journals/corr/abs-2504-13167","title":"ODHSR: Online Dense 3D Reconstruction of Humans and Scenes from Monocular Videos.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2504.13167"],"source":"https://dblp.org/rec/journals/corr/abs-2504-13167","documentPage":"https://doi.org/10.48550/ARXIV.2504.13167","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2504.13167","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2504-13167","documentUrl":"https://doi.org/10.48550/ARXIV.2504.13167","arxivId":"2504.13167","arxivUrl":"https://arxiv.org/abs/2504.13167"},{"key":"journals/corr/abs-2506-01950","title":"DualMap: Online Open-Vocabulary Semantic Mapping for Natural Language Navigation in Dynamic Changing Scenes.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2506.01950"],"source":"https://dblp.org/rec/journals/corr/abs-2506-01950","documentPage":"https://doi.org/10.48550/ARXIV.2506.01950","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2506.01950","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-01950","documentUrl":"https://doi.org/10.48550/ARXIV.2506.01950","arxivId":"2506.01950","arxivUrl":"https://arxiv.org/abs/2506.01950"},{"key":"journals/corr/abs-2507-23597","title":"MoGA: 3D Generative Avatar Prior for Monocular Gaussian Avatar Reconstruction.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2507.23597"],"source":"https://dblp.org/rec/journals/corr/abs-2507-23597","documentPage":"https://doi.org/10.48550/ARXIV.2507.23597","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2507.23597","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2507-23597","documentUrl":"https://doi.org/10.48550/ARXIV.2507.23597","arxivId":"2507.23597","arxivUrl":"https://arxiv.org/abs/2507.23597"},{"key":"journals/corr/abs-2508-05506","title":"MagicHOI: Leveraging 3D Priors for Accurate Hand-object Reconstruction from Short Monocular Video Clips.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2508.05506"],"source":"https://dblp.org/rec/journals/corr/abs-2508-05506","documentPage":"https://doi.org/10.48550/ARXIV.2508.05506","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2508.05506","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-05506","documentUrl":"https://doi.org/10.48550/ARXIV.2508.05506","arxivId":"2508.05506","arxivUrl":"https://arxiv.org/abs/2508.05506"}],"excludedFormal":[],"excludedOther":[],"excludedHomonyms":[],"unassignedCandidates":[],"retrievedAt":"2026-10-19","querySource":"https://sparql.dblp.org/","method":"DBLP yearOfPublication=2025; Article + Inproceedings; excludes Informal/CoRR and explicit editorial/correction/erratum/preface; unique DBLP record keys within person.","labName":null,"labUrl":null,"labEvidence":"港科大广州官方教师页及定向检索未获得当前命名Lab的直接证据；ETH AIT是旧任职，不能当作当前组。","labSourceUrl":"https://facultyprofiles.hkust-gz.edu.cn/faculty-personal-page/SONG-Jie/jsongroas","affiliationZh":"香港科技大学（广州）","sourceWarning":false,"knownPreprintMinimum2025":null,"excludedMisattributed":[],"displayNotes":"身份已经个人或机构主页核对。2025 年正式记录 11 条（会议 10、期刊 1），所有作者位置均计入，不表示主导或贡献份额；预印本 9 条单列，不加总。","labDisplayNotes":"港科大（广州）官方教师页未见当前实验室名称；ETH AIT 是旧任职，不采用。图中以「姓名及合作者」单列。"},{"index":81,"name":"Hang Su","nameZh":"苏航","affiliation":"Tsinghua University","source":"DBLP Knowledge Graph official SPARQL API","profileUrl":"https://dblp.org/pid/26/5371-6","identifier":"26/5371-6","identityEvidence":[{"url":"https://dblp.org/pid/26/5371-6","evidence":"DBLP curated profile affiliations: Tsinghua University, Department of Computer Science and Technology, Beijing, China; Tsinghua University, Tsinghua-Bosch Joint Center for ML, BNRist Center, THBI Lab, Beijing, China."},{"url":"https://dblp.org/pid/26/5371-6","evidence":"DBLP curated profile homepages: https://openreview.net/profile?id=~Hang_Su3."}],"count2025":30,"conference2025":15,"journal2025":15,"preprint2025":28,"status":"verified","notes":"Counts are DBLP indexed coauthored records, not first-author counts, laboratory totals, unique scientific discoveries, or quality assessments. DBLP yearOfPublication=2025; yearOfEvent retained and can differ. Conference workshops are included. Preprints are separate and may overlap formal versions.","papers":[{"key":"conf/eccv/KangDWRCSW24","title":"DIFFender: Diffusion-Based Adversarial Defense Against Patch Attacks.","year":2025,"yearOfEvent":2024,"venue":"ECCV (52)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1007/978-3-031-72943-0_8"],"source":"https://dblp.org/rec/conf/eccv/KangDWRCSW24","documentPage":"https://doi.org/10.1007/978-3-031-72943-0_8","type":"Inproceedings","doi":"https://doi.org/10.1007/978-3-031-72943-0_8","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/eccv/KangDWRCSW24","documentUrl":"https://doi.org/10.1007/978-3-031-72943-0_8"},{"key":"conf/eccv/KongCWSHYL24","title":"Controllable Navigation Instruction Generation with Chain of Thought Prompting.","year":2025,"yearOfEvent":2024,"venue":"ECCV (29)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1007/978-3-031-73397-0_3"],"source":"https://dblp.org/rec/conf/eccv/KongCWSHYL24","documentPage":"https://doi.org/10.1007/978-3-031-73397-0_3","type":"Inproceedings","doi":"https://doi.org/10.1007/978-3-031-73397-0_3","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/eccv/KongCWSHYL24","documentUrl":"https://doi.org/10.1007/978-3-031-73397-0_3"},{"key":"conf/eccv/LiuCLZLRZYSZZGL24","title":"LLaVA-Plus: Learning to Use Tools for Creating Multimodal Agents.","year":2025,"yearOfEvent":2024,"venue":"ECCV (47)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1007/978-3-031-72970-6_8"],"source":"https://dblp.org/rec/conf/eccv/LiuCLZLRZYSZZGL24","documentPage":"https://doi.org/10.1007/978-3-031-72970-6_8","type":"Inproceedings","doi":"https://doi.org/10.1007/978-3-031-72970-6_8","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/eccv/LiuCLZLRZYSZZGL24","documentUrl":"https://doi.org/10.1007/978-3-031-72970-6_8"},{"key":"conf/eccv/LiuZRLZYJLYSZZ24","title":"Grounding DINO: Marrying DINO with Grounded Pre-training for Open-Set Object Detection.","year":2025,"yearOfEvent":2024,"venue":"ECCV (47)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1007/978-3-031-72970-6_3"],"source":"https://dblp.org/rec/conf/eccv/LiuZRLZYJLYSZZ24","documentPage":"https://doi.org/10.1007/978-3-031-72970-6_3","type":"Inproceedings","doi":"https://doi.org/10.1007/978-3-031-72970-6_3","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/eccv/LiuZRLZYJLYSZZ24","documentUrl":"https://doi.org/10.1007/978-3-031-72970-6_3"},{"key":"conf/eccv/RuanDLHSW24","title":"Omniview-Tuning: Boosting Viewpoint Invariance of Vision-Language Pre-training Models.","year":2025,"yearOfEvent":2024,"venue":"ECCV (26)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1007/978-3-031-73347-5_18"],"source":"https://dblp.org/rec/conf/eccv/RuanDLHSW24","documentPage":"https://doi.org/10.1007/978-3-031-73347-5_18","type":"Inproceedings","doi":"https://doi.org/10.1007/978-3-031-73347-5_18","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/eccv/RuanDLHSW24","documentUrl":"https://doi.org/10.1007/978-3-031-73347-5_18"},{"key":"conf/eccv/WangWCXCYLSZ24","title":"CRM: Single Image to 3D Textured Mesh with Convolutional Reconstruction Model.","year":2025,"yearOfEvent":2024,"venue":"ECCV (31)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1007/978-3-031-72751-1_4"],"source":"https://dblp.org/rec/conf/eccv/WangWCXCYLSZ24","documentPage":"https://doi.org/10.1007/978-3-031-72751-1_4","type":"Inproceedings","doi":"https://doi.org/10.1007/978-3-031-72751-1_4","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/eccv/WangWCXCYLSZ24","documentUrl":"https://doi.org/10.1007/978-3-031-72751-1_4"},{"key":"conf/emnlp/ZhangZDS25","title":"Exploring the Generalizability of Factual Hallucination Mitigation via Enhancing Precise Knowledge Utilization.","year":2025,"yearOfEvent":2025,"venue":"EMNLP (Findings)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.18653/V1/2025.FINDINGS-EMNLP.211"],"source":"https://dblp.org/rec/conf/emnlp/ZhangZDS25","documentPage":"https://doi.org/10.18653/V1/2025.FINDINGS-EMNLP.211","type":"Inproceedings","doi":"https://doi.org/10.18653/V1/2025.FINDINGS-EMNLP.211","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/emnlp/ZhangZDS25","documentUrl":"https://doi.org/10.18653/V1/2025.FINDINGS-EMNLP.211"},{"key":"conf/iccv/RuanLHWKSDW25","title":"AdvDreamer Unveils: Are Vision-Language Models Truly Ready for Real-World 3D Variations?","year":2025,"yearOfEvent":2025,"venue":"ICCV","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/ICCV51701.2025.00740"],"source":"https://dblp.org/rec/conf/iccv/RuanLHWKSDW25","documentPage":"https://doi.org/10.1109/ICCV51701.2025.00740","type":"Inproceedings","doi":"https://doi.org/10.1109/ICCV51701.2025.00740","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/RuanLHWKSDW25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.00740"},{"key":"conf/iclr/ChenSSZ25","title":"Toward Guidance-Free AR Visual Generation via Condition Contrastive Alignment.","year":2025,"yearOfEvent":2025,"venue":"ICLR","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/iclr/ChenSSZ25","documentPage":"https://openreview.net/forum?id=kGvXIlIVLM","type":"Inproceedings","doi":null,"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iclr/ChenSSZ25","documentUrl":"https://openreview.net/forum?id=kGvXIlIVLM"},{"key":"conf/iclr/LiuWLTCWX0025","title":"RDT-1B: a Diffusion Foundation Model for Bimanual Manipulation.","year":2025,"yearOfEvent":2025,"venue":"ICLR","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/iclr/LiuWLTCWX0025","documentPage":"https://openreview.net/forum?id=yAzN4tz7oI","type":"Inproceedings","doi":null,"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iclr/LiuWLTCWX0025","documentUrl":"https://openreview.net/forum?id=yAzN4tz7oI"},{"key":"conf/icml/ChengLWHZH025","title":"Accelerating PDE-Constrained Optimization by the Derivative of Neural Operators.","year":2025,"yearOfEvent":2025,"venue":"ICML","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/icml/ChengLWHZH025","documentPage":"https://proceedings.mlr.press/v267/cheng25f.html","type":"Inproceedings","doi":null,"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/icml/ChengLWHZH025","documentUrl":"https://proceedings.mlr.press/v267/cheng25f.html"},{"key":"conf/icml/ChenJZ00025","title":"Visual Generation Without Guidance.","year":2025,"yearOfEvent":2025,"venue":"ICML","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/icml/ChenJZ00025","documentPage":"https://proceedings.mlr.press/v267/chen25ac.html","type":"Inproceedings","doi":null,"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/icml/ChenJZ00025","documentUrl":"https://proceedings.mlr.press/v267/chen25ac.html"},{"key":"conf/icml/Zeng0WL25","title":"Graph Diffusion for Robust Multi-Agent Coordination.","year":2025,"yearOfEvent":2025,"venue":"ICML","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/icml/Zeng0WL25","documentPage":"https://proceedings.mlr.press/v267/zeng25f.html","type":"Inproceedings","doi":null,"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/icml/Zeng0WL25","documentUrl":"https://proceedings.mlr.press/v267/zeng25f.html"},{"key":"conf/ijcai/ZhouY00025","title":"Self-Consistent Model-based Adaptation for Visual Reinforcement Learning.","year":2025,"yearOfEvent":2025,"venue":"IJCAI","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.24963/IJCAI.2025/800"],"source":"https://dblp.org/rec/conf/ijcai/ZhouY00025","documentPage":"https://doi.org/10.24963/IJCAI.2025/800","type":"Inproceedings","doi":"https://doi.org/10.24963/IJCAI.2025/800","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/ijcai/ZhouY00025","documentUrl":"https://doi.org/10.24963/IJCAI.2025/800"},{"key":"conf/naacl/ChenYFTDYS25","title":"AutoBreach: Universal and Adaptive Jailbreaking with Efficient Wordplay-Guided Optimization via Multi-LLMs.","year":2025,"yearOfEvent":2025,"venue":"NAACL (Findings)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.18653/V1/2025.FINDINGS-NAACL.378"],"source":"https://dblp.org/rec/conf/naacl/ChenYFTDYS25","documentPage":"https://doi.org/10.18653/V1/2025.FINDINGS-NAACL.378","type":"Inproceedings","doi":"https://doi.org/10.18653/V1/2025.FINDINGS-NAACL.378","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/naacl/ChenYFTDYS25","documentUrl":"https://doi.org/10.18653/V1/2025.FINDINGS-NAACL.378"},{"key":"journals/ijcv/LiuDXYSZCHXZ25","title":"A Comprehensive Study on Robustness of Image Classification Models: Benchmarking and Rethinking.","year":2025,"yearOfEvent":null,"venue":"Int. J. Comput. Vis.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1007/S11263-024-02196-3"],"source":"https://dblp.org/rec/journals/ijcv/LiuDXYSZCHXZ25","documentPage":"https://doi.org/10.1007/S11263-024-02196-3","type":"Article","doi":"https://doi.org/10.1007/S11263-024-02196-3","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/ijcv/LiuDXYSZCHXZ25","documentUrl":"https://doi.org/10.1007/S11263-024-02196-3"},{"key":"journals/ijcv/YangXPDWSZ25","title":"Face3DAdv: Exploiting Robust Adversarial 3D Patches on Physical Face Recognition.","year":2025,"yearOfEvent":null,"venue":"Int. J. Comput. Vis.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1007/S11263-024-02177-6"],"source":"https://dblp.org/rec/journals/ijcv/YangXPDWSZ25","documentPage":"https://doi.org/10.1007/S11263-024-02177-6","type":"Article","doi":"https://doi.org/10.1007/S11263-024-02177-6","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/ijcv/YangXPDWSZ25","documentUrl":"https://doi.org/10.1007/S11263-024-02177-6"},{"key":"journals/jvcir/LiuXHXZS25","title":"Improving model generalization by on-manifold adversarial augmentation in the frequency domain.","year":2025,"yearOfEvent":null,"venue":"J. Vis. Commun. Image Represent.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1016/J.JVCIR.2025.104437"],"source":"https://dblp.org/rec/journals/jvcir/LiuXHXZS25","documentPage":"https://doi.org/10.1016/J.JVCIR.2025.104437","type":"Article","doi":"https://doi.org/10.1016/J.JVCIR.2025.104437","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/jvcir/LiuXHXZS25","documentUrl":"https://doi.org/10.1016/J.JVCIR.2025.104437"},{"key":"journals/pami/WangXZSZ25","title":"HiDe-PET: Continual Learning via Hierarchical Decomposition of Parameter-Efficient Tuning.","year":2025,"yearOfEvent":null,"venue":"IEEE Trans. Pattern Anal. Mach. Intell.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1109/TPAMI.2025.3562534"],"source":"https://dblp.org/rec/journals/pami/WangXZSZ25","documentPage":"https://doi.org/10.1109/TPAMI.2025.3562534","type":"Article","doi":"https://doi.org/10.1109/TPAMI.2025.3562534","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/pami/WangXZSZ25","documentUrl":"https://doi.org/10.1109/TPAMI.2025.3562534"},{"key":"journals/pami/WeiKDWRCS25","title":"Real-World Adversarial Defense Against Patch Attacks Based on Diffusion Model.","year":2025,"yearOfEvent":null,"venue":"IEEE Trans. Pattern Anal. Mach. Intell.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1109/TPAMI.2025.3596462"],"source":"https://dblp.org/rec/journals/pami/WeiKDWRCS25","documentPage":"https://doi.org/10.1109/TPAMI.2025.3596462","type":"Article","doi":"https://doi.org/10.1109/TPAMI.2025.3596462","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/pami/WeiKDWRCS25","documentUrl":"https://doi.org/10.1109/TPAMI.2025.3596462"},{"key":"journals/pami/WeiRDSC25","title":"Distributionally Location-Aware Transferable Adversarial Patches for Facial Images.","year":2025,"yearOfEvent":null,"venue":"IEEE Trans. Pattern Anal. Mach. Intell.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1109/TPAMI.2025.3526188"],"source":"https://dblp.org/rec/journals/pami/WeiRDSC25","documentPage":"https://doi.org/10.1109/TPAMI.2025.3526188","type":"Article","doi":"https://doi.org/10.1109/TPAMI.2025.3526188","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/pami/WeiRDSC25","documentUrl":"https://doi.org/10.1109/TPAMI.2025.3526188"},{"key":"journals/pami/YangWWYSZ25","title":"Reinforced Embodied Active Defense: Exploiting Adaptive Interaction for Robust Visual Perception in Adversarial 3D Environments.","year":2025,"yearOfEvent":null,"venue":"IEEE Trans. Pattern Anal. Mach. Intell.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1109/TPAMI.2025.3585726"],"source":"https://dblp.org/rec/journals/pami/YangWWYSZ25","documentPage":"https://doi.org/10.1109/TPAMI.2025.3585726","type":"Article","doi":"https://doi.org/10.1109/TPAMI.2025.3585726","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/pami/YangWWYSZ25","documentUrl":"https://doi.org/10.1109/TPAMI.2025.3585726"},{"key":"journals/prl/LiuXDZWDZS25","title":"RobustPrompt: Learning to defend against adversarial attacks with adaptive visual prompts.","year":2025,"yearOfEvent":null,"venue":"Pattern Recognit. Lett.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1016/J.PATREC.2025.02.015"],"source":"https://dblp.org/rec/journals/prl/LiuXDZWDZS25","documentPage":"https://doi.org/10.1016/J.PATREC.2025.02.015","type":"Article","doi":"https://doi.org/10.1016/J.PATREC.2025.02.015","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/prl/LiuXDZWDZS25","documentUrl":"https://doi.org/10.1016/J.PATREC.2025.02.015"},{"key":"journals/prl/ZhuYSZ25","title":"CamoEnv: Transferable and environment-consistent adversarial camouflage in autonomous driving.","year":2025,"yearOfEvent":null,"venue":"Pattern Recognit. Lett.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1016/J.PATREC.2024.12.003"],"source":"https://dblp.org/rec/journals/prl/ZhuYSZ25","documentPage":"https://doi.org/10.1016/J.PATREC.2024.12.003","type":"Article","doi":"https://doi.org/10.1016/J.PATREC.2024.12.003","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/prl/ZhuYSZ25","documentUrl":"https://doi.org/10.1016/J.PATREC.2024.12.003"},{"key":"journals/tbd/ChenZYYHXQS25","title":"ANF: Crafting Transferable Adversarial Point Clouds via Adversarial Noise Factorization.","year":2025,"yearOfEvent":null,"venue":"IEEE Trans. Big Data","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1109/TBDATA.2024.3436593"],"source":"https://dblp.org/rec/journals/tbd/ChenZYYHXQS25","documentPage":"https://doi.org/10.1109/TBDATA.2024.3436593","type":"Article","doi":"https://doi.org/10.1109/TBDATA.2024.3436593","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/tbd/ChenZYYHXQS25","documentUrl":"https://doi.org/10.1109/TBDATA.2024.3436593"},{"key":"journals/tbd/ZhuYSZZ25","title":"ImAdv: Transferable Implicit Adversarial Attack for 3D Object Detectors in Autonomous Driving.","year":2025,"yearOfEvent":null,"venue":"IEEE Trans. Big Data","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1109/TBDATA.2025.3588083"],"source":"https://dblp.org/rec/journals/tbd/ZhuYSZZ25","documentPage":"https://doi.org/10.1109/TBDATA.2025.3588083","type":"Article","doi":"https://doi.org/10.1109/TBDATA.2025.3588083","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/tbd/ZhuYSZZ25","documentUrl":"https://doi.org/10.1109/TBDATA.2025.3588083"},{"key":"journals/tdsc/YinZSPLL25","title":"Adversarial Examples Detection With Enhanced Image Difference Features Based on Local Histogram Equalization.","year":2025,"yearOfEvent":null,"venue":"IEEE Trans. Dependable Secur. Comput.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1109/TDSC.2025.3548402"],"source":"https://dblp.org/rec/journals/tdsc/YinZSPLL25","documentPage":"https://doi.org/10.1109/TDSC.2025.3548402","type":"Article","doi":"https://doi.org/10.1109/TDSC.2025.3548402","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/tdsc/YinZSPLL25","documentUrl":"https://doi.org/10.1109/TDSC.2025.3548402"},{"key":"journals/tip/ZhouSWH25","title":"Onet: Twin U-Net Architecture for Unsupervised Binary Semantic Segmentation in Radar and Remote Sensing Images.","year":2025,"yearOfEvent":null,"venue":"IEEE Trans. Image Process.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1109/TIP.2025.3530816"],"source":"https://dblp.org/rec/journals/tip/ZhouSWH25","documentPage":"https://doi.org/10.1109/TIP.2025.3530816","type":"Article","doi":"https://doi.org/10.1109/TIP.2025.3530816","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/tip/ZhouSWH25","documentUrl":"https://doi.org/10.1109/TIP.2025.3530816"},{"key":"journals/tits/QianHYCZSZ25","title":"Empowering Object Detection: Unleashing the Potential of Decoupled and Interactive Distillation.","year":2025,"yearOfEvent":null,"venue":"IEEE Trans. Intell. Transp. Syst.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1109/TITS.2024.3489888"],"source":"https://dblp.org/rec/journals/tits/QianHYCZSZ25","documentPage":"https://doi.org/10.1109/TITS.2024.3489888","type":"Article","doi":"https://doi.org/10.1109/TITS.2024.3489888","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/tits/QianHYCZSZ25","documentUrl":"https://doi.org/10.1109/TITS.2024.3489888"},{"key":"journals/tmm/WangHDZSH25","title":"Exploring Transferability of Multimodal Adversarial Samples for Vision-Language Pre-Training Models With Contrastive Learning.","year":2025,"yearOfEvent":null,"venue":"IEEE Trans. Multim.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1109/TMM.2025.3581811"],"source":"https://dblp.org/rec/journals/tmm/WangHDZSH25","documentPage":"https://doi.org/10.1109/TMM.2025.3581811","type":"Article","doi":"https://doi.org/10.1109/TMM.2025.3581811","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/tmm/WangHDZSH25","documentUrl":"https://doi.org/10.1109/TMM.2025.3581811"}],"preprints":[{"key":"journals/corr/abs-2501-15420","title":"Visual Generation Without Guidance.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2501.15420"],"source":"https://dblp.org/rec/journals/corr/abs-2501-15420","documentPage":"https://doi.org/10.48550/ARXIV.2501.15420","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2501.15420","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2501-15420","documentUrl":"https://doi.org/10.48550/ARXIV.2501.15420","arxivId":"2501.15420","arxivUrl":"https://arxiv.org/abs/2501.15420"},{"key":"journals/corr/abs-2501-19040","title":"Towards the Worst-case Robustness of Large Language Models.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2501.19040"],"source":"https://dblp.org/rec/journals/corr/abs-2501-19040","documentPage":"https://doi.org/10.48550/ARXIV.2501.19040","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2501.19040","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2501-19040","documentUrl":"https://doi.org/10.48550/ARXIV.2501.19040","arxivId":"2501.19040","arxivUrl":"https://arxiv.org/abs/2501.19040"},{"key":"journals/corr/abs-2502-07279","title":"Exploratory Diffusion Policy for Unsupervised Reinforcement Learning.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2502.07279"],"source":"https://dblp.org/rec/journals/corr/abs-2502-07279","documentPage":"https://doi.org/10.48550/ARXIV.2502.07279","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2502.07279","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2502-07279","documentUrl":"https://doi.org/10.48550/ARXIV.2502.07279","arxivId":"2502.07279","arxivUrl":"https://arxiv.org/abs/2502.07279"},{"key":"journals/corr/abs-2502-09923","title":"Self-Consistent Model-based Adaptation for Visual Reinforcement Learning.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2502.09923"],"source":"https://dblp.org/rec/journals/corr/abs-2502-09923","documentPage":"https://doi.org/10.48550/ARXIV.2502.09923","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2502.09923","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2502-09923","documentUrl":"https://doi.org/10.48550/ARXIV.2502.09923","arxivId":"2502.09923","arxivUrl":"https://arxiv.org/abs/2502.09923"},{"key":"journals/corr/abs-2502-19127","title":"Self-Memory Alignment: Mitigating Factual Hallucinations with Generalized Improvement.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2502.19127"],"source":"https://dblp.org/rec/journals/corr/abs-2502-19127","documentPage":"https://doi.org/10.48550/ARXIV.2502.19127","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2502.19127","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2502-19127","documentUrl":"https://doi.org/10.48550/ARXIV.2502.19127","arxivId":"2502.19127","arxivUrl":"https://arxiv.org/abs/2502.19127"},{"key":"journals/corr/abs-2503-16975","title":"EasyRobust: A Comprehensive and Easy-to-use Toolkit for Robust and Generalized Vision.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2503.16975"],"source":"https://dblp.org/rec/journals/corr/abs-2503-16975","documentPage":"https://doi.org/10.48550/ARXIV.2503.16975","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2503.16975","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-16975","documentUrl":"https://doi.org/10.48550/ARXIV.2503.16975","arxivId":"2503.16975","arxivUrl":"https://arxiv.org/abs/2503.16975"},{"key":"journals/corr/abs-2505-04662","title":"Crafting Physical Adversarial Examples by Combining Differentiable and Physically Based Renders.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2505.04662"],"source":"https://dblp.org/rec/journals/corr/abs-2505-04662","documentPage":"https://doi.org/10.48550/ARXIV.2505.04662","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2505.04662","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-04662","documentUrl":"https://doi.org/10.48550/ARXIV.2505.04662","arxivId":"2505.04662","arxivUrl":"https://arxiv.org/abs/2505.04662"},{"key":"journals/corr/abs-2505-17646","title":"Understanding Pre-training and Fine-tuning from Loss Landscape Perspectives.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2505.17646"],"source":"https://dblp.org/rec/journals/corr/abs-2505-17646","documentPage":"https://doi.org/10.48550/ARXIV.2505.17646","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2505.17646","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-17646","documentUrl":"https://doi.org/10.48550/ARXIV.2505.17646","arxivId":"2505.17646","arxivUrl":"https://arxiv.org/abs/2505.17646"},{"key":"journals/corr/abs-2506-01616","title":"MLA-Trust: Benchmarking Trustworthiness of Multimodal LLM Agents in GUI Environments.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2506.01616"],"source":"https://dblp.org/rec/journals/corr/abs-2506-01616","documentPage":"https://doi.org/10.48550/ARXIV.2506.01616","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2506.01616","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-01616","documentUrl":"https://doi.org/10.48550/ARXIV.2506.01616","arxivId":"2506.01616","arxivUrl":"https://arxiv.org/abs/2506.01616"},{"key":"journals/corr/abs-2506-12336","title":"Understanding and Benchmarking the Trustworthiness in Multimodal LLMs for Video Understanding.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2506.12336"],"source":"https://dblp.org/rec/journals/corr/abs-2506-12336","documentPage":"https://doi.org/10.48550/ARXIV.2506.12336","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2506.12336","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-12336","documentUrl":"https://doi.org/10.48550/ARXIV.2506.12336","arxivId":"2506.12336","arxivUrl":"https://arxiv.org/abs/2506.12336"},{"key":"journals/corr/abs-2506-12382","title":"Exploring the Secondary Risks of Large Language Models.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2506.12382"],"source":"https://dblp.org/rec/journals/corr/abs-2506-12382","documentPage":"https://doi.org/10.48550/ARXIV.2506.12382","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2506.12382","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-12382","documentUrl":"https://doi.org/10.48550/ARXIV.2506.12382","arxivId":"2506.12382","arxivUrl":"https://arxiv.org/abs/2506.12382"},{"key":"journals/corr/abs-2506-13120","title":"Accelerating PDE-Constrained Optimization by the Derivative of Neural Operators.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2506.13120"],"source":"https://dblp.org/rec/journals/corr/abs-2506-13120","documentPage":"https://doi.org/10.48550/ARXIV.2506.13120","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2506.13120","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-13120","documentUrl":"https://doi.org/10.48550/ARXIV.2506.13120","arxivId":"2506.13120","arxivUrl":"https://arxiv.org/abs/2506.13120"},{"key":"journals/corr/abs-2506-23844","title":"A Survey on Autonomy-Induced Security Risks in Large Model-Based Agents.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2506.23844"],"source":"https://dblp.org/rec/journals/corr/abs-2506-23844","documentPage":"https://doi.org/10.48550/ARXIV.2506.23844","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2506.23844","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-23844","documentUrl":"https://doi.org/10.48550/ARXIV.2506.23844","arxivId":"2506.23844","arxivUrl":"https://arxiv.org/abs/2506.23844"},{"key":"journals/corr/abs-2507-12768","title":"AnyPos: Automated Task-Agnostic Actions for Bimanual Manipulation.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2507.12768"],"source":"https://dblp.org/rec/journals/corr/abs-2507-12768","documentPage":"https://doi.org/10.48550/ARXIV.2507.12768","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2507.12768","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2507-12768","documentUrl":"https://doi.org/10.48550/ARXIV.2507.12768","arxivId":"2507.12768","arxivUrl":"https://arxiv.org/abs/2507.12768"},{"key":"journals/corr/abs-2507-12898","title":"Vidar: Embodied Video Diffusion Model for Generalist Bimanual Manipulation.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2507.12898"],"source":"https://dblp.org/rec/journals/corr/abs-2507-12898","documentPage":"https://doi.org/10.48550/ARXIV.2507.12898","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2507.12898","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2507-12898","documentUrl":"https://doi.org/10.48550/ARXIV.2507.12898","arxivId":"2507.12898","arxivUrl":"https://arxiv.org/abs/2507.12898"},{"key":"journals/corr/abs-2507-18484","title":"Reinforced Embodied Active Defense: Exploiting Adaptive Interaction for Robust Visual Perception in Adversarial 3D Environments.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2507.18484"],"source":"https://dblp.org/rec/journals/corr/abs-2507-18484","documentPage":"https://doi.org/10.48550/ARXIV.2507.18484","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2507.18484","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2507-18484","documentUrl":"https://doi.org/10.48550/ARXIV.2507.18484","arxivId":"2507.18484","arxivUrl":"https://arxiv.org/abs/2507.18484"},{"key":"journals/corr/abs-2507-22428","title":"Theoretical Analysis of Relative Errors in Gradient Computations for Adversarial Attacks with CE Loss.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2507.22428"],"source":"https://dblp.org/rec/journals/corr/abs-2507-22428","documentPage":"https://doi.org/10.48550/ARXIV.2507.22428","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2507.22428","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2507-22428","documentUrl":"https://doi.org/10.48550/ARXIV.2507.22428","arxivId":"2507.22428","arxivUrl":"https://arxiv.org/abs/2507.22428"},{"key":"journals/corr/abs-2507-22446","title":"RCR-AF: Enhancing Model Generalization via Rademacher Complexity Reduction Activation Function.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2507.22446"],"source":"https://dblp.org/rec/journals/corr/abs-2507-22446","documentPage":"https://doi.org/10.48550/ARXIV.2507.22446","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2507.22446","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2507-22446","documentUrl":"https://doi.org/10.48550/ARXIV.2507.22446","arxivId":"2507.22446","arxivUrl":"https://arxiv.org/abs/2507.22446"},{"key":"journals/corr/abs-2507-23523","title":"H-RDT: Human Manipulation Enhanced Bimanual Robotic Manipulation.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2507.23523"],"source":"https://dblp.org/rec/journals/corr/abs-2507-23523","documentPage":"https://doi.org/10.48550/ARXIV.2507.23523","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2507.23523","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2507-23523","documentUrl":"https://doi.org/10.48550/ARXIV.2507.23523","arxivId":"2507.23523","arxivUrl":"https://arxiv.org/abs/2507.23523"},{"key":"journals/corr/abs-2508-15370","title":"Unveiling Trust in Multimodal Large Language Models: Evaluation, Analysis, and Mitigation.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2508.15370"],"source":"https://dblp.org/rec/journals/corr/abs-2508-15370","documentPage":"https://doi.org/10.48550/ARXIV.2508.15370","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2508.15370","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-15370","documentUrl":"https://doi.org/10.48550/ARXIV.2508.15370","arxivId":"2508.15370","arxivUrl":"https://arxiv.org/abs/2508.15370"},{"key":"journals/corr/abs-2508-17198","title":"From reactive to cognitive: brain-inspired spatial intelligence for embodied agents.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2508.17198"],"source":"https://dblp.org/rec/journals/corr/abs-2508-17198","documentPage":"https://doi.org/10.48550/ARXIV.2508.17198","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2508.17198","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-17198","documentUrl":"https://doi.org/10.48550/ARXIV.2508.17198","arxivId":"2508.17198","arxivUrl":"https://arxiv.org/abs/2508.17198"},{"key":"journals/corr/abs-2509-01909","title":"Oyster-I: Beyond Refusal - Constructive Safety Alignment for Responsible Language Models.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2509.01909"],"source":"https://dblp.org/rec/journals/corr/abs-2509-01909","documentPage":"https://doi.org/10.48550/ARXIV.2509.01909","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2509.01909","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-01909","documentUrl":"https://doi.org/10.48550/ARXIV.2509.01909","arxivId":"2509.01909","arxivUrl":"https://arxiv.org/abs/2509.01909"},{"key":"journals/corr/abs-2509-16117","title":"DiffusionNFT: Online Diffusion Reinforcement with Forward Process.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2509.16117"],"source":"https://dblp.org/rec/journals/corr/abs-2509-16117","documentPage":"https://doi.org/10.48550/ARXIV.2509.16117","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2509.16117","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-16117","documentUrl":"https://doi.org/10.48550/ARXIV.2509.16117","arxivId":"2509.16117","arxivUrl":"https://arxiv.org/abs/2509.16117"},{"key":"journals/corr/abs-2509-24393","title":"Towards Safe Reasoning in Large Reasoning Models via Corrective Intervention.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2509.24393"],"source":"https://dblp.org/rec/journals/corr/abs-2509-24393","documentPage":"https://doi.org/10.48550/ARXIV.2509.24393","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2509.24393","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-24393","documentUrl":"https://doi.org/10.48550/ARXIV.2509.24393","arxivId":"2509.24393","arxivUrl":"https://arxiv.org/abs/2509.24393"},{"key":"journals/corr/abs-2511-07480","title":"KG-DF: A Black-box Defense Framework against Jailbreak Attacks Based on Knowledge Graphs.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2511.07480"],"source":"https://dblp.org/rec/journals/corr/abs-2511-07480","documentPage":"https://doi.org/10.48550/ARXIV.2511.07480","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2511.07480","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2511-07480","documentUrl":"https://doi.org/10.48550/ARXIV.2511.07480","arxivId":"2511.07480","arxivUrl":"https://arxiv.org/abs/2511.07480"},{"key":"journals/corr/abs-2512-00412","title":"Red Teaming Large Reasoning Models.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2512.00412"],"source":"https://dblp.org/rec/journals/corr/abs-2512-00412","documentPage":"https://doi.org/10.48550/ARXIV.2512.00412","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2512.00412","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-00412","documentUrl":"https://doi.org/10.48550/ARXIV.2512.00412","arxivId":"2512.00412","arxivUrl":"https://arxiv.org/abs/2512.00412"},{"key":"journals/corr/abs-2512-13030","title":"Motus: A Unified Latent Action World Model.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2512.13030"],"source":"https://dblp.org/rec/journals/corr/abs-2512-13030","documentPage":"https://doi.org/10.48550/ARXIV.2512.13030","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2512.13030","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-13030","documentUrl":"https://doi.org/10.48550/ARXIV.2512.13030","arxivId":"2512.13030","arxivUrl":"https://arxiv.org/abs/2512.13030"},{"key":"journals/corr/abs-2512-17661","title":"Vidarc: Embodied Video Diffusion Model for Closed-loop Control.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2512.17661"],"source":"https://dblp.org/rec/journals/corr/abs-2512-17661","documentPage":"https://doi.org/10.48550/ARXIV.2512.17661","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2512.17661","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-17661","documentUrl":"https://doi.org/10.48550/ARXIV.2512.17661","arxivId":"2512.17661","arxivUrl":"https://arxiv.org/abs/2512.17661"}],"excludedFormal":[],"excludedOther":[],"excludedHomonyms":[],"unassignedCandidates":[],"retrievedAt":"2026-10-19","querySource":"https://sparql.dblp.org/","method":"DBLP yearOfPublication=2025; Article + Inproceedings; excludes Informal/CoRR and explicit editorial/correction/erratum/preface; unique DBLP record keys within person.","labName":"智能技术与系统实验室","labUrl":"https://ai.cs.tsinghua.edu.cn/","labEvidence":"清华计算机系本人教师页归在智能技术与系统实验室；实验室官方师资名单明确列出苏航。只表示公开成员关系，不表示独立领导整个实验室。","labSourceUrl":"https://ai.cs.tsinghua.edu.cn/sysgk/syssz.htm","affiliationZh":"清华大学","sourceWarning":false,"knownPreprintMinimum2025":null,"excludedMisattributed":[],"displayNotes":"身份已经个人或机构主页核对。2025 年正式记录 30 条（会议 15、期刊 15），所有作者位置均计入，不表示主导或贡献份额；预印本 28 条单列，不加总。","labDisplayNotes":"清华智能技术与系统实验室的官方师资名单列有其姓名，据此归组。这是成员关系，不表示由其领导整个实验室；分组只含本人参与的记录。"},{"index":82,"name":"Hao Su","nameZh":"苏昊","affiliation":"Fudan University","source":"DBLP Knowledge Graph official SPARQL API","profileUrl":"https://dblp.org/pid/09/4945-1","identifier":"09/4945-1","identityEvidence":[{"url":"https://dblp.org/pid/09/4945-1","evidence":"DBLP curated profile affiliations: Stanford University, CA, USA; University of California San Diego, CA, USA."},{"url":"https://dblp.org/pid/09/4945-1","evidence":"DBLP curated profile homepages: https://openreview.net/profile?id=~Hao_Su1."},{"url":"https://www.haosu.ai/","evidence":"Personal website states Haoqing Distinguished Professor at Fudan and prior tenured associate professor at UC San Diego; DBLP profile lists UCSD / Stanford."},{"url":"https://www.haosu.ai/publications","evidence":"Full-title matches to the personal publication list, supplemented by UCSD author signatures and ORCID 0000-0002-1796-2682, confirm retained formal records."},{"url":"https://suhaosh.github.io/","evidence":"Different Hao Su at Zhengzhou University, Beihang PhD 2024, directly claims 3DFaceSculptor. The intended faculty member was already a tenured UCSD professor."},{"url":"https://doi.org/10.1016/j.gmod.2025.101303","evidence":"FlexPlan has a Zhengzhou University author signature and the Zhengzhou research group, not the UCSD/Fudan author; excluded as a homonym."},{"url":"https://wm-abench.maitrix.org/","evidence":"Atomic world-model evaluation project directly links author Hao Su to his UCSD homepage."},{"url":"https://papers.nips.cc/paper_files/paper/2025/file/5a8f69523f9511a5706568c552de0ebb-Paper-Datasets_and_Benchmarks_Track.pdf","evidence":"MyoChallenge 2024 paper assigns Hao Su to UCSD on the first page."}],"count2025":24,"conference2025":17,"journal2025":7,"preprint2025":null,"status":"verified_manual","notes":"Counts are DBLP indexed coauthored records, not first-author counts, laboratory totals, unique scientific discoveries, or quality assessments. DBLP yearOfPublication=2025; yearOfEvent retained and can differ. Conference workshops are included. Preprints are separate and may overlap formal versions. Formal 2025 records were reviewed individually after detected DBLP homonyms were excluded. The preprint pool is still incomplete and its total is withheld independently.","papers":[{"key":"conf/aaai/MuLSYYLS25","title":"When Should We Prefer State-to-Visual DAgger over Visual Reinforcement Learning?","year":2025,"yearOfEvent":2025,"venue":"AAAI","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1609/AAAI.V39I14.33604"],"source":"https://dblp.org/rec/conf/aaai/MuLSYYLS25","documentPage":"https://doi.org/10.1609/AAAI.V39I14.33604","type":"Inproceedings","doi":"https://doi.org/10.1609/AAAI.V39I14.33604","authorSignatures":[{}],"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/aaai/MuLSYYLS25","documentUrl":"https://doi.org/10.1609/AAAI.V39I14.33604"},{"key":"conf/eccv/XuLCLSSL24","title":"SpaRP: Fast 3D Object Reconstruction and Pose Estimation from Sparse Views.","year":2025,"yearOfEvent":2024,"venue":"ECCV (64)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1007/978-3-031-73039-9_9"],"source":"https://dblp.org/rec/conf/eccv/XuLCLSSL24","documentPage":"https://doi.org/10.1007/978-3-031-73039-9_9","type":"Inproceedings","doi":"https://doi.org/10.1007/978-3-031-73039-9_9","authorSignatures":[{"inst":"https://dblp.org/inst/1/076","instLabel":"University of California, San Diego (UCSD)"}],"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/eccv/XuLCLSSL24","documentUrl":"https://doi.org/10.1007/978-3-031-73039-9_9"},{"key":"conf/iclr/0001VSL0025","title":"Hierarchical World Models as Visual Whole-Body Humanoid Controllers.","year":2025,"yearOfEvent":2025,"venue":"ICLR","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/iclr/0001VSL0025","documentPage":"https://openreview.net/forum?id=7wuJMvK639","type":"Inproceedings","doi":null,"authorSignatures":[{}],"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iclr/0001VSL0025","documentUrl":"https://openreview.net/forum?id=7wuJMvK639"},{"key":"conf/iclr/Liu0025a","title":"Dynamic Gaussians Mesh: Consistent Mesh Reconstruction from Dynamic Scenes.","year":2025,"yearOfEvent":2025,"venue":"ICLR","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/iclr/Liu0025a","documentPage":"https://openreview.net/forum?id=LuGHbK8qTa","type":"Inproceedings","doi":null,"authorSignatures":[{}],"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iclr/Liu0025a","documentUrl":"https://openreview.net/forum?id=LuGHbK8qTa"},{"key":"conf/iclr/ShuklaTS25","title":"ManiSkill-HAB: A Benchmark for Low-Level Manipulation in Home Rearrangement Tasks.","year":2025,"yearOfEvent":2025,"venue":"ICLR","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/iclr/ShuklaTS25","documentPage":"https://openreview.net/forum?id=6bKEWevgSd","type":"Inproceedings","doi":null,"authorSignatures":[{}],"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iclr/ShuklaTS25","documentUrl":"https://openreview.net/forum?id=6bKEWevgSd"},{"key":"conf/iclr/YuanMTFZ025","title":"Policy Decorator: Model-Agnostic Online Refinement for Large Policy Model.","year":2025,"yearOfEvent":2025,"venue":"ICLR","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/iclr/YuanMTFZ025","documentPage":"https://openreview.net/forum?id=e5jGTEiJMT","type":"Inproceedings","doi":null,"authorSignatures":[{}],"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iclr/YuanMTFZ025","documentUrl":"https://openreview.net/forum?id=e5jGTEiJMT"},{"key":"conf/iclr/ZhouGCXS25","title":"Point-SAM: Promptable 3D Segmentation Model for Point Clouds.","year":2025,"yearOfEvent":2025,"venue":"ICLR","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/iclr/ZhouGCXS25","documentPage":"https://openreview.net/forum?id=yXCTDhZDh6","type":"Inproceedings","doi":null,"authorSignatures":[{}],"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iclr/ZhouGCXS25","documentUrl":"https://openreview.net/forum?id=yXCTDhZDh6"},{"key":"conf/icml/Escoriza0TM025","title":"Multi-Stage Manipulation with Demonstration-Augmented Reward, Policy, and World Model Learning.","year":2025,"yearOfEvent":2025,"venue":"ICML","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/icml/Escoriza0TM025","documentPage":"https://proceedings.mlr.press/v267/escoriza25a.html","type":"Inproceedings","doi":null,"authorSignatures":[{}],"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/icml/Escoriza0TM025","documentUrl":"https://proceedings.mlr.press/v267/escoriza25a.html"},{"key":"conf/icml/LiH025a","title":"Reward-free World Models for Online Imitation Learning.","year":2025,"yearOfEvent":2025,"venue":"ICML","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/icml/LiH025a","documentPage":"https://proceedings.mlr.press/v267/li25af.html","type":"Inproceedings","doi":null,"authorSignatures":[{}],"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/icml/LiH025a","documentUrl":"https://proceedings.mlr.press/v267/li25af.html"},{"key":"conf/iros/ShiLZAHS25","title":"Learning Adaptive Dexterous Grasping from Single Demonstrations.","year":2025,"yearOfEvent":2025,"venue":"IROS","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/IROS60139.2025.11246731"],"source":"https://dblp.org/rec/conf/iros/ShiLZAHS25","documentPage":"https://doi.org/10.1109/IROS60139.2025.11246731","type":"Inproceedings","doi":"https://doi.org/10.1109/IROS60139.2025.11246731","authorSignatures":[{"inst":"https://dblp.org/inst/1/076","instLabel":"University of California, San Diego (UCSD)"}],"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iros/ShiLZAHS25","documentUrl":"https://doi.org/10.1109/IROS60139.2025.11246731"},{"key":"conf/siggrapha/0003LW0L25","title":"FreeArt3D: Training-Free Articulated Object Generation using 3D Diffusion.","year":2025,"yearOfEvent":2025,"venue":"SIGGRAPH Asia","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1145/3757377.3763845"],"source":"https://dblp.org/rec/conf/siggrapha/0003LW0L25","documentPage":"https://doi.org/10.1145/3757377.3763845","type":"Inproceedings","doi":"https://doi.org/10.1145/3757377.3763845","authorSignatures":[{"orcid":"https://orcid.org/0000-0002-1796-2682","inst":"https://dblp.org/inst/1/076","instLabel":"University of California, San Diego (UCSD)"}],"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/siggrapha/0003LW0L25","documentUrl":"https://doi.org/10.1145/3757377.3763845"},{"key":"conf/siggrapha/WangWSZ0L25","title":"PartUV: Part-Based UV Unwrapping of 3D Meshes.","year":2025,"yearOfEvent":2025,"venue":"SIGGRAPH Asia","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1145/3757377.3763843"],"source":"https://dblp.org/rec/conf/siggrapha/WangWSZ0L25","documentPage":"https://doi.org/10.1145/3757377.3763843","type":"Inproceedings","doi":"https://doi.org/10.1145/3757377.3763843","authorSignatures":[{"orcid":"https://orcid.org/0000-0002-1796-2682","inst":"https://dblp.org/inst/1/076","instLabel":"University of California, San Diego (UCSD)"}],"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/siggrapha/WangWSZ0L25","documentUrl":"https://doi.org/10.1145/3757377.3763843"},{"key":"conf/siggrapha/YuanSWZSL25","title":"LARM: A Large Articulated Object Reconstruction Model.","year":2025,"yearOfEvent":2025,"venue":"SIGGRAPH Asia","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1145/3757377.3763844"],"source":"https://dblp.org/rec/conf/siggrapha/YuanSWZSL25","documentPage":"https://doi.org/10.1145/3757377.3763844","type":"Inproceedings","doi":"https://doi.org/10.1145/3757377.3763844","authorSignatures":[{"orcid":"https://orcid.org/0000-0002-1796-2682","inst":"https://dblp.org/inst/1/076","instLabel":"University of California, San Diego (UCSD)"}],"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/siggrapha/YuanSWZSL25","documentUrl":"https://doi.org/10.1145/3757377.3763844"},{"key":"conf/wacv/WeiXBCSX025","title":"NeuManifold: Neural Watertight Manifold Reconstruction with Efficient and High-Quality Rendering Support.","year":2025,"yearOfEvent":2025,"venue":"WACV","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/WACV61041.2025.00081"],"source":"https://dblp.org/rec/conf/wacv/WeiXBCSX025","documentPage":"https://doi.org/10.1109/WACV61041.2025.00081","type":"Inproceedings","doi":"https://doi.org/10.1109/WACV61041.2025.00081","authorSignatures":[{"inst":"https://dblp.org/inst/1/076","instLabel":"University of California, San Diego (UCSD)"}],"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/wacv/WeiXBCSX025","documentUrl":"https://doi.org/10.1109/WACV61041.2025.00081"},{"key":"journals/cgf/OhYWSXLS25","title":"PaMO: Parallel Mesh Optimization for Intersection-Free Low-Poly Modeling on the GPU.","year":2025,"yearOfEvent":null,"venue":"Comput. Graph. Forum","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1111/CGF.70267"],"source":"https://dblp.org/rec/journals/cgf/OhYWSXLS25","documentPage":"https://doi.org/10.1111/CGF.70267","type":"Article","doi":"https://doi.org/10.1111/CGF.70267","authorSignatures":[{"orcid":"https://orcid.org/0000-0002-1796-2682","inst":"https://dblp.org/inst/1/076","instLabel":"University of California, San Diego (UCSD)"}],"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/cgf/OhYWSXLS25","documentUrl":"https://doi.org/10.1111/CGF.70267"},{"key":"journals/scirobotics/AiTSWPTCSWL25","title":"A review of learning-based dynamics models for robotic manipulation.","year":2025,"yearOfEvent":null,"venue":"Sci. Robotics","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1126/SCIROBOTICS.ADT1497"],"source":"https://dblp.org/rec/journals/scirobotics/AiTSWPTCSWL25","documentPage":"https://doi.org/10.1126/SCIROBOTICS.ADT1497","type":"Article","doi":"https://doi.org/10.1126/SCIROBOTICS.ADT1497","authorSignatures":[{"orcid":"https://orcid.org/0000-0002-1796-2682","inst":"https://dblp.org/inst/1/076","instLabel":"University of California, San Diego (UCSD)"}],"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/scirobotics/AiTSWPTCSWL25","documentUrl":"https://doi.org/10.1126/SCIROBOTICS.ADT1497"},{"key":"journals/tmlr/ChenYM025","title":"Responsive Noise-Relaying Diffusion Policy: Responsive and Efficient Visuomotor Control.","year":2025,"yearOfEvent":null,"venue":"Trans. Mach. Learn. Res.","types":["https://dblp.org/rdf/schema#Article"],"dois":[],"source":"https://dblp.org/rec/journals/tmlr/ChenYM025","documentPage":"https://openreview.net/forum?id=LLWJkR6gaI","type":"Article","doi":null,"authorSignatures":[{}],"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/tmlr/ChenYM025","documentUrl":"https://openreview.net/forum?id=LLWJkR6gaI"},{"key":"journals/tog/YuanXYS25","title":"C5D: Sequential Continuous Convex Collision Detection Using Cone Casting.","year":2025,"yearOfEvent":null,"venue":"ACM Trans. Graph.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1145/3731151"],"source":"https://dblp.org/rec/journals/tog/YuanXYS25","documentPage":"https://doi.org/10.1145/3731151","type":"Article","doi":"https://doi.org/10.1145/3731151","authorSignatures":[{"orcid":"https://orcid.org/0000-0002-1796-2682","inst":"https://dblp.org/inst/1/076","instLabel":"University of California, San Diego (UCSD)"}],"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/tog/YuanXYS25","documentUrl":"https://doi.org/10.1145/3731151"},{"key":"conf/eccv/ZhangWZGGJSG24","title":"CONDENSE: Consistent 2D/3D Pre-training for Dense and Sparse Features from Multi-View Images.","year":2025,"yearOfEvent":2024,"venue":"ECCV (54)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1007/978-3-031-72949-2_2"],"source":"https://dblp.org/rec/conf/eccv/ZhangWZGGJSG24","documentPage":"https://doi.org/10.1007/978-3-031-72949-2_2","type":"Inproceedings","doi":"https://doi.org/10.1007/978-3-031-72949-2_2","authorSignatures":[{"inst":"https://dblp.org/inst/1/076","instLabel":"University of California, San Diego (UCSD)"}],"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/eccv/ZhangWZGGJSG24","documentUrl":"https://doi.org/10.1007/978-3-031-72949-2_2"},{"key":"journals/tog/LanLYXSWJY25","title":"JGS2: Near Second-order Converging Jacobi/Gauss-Seidel for GPU Elastodynamics.","year":2025,"yearOfEvent":null,"venue":"ACM Trans. Graph.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1145/3731183"],"source":"https://dblp.org/rec/journals/tog/LanLYXSWJY25","documentPage":"https://doi.org/10.1145/3731183","type":"Article","doi":"https://doi.org/10.1145/3731183","authorSignatures":[{"orcid":"https://orcid.org/0000-0002-1796-2682","inst":"https://dblp.org/inst/1/076","instLabel":"University of California, San Diego (UCSD)"}],"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/tog/LanLYXSWJY25","documentUrl":"https://doi.org/10.1145/3731183"},{"key":"journals/tog/LiuXYTXWSS25","title":"RigAnything: Template-Free Autoregressive Rigging for Diverse 3D Assets.","year":2025,"yearOfEvent":null,"venue":"ACM Trans. Graph.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1145/3731149"],"source":"https://dblp.org/rec/journals/tog/LiuXYTXWSS25","documentPage":"https://doi.org/10.1145/3731149","type":"Article","doi":"https://doi.org/10.1145/3731149","authorSignatures":[{"orcid":"https://orcid.org/0000-0002-1796-2682","inst":"https://dblp.org/inst/1/076","instLabel":"University of California, San Diego (UCSD)"}],"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/tog/LiuXYTXWSS25","documentUrl":"https://doi.org/10.1145/3731149"},{"key":"journals/tog/YangDLZSCXS25","title":"IMLS-Splatting: Efficient Mesh Reconstruction from Multi-view Images via Point Representation.","year":2025,"yearOfEvent":null,"venue":"ACM Trans. Graph.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1145/3731210"],"source":"https://dblp.org/rec/journals/tog/YangDLZSCXS25","documentPage":"https://doi.org/10.1145/3731210","type":"Article","doi":"https://doi.org/10.1145/3731210","authorSignatures":[{"orcid":"https://orcid.org/0000-0002-1796-2682","inst":"https://dblp.org/inst/1/076","instLabel":"University of California, San Diego (UCSD)"}],"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/tog/YangDLZSCXS25","documentUrl":"https://doi.org/10.1145/3731210"},{"key":"conf/acl/GaoPLCYHFSK0TLY25","title":"Do Vision-Language Models Have Internal World Models? Towards an Atomic Evaluation.","year":2025,"yearOfEvent":2025,"venue":"ACL (Findings)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.18653/V1/2025.FINDINGS-ACL.1342"],"source":"https://dblp.org/rec/conf/acl/GaoPLCYHFSK0TLY25","documentPage":"https://doi.org/10.18653/V1/2025.FINDINGS-ACL.1342","type":"Inproceedings","doi":"https://doi.org/10.18653/V1/2025.FINDINGS-ACL.1342","authorSignatures":[{}],"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/acl/GaoPLCYHFSK0TLY25","documentUrl":"https://doi.org/10.18653/V1/2025.FINDINGS-ACL.1342"},{"key":"conf/nips/WangTHLSHBHSPSP25","title":"MyoChallenge 2024: A New Benchmark for Physiological Dexterity and Agility in Bionic Humans.","year":2025,"yearOfEvent":2025,"venue":"NeurIPS","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/nips/WangTHLSHBHSPSP25","documentPage":"http://papers.nips.cc/paper_files/paper/2025/hash/5a8f69523f9511a5706568c552de0ebb-Abstract-Datasets_and_Benchmarks_Track.html","type":"Inproceedings","doi":null,"authorSignatures":[{}],"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/nips/WangTHLSHBHSPSP25","documentUrl":"http://papers.nips.cc/paper_files/paper/2025/hash/5a8f69523f9511a5706568c552de0ebb-Abstract-Datasets_and_Benchmarks_Track.html"}],"preprints":[{"key":"journals/corr/abs-2502-12724","title":"Responsive Noise-Relaying Diffusion Policy: Responsive and Efficient Visuomotor Control.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2502.12724"],"source":"https://dblp.org/rec/journals/corr/abs-2502-12724","documentPage":"https://doi.org/10.48550/ARXIV.2502.12724","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2502.12724","authorSignatures":[{}],"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2502-12724","documentUrl":"https://doi.org/10.48550/ARXIV.2502.12724","arxivId":"2502.12724","arxivUrl":"https://arxiv.org/abs/2502.12724"},{"key":"journals/corr/abs-2503-01837","title":"Multi-Stage Manipulation with Demonstration-Augmented Reward, Policy, and World Model Learning.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2503.01837"],"source":"https://dblp.org/rec/journals/corr/abs-2503-01837","documentPage":"https://doi.org/10.48550/ARXIV.2503.01837","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2503.01837","authorSignatures":[{}],"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-01837","documentUrl":"https://doi.org/10.48550/ARXIV.2503.01837","arxivId":"2503.01837","arxivUrl":"https://arxiv.org/abs/2503.01837"},{"key":"journals/corr/abs-2503-11999","title":"Diffusion Dynamics Models with Generative State Estimation for Cloth Manipulation.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2503.11999"],"source":"https://dblp.org/rec/journals/corr/abs-2503-11999","documentPage":"https://doi.org/10.48550/ARXIV.2503.11999","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2503.11999","authorSignatures":[{}],"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-11999","documentUrl":"https://doi.org/10.48550/ARXIV.2503.11999","arxivId":"2503.11999","arxivUrl":"https://arxiv.org/abs/2503.11999"},{"key":"journals/corr/abs-2503-20208","title":"Learning Adaptive Dexterous Grasping from Single Demonstrations.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2503.20208"],"source":"https://dblp.org/rec/journals/corr/abs-2503-20208","documentPage":"https://doi.org/10.48550/ARXIV.2503.20208","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2503.20208","authorSignatures":[{}],"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-20208","documentUrl":"https://doi.org/10.48550/ARXIV.2503.20208","arxivId":"2503.20208","arxivUrl":"https://arxiv.org/abs/2503.20208"},{"key":"journals/corr/abs-2505-05753","title":"Towards Embodiment Scaling Laws in Robot Locomotion.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2505.05753"],"source":"https://dblp.org/rec/journals/corr/abs-2505-05753","documentPage":"https://doi.org/10.48550/ARXIV.2505.05753","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2505.05753","authorSignatures":[{}],"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-05753","documentUrl":"https://doi.org/10.48550/ARXIV.2505.05753","arxivId":"2505.05753","arxivUrl":"https://arxiv.org/abs/2505.05753"},{"key":"journals/corr/abs-2509-05595","title":"PaMO: Parallel Mesh Optimization for Intersection-Free Low-Poly Modeling on the GPU.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2509.05595"],"source":"https://dblp.org/rec/journals/corr/abs-2509-05595","documentPage":"https://doi.org/10.48550/ARXIV.2509.05595","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2509.05595","authorSignatures":[{}],"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-05595","documentUrl":"https://doi.org/10.48550/ARXIV.2509.05595","arxivId":"2509.05595","arxivUrl":"https://arxiv.org/abs/2509.05595"},{"key":"journals/corr/abs-2509-11417","title":"Enhancing Generalization in Vision-Language-Action Models by Preserving Pretrained Representations.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2509.11417"],"source":"https://dblp.org/rec/journals/corr/abs-2509-11417","documentPage":"https://doi.org/10.48550/ARXIV.2509.11417","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2509.11417","authorSignatures":[{}],"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-11417","documentUrl":"https://doi.org/10.48550/ARXIV.2509.11417","arxivId":"2509.11417","arxivUrl":"https://arxiv.org/abs/2509.11417"},{"key":"journals/corr/abs-2510-25765","title":"FreeArt3D: Training-Free Articulated Object Generation using 3D Diffusion.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2510.25765"],"source":"https://dblp.org/rec/journals/corr/abs-2510-25765","documentPage":"https://doi.org/10.48550/ARXIV.2510.25765","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2510.25765","authorSignatures":[{}],"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-25765","documentUrl":"https://doi.org/10.48550/ARXIV.2510.25765","arxivId":"2510.25765","arxivUrl":"https://arxiv.org/abs/2510.25765"},{"key":"journals/corr/abs-2511-01177","title":"Scaling Cross-Embodiment World Models for Dexterous Manipulation.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2511.01177"],"source":"https://dblp.org/rec/journals/corr/abs-2511-01177","documentPage":"https://doi.org/10.48550/ARXIV.2511.01177","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2511.01177","authorSignatures":[{}],"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2511-01177","documentUrl":"https://doi.org/10.48550/ARXIV.2511.01177","arxivId":"2511.01177","arxivUrl":"https://arxiv.org/abs/2511.01177"},{"key":"journals/corr/abs-2511-11563","title":"LARM: A Large Articulated-Object Reconstruction Model.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2511.11563"],"source":"https://dblp.org/rec/journals/corr/abs-2511-11563","documentPage":"https://doi.org/10.48550/ARXIV.2511.11563","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2511.11563","authorSignatures":[{}],"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2511-11563","documentUrl":"https://doi.org/10.48550/ARXIV.2511.11563","arxivId":"2511.11563","arxivUrl":"https://arxiv.org/abs/2511.11563"},{"key":"journals/corr/abs-2511-16659","title":"PartUV: Part-Based UV Unwrapping of 3D Meshes.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2511.16659"],"source":"https://dblp.org/rec/journals/corr/abs-2511-16659","documentPage":"https://doi.org/10.48550/ARXIV.2511.16659","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2511.16659","authorSignatures":[{}],"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2511-16659","documentUrl":"https://doi.org/10.48550/ARXIV.2511.16659","arxivId":"2511.16659","arxivUrl":"https://arxiv.org/abs/2511.16659"}],"excludedFormal":[{"key":"journals/jsac/ZhaoSSNSP25","title":"Guest Editorial: Edge-Intelligence for Real-Time Computer Vision in 6G.","year":2025,"yearOfEvent":null,"venue":"IEEE J. Sel. Areas Commun.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1109/JSAC.2025.3629199"],"source":"https://dblp.org/rec/journals/jsac/ZhaoSSNSP25","documentPage":"https://doi.org/10.1109/JSAC.2025.3629199","type":"Article","doi":"https://doi.org/10.1109/JSAC.2025.3629199","authorSignatures":[{"inst":"https://dblp.org/inst/1/076","instLabel":"University of California, San Diego (UCSD)"}],"exclusionReason":"Explicit editorial, correction, erratum or preface; excluded from research-paper count.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/jsac/ZhaoSSNSP25","documentUrl":"https://doi.org/10.1109/JSAC.2025.3629199"}],"excludedOther":[],"excludedHomonyms":[{"key":"journals/cvgip/WangWLSLX25","title":"FlexPlan: High-flexibility interactive floorplan design based on ArchiGraph.","year":2025,"yearOfEvent":null,"venue":"Graph. Model.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1016/J.GMOD.2025.101303"],"source":"https://dblp.org/rec/journals/cvgip/WangWLSLX25","documentPage":"https://doi.org/10.1016/J.GMOD.2025.101303","type":"Article","doi":"https://doi.org/10.1016/J.GMOD.2025.101303","authorSignatures":[{"inst":"https://dblp.org/inst/2/466","instLabel":"Zhengzhou University"}],"exclusionReason":"Author signature assigns Zhengzhou University, matching the Zhengzhou Hao Su research group rather than UCSD/Fudan.","exclusionSource":"https://doi.org/10.1016/j.gmod.2025.101303","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/cvgip/WangWLSLX25","documentUrl":"https://doi.org/10.1016/J.GMOD.2025.101303"},{"key":"journals/tvcg/SuW00W025","title":"3DFaceSculptor: A Common Framework for Image-Guided 3D Face Deformation.","year":2025,"yearOfEvent":null,"venue":"IEEE Trans. Vis. Comput. Graph.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1109/TVCG.2025.3596482"],"source":"https://dblp.org/rec/journals/tvcg/SuW00W025","documentPage":"https://doi.org/10.1109/TVCG.2025.3596482","type":"Article","doi":"https://doi.org/10.1109/TVCG.2025.3596482","authorSignatures":[{"orcid":"https://orcid.org/0000-0001-5853-648X","inst":"https://dblp.org/inst/2/466","instLabel":"Zhengzhou University"}],"exclusionReason":"Different Zhengzhou University Hao Su explicitly claims the paper on his personal page; his Beihang PhD 2024 career differs from the UCSD/Fudan signatory.","exclusionSource":"https://suhaosh.github.io/","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/tvcg/SuW00W025","documentUrl":"https://doi.org/10.1109/TVCG.2025.3596482"}],"unassignedCandidates":[{"key":"journals/corr/abs-2502-09615","title":"RigAnything: Template-Free Autoregressive Rigging for Diverse 3D Assets.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2502.09615"],"source":"https://dblp.org/rec/journals/corr/abs-2502-09615","documentPage":"https://doi.org/10.48550/ARXIV.2502.09615","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2502.09615","authorSignatures":[{}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2502-09615","documentUrl":"https://doi.org/10.48550/ARXIV.2502.09615"},{"key":"journals/corr/abs-2505-02228","title":"Coupled Distributional Random Expert Distillation for World Model Online Imitation Learning.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2505.02228"],"source":"https://dblp.org/rec/journals/corr/abs-2505-02228","documentPage":"https://doi.org/10.48550/ARXIV.2505.02228","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2505.02228","authorSignatures":[{}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-02228","documentUrl":"https://doi.org/10.48550/ARXIV.2505.02228"},{"key":"journals/corr/abs-2506-06494","title":"JGS2: Near Second-order Converging Jacobi/Gauss-Seidel for GPU Elastodynamics.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2506.06494"],"source":"https://dblp.org/rec/journals/corr/abs-2506-06494","documentPage":"https://doi.org/10.48550/ARXIV.2506.06494","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2506.06494","authorSignatures":[{}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-06494","documentUrl":"https://doi.org/10.48550/ARXIV.2506.06494"},{"key":"journals/corr/abs-2506-21876","title":"Do Vision-Language Models Have Internal World Models? Towards an Atomic Evaluation.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2506.21876"],"source":"https://dblp.org/rec/journals/corr/abs-2506-21876","documentPage":"https://doi.org/10.48550/ARXIV.2506.21876","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2506.21876","authorSignatures":[{}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-21876","documentUrl":"https://doi.org/10.48550/ARXIV.2506.21876"},{"key":"journals/corr/abs-2507-14501","title":"Advances in Feed-Forward 3D Reconstruction and View Synthesis: A Survey.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2507.14501"],"source":"https://dblp.org/rec/journals/corr/abs-2507-14501","documentPage":"https://doi.org/10.48550/ARXIV.2507.14501","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2507.14501","authorSignatures":[{}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2507-14501","documentUrl":"https://doi.org/10.48550/ARXIV.2507.14501"},{"key":"journals/corr/abs-2509-15695","title":"ORIC: Benchmarking Object Recognition in Incongruous Context for Large Vision-Language Models.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2509.15695"],"source":"https://dblp.org/rec/journals/corr/abs-2509-15695","documentPage":"https://doi.org/10.48550/ARXIV.2509.15695","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2509.15695","authorSignatures":[{}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-15695","documentUrl":"https://doi.org/10.48550/ARXIV.2509.15695"},{"key":"journals/corr/abs-2510-02538","title":"A Recipe for Efficient Sim-to-Real Transfer in Manipulation with Online Imitation-Pretrained World Models.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2510.02538"],"source":"https://dblp.org/rec/journals/corr/abs-2510-02538","documentPage":"https://doi.org/10.48550/ARXIV.2510.02538","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2510.02538","authorSignatures":[{}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-02538","documentUrl":"https://doi.org/10.48550/ARXIV.2510.02538"},{"key":"journals/corr/abs-2510-03885","title":"Seeing the Bigger Picture: 3D Latent Mapping for Mobile Manipulation Policy Learning.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2510.03885"],"source":"https://dblp.org/rec/journals/corr/abs-2510-03885","documentPage":"https://doi.org/10.48550/ARXIV.2510.03885","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2510.03885","authorSignatures":[{}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-03885","documentUrl":"https://doi.org/10.48550/ARXIV.2510.03885"},{"key":"journals/corr/abs-2511-19584","title":"Learning Massively Multitask World Models for Continuous Control.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2511.19584"],"source":"https://dblp.org/rec/journals/corr/abs-2511-19584","documentPage":"https://doi.org/10.48550/ARXIV.2511.19584","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2511.19584","authorSignatures":[{}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2511-19584","documentUrl":"https://doi.org/10.48550/ARXIV.2511.19584"},{"key":"journals/corr/abs-2512-03743","title":"Cross-embodied Co-design for Dexterous Hands.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2512.03743"],"source":"https://dblp.org/rec/journals/corr/abs-2512-03743","documentPage":"https://doi.org/10.48550/ARXIV.2512.03743","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2512.03743","authorSignatures":[{}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-03743","documentUrl":"https://doi.org/10.48550/ARXIV.2512.03743"}],"retrievedAt":"2026-10-19","querySource":"https://sparql.dblp.org/","method":"DBLP yearOfPublication=2025; Article + Inproceedings; excludes Informal/CoRR and explicit editorial/correction/erratum/preface; unique DBLP record keys within person.","preprintStatus":"partial_identity_review","preprintLowerBound2025":11,"sourceWarning":true,"labName":"STAIR Lab, Fudan University","labUrl":null,"labEvidence":"本人当前主页及 Contact 页面明确以 STAIR Lab, Fudan University 招募学生和学术合作；这是2026年加入复旦后的当前名称，不将2025年UCSD合作论文称为复旦实验室全年产量。","labSourceUrl":"https://www.haosu.ai/contact","affiliationZh":"复旦大学","knownPreprintMinimum2025":11,"excludedMisattributed":[{"key":"journals/cvgip/WangWLSLX25","title":"FlexPlan: High-flexibility interactive floorplan design based on ArchiGraph.","year":2025,"yearOfEvent":null,"venue":"Graph. Model.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1016/J.GMOD.2025.101303"],"source":"https://dblp.org/rec/journals/cvgip/WangWLSLX25","documentPage":"https://doi.org/10.1016/J.GMOD.2025.101303","type":"Article","doi":"https://doi.org/10.1016/J.GMOD.2025.101303","authorSignatures":[{"inst":"https://dblp.org/inst/2/466","instLabel":"Zhengzhou University"}],"exclusionReason":"Author signature assigns Zhengzhou University, matching the Zhengzhou Hao Su research group rather than UCSD/Fudan.","exclusionSource":"https://doi.org/10.1016/j.gmod.2025.101303","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/cvgip/WangWLSLX25","documentUrl":"https://doi.org/10.1016/J.GMOD.2025.101303"},{"key":"journals/tvcg/SuW00W025","title":"3DFaceSculptor: A Common Framework for Image-Guided 3D Face Deformation.","year":2025,"yearOfEvent":null,"venue":"IEEE Trans. Vis. Comput. Graph.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1109/TVCG.2025.3596482"],"source":"https://dblp.org/rec/journals/tvcg/SuW00W025","documentPage":"https://doi.org/10.1109/TVCG.2025.3596482","type":"Article","doi":"https://doi.org/10.1109/TVCG.2025.3596482","authorSignatures":[{"orcid":"https://orcid.org/0000-0001-5853-648X","inst":"https://dblp.org/inst/2/466","instLabel":"Zhengzhou University"}],"exclusionReason":"Different Zhengzhou University Hao Su explicitly claims the paper on his personal page; his Beihang PhD 2024 career differs from the UCSD/Fudan signatory.","exclusionSource":"https://suhaosh.github.io/","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/tvcg/SuW00W025","documentUrl":"https://doi.org/10.1109/TVCG.2025.3596482"}],"displayNotes":"检出的 DBLP 同名记录已排除，2025 年的正式记录已逐条复核。计入 24 条（会议 17、期刊 7），所有作者位置均计入。预印本候选池尚不完整，暂不给出总数，这不是零。","labDisplayNotes":"本人主页与 Contact 页以 STAIR Lab, Fudan University 的名义招募学生，据此归组。这是其 2026 年加入复旦后的名称；所列 2025 年论文不是复旦这个实验室的产量。"},{"index":83,"name":"Zhenglong Sun","nameZh":"孙正隆","affiliation":"The Chinese University of Hong Kong, Shenzhen","source":"DBLP Knowledge Graph official SPARQL API","profileUrl":"https://dblp.org/pid/02/3837","identifier":"02/3837","identityEvidence":[{"url":"https://dblp.org/pid/02/3837","evidence":"DBLP curated profile affiliations: Chinese University of Hong Kong, Shenzhen, China."}],"count2025":12,"conference2025":6,"journal2025":6,"preprint2025":4,"status":"verified","notes":"Counts are DBLP indexed coauthored records, not first-author counts, laboratory totals, unique scientific discoveries, or quality assessments. DBLP yearOfPublication=2025; yearOfEvent retained and can differ. Conference workshops are included. Preprints are separate and may overlap formal versions.","papers":[{"key":"conf/acl/YanLZ0G25","title":"Entrospect: Information-Theoretic Self-Reflection Elicits Better Response Refinement of Small Language Models.","year":2025,"yearOfEvent":2025,"venue":"ACL (Findings)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.18653/V1/2025.FINDINGS-ACL.1261"],"source":"https://dblp.org/rec/conf/acl/YanLZ0G25","documentPage":"https://doi.org/10.18653/V1/2025.FINDINGS-ACL.1261","type":"Inproceedings","doi":"https://doi.org/10.18653/V1/2025.FINDINGS-ACL.1261","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/acl/YanLZ0G25","documentUrl":"https://doi.org/10.18653/V1/2025.FINDINGS-ACL.1261"},{"key":"conf/iros/JiS25","title":"An Open-Source Snake Hole-Digging Inspired Safety-Critical Insertion Planning and Replanning Framework for Continuum Robots.","year":2025,"yearOfEvent":2025,"venue":"IROS","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/IROS60139.2025.11247533"],"source":"https://dblp.org/rec/conf/iros/JiS25","documentPage":"https://doi.org/10.1109/IROS60139.2025.11247533","type":"Inproceedings","doi":"https://doi.org/10.1109/IROS60139.2025.11247533","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iros/JiS25","documentUrl":"https://doi.org/10.1109/IROS60139.2025.11247533"},{"key":"conf/iros/WangQGJS25","title":"Towards Fully Autonomous Robotic Ultrasound-guided Biopsy for Superficial Organs.","year":2025,"yearOfEvent":2025,"venue":"IROS","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/IROS60139.2025.11245946"],"source":"https://dblp.org/rec/conf/iros/WangQGJS25","documentPage":"https://doi.org/10.1109/IROS60139.2025.11245946","type":"Inproceedings","doi":"https://doi.org/10.1109/IROS60139.2025.11245946","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iros/WangQGJS25","documentUrl":"https://doi.org/10.1109/IROS60139.2025.11245946"},{"key":"conf/iros/XuSW25","title":"High-dynamic Tactile Sensing for Tactile Servo Manipulation: Let Robots Swing a Hammer.","year":2025,"yearOfEvent":2025,"venue":"IROS","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/IROS60139.2025.11246617"],"source":"https://dblp.org/rec/conf/iros/XuSW25","documentPage":"https://doi.org/10.1109/IROS60139.2025.11246617","type":"Inproceedings","doi":"https://doi.org/10.1109/IROS60139.2025.11246617","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iros/XuSW25","documentUrl":"https://doi.org/10.1109/IROS60139.2025.11246617"},{"key":"conf/rcar/ChenQLJS25","title":"Design of a Novel Master-slave Robotic System for Natural Orifice Transluminal Endoscopic Surgery: A Prototype Study.","year":2025,"yearOfEvent":2025,"venue":"RCAR","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/RCAR65431.2025.11139499"],"source":"https://dblp.org/rec/conf/rcar/ChenQLJS25","documentPage":"https://doi.org/10.1109/RCAR65431.2025.11139499","type":"Inproceedings","doi":"https://doi.org/10.1109/RCAR65431.2025.11139499","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/rcar/ChenQLJS25","documentUrl":"https://doi.org/10.1109/RCAR65431.2025.11139499"},{"key":"conf/rcar/WeiWHWZSCJ25","title":"Fast Aesthetic Image Generation for Paper-Cutting Style.","year":2025,"yearOfEvent":2025,"venue":"RCAR","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/RCAR65431.2025.11139511"],"source":"https://dblp.org/rec/conf/rcar/WeiWHWZSCJ25","documentPage":"https://doi.org/10.1109/RCAR65431.2025.11139511","type":"Inproceedings","doi":"https://doi.org/10.1109/RCAR65431.2025.11139511","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/rcar/WeiWHWZSCJ25","documentUrl":"https://doi.org/10.1109/RCAR65431.2025.11139511"},{"key":"journals/bib/XieGZLCHLTSLYC25","title":"Toward high-efficiency, low-resource, and explainable neuropeptide prediction with MSKDNP.","year":2025,"yearOfEvent":null,"venue":"Briefings Bioinform.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1093/BIB/BBAF466"],"source":"https://dblp.org/rec/journals/bib/XieGZLCHLTSLYC25","documentPage":"https://doi.org/10.1093/BIB/BBAF466","type":"Article","doi":"https://doi.org/10.1093/BIB/BBAF466","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/bib/XieGZLCHLTSLYC25","documentUrl":"https://doi.org/10.1093/BIB/BBAF466"},{"key":"journals/jfr/WanZWWLCDHSZJ25","title":"Toward Universal Embodied Planning in Scalable Heterogeneous Field Robots Collaboration and Control.","year":2025,"yearOfEvent":null,"venue":"J. Field Robotics","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1002/ROB.22522"],"source":"https://dblp.org/rec/journals/jfr/WanZWWLCDHSZJ25","documentPage":"https://doi.org/10.1002/ROB.22522","type":"Article","doi":"https://doi.org/10.1002/ROB.22522","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/jfr/WanZWWLCDHSZJ25","documentUrl":"https://doi.org/10.1002/ROB.22522"},{"key":"journals/tie/JiGXS25","title":"Efficient Real2Sim2Real of Continuum Robots Using Deep Reinforcement Learning With Koopman Operator.","year":2025,"yearOfEvent":null,"venue":"IEEE Trans. Ind. Electron.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1109/TIE.2025.3532733"],"source":"https://dblp.org/rec/journals/tie/JiGXS25","documentPage":"https://doi.org/10.1109/TIE.2025.3532733","type":"Article","doi":"https://doi.org/10.1109/TIE.2025.3532733","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/tie/JiGXS25","documentUrl":"https://doi.org/10.1109/TIE.2025.3532733"},{"key":"journals/tnn/ZhuBYLSMC25","title":"Teaching Masked Autoencoder With Strong Augmentations.","year":2025,"yearOfEvent":null,"venue":"IEEE Trans. Neural Networks Learn. Syst.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1109/TNNLS.2024.3419898"],"source":"https://dblp.org/rec/journals/tnn/ZhuBYLSMC25","documentPage":"https://doi.org/10.1109/TNNLS.2024.3419898","type":"Article","doi":"https://doi.org/10.1109/TNNLS.2024.3419898","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/tnn/ZhuBYLSMC25","documentUrl":"https://doi.org/10.1109/TNNLS.2024.3419898"},{"key":"journals/trob/GaoJSXRS25","title":"Dynamic Hysteresis Compensation for Tendon-Sheath Mechanism in Flexible Surgical Robots Without Distal Perception.","year":2025,"yearOfEvent":null,"venue":"IEEE Trans. Robotics","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1109/TRO.2025.3577011"],"source":"https://dblp.org/rec/journals/trob/GaoJSXRS25","documentPage":"https://doi.org/10.1109/TRO.2025.3577011","type":"Article","doi":"https://doi.org/10.1109/TRO.2025.3577011","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/trob/GaoJSXRS25","documentUrl":"https://doi.org/10.1109/TRO.2025.3577011"},{"key":"journals/tsmc/WangLSX25","title":"Design and Analysis of a Closed-Loop Emotion Regulation System Based on Multimodal Affective Computing and Emotional Markov Chain.","year":2025,"yearOfEvent":null,"venue":"IEEE Trans. Syst. Man Cybern. Syst.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1109/TSMC.2024.3523342"],"source":"https://dblp.org/rec/journals/tsmc/WangLSX25","documentPage":"https://doi.org/10.1109/TSMC.2024.3523342","type":"Article","doi":"https://doi.org/10.1109/TSMC.2024.3523342","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/tsmc/WangLSX25","documentUrl":"https://doi.org/10.1109/TSMC.2024.3523342"}],"preprints":[{"key":"journals/corr/abs-2504-09997","title":"GenTe: Generative Real-world Terrains for General Legged Robot Locomotion Control.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2504.09997"],"source":"https://dblp.org/rec/journals/corr/abs-2504-09997","documentPage":"https://doi.org/10.48550/ARXIV.2504.09997","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2504.09997","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2504-09997","documentUrl":"https://doi.org/10.48550/ARXIV.2504.09997","arxivId":"2504.09997","arxivUrl":"https://arxiv.org/abs/2504.09997"},{"key":"journals/corr/abs-2509-02055","title":"Align-Then-stEer: Adapting the Vision-Language Action Models through Unified Latent Guidance.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2509.02055"],"source":"https://dblp.org/rec/journals/corr/abs-2509-02055","documentPage":"https://doi.org/10.48550/ARXIV.2509.02055","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2509.02055","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-02055","documentUrl":"https://doi.org/10.48550/ARXIV.2509.02055","arxivId":"2509.02055","arxivUrl":"https://arxiv.org/abs/2509.02055"},{"key":"journals/corr/abs-2509-24413","title":"DynaMIC: Dynamic Multimodal In-Context Learning Enabled Embodied Robot Counterfactual Resistance Ability.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2509.24413"],"source":"https://dblp.org/rec/journals/corr/abs-2509-24413","documentPage":"https://doi.org/10.48550/ARXIV.2509.24413","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2509.24413","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-24413","documentUrl":"https://doi.org/10.48550/ARXIV.2509.24413","arxivId":"2509.24413","arxivUrl":"https://arxiv.org/abs/2509.24413"},{"key":"journals/corr/abs-2512-03548","title":"A Learning-based Control Methodology for Transitioning VTOL UAVs.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2512.03548"],"source":"https://dblp.org/rec/journals/corr/abs-2512-03548","documentPage":"https://doi.org/10.48550/ARXIV.2512.03548","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2512.03548","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-03548","documentUrl":"https://doi.org/10.48550/ARXIV.2512.03548","arxivId":"2512.03548","arxivUrl":"https://arxiv.org/abs/2512.03548"}],"excludedFormal":[],"excludedOther":[],"excludedHomonyms":[],"unassignedCandidates":[],"retrievedAt":"2026-10-19","querySource":"https://sparql.dblp.org/","method":"DBLP yearOfPublication=2025; Article + Inproceedings; excludes Informal/CoRR and explicit editorial/correction/erratum/preface; unique DBLP record keys within person.","labName":"Sun’s Lab","labUrl":"https://sites.google.com/site/sunkurt/","labEvidence":"本人主页实际使用 Sun’s Lab 标题，主页列孙正隆姓名、港中深任职及2026年实验室动态；名称源于页面原称，并非由姓名自动编造。","labSourceUrl":"https://sites.google.com/site/sunkurt/","affiliationZh":"香港中文大学（深圳）","sourceWarning":false,"knownPreprintMinimum2025":null,"excludedMisattributed":[],"displayNotes":"身份已经个人或机构主页核对。2025 年正式记录 12 条（会议 6、期刊 6），所有作者位置均计入；预印本 4 条单列，不加总。","labDisplayNotes":"本人主页即以 Sun’s Lab 为标题，列出其港中深职务与 2026 年组内动态，据此归组；名称取自页面原称，不是按姓名生成的。"},{"index":84,"name":"Ping Tan","nameZh":"谭平","affiliation":"The Hong Kong University of Science and Technology","source":"DBLP Knowledge Graph official SPARQL API","profileUrl":"https://dblp.org/pid/61/6118-2","identifier":"61/6118-2","identityEvidence":[{"url":"https://dblp.org/pid/61/6118-2","evidence":"DBLP curated profile affiliations: Hong Kong University of Science and Technology, Hong Kong."},{"url":"https://dblp.org/pid/61/6118-2","evidence":"DBLP curated profile homepages: https://openreview.net/profile?id=~Ping_Tan2; https://pingtan.people.ust.hk/index.html."}],"count2025":16,"conference2025":12,"journal2025":4,"preprint2025":19,"status":"verified","notes":"Counts are DBLP indexed coauthored records, not first-author counts, laboratory totals, unique scientific discoveries, or quality assessments. DBLP yearOfPublication=2025; yearOfEvent retained and can differ. Conference workshops are included. Preprints are separate and may overlap formal versions.","papers":[{"key":"conf/3dim/FangDLHST25","title":"Ctrl-Room: Controllable Text-to-3D Room Meshes Generation with Layout Constraints.","year":2025,"yearOfEvent":2025,"venue":"3DV","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/3DV66043.2025.00069"],"source":"https://dblp.org/rec/conf/3dim/FangDLHST25","documentPage":"https://doi.org/10.1109/3DV66043.2025.00069","type":"Inproceedings","doi":"https://doi.org/10.1109/3DV66043.2025.00069","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/3dim/FangDLHST25","documentUrl":"https://doi.org/10.1109/3DV66043.2025.00069"},{"key":"conf/3dim/LiuLLZLYT25","title":"Gaussianavatar-Editor: Photorealistic Animatable Gaussian Head Avatar Editor.","year":2025,"yearOfEvent":2025,"venue":"3DV","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/3DV66043.2025.00108"],"source":"https://dblp.org/rec/conf/3dim/LiuLLZLYT25","documentPage":"https://doi.org/10.1109/3DV66043.2025.00108","type":"Inproceedings","doi":"https://doi.org/10.1109/3DV66043.2025.00108","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/3dim/LiuLLZLYT25","documentUrl":"https://doi.org/10.1109/3DV66043.2025.00108"},{"key":"conf/aaai/QuML0MWZ0T25","title":"Universal Features Guided Zero-Shot Category-Level Object Pose Estimation.","year":2025,"yearOfEvent":2025,"venue":"AAAI","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1609/AAAI.V39I6.32713"],"source":"https://dblp.org/rec/conf/aaai/QuML0MWZ0T25","documentPage":"https://doi.org/10.1609/AAAI.V39I6.32713","type":"Inproceedings","doi":"https://doi.org/10.1609/AAAI.V39I6.32713","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/aaai/QuML0MWZ0T25","documentUrl":"https://doi.org/10.1609/AAAI.V39I6.32713"},{"key":"conf/aaai/YanLLLT25","title":"SymmCompletion: High-Fidelity and High-Consistency Point Cloud Completion with Symmetry Guidance.","year":2025,"yearOfEvent":2025,"venue":"AAAI","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1609/AAAI.V39I9.32984"],"source":"https://dblp.org/rec/conf/aaai/YanLLLT25","documentPage":"https://doi.org/10.1609/AAAI.V39I9.32984","type":"Inproceedings","doi":"https://doi.org/10.1609/AAAI.V39I9.32984","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/aaai/YanLLLT25","documentUrl":"https://doi.org/10.1609/AAAI.V39I9.32984"},{"key":"conf/cvpr/ChenZLLLLLLFT25","title":"Dora: Sampling and Benchmarking for 3D Shape Variational Auto-Encoders.","year":2025,"yearOfEvent":2025,"venue":"CVPR","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/CVPR52734.2025.01515"],"source":"https://dblp.org/rec/conf/cvpr/ChenZLLLLLLFT25","documentPage":"https://openaccess.thecvf.com/content/CVPR2025/html/Chen_Dora_Sampling_and_Benchmarking_for_3D_Shape_Variational_Auto-Encoders_CVPR_2025_paper.html","type":"Inproceedings","doi":"https://doi.org/10.1109/CVPR52734.2025.01515","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/ChenZLLLLLLFT25","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Chen_Dora_Sampling_and_Benchmarking_for_3D_Shape_Variational_Auto-Encoders_CVPR_2025_paper.html"},{"key":"conf/cvpr/LiLYCLCTL25","title":"CraftsMan3D: High-fidelity Mesh Generation with 3D Native Diffusion and Interactive Geometry Refiner.","year":2025,"yearOfEvent":2025,"venue":"CVPR","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/CVPR52734.2025.00500"],"source":"https://dblp.org/rec/conf/cvpr/LiLYCLCTL25","documentPage":"https://openaccess.thecvf.com/content/CVPR2025/html/Li_CraftsMan3D_High-fidelity_Mesh_Generation_with_3D_Native_Diffusion_and_Interactive_CVPR_2025_paper.html","type":"Inproceedings","doi":"https://doi.org/10.1109/CVPR52734.2025.00500","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/LiLYCLCTL25","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Li_CraftsMan3D_High-fidelity_Mesh_Generation_with_3D_Native_Diffusion_and_Interactive_CVPR_2025_paper.html"},{"key":"conf/cvpr/WangZ0TZLLY0C0Z25","title":"SkillMimic: Learning Basketball Interaction Skills from Demonstrations.","year":2025,"yearOfEvent":2025,"venue":"CVPR","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/CVPR52734.2025.01634"],"source":"https://dblp.org/rec/conf/cvpr/WangZ0TZLLY0C0Z25","documentPage":"https://openaccess.thecvf.com/content/CVPR2025/html/Wang_SkillMimic_Learning_Basketball_Interaction_Skills_from_Demonstrations_CVPR_2025_paper.html","type":"Inproceedings","doi":"https://doi.org/10.1109/CVPR52734.2025.01634","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/WangZ0TZLLY0C0Z25","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Wang_SkillMimic_Learning_Basketball_Interaction_Skills_from_Demonstrations_CVPR_2025_paper.html"},{"key":"conf/eccv/ChenXLLLFTL24","title":"PointRegGPT: Boosting 3D Point Cloud Registration Using Generative Point-Cloud Pairs for Training.","year":2025,"yearOfEvent":2024,"venue":"ECCV (51)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1007/978-3-031-72983-6_16"],"source":"https://dblp.org/rec/conf/eccv/ChenXLLLFTL24","documentPage":"https://doi.org/10.1007/978-3-031-72983-6_16","type":"Inproceedings","doi":"https://doi.org/10.1007/978-3-031-72983-6_16","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/eccv/ChenXLLLFTL24","documentUrl":"https://doi.org/10.1007/978-3-031-72983-6_16"},{"key":"conf/eccv/FuYHWMTSLL24","title":"GeoWizard: Unleashing the Diffusion Priors for 3D Geometry Estimation from a Single Image.","year":2025,"yearOfEvent":2024,"venue":"ECCV (22)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1007/978-3-031-72670-5_14"],"source":"https://dblp.org/rec/conf/eccv/FuYHWMTSLL24","documentPage":"https://doi.org/10.1007/978-3-031-72670-5_14","type":"Inproceedings","doi":"https://doi.org/10.1007/978-3-031-72670-5_14","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/eccv/FuYHWMTSLL24","documentUrl":"https://doi.org/10.1007/978-3-031-72670-5_14"},{"key":"conf/iccv/DengYGZHRLT25","title":"Boost 3D Reconstruction Using Diffusion-Based Monocular Camera Calibration.","year":2025,"yearOfEvent":2025,"venue":"ICCV","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/ICCV51701.2025.00668"],"source":"https://dblp.org/rec/conf/iccv/DengYGZHRLT25","documentPage":"https://doi.org/10.1109/ICCV51701.2025.00668","type":"Inproceedings","doi":"https://doi.org/10.1109/ICCV51701.2025.00668","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/DengYGZHRLT25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.00668"},{"key":"conf/nips/MaoZFZTZTZ25","title":"SpatialLM: Training Large Language Models for Structured Indoor Modeling.","year":2025,"yearOfEvent":2025,"venue":"NeurIPS","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/nips/MaoZFZTZTZ25","documentPage":"http://papers.nips.cc/paper_files/paper/2025/hash/40223e204a9e18dd8b01d7d11ea97939-Abstract-Conference.html","type":"Inproceedings","doi":null,"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/nips/MaoZFZTZTZ25","documentUrl":"http://papers.nips.cc/paper_files/paper/2025/hash/40223e204a9e18dd8b01d7d11ea97939-Abstract-Conference.html"},{"key":"conf/siggraph/0003WZT00025","title":"SkillMimic-V2: Learning Robust and Generalizable Interaction Skills from Sparse and Noisy Demonstrations.","year":2025,"yearOfEvent":2025,"venue":"SIGGRAPH (Conference Paper Track)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1145/3721238.3730640"],"source":"https://dblp.org/rec/conf/siggraph/0003WZT00025","documentPage":"https://doi.org/10.1145/3721238.3730640","type":"Inproceedings","doi":"https://doi.org/10.1145/3721238.3730640","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/siggraph/0003WZT00025","documentUrl":"https://doi.org/10.1145/3721238.3730640"},{"key":"journals/pami/LiuZLTZ25","title":"Minimum Latency Deep Online Video Stabilization and Its Extensions.","year":2025,"yearOfEvent":null,"venue":"IEEE Trans. Pattern Anal. Mach. Intell.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1109/TPAMI.2024.3493175"],"source":"https://dblp.org/rec/journals/pami/LiuZLTZ25","documentPage":"https://doi.org/10.1109/TPAMI.2024.3493175","type":"Article","doi":"https://doi.org/10.1109/TPAMI.2024.3493175","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/pami/LiuZLTZ25","documentUrl":"https://doi.org/10.1109/TPAMI.2024.3493175"},{"key":"journals/ral/HuWJYJJZHT25","title":"MapEval: Towards Unified, Robust and Efficient SLAM Map Evaluation Framework.","year":2025,"yearOfEvent":null,"venue":"IEEE Robotics Autom. Lett.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1109/LRA.2025.3548441"],"source":"https://dblp.org/rec/journals/ral/HuWJYJJZHT25","documentPage":"https://doi.org/10.1109/LRA.2025.3548441","type":"Article","doi":"https://doi.org/10.1109/LRA.2025.3548441","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/ral/HuWJYJJZHT25","documentUrl":"https://doi.org/10.1109/LRA.2025.3548441"},{"key":"journals/tim/HuWXZJQJTZ25","title":"AM-Align: Globally Optimal Estimation of Accelerometer-Magnetometer Misalignment.","year":2025,"yearOfEvent":null,"venue":"IEEE Trans. Instrum. Meas.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1109/TIM.2025.3541657"],"source":"https://dblp.org/rec/journals/tim/HuWXZJQJTZ25","documentPage":"https://doi.org/10.1109/TIM.2025.3541657","type":"Article","doi":"https://doi.org/10.1109/TIM.2025.3541657","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/tim/HuWXZJQJTZ25","documentUrl":"https://doi.org/10.1109/TIM.2025.3541657"},{"key":"journals/tvcg/FengKPDYTZW25","title":"Learning Photometric Feature Transform for Free-Form Object Scan.","year":2025,"yearOfEvent":null,"venue":"IEEE Trans. Vis. Comput. Graph.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1109/TVCG.2024.3515478"],"source":"https://dblp.org/rec/journals/tvcg/FengKPDYTZW25","documentPage":"https://doi.org/10.1109/TVCG.2024.3515478","type":"Article","doi":"https://doi.org/10.1109/TVCG.2024.3515478","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/tvcg/FengKPDYTZW25","documentUrl":"https://doi.org/10.1109/TVCG.2024.3515478"}],"preprints":[{"key":"journals/corr/abs-2501-02831","title":"Universal Features Guided Zero-Shot Category-Level Object Pose Estimation.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2501.02831"],"source":"https://dblp.org/rec/journals/corr/abs-2501-02831","documentPage":"https://doi.org/10.48550/ARXIV.2501.02831","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2501.02831","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2501-02831","documentUrl":"https://doi.org/10.48550/ARXIV.2501.02831","arxivId":"2501.02831","arxivUrl":"https://arxiv.org/abs/2501.02831"},{"key":"journals/corr/abs-2501-09978","title":"GaussianAvatar-Editor: Photorealistic Animatable Gaussian Head Avatar Editor.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2501.09978"],"source":"https://dblp.org/rec/journals/corr/abs-2501-09978","documentPage":"https://doi.org/10.48550/ARXIV.2501.09978","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2501.09978","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2501-09978","documentUrl":"https://doi.org/10.48550/ARXIV.2501.09978","arxivId":"2501.09978","arxivUrl":"https://arxiv.org/abs/2501.09978"},{"key":"journals/corr/abs-2503-18007","title":"SymmCompletion: High-Fidelity and High-Consistency Point Cloud Completion with Symmetry Guidance.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2503.18007"],"source":"https://dblp.org/rec/journals/corr/abs-2503-18007","documentPage":"https://doi.org/10.48550/ARXIV.2503.18007","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2503.18007","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-18007","documentUrl":"https://doi.org/10.48550/ARXIV.2503.18007","arxivId":"2503.18007","arxivUrl":"https://arxiv.org/abs/2503.18007"},{"key":"journals/corr/abs-2505-02094","title":"SkillMimic-V2: Learning Robust and Generalizable Interaction Skills from Sparse and Noisy Demonstrations.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2505.02094"],"source":"https://dblp.org/rec/journals/corr/abs-2505-02094","documentPage":"https://doi.org/10.48550/ARXIV.2505.02094","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2505.02094","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-02094","documentUrl":"https://doi.org/10.48550/ARXIV.2505.02094","arxivId":"2505.02094","arxivUrl":"https://arxiv.org/abs/2505.02094"},{"key":"journals/corr/abs-2505-07747","title":"Step1X-3D: Towards High-Fidelity and Controllable Generation of Textured 3D Assets.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2505.07747"],"source":"https://dblp.org/rec/journals/corr/abs-2505-07747","documentPage":"https://doi.org/10.48550/ARXIV.2505.07747","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2505.07747","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-07747","documentUrl":"https://doi.org/10.48550/ARXIV.2505.07747","arxivId":"2505.07747","arxivUrl":"https://arxiv.org/abs/2505.07747"},{"key":"journals/corr/abs-2505-22394","title":"PacTure: Efficient PBR Texture Generation on Packed Views with Visual Autoregressive Models.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2505.22394"],"source":"https://dblp.org/rec/journals/corr/abs-2505-22394","documentPage":"https://doi.org/10.48550/ARXIV.2505.22394","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2505.22394","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-22394","documentUrl":"https://doi.org/10.48550/ARXIV.2505.22394","arxivId":"2505.22394","arxivUrl":"https://arxiv.org/abs/2505.22394"},{"key":"journals/corr/abs-2505-23253","title":"UniTEX: Universal High Fidelity Generative Texturing for 3D Shapes.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2505.23253"],"source":"https://dblp.org/rec/journals/corr/abs-2505-23253","documentPage":"https://doi.org/10.48550/ARXIV.2505.23253","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2505.23253","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-23253","documentUrl":"https://doi.org/10.48550/ARXIV.2505.23253","arxivId":"2505.23253","arxivUrl":"https://arxiv.org/abs/2505.23253"},{"key":"journals/corr/abs-2506-01337","title":"NoiseAR: AutoRegressing Initial Noise Prior for Diffusion Models.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2506.01337"],"source":"https://dblp.org/rec/journals/corr/abs-2506-01337","documentPage":"https://doi.org/10.48550/ARXIV.2506.01337","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2506.01337","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-01337","documentUrl":"https://doi.org/10.48550/ARXIV.2506.01337","arxivId":"2506.01337","arxivUrl":"https://arxiv.org/abs/2506.01337"},{"key":"journals/corr/abs-2506-07491","title":"SpatialLM: Training Large Language Models for Structured Indoor Modeling.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2506.07491"],"source":"https://dblp.org/rec/journals/corr/abs-2506-07491","documentPage":"https://doi.org/10.48550/ARXIV.2506.07491","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2506.07491","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-07491","documentUrl":"https://doi.org/10.48550/ARXIV.2506.07491","arxivId":"2506.07491","arxivUrl":"https://arxiv.org/abs/2506.07491"},{"key":"journals/corr/abs-2506-21076","title":"PoseMaster: Generating 3D Characters in Arbitrary Poses from a Single Image.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2506.21076"],"source":"https://dblp.org/rec/journals/corr/abs-2506-21076","documentPage":"https://doi.org/10.48550/ARXIV.2506.21076","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2506.21076","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-21076","documentUrl":"https://doi.org/10.48550/ARXIV.2506.21076","arxivId":"2506.21076","arxivUrl":"https://arxiv.org/abs/2506.21076"},{"key":"journals/corr/abs-2507-07997","title":"MGVQ: Could VQ-VAE Beat VAE? A Generalizable Tokenizer with Multi-group Quantization.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2507.07997"],"source":"https://dblp.org/rec/journals/corr/abs-2507-07997","documentPage":"https://doi.org/10.48550/ARXIV.2507.07997","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2507.07997","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2507-07997","documentUrl":"https://doi.org/10.48550/ARXIV.2507.07997","arxivId":"2507.07997","arxivUrl":"https://arxiv.org/abs/2507.07997"},{"key":"journals/corr/abs-2508-13488","title":"ROVER: Robust Loop Closure Verification with Trajectory Prior in Repetitive Environments.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2508.13488"],"source":"https://dblp.org/rec/journals/corr/abs-2508-13488","documentPage":"https://doi.org/10.48550/ARXIV.2508.13488","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2508.13488","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-13488","documentUrl":"https://doi.org/10.48550/ARXIV.2508.13488","arxivId":"2508.13488","arxivUrl":"https://arxiv.org/abs/2508.13488"},{"key":"journals/corr/abs-2508-17972","title":"SAIL-Recon: Large SfM by Augmenting Scene Regression with Localization.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2508.17972"],"source":"https://dblp.org/rec/journals/corr/abs-2508-17972","documentPage":"https://doi.org/10.48550/ARXIV.2508.17972","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2508.17972","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-17972","documentUrl":"https://doi.org/10.48550/ARXIV.2508.17972","arxivId":"2508.17972","arxivUrl":"https://arxiv.org/abs/2508.17972"},{"key":"journals/corr/abs-2509-06285","title":"DCReg: Decoupled Characterization for Efficient Degenerate LiDAR Registration.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2509.06285"],"source":"https://dblp.org/rec/journals/corr/abs-2509-06285","documentPage":"https://doi.org/10.48550/ARXIV.2509.06285","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2509.06285","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-06285","documentUrl":"https://doi.org/10.48550/ARXIV.2509.06285","arxivId":"2509.06285","arxivUrl":"https://arxiv.org/abs/2509.06285"},{"key":"journals/corr/abs-2509-14981","title":"SPATIALGEN: Layout-guided 3D Indoor Scene Generation.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2509.14981"],"source":"https://dblp.org/rec/journals/corr/abs-2509-14981","documentPage":"https://doi.org/10.48550/ARXIV.2509.14981","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2509.14981","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-14981","documentUrl":"https://doi.org/10.48550/ARXIV.2509.14981","arxivId":"2509.14981","arxivUrl":"https://arxiv.org/abs/2509.14981"},{"key":"journals/corr/abs-2510-04111","title":"Learning Efficient Meshflow and Optical Flow from Event Cameras.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2510.04111"],"source":"https://dblp.org/rec/journals/corr/abs-2510-04111","documentPage":"https://doi.org/10.48550/ARXIV.2510.04111","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2510.04111","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-04111","documentUrl":"https://doi.org/10.48550/ARXIV.2510.04111","arxivId":"2510.04111","arxivUrl":"https://arxiv.org/abs/2510.04111"},{"key":"journals/corr/abs-2511-20565","title":"DINO-Tok: Adapting DINO for Visual Tokenizers.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2511.20565"],"source":"https://dblp.org/rec/journals/corr/abs-2511-20565","documentPage":"https://doi.org/10.48550/ARXIV.2511.20565","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2511.20565","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2511-20565","documentUrl":"https://doi.org/10.48550/ARXIV.2511.20565","arxivId":"2511.20565","arxivUrl":"https://arxiv.org/abs/2511.20565"},{"key":"journals/corr/abs-2512-10957","title":"SceneMaker: Open-set 3D Scene Generation with Decoupled De-occlusion and Pose Estimation Model.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2512.10957"],"source":"https://dblp.org/rec/journals/corr/abs-2512-10957","documentPage":"https://doi.org/10.48550/ARXIV.2512.10957","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2512.10957","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-10957","documentUrl":"https://doi.org/10.48550/ARXIV.2512.10957","arxivId":"2512.10957","arxivUrl":"https://arxiv.org/abs/2512.10957"},{"key":"journals/corr/abs-2512-19583","title":"Learning Generalizable Hand-Object Tracking from Synthetic Demonstrations.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2512.19583"],"source":"https://dblp.org/rec/journals/corr/abs-2512-19583","documentPage":"https://doi.org/10.48550/ARXIV.2512.19583","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2512.19583","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-19583","documentUrl":"https://doi.org/10.48550/ARXIV.2512.19583","arxivId":"2512.19583","arxivUrl":"https://arxiv.org/abs/2512.19583"}],"excludedFormal":[],"excludedOther":[],"excludedHomonyms":[],"unassignedCandidates":[],"retrievedAt":"2026-10-19","querySource":"https://sparql.dblp.org/","method":"DBLP yearOfPublication=2025; Article + Inproceedings; excludes Informal/CoRR and explicit editorial/correction/erratum/preface; unique DBLP record keys within person.","labName":null,"labUrl":null,"labEvidence":"本人港科大主页仅明确现任学校；Alibaba XR Lab 被写为加入港科大前经历，未据此填写当前Lab。","labSourceUrl":"https://pingtan.people.ust.hk/index.html","affiliationZh":"香港科技大学","sourceWarning":false,"knownPreprintMinimum2025":null,"excludedMisattributed":[],"displayNotes":"身份已经个人或机构主页核对。2025 年正式记录 16 条（会议 12、期刊 4），所有作者位置均计入，不表示主导或贡献份额；预印本 19 条单列，不加总。","labDisplayNotes":"本人港科大主页把阿里巴巴 XR Lab 列为加入港科大前的经历，未写当前实验室名称；图中以「姓名及合作者」单列。"},{"index":85,"name":"Benyou Wang","nameZh":"王本友","affiliation":"The Chinese University of Hong Kong, Shenzhen","source":"DBLP Knowledge Graph official SPARQL API","profileUrl":"https://dblp.org/pid/169/1793","identifier":"169/1793","identityEvidence":[{"url":"https://dblp.org/pid/169/1793","evidence":"DBLP curated profile affiliations: Chinese University of Hong Kong-Shenzhen (CUHK-SZ), Shenzhen, China."},{"url":"https://dblp.org/pid/169/1793","evidence":"DBLP curated profile homepages: https://openreview.net/profile?id=~Benyou_Wang2; https://wabyking.github.io/old.html."}],"count2025":37,"conference2025":34,"journal2025":3,"preprint2025":41,"status":"verified","notes":"Counts are DBLP indexed coauthored records, not first-author counts, laboratory totals, unique scientific discoveries, or quality assessments. DBLP yearOfPublication=2025; yearOfEvent retained and can differ. Conference workshops are included. Preprints are separate and may overlap formal versions.","papers":[{"key":"conf/acl/CaiCWWDSCZW25","title":"Exploring Compositional Generalization of Multimodal LLMs for Medical Imaging.","year":2025,"yearOfEvent":2025,"venue":"ACL (1)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.18653/V1/2025.ACL-LONG.639"],"source":"https://dblp.org/rec/conf/acl/CaiCWWDSCZW25","documentPage":"https://doi.org/10.18653/V1/2025.ACL-LONG.639","type":"Inproceedings","doi":"https://doi.org/10.18653/V1/2025.ACL-LONG.639","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/acl/CaiCWWDSCZW25","documentUrl":"https://doi.org/10.18653/V1/2025.ACL-LONG.639"},{"key":"conf/acl/ChenCJWLWW25","title":"Towards Medical Complex Reasoning with LLMs through Medical Verifiable Problems.","year":2025,"yearOfEvent":2025,"venue":"ACL (Findings)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.18653/V1/2025.FINDINGS-ACL.751"],"source":"https://dblp.org/rec/conf/acl/ChenCJWLWW25","documentPage":"https://doi.org/10.18653/V1/2025.FINDINGS-ACL.751","type":"Inproceedings","doi":"https://doi.org/10.18653/V1/2025.FINDINGS-ACL.751","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/acl/ChenCJWLWW25","documentUrl":"https://doi.org/10.18653/V1/2025.FINDINGS-ACL.751"},{"key":"conf/acl/ChenGGJWWW25","title":"CoD, Towards an Interpretable Medical Agent using Chain of Diagnosis.","year":2025,"yearOfEvent":2025,"venue":"ACL (Findings)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.18653/V1/2025.FINDINGS-ACL.740"],"source":"https://dblp.org/rec/conf/acl/ChenGGJWWW25","documentPage":"https://doi.org/10.18653/V1/2025.FINDINGS-ACL.740","type":"Inproceedings","doi":"https://doi.org/10.18653/V1/2025.FINDINGS-ACL.740","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/acl/ChenGGJWWW25","documentUrl":"https://doi.org/10.18653/V1/2025.FINDINGS-ACL.740"},{"key":"conf/acl/JiCGXWW25","title":"Unlocking LLMs' Self-Improvement Capacity with Autonomous Learning for Domain Adaptation.","year":2025,"yearOfEvent":2025,"venue":"ACL (Findings)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.18653/V1/2025.FINDINGS-ACL.1084"],"source":"https://dblp.org/rec/conf/acl/JiCGXWW25","documentPage":"https://doi.org/10.18653/V1/2025.FINDINGS-ACL.1084","type":"Inproceedings","doi":"https://doi.org/10.18653/V1/2025.FINDINGS-ACL.1084","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/acl/JiCGXWW25","documentUrl":"https://doi.org/10.18653/V1/2025.FINDINGS-ACL.1084"},{"key":"conf/acl/ZhangLBZW025","title":"Soundwave: Less is More for Speech-Text Alignment in LLMs.","year":2025,"yearOfEvent":2025,"venue":"ACL (1)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.18653/V1/2025.ACL-LONG.917"],"source":"https://dblp.org/rec/conf/acl/ZhangLBZW025","documentPage":"https://doi.org/10.18653/V1/2025.ACL-LONG.917","type":"Inproceedings","doi":"https://doi.org/10.18653/V1/2025.ACL-LONG.917","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/acl/ZhangLBZW025","documentUrl":"https://doi.org/10.18653/V1/2025.ACL-LONG.917"},{"key":"conf/acl/ZhangMKLSWXH0Z25","title":"Leveraging Unit Language Guidance to Advance Speech Modeling in Textless Speech-to-Speech Translation.","year":2025,"yearOfEvent":2025,"venue":"ACL (Findings)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.18653/V1/2025.FINDINGS-ACL.75"],"source":"https://dblp.org/rec/conf/acl/ZhangMKLSWXH0Z25","documentPage":"https://doi.org/10.18653/V1/2025.FINDINGS-ACL.75","type":"Inproceedings","doi":"https://doi.org/10.18653/V1/2025.FINDINGS-ACL.75","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/acl/ZhangMKLSWXH0Z25","documentUrl":"https://doi.org/10.18653/V1/2025.FINDINGS-ACL.75"},{"key":"conf/acl/ZhuHLLTAA0HWYCM25","title":"Second Language (Arabic) Acquisition of LLMs via Progressive Vocabulary Expansion.","year":2025,"yearOfEvent":2025,"venue":"ACL (1)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.18653/V1/2025.ACL-LONG.100"],"source":"https://dblp.org/rec/conf/acl/ZhuHLLTAA0HWYCM25","documentPage":"https://doi.org/10.18653/V1/2025.ACL-LONG.100","type":"Inproceedings","doi":"https://doi.org/10.18653/V1/2025.ACL-LONG.100","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/acl/ZhuHLLTAA0HWYCM25","documentUrl":"https://doi.org/10.18653/V1/2025.ACL-LONG.100"},{"key":"conf/coling/SongWCWGW25","title":"Less is More: A Simple yet Effective Token Reduction Method for Efficient Multi-modal LLMs.","year":2025,"yearOfEvent":2025,"venue":"COLING","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/coling/SongWCWGW25","documentPage":"https://aclanthology.org/2025.coling-main.508/","type":"Inproceedings","doi":null,"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/coling/SongWCWGW25","documentUrl":"https://aclanthology.org/2025.coling-main.508/"},{"key":"conf/emnlp/ChenGJHGYW25","title":"DRBO: Mitigating Short Board Effect via Dynamic Reward Balancing in Multi-reward LLM Optimization.","year":2025,"yearOfEvent":2025,"venue":"EMNLP (Findings)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.18653/V1/2025.FINDINGS-EMNLP.468"],"source":"https://dblp.org/rec/conf/emnlp/ChenGJHGYW25","documentPage":"https://doi.org/10.18653/V1/2025.FINDINGS-EMNLP.468","type":"Inproceedings","doi":"https://doi.org/10.18653/V1/2025.FINDINGS-EMNLP.468","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/emnlp/ChenGJHGYW25","documentUrl":"https://doi.org/10.18653/V1/2025.FINDINGS-EMNLP.468"},{"key":"conf/emnlp/DaiZWL25","title":"From Word to World: Evaluate and Mitigate Culture Bias in LLMs via Word Association Test.","year":2025,"yearOfEvent":2025,"venue":"EMNLP","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.18653/V1/2025.EMNLP-MAIN.1246"],"source":"https://dblp.org/rec/conf/emnlp/DaiZWL25","documentPage":"https://doi.org/10.18653/V1/2025.EMNLP-MAIN.1246","type":"Inproceedings","doi":"https://doi.org/10.18653/V1/2025.EMNLP-MAIN.1246","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/emnlp/DaiZWL25","documentUrl":"https://doi.org/10.18653/V1/2025.EMNLP-MAIN.1246"},{"key":"conf/emnlp/LaiZCLYLHW25","title":"Can Multimodal LLMs See Materials Clearly? A Multimodal Benchmark on Materials Characterization.","year":2025,"yearOfEvent":2025,"venue":"EMNLP (Findings)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.18653/V1/2025.FINDINGS-EMNLP.235"],"source":"https://dblp.org/rec/conf/emnlp/LaiZCLYLHW25","documentPage":"https://doi.org/10.18653/V1/2025.FINDINGS-EMNLP.235","type":"Inproceedings","doi":"https://doi.org/10.18653/V1/2025.FINDINGS-EMNLP.235","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/emnlp/LaiZCLYLHW25","documentUrl":"https://doi.org/10.18653/V1/2025.FINDINGS-EMNLP.235"},{"key":"conf/emnlp/LiuCJZCW25","title":"RAG-Instruct: Boosting LLMs with Diverse Retrieval-Augmented Instructions.","year":2025,"yearOfEvent":2025,"venue":"EMNLP","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.18653/V1/2025.EMNLP-MAIN.192"],"source":"https://dblp.org/rec/conf/emnlp/LiuCJZCW25","documentPage":"https://doi.org/10.18653/V1/2025.EMNLP-MAIN.192","type":"Inproceedings","doi":"https://doi.org/10.18653/V1/2025.EMNLP-MAIN.192","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/emnlp/LiuCJZCW25","documentUrl":"https://doi.org/10.18653/V1/2025.EMNLP-MAIN.192"},{"key":"conf/emnlp/SongLWCSW25","title":"Both Text and Images Leaked! A Systematic Analysis of Data Contamination in Multimodal LLM.","year":2025,"yearOfEvent":2025,"venue":"EMNLP (Findings)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.18653/V1/2025.FINDINGS-EMNLP.556"],"source":"https://dblp.org/rec/conf/emnlp/SongLWCSW25","documentPage":"https://doi.org/10.18653/V1/2025.FINDINGS-EMNLP.556","type":"Inproceedings","doi":"https://doi.org/10.18653/V1/2025.FINDINGS-EMNLP.556","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/emnlp/SongLWCSW25","documentUrl":"https://doi.org/10.18653/V1/2025.FINDINGS-EMNLP.556"},{"key":"conf/emnlp/WangLWHZ25","title":"Model Unlearning via Sparse Autoencoder Subspace Guided Projections.","year":2025,"yearOfEvent":2025,"venue":"EMNLP","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.18653/V1/2025.EMNLP-MAIN.1348"],"source":"https://dblp.org/rec/conf/emnlp/WangLWHZ25","documentPage":"https://doi.org/10.18653/V1/2025.EMNLP-MAIN.1348","type":"Inproceedings","doi":"https://doi.org/10.18653/V1/2025.EMNLP-MAIN.1348","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/emnlp/WangLWHZ25","documentUrl":"https://doi.org/10.18653/V1/2025.EMNLP-MAIN.1348"},{"key":"conf/emnlp/WangSCCCZSW25","title":"LongLLaVA: Scaling Multi-modal LLMs to 1000 Images Efficiently via a Hybrid Architecture.","year":2025,"yearOfEvent":2025,"venue":"EMNLP (Findings)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.18653/V1/2025.FINDINGS-EMNLP.1168"],"source":"https://dblp.org/rec/conf/emnlp/WangSCCCZSW25","documentPage":"https://doi.org/10.18653/V1/2025.FINDINGS-EMNLP.1168","type":"Inproceedings","doi":"https://doi.org/10.18653/V1/2025.FINDINGS-EMNLP.1168","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/emnlp/WangSCCCZSW25","documentUrl":"https://doi.org/10.18653/V1/2025.FINDINGS-EMNLP.1168"},{"key":"conf/iclr/Gao0YCMDLMCXTWZ25","title":"Omni-MATH: A Universal Olympiad Level Mathematic Benchmark for Large Language Models.","year":2025,"yearOfEvent":2025,"venue":"ICLR","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/iclr/Gao0YCMDLMCXTWZ25","documentPage":"https://openreview.net/forum?id=yaqPf0KAlN","type":"Inproceedings","doi":null,"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iclr/Gao0YCMDLMCXTWZ25","documentUrl":"https://openreview.net/forum?id=yaqPf0KAlN"},{"key":"conf/iclr/ZhengWL0ZW25","title":"Efficiently Democratizing Medical LLMs for 50 Languages via a Mixture of Language Family Experts.","year":2025,"yearOfEvent":2025,"venue":"ICLR","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/iclr/ZhengWL0ZW25","documentPage":"https://openreview.net/forum?id=JSB171dSUU","type":"Inproceedings","doi":null,"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iclr/ZhengWL0ZW25","documentUrl":"https://openreview.net/forum?id=JSB171dSUU"},{"key":"conf/icml/WangHDCWZ25","title":"Towards Understanding Fine-Tuning Mechanisms of LLMs via Circuit Analysis.","year":2025,"yearOfEvent":2025,"venue":"ICML","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/icml/WangHDCWZ25","documentPage":"https://proceedings.mlr.press/v267/wang25ak.html","type":"Inproceedings","doi":null,"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/icml/WangHDCWZ25","documentUrl":"https://proceedings.mlr.press/v267/wang25ak.html"},{"key":"conf/icra/QinSHWZ25","title":"NavigateDiff: Visual Predictors are Zero-Shot Navigation Assistants.","year":2025,"yearOfEvent":2025,"venue":"ICRA","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/ICRA55743.2025.11127507"],"source":"https://dblp.org/rec/conf/icra/QinSHWZ25","documentPage":"https://doi.org/10.1109/ICRA55743.2025.11127507","type":"Inproceedings","doi":"https://doi.org/10.1109/ICRA55743.2025.11127507","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/icra/QinSHWZ25","documentUrl":"https://doi.org/10.1109/ICRA55743.2025.11127507"},{"key":"conf/mm/XiaoLPZZHLCTW25","title":"Can Audio Language Models Listen Between the Lines? A Study on Metaphorical Reasoning via Unspoken.","year":2025,"yearOfEvent":2025,"venue":"ACM Multimedia","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1145/3746027.3758173"],"source":"https://dblp.org/rec/conf/mm/XiaoLPZZHLCTW25","documentPage":"https://doi.org/10.1145/3746027.3758173","type":"Inproceedings","doi":"https://doi.org/10.1145/3746027.3758173","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/mm/XiaoLPZZHLCTW25","documentUrl":"https://doi.org/10.1145/3746027.3758173"},{"key":"conf/naacl/ChenghaoZhuCGZTW25","title":"Is Your LLM Outdated? A Deep Look at Temporal Generalization.","year":2025,"yearOfEvent":2025,"venue":"NAACL (Long Papers)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.18653/V1/2025.NAACL-LONG.381"],"source":"https://dblp.org/rec/conf/naacl/ChenghaoZhuCGZTW25","documentPage":"https://doi.org/10.18653/V1/2025.NAACL-LONG.381","type":"Inproceedings","doi":"https://doi.org/10.18653/V1/2025.NAACL-LONG.381","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/naacl/ChenghaoZhuCGZTW25","documentUrl":"https://doi.org/10.18653/V1/2025.NAACL-LONG.381"},{"key":"conf/naacl/ChenLW25","title":"Smurfs: Multi-Agent System using Context-Efficient DFSDT for Tool Planning.","year":2025,"yearOfEvent":2025,"venue":"NAACL (Long Papers)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.18653/V1/2025.NAACL-LONG.169"],"source":"https://dblp.org/rec/conf/naacl/ChenLW25","documentPage":"https://doi.org/10.18653/V1/2025.NAACL-LONG.169","type":"Inproceedings","doi":"https://doi.org/10.18653/V1/2025.NAACL-LONG.169","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/naacl/ChenLW25","documentUrl":"https://doi.org/10.18653/V1/2025.NAACL-LONG.169"},{"key":"conf/naacl/GanFZLJWCCXHW25","title":"UCL-Bench: A Chinese User-Centric Legal Benchmark for Large Language Models.","year":2025,"yearOfEvent":2025,"venue":"NAACL (Findings)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.18653/V1/2025.FINDINGS-NAACL.444"],"source":"https://dblp.org/rec/conf/naacl/GanFZLJWCCXHW25","documentPage":"https://doi.org/10.18653/V1/2025.FINDINGS-NAACL.444","type":"Inproceedings","doi":"https://doi.org/10.18653/V1/2025.FINDINGS-NAACL.444","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/naacl/GanFZLJWCCXHW25","documentUrl":"https://doi.org/10.18653/V1/2025.FINDINGS-NAACL.444"},{"key":"conf/naacl/GeCCCCCXYCLSWGZLWW25","title":"MLLM-Bench: Evaluating Multimodal LLMs with Per-sample Criteria.","year":2025,"yearOfEvent":2025,"venue":"NAACL (Long Papers)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.18653/V1/2025.NAACL-LONG.256"],"source":"https://dblp.org/rec/conf/naacl/GeCCCCCXYCLSWGZLWW25","documentPage":"https://doi.org/10.18653/V1/2025.NAACL-LONG.256","type":"Inproceedings","doi":"https://doi.org/10.18653/V1/2025.NAACL-LONG.256","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/naacl/GeCCCCCXYCLSWGZLWW25","documentUrl":"https://doi.org/10.18653/V1/2025.NAACL-LONG.256"},{"key":"conf/naacl/HuangSHGW25","title":"LLMs for Mathematical Modeling: Towards Bridging the Gap between Natural and Mathematical Languages.","year":2025,"yearOfEvent":2025,"venue":"NAACL (Findings)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.18653/V1/2025.FINDINGS-NAACL.146"],"source":"https://dblp.org/rec/conf/naacl/HuangSHGW25","documentPage":"https://doi.org/10.18653/V1/2025.FINDINGS-NAACL.146","type":"Inproceedings","doi":"https://doi.org/10.18653/V1/2025.FINDINGS-NAACL.146","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/naacl/HuangSHGW25","documentUrl":"https://doi.org/10.18653/V1/2025.FINDINGS-NAACL.146"},{"key":"conf/naacl/WangLCZWZXCFWGW25","title":"Huatuo-26M, a Large-scale Chinese Medical QA Dataset.","year":2025,"yearOfEvent":2025,"venue":"NAACL (Findings)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.18653/V1/2025.FINDINGS-NAACL.211"],"source":"https://dblp.org/rec/conf/naacl/WangLCZWZXCFWGW25","documentPage":"https://doi.org/10.18653/V1/2025.FINDINGS-NAACL.211","type":"Inproceedings","doi":"https://doi.org/10.18653/V1/2025.FINDINGS-NAACL.211","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/naacl/WangLCZWZXCFWGW25","documentUrl":"https://doi.org/10.18653/V1/2025.FINDINGS-NAACL.211"},{"key":"conf/naacl/YangZHGGHLZWXHYW25","title":"UCFE: A User-Centric Financial Expertise Benchmark for Large Language Models.","year":2025,"yearOfEvent":2025,"venue":"NAACL (Findings)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.18653/V1/2025.FINDINGS-NAACL.300"],"source":"https://dblp.org/rec/conf/naacl/YangZHGGHLZWXHYW25","documentPage":"https://doi.org/10.18653/V1/2025.FINDINGS-NAACL.300","type":"Inproceedings","doi":"https://doi.org/10.18653/V1/2025.FINDINGS-NAACL.300","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/naacl/YangZHGGHLZWXHYW25","documentUrl":"https://doi.org/10.18653/V1/2025.FINDINGS-NAACL.300"},{"key":"conf/nips/FengGLGWPWZWY25","title":"Video-R1: Reinforcing Video Reasoning in MLLMs.","year":2025,"yearOfEvent":2025,"venue":"NeurIPS","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/nips/FengGLGWPWZWY25","documentPage":"http://papers.nips.cc/paper_files/paper/2025/hash/8eb3976840e08b80dda9667562574246-Abstract-Conference.html","type":"Inproceedings","doi":null,"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/nips/FengGLGWPWZWY25","documentUrl":"http://papers.nips.cc/paper_files/paper/2025/hash/8eb3976840e08b80dda9667562574246-Abstract-Conference.html"},{"key":"conf/nips/JiXLLHLCCWTMY25","title":"The First Few Tokens Are All You Need: An Efficient and Effective Unsupervised Prefix Fine-Tuning Method for Reasoning Models.","year":2025,"yearOfEvent":2025,"venue":"NeurIPS","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/nips/JiXLLHLCCWTMY25","documentPage":"http://papers.nips.cc/paper_files/paper/2025/hash/0d6da26625f780df1572cf7c8dc3faa6-Abstract-Conference.html","type":"Inproceedings","doi":null,"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/nips/JiXLLHLCCWTMY25","documentUrl":"http://papers.nips.cc/paper_files/paper/2025/hash/0d6da26625f780df1572cf7c8dc3faa6-Abstract-Conference.html"},{"key":"conf/nips/LiTLXBDSWWLL25","title":"Teaching Language Models to Reason with Tools.","year":2025,"yearOfEvent":2025,"venue":"NeurIPS","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/nips/LiTLXBDSWWLL25","documentPage":"http://papers.nips.cc/paper_files/paper/2025/hash/6087df8ad77f2fc8025ee0d861224596-Abstract-Conference.html","type":"Inproceedings","doi":null,"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/nips/LiTLXBDSWWLL25","documentUrl":"http://papers.nips.cc/paper_files/paper/2025/hash/6087df8ad77f2fc8025ee0d861224596-Abstract-Conference.html"},{"key":"conf/nips/LiuXYLJCSWXW25","title":"QFFT, Question-Free Fine-Tuning for Adaptive Reasoning.","year":2025,"yearOfEvent":2025,"venue":"NeurIPS","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/nips/LiuXYLJCSWXW25","documentPage":"http://papers.nips.cc/paper_files/paper/2025/hash/28312c9491d60ed0c77f7fff4ad86dd1-Abstract-Conference.html","type":"Inproceedings","doi":null,"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/nips/LiuXYLJCSWXW25","documentUrl":"http://papers.nips.cc/paper_files/paper/2025/hash/28312c9491d60ed0c77f7fff4ad86dd1-Abstract-Conference.html"},{"key":"conf/nips/YangZWZZYHW25","title":"TwinMarket: A Scalable Behavioral and Social Simulation for Financial Markets.","year":2025,"yearOfEvent":2025,"venue":"NeurIPS","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/nips/YangZWZZYHW25","documentPage":"http://papers.nips.cc/paper_files/paper/2025/hash/5bf234ecf83cd77bc5b77a24ba9338b0-Abstract-Conference.html","type":"Inproceedings","doi":null,"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/nips/YangZWZZYHW25","documentUrl":"http://papers.nips.cc/paper_files/paper/2025/hash/5bf234ecf83cd77bc5b77a24ba9338b0-Abstract-Conference.html"},{"key":"conf/uai/LiuLLYW25","title":"Periodical Moving Average Accelerates Gradient Accumulation for Post-Training.","year":2025,"yearOfEvent":2025,"venue":"UAI","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/uai/LiuLLYW25","documentPage":"https://proceedings.mlr.press/v286/liu25e.html","type":"Inproceedings","doi":null,"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/uai/LiuLLYW25","documentUrl":"https://proceedings.mlr.press/v286/liu25e.html"},{"key":"conf/www/ChengZJW025","title":"Beyond Binary: Towards Fine-Grained LLM-Generated Text Detection via Role Recognition and Involvement Measurement.","year":2025,"yearOfEvent":2025,"venue":"WWW","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1145/3696410.3714770"],"source":"https://dblp.org/rec/conf/www/ChengZJW025","documentPage":"https://doi.org/10.1145/3696410.3714770","type":"Inproceedings","doi":"https://doi.org/10.1145/3696410.3714770","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/www/ChengZJW025","documentUrl":"https://doi.org/10.1145/3696410.3714770"},{"key":"journals/ior/HuangTHJZGWW25","title":"ORLM: A Customizable Framework in Training Large Models for Automated Optimization Modeling.","year":2025,"yearOfEvent":null,"venue":"Oper. Res.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1287/OPRE.2024.1233"],"source":"https://dblp.org/rec/journals/ior/HuangTHJZGWW25","documentPage":"https://doi.org/10.1287/OPRE.2024.1233","type":"Article","doi":"https://doi.org/10.1287/OPRE.2024.1233","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/ior/HuangTHJZGWW25","documentUrl":"https://doi.org/10.1287/OPRE.2024.1233"},{"key":"journals/nn/ZhangWWTLWQ25","title":"DialogueLLM: Context and emotion knowledge-tuned large language models for emotion recognition in conversations.","year":2025,"yearOfEvent":null,"venue":"Neural Networks","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1016/J.NEUNET.2025.107901"],"source":"https://dblp.org/rec/journals/nn/ZhangWWTLWQ25","documentPage":"https://doi.org/10.1016/J.NEUNET.2025.107901","type":"Article","doi":"https://doi.org/10.1016/J.NEUNET.2025.107901","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/nn/ZhangWWTLWQ25","documentUrl":"https://doi.org/10.1016/J.NEUNET.2025.107901"},{"key":"journals/tmlr/LiDTWZHHHHZGCWCDLSWLW25","title":"Synthetic Data (Almost) from Scratch: Generalized Instruction Tuning for Language Models.","year":2025,"yearOfEvent":null,"venue":"Trans. Mach. Learn. Res.","types":["https://dblp.org/rdf/schema#Article"],"dois":[],"source":"https://dblp.org/rec/journals/tmlr/LiDTWZHHHHZGCWCDLSWLW25","documentPage":"https://openreview.net/forum?id=PahnCreCxK","type":"Article","doi":null,"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/tmlr/LiDTWZHHHHZGCWCDLSWLW25","documentUrl":"https://openreview.net/forum?id=PahnCreCxK"}],"preprints":[{"key":"journals/corr/abs-2501-00353","title":"RAG-Instruct: Boosting LLMs with Diverse Retrieval-Augmented Instructions.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2501.00353"],"source":"https://dblp.org/rec/journals/corr/abs-2501-00353","documentPage":"https://doi.org/10.48550/ARXIV.2501.00353","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2501.00353","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2501-00353","documentUrl":"https://doi.org/10.48550/ARXIV.2501.00353","arxivId":"2501.00353","arxivUrl":"https://arxiv.org/abs/2501.00353"},{"key":"journals/corr/abs-2501-05727","title":"Enabling Scalable Oversight via Self-Evolving Critic.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2501.05727"],"source":"https://dblp.org/rec/journals/corr/abs-2501-05727","documentPage":"https://doi.org/10.48550/ARXIV.2501.05727","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2501.05727","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2501-05727","documentUrl":"https://doi.org/10.48550/ARXIV.2501.05727","arxivId":"2501.05727","arxivUrl":"https://arxiv.org/abs/2501.05727"},{"key":"journals/corr/abs-2501-14492","title":"RealCritic: Towards Effectiveness-Driven Evaluation of Language Model Critiques.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2501.14492"],"source":"https://dblp.org/rec/journals/corr/abs-2501-14492","documentPage":"https://doi.org/10.48550/ARXIV.2501.14492","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2501.14492","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2501-14492","documentUrl":"https://doi.org/10.48550/ARXIV.2501.14492","arxivId":"2501.14492","arxivUrl":"https://arxiv.org/abs/2501.14492"},{"key":"journals/corr/abs-2502-00271","title":"Scaling Flaws of Verifier-Guided Search in Mathematical Reasoning.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2502.00271"],"source":"https://dblp.org/rec/journals/corr/abs-2502-00271","documentPage":"https://doi.org/10.48550/ARXIV.2502.00271","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2502.00271","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2502-00271","documentUrl":"https://doi.org/10.48550/ARXIV.2502.00271","arxivId":"2502.00271","arxivUrl":"https://arxiv.org/abs/2502.00271"},{"key":"journals/corr/abs-2502-01085","title":"Federated Linear Dueling Bandits.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2502.01085"],"source":"https://dblp.org/rec/journals/corr/abs-2502-01085","documentPage":"https://doi.org/10.48550/ARXIV.2502.01085","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2502.01085","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2502-01085","documentUrl":"https://doi.org/10.48550/ARXIV.2502.01085","arxivId":"2502.01085","arxivUrl":"https://arxiv.org/abs/2502.01085"},{"key":"journals/corr/abs-2502-01506","title":"TwinMarket: A Scalable Behavioral and Social Simulation for Financial Markets.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2502.01506"],"source":"https://dblp.org/rec/journals/corr/abs-2502-01506","documentPage":"https://doi.org/10.48550/ARXIV.2502.01506","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2502.01506","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2502-01506","documentUrl":"https://doi.org/10.48550/ARXIV.2502.01506","arxivId":"2502.01506","arxivUrl":"https://arxiv.org/abs/2502.01506"},{"key":"journals/corr/abs-2502-11155","title":"Uncertainty-Aware Search and Value Models: Mitigating Search Scaling Flaws in LLMs.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2502.11155"],"source":"https://dblp.org/rec/journals/corr/abs-2502-11155","documentPage":"https://doi.org/10.48550/ARXIV.2502.11155","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2502.11155","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2502-11155","documentUrl":"https://doi.org/10.48550/ARXIV.2502.11155","arxivId":"2502.11155","arxivUrl":"https://arxiv.org/abs/2502.11155"},{"key":"journals/corr/abs-2502-11812","title":"Towards Understanding Fine-Tuning Mechanisms of LLMs via Circuit Analysis.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2502.11812"],"source":"https://dblp.org/rec/journals/corr/abs-2502-11812","documentPage":"https://doi.org/10.48550/ARXIV.2502.11812","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2502.11812","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2502-11812","documentUrl":"https://doi.org/10.48550/ARXIV.2502.11812","arxivId":"2502.11812","arxivUrl":"https://arxiv.org/abs/2502.11812"},{"key":"journals/corr/abs-2502-12900","title":"Soundwave: Less is More for Speech-Text Alignment in LLMs.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2502.12900"],"source":"https://dblp.org/rec/journals/corr/abs-2502-12900","documentPage":"https://doi.org/10.48550/ARXIV.2502.12900","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2502.12900","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2502-12900","documentUrl":"https://doi.org/10.48550/ARXIV.2502.12900","arxivId":"2502.12900","arxivUrl":"https://arxiv.org/abs/2502.12900"},{"key":"journals/corr/abs-2502-13894","title":"NavigateDiff: Visual Predictors are Zero-Shot Navigation Assistants.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2502.13894"],"source":"https://dblp.org/rec/journals/corr/abs-2502-13894","documentPage":"https://doi.org/10.48550/ARXIV.2502.13894","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2502.13894","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2502-13894","documentUrl":"https://doi.org/10.48550/ARXIV.2502.13894","arxivId":"2502.13894","arxivUrl":"https://arxiv.org/abs/2502.13894"},{"key":"journals/corr/abs-2503-02875","title":"The First Few Tokens Are All You Need: An Efficient and Effective Unsupervised Prefix Fine-Tuning Method for Reasoning Models.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2503.02875"],"source":"https://dblp.org/rec/journals/corr/abs-2503-02875","documentPage":"https://doi.org/10.48550/ARXIV.2503.02875","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2503.02875","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-02875","documentUrl":"https://doi.org/10.48550/ARXIV.2503.02875","arxivId":"2503.02875","arxivUrl":"https://arxiv.org/abs/2503.02875"},{"key":"journals/corr/abs-2503-05085","title":"S2S-Arena, Evaluating Speech2Speech Protocols on Instruction Following with Paralinguistic Information.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2503.05085"],"source":"https://dblp.org/rec/journals/corr/abs-2503-05085","documentPage":"https://doi.org/10.48550/ARXIV.2503.05085","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2503.05085","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-05085","documentUrl":"https://doi.org/10.48550/ARXIV.2503.05085","arxivId":"2503.05085","arxivUrl":"https://arxiv.org/abs/2503.05085"},{"key":"journals/corr/abs-2503-08292","title":"Large Language Models for Outpatient Referral: Problem Definition, Benchmarking and Challenges.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2503.08292"],"source":"https://dblp.org/rec/journals/corr/abs-2503-08292","documentPage":"https://doi.org/10.48550/ARXIV.2503.08292","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2503.08292","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-08292","documentUrl":"https://doi.org/10.48550/ARXIV.2503.08292","arxivId":"2503.08292","arxivUrl":"https://arxiv.org/abs/2503.08292"},{"key":"journals/corr/abs-2503-21776","title":"Video-R1: Reinforcing Video Reasoning in MLLMs.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2503.21776"],"source":"https://dblp.org/rec/journals/corr/abs-2503-21776","documentPage":"https://doi.org/10.48550/ARXIV.2503.21776","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2503.21776","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-21776","documentUrl":"https://doi.org/10.48550/ARXIV.2503.21776","arxivId":"2503.21776","arxivUrl":"https://arxiv.org/abs/2503.21776"},{"key":"journals/corr/abs-2505-07787","title":"Learning from Peers in Reasoning Models.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2505.07787"],"source":"https://dblp.org/rec/journals/corr/abs-2505-07787","documentPage":"https://doi.org/10.48550/ARXIV.2505.07787","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2505.07787","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-07787","documentUrl":"https://doi.org/10.48550/ARXIV.2505.07787","arxivId":"2505.07787","arxivUrl":"https://arxiv.org/abs/2505.07787"},{"key":"journals/corr/abs-2505-11175","title":"Real-Time Verification of Embodied Reasoning for Generative Skill Acquisition.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2505.11175"],"source":"https://dblp.org/rec/journals/corr/abs-2505-11175","documentPage":"https://doi.org/10.48550/ARXIV.2505.11175","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2505.11175","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-11175","documentUrl":"https://doi.org/10.48550/ARXIV.2505.11175","arxivId":"2505.11175","arxivUrl":"https://arxiv.org/abs/2505.11175"},{"key":"journals/corr/abs-2505-15333","title":"Leveraging Unit Language Guidance to Advance Speech Modeling in Textless Speech-to-Speech Translation.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2505.15333"],"source":"https://dblp.org/rec/journals/corr/abs-2505-15333","documentPage":"https://doi.org/10.48550/ARXIV.2505.15333","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2505.15333","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-15333","documentUrl":"https://doi.org/10.48550/ARXIV.2505.15333","arxivId":"2505.15333","arxivUrl":"https://arxiv.org/abs/2505.15333"},{"key":"journals/corr/abs-2505-18562","title":"From Word to World: Evaluate and Mitigate Culture Bias via Word Association Test.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2505.18562"],"source":"https://dblp.org/rec/journals/corr/abs-2505-18562","documentPage":"https://doi.org/10.48550/ARXIV.2505.18562","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2505.18562","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-18562","documentUrl":"https://doi.org/10.48550/ARXIV.2505.18562","arxivId":"2505.18562","arxivUrl":"https://arxiv.org/abs/2505.18562"},{"key":"journals/corr/abs-2505-24428","title":"Model Unlearning via Sparse Autoencoder Subspace Guided Projections.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2505.24428"],"source":"https://dblp.org/rec/journals/corr/abs-2505-24428","documentPage":"https://doi.org/10.48550/ARXIV.2505.24428","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2505.24428","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-24428","documentUrl":"https://doi.org/10.48550/ARXIV.2505.24428","arxivId":"2505.24428","arxivUrl":"https://arxiv.org/abs/2505.24428"},{"key":"journals/corr/abs-2506-01111","title":"FusionAudio-1.2M: Towards Fine-grained Audio Captioning with Multimodal Contextual Fusion.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2506.01111"],"source":"https://dblp.org/rec/journals/corr/abs-2506-01111","documentPage":"https://doi.org/10.48550/ARXIV.2506.01111","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2506.01111","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-01111","documentUrl":"https://doi.org/10.48550/ARXIV.2506.01111","arxivId":"2506.01111","arxivUrl":"https://arxiv.org/abs/2506.01111"},{"key":"journals/corr/abs-2506-09820","title":"CoRT: Code-integrated Reasoning within Thinking.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2506.09820"],"source":"https://dblp.org/rec/journals/corr/abs-2506-09820","documentPage":"https://doi.org/10.48550/ARXIV.2506.09820","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2506.09820","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-09820","documentUrl":"https://doi.org/10.48550/ARXIV.2506.09820","arxivId":"2506.09820","arxivUrl":"https://arxiv.org/abs/2506.09820"},{"key":"journals/corr/abs-2506-09968","title":"SRLAgent: Enhancing Self-Regulated Learning Skills through Gamification and LLM Assistance.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2506.09968"],"source":"https://dblp.org/rec/journals/corr/abs-2506-09968","documentPage":"https://doi.org/10.48550/ARXIV.2506.09968","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2506.09968","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-09968","documentUrl":"https://doi.org/10.48550/ARXIV.2506.09968","arxivId":"2506.09968","arxivUrl":"https://arxiv.org/abs/2506.09968"},{"key":"journals/corr/abs-2506-12860","title":"QFFT, Question-Free Fine-Tuning for Adaptive Reasoning.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2506.12860"],"source":"https://dblp.org/rec/journals/corr/abs-2506-12860","documentPage":"https://doi.org/10.48550/ARXIV.2506.12860","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2506.12860","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-12860","documentUrl":"https://doi.org/10.48550/ARXIV.2506.12860","arxivId":"2506.12860","arxivUrl":"https://arxiv.org/abs/2506.12860"},{"key":"journals/corr/abs-2506-18095","title":"ShareGPT-4o-Image: Aligning Multimodal Models with GPT-4o-Level Image Generation.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2506.18095"],"source":"https://dblp.org/rec/journals/corr/abs-2506-18095","documentPage":"https://doi.org/10.48550/ARXIV.2506.18095","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2506.18095","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-18095","documentUrl":"https://doi.org/10.48550/ARXIV.2506.18095","arxivId":"2506.18095","arxivUrl":"https://arxiv.org/abs/2506.18095"},{"key":"journals/corr/abs-2507-05675","title":"MedGen: Unlocking Medical Video Generation by Scaling Granularly-annotated Medical Videos.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2507.05675"],"source":"https://dblp.org/rec/journals/corr/abs-2507-05675","documentPage":"https://doi.org/10.48550/ARXIV.2507.05675","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2507.05675","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2507-05675","documentUrl":"https://doi.org/10.48550/ARXIV.2507.05675","arxivId":"2507.05675","arxivUrl":"https://arxiv.org/abs/2507.05675"},{"key":"journals/corr/abs-2508-05132","title":"Towards Assessing Medical Ethics from Knowledge to Practice.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2508.05132"],"source":"https://dblp.org/rec/journals/corr/abs-2508-05132","documentPage":"https://doi.org/10.48550/ARXIV.2508.05132","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2508.05132","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-05132","documentUrl":"https://doi.org/10.48550/ARXIV.2508.05132","arxivId":"2508.05132","arxivUrl":"https://arxiv.org/abs/2508.05132"},{"key":"journals/corr/abs-2508-13618","title":"TalkVid: A Large-Scale Diversified Dataset for Audio-Driven Talking Head Synthesis.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2508.13618"],"source":"https://dblp.org/rec/journals/corr/abs-2508-13618","documentPage":"https://doi.org/10.48550/ARXIV.2508.13618","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2508.13618","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-13618","documentUrl":"https://doi.org/10.48550/ARXIV.2508.13618","arxivId":"2508.13618","arxivUrl":"https://arxiv.org/abs/2508.13618"},{"key":"journals/corr/abs-2508-14706","title":"ShizhenGPT: Towards Multimodal LLMs for Traditional Chinese Medicine.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2508.14706"],"source":"https://dblp.org/rec/journals/corr/abs-2508-14706","documentPage":"https://doi.org/10.48550/ARXIV.2508.14706","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2508.14706","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-14706","documentUrl":"https://doi.org/10.48550/ARXIV.2508.14706","arxivId":"2508.14706","arxivUrl":"https://arxiv.org/abs/2508.14706"},{"key":"journals/corr/abs-2508-18240","title":"MTalk-Bench: Evaluating Speech-to-Speech Models in Multi-Turn Dialogues via Arena-style and Rubrics Protocols.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2508.18240"],"source":"https://dblp.org/rec/journals/corr/abs-2508-18240","documentPage":"https://doi.org/10.48550/ARXIV.2508.18240","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2508.18240","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-18240","documentUrl":"https://doi.org/10.48550/ARXIV.2508.18240","arxivId":"2508.18240","arxivUrl":"https://arxiv.org/abs/2508.18240"},{"key":"journals/corr/abs-2508-21148","title":"A Survey of Scientific Large Language Models: From Data Foundations to Agent Frontiers.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2508.21148"],"source":"https://dblp.org/rec/journals/corr/abs-2508-21148","documentPage":"https://doi.org/10.48550/ARXIV.2508.21148","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2508.21148","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-21148","documentUrl":"https://doi.org/10.48550/ARXIV.2508.21148","arxivId":"2508.21148","arxivUrl":"https://arxiv.org/abs/2508.21148"},{"key":"journals/corr/abs-2509-09174","title":"EchoX: Towards Mitigating Acoustic-Semantic Gap via Echo Training for Speech-to-Speech LLMs.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2509.09174"],"source":"https://dblp.org/rec/journals/corr/abs-2509-09174","documentPage":"https://doi.org/10.48550/ARXIV.2509.09174","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2509.09174","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-09174","documentUrl":"https://doi.org/10.48550/ARXIV.2509.09174","arxivId":"2509.09174","arxivUrl":"https://arxiv.org/abs/2509.09174"},{"key":"journals/corr/abs-2509-09307","title":"Can Multimodal LLMs See Materials Clearly? A Multimodal Benchmark on Materials Characterization.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2509.09307"],"source":"https://dblp.org/rec/journals/corr/abs-2509-09307","documentPage":"https://doi.org/10.48550/ARXIV.2509.09307","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2509.09307","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-09307","documentUrl":"https://doi.org/10.48550/ARXIV.2509.09307","arxivId":"2509.09307","arxivUrl":"https://arxiv.org/abs/2509.09307"},{"key":"journals/corr/abs-2510-00032","title":"WaveMind: Towards a Conversational EEG Foundation Model Aligned to Textual and Visual Modalities.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2510.00032"],"source":"https://dblp.org/rec/journals/corr/abs-2510-00032","documentPage":"https://doi.org/10.48550/ARXIV.2510.00032","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2510.00032","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-00032","documentUrl":"https://doi.org/10.48550/ARXIV.2510.00032","arxivId":"2510.00032","arxivUrl":"https://arxiv.org/abs/2510.00032"},{"key":"journals/corr/abs-2510-03659","title":"Does higher interpretability imply better utility? A Pairwise Analysis on Sparse Autoencoders.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2510.03659"],"source":"https://dblp.org/rec/journals/corr/abs-2510-03659","documentPage":"https://doi.org/10.48550/ARXIV.2510.03659","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2510.03659","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-03659","documentUrl":"https://doi.org/10.48550/ARXIV.2510.03659","arxivId":"2510.03659","arxivUrl":"https://arxiv.org/abs/2510.03659"},{"key":"journals/corr/abs-2510-04204","title":"CALM Before the STORM: Unlocking Native Reasoning for Optimization Modeling.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2510.04204"],"source":"https://dblp.org/rec/journals/corr/abs-2510-04204","documentPage":"https://doi.org/10.48550/ARXIV.2510.04204","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2510.04204","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-04204","documentUrl":"https://doi.org/10.48550/ARXIV.2510.04204","arxivId":"2510.04204","arxivUrl":"https://arxiv.org/abs/2510.04204"},{"key":"journals/corr/abs-2510-11040","title":"Enabling Doctor-Centric Medical AI with LLMs through Workflow-Aligned Tasks and Benchmarks.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2510.11040"],"source":"https://dblp.org/rec/journals/corr/abs-2510-11040","documentPage":"https://doi.org/10.48550/ARXIV.2510.11040","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2510.11040","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-11040","documentUrl":"https://doi.org/10.48550/ARXIV.2510.11040","arxivId":"2510.11040","arxivUrl":"https://arxiv.org/abs/2510.11040"},{"key":"journals/corr/abs-2510-20342","title":"Teaching Language Models to Reason with Tools.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2510.20342"],"source":"https://dblp.org/rec/journals/corr/abs-2510-20342","documentPage":"https://doi.org/10.48550/ARXIV.2510.20342","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2510.20342","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-20342","documentUrl":"https://doi.org/10.48550/ARXIV.2510.20342","arxivId":"2510.20342","arxivUrl":"https://arxiv.org/abs/2510.20342"},{"key":"journals/corr/abs-2510-20513","title":"Decoding the Ear: A Framework for Objectifying Expressiveness from Human Preference Through Efficient Alignment.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2510.20513"],"source":"https://dblp.org/rec/journals/corr/abs-2510-20513","documentPage":"https://doi.org/10.48550/ARXIV.2510.20513","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2510.20513","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-20513","documentUrl":"https://doi.org/10.48550/ARXIV.2510.20513","arxivId":"2510.20513","arxivUrl":"https://arxiv.org/abs/2510.20513"},{"key":"journals/corr/abs-2510-22758","title":"EchoMind: An Interrelated Multi-level Benchmark for Evaluating Empathetic Speech Language Models.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2510.22758"],"source":"https://dblp.org/rec/journals/corr/abs-2510-22758","documentPage":"https://doi.org/10.48550/ARXIV.2510.22758","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2510.22758","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-22758","documentUrl":"https://doi.org/10.48550/ARXIV.2510.22758","arxivId":"2510.22758","arxivUrl":"https://arxiv.org/abs/2510.22758"},{"key":"journals/corr/abs-2511-14783","title":"Human or LLM as Standardized Patients? A Comparative Study for Medical Education.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2511.14783"],"source":"https://dblp.org/rec/journals/corr/abs-2511-14783","documentPage":"https://doi.org/10.48550/ARXIV.2511.14783","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2511.14783","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2511-14783","documentUrl":"https://doi.org/10.48550/ARXIV.2511.14783","arxivId":"2511.14783","arxivUrl":"https://arxiv.org/abs/2511.14783"},{"key":"journals/corr/abs-2512-11558","title":"DentalGPT: Incentivizing Multimodal Complex Reasoning in Dentistry.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2512.11558"],"source":"https://dblp.org/rec/journals/corr/abs-2512-11558","documentPage":"https://doi.org/10.48550/ARXIV.2512.11558","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2512.11558","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-11558","documentUrl":"https://doi.org/10.48550/ARXIV.2512.11558","arxivId":"2512.11558","arxivUrl":"https://arxiv.org/abs/2512.11558"}],"excludedFormal":[],"excludedOther":[],"excludedHomonyms":[],"unassignedCandidates":[],"retrievedAt":"2026-10-19","querySource":"https://sparql.dblp.org/","method":"DBLP yearOfPublication=2025; Article + Inproceedings; excludes Informal/CoRR and explicit editorial/correction/erratum/preface; unique DBLP record keys within person.","labName":"Freedom AI","labUrl":"https://freedomintelligence.github.io/","labEvidence":"本人主页明确以“our lab / CUHKSZ LLM group”链接到该团队网站；团队当前首页自称 Freedom AI。没有使用未获一手验证的 WISDOM 名称。","labSourceUrl":"https://wabyking.github.io/","affiliationZh":"香港中文大学（深圳）","sourceWarning":false,"knownPreprintMinimum2025":null,"excludedMisattributed":[],"displayNotes":"身份已经个人或机构主页核对。2025 年正式记录 37 条（会议 34、期刊 3），所有作者位置均计入，不表示主导或贡献份额；预印本 41 条单列，不加总。","labDisplayNotes":"本人主页以「our lab / CUHKSZ LLM group」链接到团队网站，该站现称 Freedom AI，据此归组。"},{"index":86,"name":"Liang Wang","nameZh":"王亮","affiliation":"Institute of Automation, Chinese Academy of Sciences","source":"DBLP Knowledge Graph official SPARQL API","profileUrl":"https://dblp.org/pid/56/4499-1","identifier":"56/4499-1","identityEvidence":[{"url":"https://dblp.org/pid/56/4499-1","evidence":"DBLP curated profile affiliations: Chinese Academy of Sciences, Institute of Automation, Center for Research on Intelligent Perception and Computing, Beijing, China; Chinese Academy of Sciences, Institute of Automation, National Lab of Pattern Recognition, Beijing, China; Chinese Academy of Sciences, Institute of Automation, National Laboratory of Pattern Recognition, Beijing, China; Imperial College London, UK; Monash University, Australia; University of Bath, Department of Computer Science, Bath, UK; University of Chinese Academy of Sciences, School of Artificial Intelligence, Beijing, China; University of Melbourne, Australia."},{"url":"https://dblp.org/pid/56/4499-1","evidence":"DBLP curated profile homepages: http://people.ucas.ac.cn/~wangliang; http://www.cbsr.ia.ac.cn/users/liangwang/."},{"url":"https://people.ucas.ac.cn/~wangliang","evidence":"Official faculty page identifies 王亮 at CAS Institute of Automation; DBLP paper signatures for the intended person use ORCID 0000-0001-5224-8647. This PID nevertheless contains confirmed foreign-author records."},{"url":"https://api.crossref.org/works/10.1145%2F3696410.3714917","evidence":"Publisher-deposited metadata identifies the DAGPrompT author as Liang Wang, Alibaba Group, ORCID 0000-0001-5353-7803, a different person."},{"url":"https://api.crossref.org/works/10.1145%2F3696410.3714847","evidence":"Publisher-deposited metadata identifies the auction-paper author as Liang Wang, Alibaba Group, ORCID 0000-0001-5353-7803, a different person."},{"url":"https://api.crossref.org/works/10.1109%2FTIP.2025.3622374","evidence":"Publisher-deposited metadata identifies the C-NeRF author as Liang Wan (not Wang), Tianjin University, ORCID 0000-0001-5501-9575."},{"url":"https://api.crossref.org/works/10.1016%2FJ.ESWA.2025.126623","evidence":"Publisher-deposited metadata identifies the sign-language paper author as Liang Wan (not Wang); DBLP signature assigns Tianjin University."},{"url":"https://api.crossref.org/works/10.1016%2FJ.PATCOG.2024.111246","evidence":"Publisher-deposited metadata identifies the benchmark paper author as Liang Wan (not Wang); DBLP signature assigns Tianjin University."}],"count2025":null,"conference2025":null,"journal2025":null,"preprint2025":null,"status":"partial_identity_review","notes":"Counts are DBLP indexed coauthored records, not first-author counts, laboratory totals, unique scientific discoveries, or quality assessments. DBLP yearOfPublication=2025; yearOfEvent retained and can differ. Conference workshops are included. Preprints are separate and may overlap formal versions. Mixed / unassigned DBLP profile. Main counts withheld pending review of every remaining candidate; retained papers establish a verified lower bound only. Do not present this lower bound as an exact annual total.","papers":[{"key":"conf/cvpr/Yang0H0C0H25","title":"Bridging Gait Recognition and Large Language Models Sequence Modeling.","year":2025,"yearOfEvent":2025,"venue":"CVPR","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/CVPR52734.2025.00328"],"source":"https://dblp.org/rec/conf/cvpr/Yang0H0C0H25","documentPage":"https://openaccess.thecvf.com/content/CVPR2025/html/Yang_Bridging_Gait_Recognition_and_Large_Language_Models_Sequence_Modeling_CVPR_2025_paper.html","type":"Inproceedings","doi":"https://doi.org/10.1109/CVPR52734.2025.00328","authorSignatures":[{"inst":"https://dblp.org/inst/11/691","instLabel":"Chinese Academy of Sciences (CAS)"},{"inst":"https://dblp.org/inst/12/312","instLabel":"Institute of Automation (CASIA)"}],"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/Yang0H0C0H25","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Yang_Bridging_Gait_Recognition_and_Large_Language_Models_Sequence_Modeling_CVPR_2025_paper.html"},{"key":"conf/eccv/WangHHCLHZW24","title":"Free Lunch for Gait Recognition: A Novel Relation Descriptor.","year":2025,"yearOfEvent":2024,"venue":"ECCV (38)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1007/978-3-031-72920-1_3"],"source":"https://dblp.org/rec/conf/eccv/WangHHCLHZW24","documentPage":"https://doi.org/10.1007/978-3-031-72920-1_3","type":"Inproceedings","doi":"https://doi.org/10.1007/978-3-031-72920-1_3","authorSignatures":[{"orcid":"https://orcid.org/0000-0001-5224-8647","inst":"https://dblp.org/inst/11/691","instLabel":"Chinese Academy of Sciences (CAS)"},{"orcid":"https://orcid.org/0000-0001-5224-8647","inst":"https://dblp.org/inst/12/312","instLabel":"Institute of Automation (CASIA)"}],"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/eccv/WangHHCLHZW24","documentUrl":"https://doi.org/10.1007/978-3-031-72920-1_3"},{"key":"conf/icb/MaZYLXCZWLWOLAWZXWWKGXB25","title":"Human Identification at a Distance: Challenges, Methods and Results on the Competition HID 2025.","year":2025,"yearOfEvent":2025,"venue":"IJCB","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/IJCB65343.2025.11411399"],"source":"https://dblp.org/rec/conf/icb/MaZYLXCZWLWOLAWZXWWKGXB25","documentPage":"https://doi.org/10.1109/IJCB65343.2025.11411399","type":"Inproceedings","doi":"https://doi.org/10.1109/IJCB65343.2025.11411399","authorSignatures":[{"inst":"https://dblp.org/inst/11/691","instLabel":"Chinese Academy of Sciences (CAS)"},{"inst":"https://dblp.org/inst/12/312","instLabel":"Institute of Automation (CASIA)"}],"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/icb/MaZYLXCZWLWOLAWZXWWKGXB25","documentUrl":"https://doi.org/10.1109/IJCB65343.2025.11411399"},{"key":"conf/iccv/ChenLHYCW25","title":"EC-Flow: Enabling Versatile Robotic Manipulation from Action-Unlabeled Videos via Embodiment-Centric Flow.","year":2025,"yearOfEvent":2025,"venue":"ICCV","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/ICCV51701.2025.01112"],"source":"https://dblp.org/rec/conf/iccv/ChenLHYCW25","documentPage":"https://doi.org/10.1109/ICCV51701.2025.01112","type":"Inproceedings","doi":"https://doi.org/10.1109/ICCV51701.2025.01112","authorSignatures":[{"inst":"https://dblp.org/inst/11/691","instLabel":"Chinese Academy of Sciences (CAS)"},{"inst":"https://dblp.org/inst/12/312","instLabel":"Institute of Automation (CASIA)"},{"inst":"https://dblp.org/inst/5/099","instLabel":"University of the Chinese Academy of Sciences (UCAS)"}],"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/ChenLHYCW25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.01112"},{"key":"conf/icmcs/ShiLLSHFZW25","title":"Controllable Continual Test-Time Adaptation.","year":2025,"yearOfEvent":2025,"venue":"ICME","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/ICME59968.2025.11209779"],"source":"https://dblp.org/rec/conf/icmcs/ShiLLSHFZW25","documentPage":"https://doi.org/10.1109/ICME59968.2025.11209779","type":"Inproceedings","doi":"https://doi.org/10.1109/ICME59968.2025.11209779","authorSignatures":[{"inst":"https://dblp.org/inst/11/691","instLabel":"Chinese Academy of Sciences (CAS)"},{"inst":"https://dblp.org/inst/12/312","instLabel":"Institute of Automation (CASIA)"},{"inst":"https://dblp.org/inst/5/099","instLabel":"University of the Chinese Academy of Sciences (UCAS)"}],"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/icmcs/ShiLLSHFZW25","documentUrl":"https://doi.org/10.1109/ICME59968.2025.11209779"},{"key":"conf/icpr/DuYWHW24","title":"SPK: Semantic and Positional Knowledge for Zero-Shot Referring Expression Comprehension.","year":2025,"yearOfEvent":2024,"venue":"ICPR (30)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1007/978-3-031-78113-1_19"],"source":"https://dblp.org/rec/conf/icpr/DuYWHW24","documentPage":"https://doi.org/10.1007/978-3-031-78113-1_19","type":"Inproceedings","doi":"https://doi.org/10.1007/978-3-031-78113-1_19","authorSignatures":[{"inst":"https://dblp.org/inst/11/691","instLabel":"Chinese Academy of Sciences (CAS)"},{"inst":"https://dblp.org/inst/12/312","instLabel":"Institute of Automation (CASIA)"}],"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/icpr/DuYWHW24","documentUrl":"https://doi.org/10.1007/978-3-031-78113-1_19"},{"key":"conf/itsc/LiZLLW25","title":"Dynamic Gesture-Guided Pedestrian Intention Prediction via Dual-Stream Information Fusion.","year":2025,"yearOfEvent":2025,"venue":"ITSC","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/ITSC60802.2025.11423687"],"source":"https://dblp.org/rec/conf/itsc/LiZLLW25","documentPage":"https://doi.org/10.1109/ITSC60802.2025.11423687","type":"Inproceedings","doi":"https://doi.org/10.1109/ITSC60802.2025.11423687","authorSignatures":[{"inst":"https://dblp.org/inst/11/691","instLabel":"Chinese Academy of Sciences (CAS)"},{"inst":"https://dblp.org/inst/12/312","instLabel":"Institute of Automation (CASIA)"},{"inst":"https://dblp.org/inst/5/099","instLabel":"University of the Chinese Academy of Sciences (UCAS)"}],"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/itsc/LiZLLW25","documentUrl":"https://doi.org/10.1109/ITSC60802.2025.11423687"},{"key":"conf/mm/00040YW0000025","title":"Debiasing Multimodal Large Language Models via Penalization of Language Priors.","year":2025,"yearOfEvent":2025,"venue":"ACM Multimedia","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1145/3746027.3755364"],"source":"https://dblp.org/rec/conf/mm/00040YW0000025","documentPage":"https://doi.org/10.1145/3746027.3755364","type":"Inproceedings","doi":"https://doi.org/10.1145/3746027.3755364","authorSignatures":[{"orcid":"https://orcid.org/0000-0001-5224-8647","inst":"https://dblp.org/inst/11/691","instLabel":"Chinese Academy of Sciences (CAS)"},{"orcid":"https://orcid.org/0000-0001-5224-8647","inst":"https://dblp.org/inst/12/312","instLabel":"Institute of Automation (CASIA)"}],"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/mm/00040YW0000025","documentUrl":"https://doi.org/10.1145/3746027.3755364"},{"key":"conf/mm/Wang0LWHLW025","title":"VicKAM: Visual Conceptual Knowledge Guided Action Map for Weakly Supervised Group Activity Recognition.","year":2025,"yearOfEvent":2025,"venue":"ACM Multimedia","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1145/3746027.3755496"],"source":"https://dblp.org/rec/conf/mm/Wang0LWHLW025","documentPage":"https://doi.org/10.1145/3746027.3755496","type":"Inproceedings","doi":"https://doi.org/10.1145/3746027.3755496","authorSignatures":[{"orcid":"https://orcid.org/0000-0001-5224-8647","inst":"https://dblp.org/inst/11/691","instLabel":"Chinese Academy of Sciences (CAS)"},{"orcid":"https://orcid.org/0000-0001-5224-8647","inst":"https://dblp.org/inst/12/312","instLabel":"Institute of Automation (CASIA)"}],"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/mm/Wang0LWHLW025","documentUrl":"https://doi.org/10.1145/3746027.3755496"},{"key":"conf/mm/WuZCHZZ0025","title":"AeroDuo: Aerial Duo for UAV-based Vision and Language Navigation.","year":2025,"yearOfEvent":2025,"venue":"ACM Multimedia","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1145/3746027.3754498"],"source":"https://dblp.org/rec/conf/mm/WuZCHZZ0025","documentPage":"https://doi.org/10.1145/3746027.3754498","type":"Inproceedings","doi":"https://doi.org/10.1145/3746027.3754498","authorSignatures":[{"orcid":"https://orcid.org/0000-0001-5224-8647","inst":"https://dblp.org/inst/11/691","instLabel":"Chinese Academy of Sciences (CAS)"},{"orcid":"https://orcid.org/0000-0001-5224-8647","inst":"https://dblp.org/inst/12/312","instLabel":"Institute of Automation (CASIA)"}],"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/mm/WuZCHZZ0025","documentUrl":"https://doi.org/10.1145/3746027.3754498"},{"key":"journals/ijautcomp/Wu0SC0025","title":"GraphFM: Graph Factorization Machines for Feature Interaction Modelling.","year":2025,"yearOfEvent":null,"venue":"Int. J. Autom. Comput.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1007/S11633-024-1505-5"],"source":"https://dblp.org/rec/journals/ijautcomp/Wu0SC0025","documentPage":"https://doi.org/10.1007/S11633-024-1505-5","type":"Article","doi":"https://doi.org/10.1007/S11633-024-1505-5","authorSignatures":[{"orcid":"https://orcid.org/0000-0001-5224-8647","inst":"https://dblp.org/inst/11/691","instLabel":"Chinese Academy of Sciences (CAS)"},{"orcid":"https://orcid.org/0000-0001-5224-8647","inst":"https://dblp.org/inst/12/312","instLabel":"Institute of Automation (CASIA)"}],"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/ijautcomp/Wu0SC0025","documentUrl":"https://doi.org/10.1007/S11633-024-1505-5"},{"key":"journals/ijcv/HuangHZWZW25","title":"CSFRNet: Integrating Clothing Status Awareness for Long-Term Person Re-identification.","year":2025,"yearOfEvent":null,"venue":"Int. J. Comput. Vis.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1007/S11263-024-02315-0"],"source":"https://dblp.org/rec/journals/ijcv/HuangHZWZW25","documentPage":"https://doi.org/10.1007/S11263-024-02315-0","type":"Article","doi":"https://doi.org/10.1007/S11263-024-02315-0","authorSignatures":[{"inst":"https://dblp.org/inst/11/691","instLabel":"Chinese Academy of Sciences (CAS)"},{"inst":"https://dblp.org/inst/12/312","instLabel":"Institute of Automation (CASIA)"},{"inst":"https://dblp.org/inst/5/099","instLabel":"University of the Chinese Academy of Sciences (UCAS)"}],"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/ijcv/HuangHZWZW25","documentUrl":"https://doi.org/10.1007/S11263-024-02315-0"},{"key":"journals/pami/AnWWWHHW25","title":"ETPNav: Evolving Topological Planning for Vision-Language Navigation in Continuous Environments.","year":2025,"yearOfEvent":null,"venue":"IEEE Trans. Pattern Anal. Mach. Intell.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1109/TPAMI.2024.3386695"],"source":"https://dblp.org/rec/journals/pami/AnWWWHHW25","documentPage":"https://doi.org/10.1109/TPAMI.2024.3386695","type":"Article","doi":"https://doi.org/10.1109/TPAMI.2024.3386695","authorSignatures":[{"orcid":"https://orcid.org/0000-0001-5224-8647","inst":"https://dblp.org/inst/12/312","instLabel":"Institute of Automation (CASIA)"},{"orcid":"https://orcid.org/0000-0001-5224-8647","inst":"https://dblp.org/inst/5/099","instLabel":"University of the Chinese Academy of Sciences (UCAS)"}],"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/pami/AnWWWHHW25","documentUrl":"https://doi.org/10.1109/TPAMI.2024.3386695"},{"key":"journals/pami/ChenAHXSLRW25","title":"Constraint-Aware Zero-Shot Vision-Language Navigation in Continuous Environments.","year":2025,"yearOfEvent":null,"venue":"IEEE Trans. Pattern Anal. Mach. Intell.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1109/TPAMI.2025.3594204"],"source":"https://dblp.org/rec/journals/pami/ChenAHXSLRW25","documentPage":"https://doi.org/10.1109/TPAMI.2025.3594204","type":"Article","doi":"https://doi.org/10.1109/TPAMI.2025.3594204","authorSignatures":[{"orcid":"https://orcid.org/0000-0001-5224-8647","inst":"https://dblp.org/inst/11/691","instLabel":"Chinese Academy of Sciences (CAS)"},{"orcid":"https://orcid.org/0000-0001-5224-8647","inst":"https://dblp.org/inst/12/312","instLabel":"Institute of Automation (CASIA)"},{"orcid":"https://orcid.org/0000-0001-5224-8647","inst":"https://dblp.org/inst/5/099","instLabel":"University of the Chinese Academy of Sciences (UCAS)"}],"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/pami/ChenAHXSLRW25","documentUrl":"https://doi.org/10.1109/TPAMI.2025.3594204"},{"key":"journals/pami/HuangWZHCW25","title":"Unpaired Image-Text Matching via Multimodal Aligned Conceptual Knowledge.","year":2025,"yearOfEvent":null,"venue":"IEEE Trans. Pattern Anal. Mach. Intell.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1109/TPAMI.2024.3432552"],"source":"https://dblp.org/rec/journals/pami/HuangWZHCW25","documentPage":"https://doi.org/10.1109/TPAMI.2024.3432552","type":"Article","doi":"https://doi.org/10.1109/TPAMI.2024.3432552","authorSignatures":[{"orcid":"https://orcid.org/0000-0001-5224-8647","inst":"https://dblp.org/inst/11/691","instLabel":"Chinese Academy of Sciences (CAS)"},{"orcid":"https://orcid.org/0000-0001-5224-8647","inst":"https://dblp.org/inst/12/312","instLabel":"Institute of Automation (CASIA)"},{"orcid":"https://orcid.org/0000-0001-5224-8647","inst":"https://dblp.org/inst/5/099","instLabel":"University of the Chinese Academy of Sciences (UCAS)"}],"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/pami/HuangWZHCW25","documentUrl":"https://doi.org/10.1109/TPAMI.2024.3432552"},{"key":"journals/ral/LiWHCWK25","title":"GR-MG: Leveraging Partially-Annotated Data via Multi-Modal Goal-Conditioned Policy.","year":2025,"yearOfEvent":null,"venue":"IEEE Robotics Autom. Lett.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1109/LRA.2025.3526436"],"source":"https://dblp.org/rec/journals/ral/LiWHCWK25","documentPage":"https://doi.org/10.1109/LRA.2025.3526436","type":"Article","doi":"https://doi.org/10.1109/LRA.2025.3526436","authorSignatures":[{"orcid":"https://orcid.org/0000-0001-5224-8647","inst":"https://dblp.org/inst/11/691","instLabel":"Chinese Academy of Sciences (CAS)"},{"orcid":"https://orcid.org/0000-0001-5224-8647","inst":"https://dblp.org/inst/12/312","instLabel":"Institute of Automation (CASIA)"},{"orcid":"https://orcid.org/0000-0001-5224-8647","inst":"https://dblp.org/inst/5/099","instLabel":"University of the Chinese Academy of Sciences (UCAS)"}],"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/ral/LiWHCWK25","documentUrl":"https://doi.org/10.1109/LRA.2025.3526436"},{"key":"journals/tbbis/Shen00H025","title":"A Comprehensive Survey on Deep Gait Recognition: Algorithms, Datasets, and Challenges.","year":2025,"yearOfEvent":null,"venue":"IEEE Trans. Biom. Behav. Identity Sci.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1109/TBIOM.2024.3486345"],"source":"https://dblp.org/rec/journals/tbbis/Shen00H025","documentPage":"https://doi.org/10.1109/TBIOM.2024.3486345","type":"Article","doi":"https://doi.org/10.1109/TBIOM.2024.3486345","authorSignatures":[{"orcid":"https://orcid.org/0000-0001-5224-8647","inst":"https://dblp.org/inst/11/691","instLabel":"Chinese Academy of Sciences (CAS)"},{"orcid":"https://orcid.org/0000-0001-5224-8647","inst":"https://dblp.org/inst/12/312","instLabel":"Institute of Automation (CASIA)"}],"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/tbbis/Shen00H025","documentUrl":"https://doi.org/10.1109/TBIOM.2024.3486345"},{"key":"journals/tcsv/LiuZZLFW25","title":"Few-Shot Class-Incremental Learning via Asymmetric Supervised Contrastive Learning.","year":2025,"yearOfEvent":null,"venue":"IEEE Trans. Circuits Syst. Video Technol.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1109/TCSVT.2025.3562603"],"source":"https://dblp.org/rec/journals/tcsv/LiuZZLFW25","documentPage":"https://doi.org/10.1109/TCSVT.2025.3562603","type":"Article","doi":"https://doi.org/10.1109/TCSVT.2025.3562603","authorSignatures":[{"orcid":"https://orcid.org/0000-0001-5224-8647","inst":"https://dblp.org/inst/11/691","instLabel":"Chinese Academy of Sciences (CAS)"},{"orcid":"https://orcid.org/0000-0001-5224-8647","inst":"https://dblp.org/inst/12/068","instLabel":"Shandong Institute of Automation"},{"orcid":"https://orcid.org/0000-0001-5224-8647","inst":"https://dblp.org/inst/12/172","instLabel":"Institute of Computing Technology (ICT)"},{"orcid":"https://orcid.org/0000-0001-5224-8647","inst":"https://dblp.org/inst/12/312","instLabel":"Institute of Automation (CASIA)"}],"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/tcsv/LiuZZLFW25","documentUrl":"https://doi.org/10.1109/TCSVT.2025.3562603"},{"key":"journals/tcsv/WangHGHHZW25","title":"GaitC3I: Robust Cross-Covariate Gait Recognition via Causal Intervention.","year":2025,"yearOfEvent":null,"venue":"IEEE Trans. Circuits Syst. Video Technol.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1109/TCSVT.2025.3545210"],"source":"https://dblp.org/rec/journals/tcsv/WangHGHHZW25","documentPage":"https://doi.org/10.1109/TCSVT.2025.3545210","type":"Article","doi":"https://doi.org/10.1109/TCSVT.2025.3545210","authorSignatures":[{"orcid":"https://orcid.org/0000-0001-5224-8647","inst":"https://dblp.org/inst/11/691","instLabel":"Chinese Academy of Sciences (CAS)"},{"orcid":"https://orcid.org/0000-0001-5224-8647","inst":"https://dblp.org/inst/12/312","instLabel":"Institute of Automation (CASIA)"},{"orcid":"https://orcid.org/0000-0001-5224-8647","inst":"https://dblp.org/inst/2/628","instLabel":"Wuhan University (WHU)"}],"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/tcsv/WangHGHHZW25","documentUrl":"https://doi.org/10.1109/TCSVT.2025.3545210"},{"key":"journals/tifs/HouWLWWH25","title":"GaitAsset: In Defense of Regarding Gait as a Set.","year":2025,"yearOfEvent":null,"venue":"IEEE Trans. Inf. Forensics Secur.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1109/TIFS.2025.3630892"],"source":"https://dblp.org/rec/journals/tifs/HouWLWWH25","documentPage":"https://doi.org/10.1109/TIFS.2025.3630892","type":"Article","doi":"https://doi.org/10.1109/TIFS.2025.3630892","authorSignatures":[{"orcid":"https://orcid.org/0000-0001-5224-8647","inst":"https://dblp.org/inst/11/691","instLabel":"Chinese Academy of Sciences (CAS)"},{"orcid":"https://orcid.org/0000-0001-5224-8647","inst":"https://dblp.org/inst/12/068","instLabel":"Shandong Institute of Automation"},{"orcid":"https://orcid.org/0000-0001-5224-8647","inst":"https://dblp.org/inst/12/312","instLabel":"Institute of Automation (CASIA)"}],"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/tifs/HouWLWWH25","documentUrl":"https://doi.org/10.1109/TIFS.2025.3630892"},{"key":"journals/tip/ZhengWWWC25","title":"Motion Attention-Guided Relational Reasoning for Weakly Supervised Group Activity Recognition.","year":2025,"yearOfEvent":null,"venue":"IEEE Trans. Image Process.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1109/TIP.2025.3636094"],"source":"https://dblp.org/rec/journals/tip/ZhengWWWC25","documentPage":"https://doi.org/10.1109/TIP.2025.3636094","type":"Article","doi":"https://doi.org/10.1109/TIP.2025.3636094","authorSignatures":[{"orcid":"https://orcid.org/0000-0001-5224-8647","inst":"https://dblp.org/inst/11/691","instLabel":"Chinese Academy of Sciences (CAS)"},{"orcid":"https://orcid.org/0000-0001-5224-8647","inst":"https://dblp.org/inst/12/068","instLabel":"Shandong Institute of Automation"},{"orcid":"https://orcid.org/0000-0001-5224-8647","inst":"https://dblp.org/inst/12/312","instLabel":"Institute of Automation (CASIA)"}],"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/tip/ZhengWWWC25","documentUrl":"https://doi.org/10.1109/TIP.2025.3636094"},{"key":"journals/titb/FanYHWYJ25","title":"SliceMamba With Neural Architecture Search for Medical Image Segmentation.","year":2025,"yearOfEvent":null,"venue":"IEEE J. Biomed. Health Informatics","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1109/JBHI.2025.3564381"],"source":"https://dblp.org/rec/journals/titb/FanYHWYJ25","documentPage":"https://doi.org/10.1109/JBHI.2025.3564381","type":"Article","doi":"https://doi.org/10.1109/JBHI.2025.3564381","authorSignatures":[{"orcid":"https://orcid.org/0000-0001-5224-8647","inst":"https://dblp.org/inst/11/691","instLabel":"Chinese Academy of Sciences (CAS)"},{"orcid":"https://orcid.org/0000-0001-5224-8647","inst":"https://dblp.org/inst/12/312","instLabel":"Institute of Automation (CASIA)"}],"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/titb/FanYHWYJ25","documentUrl":"https://doi.org/10.1109/JBHI.2025.3564381"},{"key":"journals/tiv/ZhangCDW25","title":"Trajectory-Guided Driving Behavior Prediction for Autonomous Driving.","year":2025,"yearOfEvent":null,"venue":"IEEE Trans. Intell. Veh.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1109/TIV.2024.3486108"],"source":"https://dblp.org/rec/journals/tiv/ZhangCDW25","documentPage":"https://doi.org/10.1109/TIV.2024.3486108","type":"Article","doi":"https://doi.org/10.1109/TIV.2024.3486108","authorSignatures":[{"orcid":"https://orcid.org/0000-0001-5224-8647","inst":"https://dblp.org/inst/11/691","instLabel":"Chinese Academy of Sciences (CAS)"},{"orcid":"https://orcid.org/0000-0001-5224-8647","inst":"https://dblp.org/inst/12/312","instLabel":"Institute of Automation (CASIA)"},{"orcid":"https://orcid.org/0000-0001-5224-8647","inst":"https://dblp.org/inst/5/099","instLabel":"University of the Chinese Academy of Sciences (UCAS)"}],"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/tiv/ZhangCDW25","documentUrl":"https://doi.org/10.1109/TIV.2024.3486108"},{"key":"journals/tkde/HuSLWW25","title":"Uncertainty Calibration for Counterfactual Propensity Estimation in Recommendation.","year":2025,"yearOfEvent":null,"venue":"IEEE Trans. Knowl. Data Eng.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1109/TKDE.2025.3552658"],"source":"https://dblp.org/rec/journals/tkde/HuSLWW25","documentPage":"https://doi.org/10.1109/TKDE.2025.3552658","type":"Article","doi":"https://doi.org/10.1109/TKDE.2025.3552658","authorSignatures":[{"orcid":"https://orcid.org/0000-0001-5224-8647","inst":"https://dblp.org/inst/11/691","instLabel":"Chinese Academy of Sciences (CAS)"},{"orcid":"https://orcid.org/0000-0001-5224-8647","inst":"https://dblp.org/inst/12/068","instLabel":"Shandong Institute of Automation"},{"orcid":"https://orcid.org/0000-0001-5224-8647","inst":"https://dblp.org/inst/12/312","instLabel":"Institute of Automation (CASIA)"}],"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/tkde/HuSLWW25","documentUrl":"https://doi.org/10.1109/TKDE.2025.3552658"},{"key":"journals/tkde/ZhangXZZWB25","title":"TimeRAF: Retrieval-Augmented Foundation Model for Zero-Shot Time Series Forecasting.","year":2025,"yearOfEvent":null,"venue":"IEEE Trans. Knowl. Data Eng.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1109/TKDE.2025.3579137"],"source":"https://dblp.org/rec/journals/tkde/ZhangXZZWB25","documentPage":"https://doi.org/10.1109/TKDE.2025.3579137","type":"Article","doi":"https://doi.org/10.1109/TKDE.2025.3579137","authorSignatures":[{"orcid":"https://orcid.org/0000-0001-5224-8647","inst":"https://dblp.org/inst/11/691","instLabel":"Chinese Academy of Sciences (CAS)"},{"orcid":"https://orcid.org/0000-0001-5224-8647","inst":"https://dblp.org/inst/12/312","instLabel":"Institute of Automation (CASIA)"},{"orcid":"https://orcid.org/0000-0001-5224-8647","inst":"https://dblp.org/inst/5/099","instLabel":"University of the Chinese Academy of Sciences (UCAS)"}],"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/tkde/ZhangXZZWB25","documentUrl":"https://doi.org/10.1109/TKDE.2025.3579137"},{"key":"journals/tmm/LiJZLMW25","title":"Multi-View Knowledge Guided Semantic Prototype Learning for Generalized Zero-Shot Action Recognition.","year":2025,"yearOfEvent":null,"venue":"IEEE Trans. Multim.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1109/TMM.2025.3618570"],"source":"https://dblp.org/rec/journals/tmm/LiJZLMW25","documentPage":"https://doi.org/10.1109/TMM.2025.3618570","type":"Article","doi":"https://doi.org/10.1109/TMM.2025.3618570","authorSignatures":[{"orcid":"https://orcid.org/0000-0001-5224-8647","inst":"https://dblp.org/inst/11/691","instLabel":"Chinese Academy of Sciences (CAS)"},{"orcid":"https://orcid.org/0000-0001-5224-8647","inst":"https://dblp.org/inst/12/312","instLabel":"Institute of Automation (CASIA)"},{"orcid":"https://orcid.org/0000-0001-5224-8647","inst":"https://dblp.org/inst/5/099","instLabel":"University of the Chinese Academy of Sciences (UCAS)"}],"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/tmm/LiJZLMW25","documentUrl":"https://doi.org/10.1109/TMM.2025.3618570"},{"key":"journals/tnn/LuQLTW25","title":"Duality-Gated Mutual Condition Network for RGBT Tracking.","year":2025,"yearOfEvent":null,"venue":"IEEE Trans. Neural Networks Learn. Syst.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1109/TNNLS.2022.3157594"],"source":"https://dblp.org/rec/journals/tnn/LuQLTW25","documentPage":"https://doi.org/10.1109/TNNLS.2022.3157594","type":"Article","doi":"https://doi.org/10.1109/TNNLS.2022.3157594","authorSignatures":[{"orcid":"https://orcid.org/0000-0001-5224-8647","inst":"https://dblp.org/inst/11/691","instLabel":"Chinese Academy of Sciences (CAS)"},{"orcid":"https://orcid.org/0000-0001-5224-8647","inst":"https://dblp.org/inst/12/312","instLabel":"Institute of Automation (CASIA)"}],"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/tnn/LuQLTW25","documentUrl":"https://doi.org/10.1109/TNNLS.2022.3157594"}],"preprints":[],"excludedFormal":[{"key":"journals/ijautcomp/WuLSCZW25","title":"Correction to: GraphFM: Graph Factorization Machines for Feature Interaction Modelling.","year":2025,"yearOfEvent":null,"venue":"Mach. Intell. Res.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1007/S11633-025-1548-2"],"source":"https://dblp.org/rec/journals/ijautcomp/WuLSCZW25","documentPage":"https://doi.org/10.1007/S11633-025-1548-2","type":"Article","doi":"https://doi.org/10.1007/S11633-025-1548-2","authorSignatures":[{"inst":"https://dblp.org/inst/11/691","instLabel":"Chinese Academy of Sciences (CAS)"},{"inst":"https://dblp.org/inst/12/312","instLabel":"Institute of Automation (CASIA)"}],"exclusionReason":"Explicit editorial, correction, erratum or preface; excluded from research-paper count.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/ijautcomp/WuLSCZW25","documentUrl":"https://doi.org/10.1007/S11633-025-1548-2"}],"excludedOther":[],"excludedHomonyms":[{"key":"conf/www/0025XYDK00YX025","title":"Learning against Non-credible Second-Price Auctions.","year":2025,"yearOfEvent":2025,"venue":"WWW","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1145/3696410.3714847"],"source":"https://dblp.org/rec/conf/www/0025XYDK00YX025","documentPage":"https://doi.org/10.1145/3696410.3714847","type":"Inproceedings","doi":"https://doi.org/10.1145/3696410.3714847","authorSignatures":[{"orcid":"https://orcid.org/0000-0001-5353-7803","inst":"https://dblp.org/inst/12/039","instLabel":"Alibaba Group"}],"exclusionReason":"Crossref identifies Alibaba Liang Wang, ORCID 0000-0001-5353-7803, not CASIA Wang Liang.","exclusionSource":"https://api.crossref.org/works/10.1145/3696410.3714847","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/www/0025XYDK00YX025","documentUrl":"https://doi.org/10.1145/3696410.3714847"},{"key":"conf/www/ChenW0S25","title":"DAGPrompT: Pushing the Limits of Graph Prompting with a Distribution-aware Graph Prompt Tuning Approach.","year":2025,"yearOfEvent":2025,"venue":"WWW","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1145/3696410.3714917"],"source":"https://dblp.org/rec/conf/www/ChenW0S25","documentPage":"https://doi.org/10.1145/3696410.3714917","type":"Inproceedings","doi":"https://doi.org/10.1145/3696410.3714917","authorSignatures":[{"orcid":"https://orcid.org/0000-0001-5353-7803","inst":"https://dblp.org/inst/12/039","instLabel":"Alibaba Group"}],"exclusionReason":"Crossref identifies Alibaba Liang Wang, ORCID 0000-0001-5353-7803, not CASIA Wang Liang.","exclusionSource":"https://api.crossref.org/works/10.1145/3696410.3714917","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/www/ChenW0S25","documentUrl":"https://doi.org/10.1145/3696410.3714917"},{"key":"journals/eswa/GaoZHSWF25","title":"A structure-based disentangled network with contrastive regularization for sign language recognition.","year":2025,"yearOfEvent":null,"venue":"Expert Syst. Appl.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1016/J.ESWA.2025.126623"],"source":"https://dblp.org/rec/journals/eswa/GaoZHSWF25","documentPage":"https://doi.org/10.1016/J.ESWA.2025.126623","type":"Article","doi":"https://doi.org/10.1016/J.ESWA.2025.126623","authorSignatures":[{"inst":"https://dblp.org/inst/2/152","instLabel":"Tianjin University (TJU)"}],"exclusionReason":"Crossref author family name is Wan (not Wang); DBLP signature identifies Tianjin University.","exclusionSource":"https://api.crossref.org/works/10.1016/J.ESWA.2025.126623","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/eswa/GaoZHSWF25","documentUrl":"https://doi.org/10.1016/J.ESWA.2025.126623"},{"key":"journals/pr/GaoWHHLSSF25","title":"A large-scale combinatorial benchmark for sign language recognition.","year":2025,"yearOfEvent":null,"venue":"Pattern Recognit.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1016/J.PATCOG.2024.111246"],"source":"https://dblp.org/rec/journals/pr/GaoWHHLSSF25","documentPage":"https://doi.org/10.1016/J.PATCOG.2024.111246","type":"Article","doi":"https://doi.org/10.1016/J.PATCOG.2024.111246","authorSignatures":[{"inst":"https://dblp.org/inst/2/152","instLabel":"Tianjin University (TJU)"}],"exclusionReason":"Crossref author family name is Wan (not Wang); DBLP signature identifies Tianjin University.","exclusionSource":"https://api.crossref.org/works/10.1016/J.PATCOG.2024.111246","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/pr/GaoWHHLSSF25","documentUrl":"https://doi.org/10.1016/J.PATCOG.2024.111246"},{"key":"journals/tip/HuangTJZWG25","title":"C-NeRF: Representing Scene Changes as Directional Consistency Difference-Based NeRF.","year":2025,"yearOfEvent":null,"venue":"IEEE Trans. Image Process.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1109/TIP.2025.3622374"],"source":"https://dblp.org/rec/journals/tip/HuangTJZWG25","documentPage":"https://doi.org/10.1109/TIP.2025.3622374","type":"Article","doi":"https://doi.org/10.1109/TIP.2025.3622374","authorSignatures":[{"orcid":"https://orcid.org/0000-0001-5501-9575","inst":"https://dblp.org/inst/2/152","instLabel":"Tianjin University (TJU)"}],"exclusionReason":"Crossref author family name is Wan (not Wang), Tianjin University, ORCID 0000-0001-5501-9575.","exclusionSource":"https://api.crossref.org/works/10.1109/TIP.2025.3622374","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/tip/HuangTJZWG25","documentUrl":"https://doi.org/10.1109/TIP.2025.3622374"}],"unassignedCandidates":[{"key":"conf/aaai/SuACYNLHW25","title":"Learning Fine-Grained Alignment for Aerial Vision-Dialog Navigation.","year":2025,"yearOfEvent":2025,"venue":"AAAI","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1609/AAAI.V39I7.32758"],"source":"https://dblp.org/rec/conf/aaai/SuACYNLHW25","documentPage":"https://doi.org/10.1609/AAAI.V39I7.32758","type":"Inproceedings","doi":"https://doi.org/10.1609/AAAI.V39I7.32758","authorSignatures":[{}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/aaai/SuACYNLHW25","documentUrl":"https://doi.org/10.1609/AAAI.V39I7.32758"},{"key":"conf/acl/HuXYWX0YTZZLXWX25","title":"OS Agents: A Survey on MLLM-based Agents for Computer, Phone and Browser Use.","year":2025,"yearOfEvent":2025,"venue":"ACL (1)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.18653/V1/2025.ACL-LONG.369"],"source":"https://dblp.org/rec/conf/acl/HuXYWX0YTZZLXWX25","documentPage":"https://doi.org/10.18653/V1/2025.ACL-LONG.369","type":"Inproceedings","doi":"https://doi.org/10.18653/V1/2025.ACL-LONG.369","authorSignatures":[{}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/acl/HuXYWX0YTZZLXWX25","documentUrl":"https://doi.org/10.18653/V1/2025.ACL-LONG.369"},{"key":"conf/acl/SunXCLWCSWWW25","title":"Divide-Then-Align: Honest Alignment based on the Knowledge Boundary of RAG.","year":2025,"yearOfEvent":2025,"venue":"ACL (1)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.18653/V1/2025.ACL-LONG.561"],"source":"https://dblp.org/rec/conf/acl/SunXCLWCSWWW25","documentPage":"https://doi.org/10.18653/V1/2025.ACL-LONG.561","type":"Inproceedings","doi":"https://doi.org/10.18653/V1/2025.ACL-LONG.561","authorSignatures":[{}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/acl/SunXCLWCSWWW25","documentUrl":"https://doi.org/10.18653/V1/2025.ACL-LONG.561"},{"key":"conf/acl/Zhang0WLWWC25","title":"Personalized Text Generation with Contrastive Activation Steering.","year":2025,"yearOfEvent":2025,"venue":"ACL (1)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.18653/V1/2025.ACL-LONG.353"],"source":"https://dblp.org/rec/conf/acl/Zhang0WLWWC25","documentPage":"https://doi.org/10.18653/V1/2025.ACL-LONG.353","type":"Inproceedings","doi":"https://doi.org/10.18653/V1/2025.ACL-LONG.353","authorSignatures":[{}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/acl/Zhang0WLWWC25","documentUrl":"https://doi.org/10.18653/V1/2025.ACL-LONG.353"},{"key":"conf/acl/ZhangLTWW25","title":"SINCon: Mitigate LLM-Generated Malicious Message Injection Attack for Rumor Detection.","year":2025,"yearOfEvent":2025,"venue":"ACL (1)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.18653/V1/2025.ACL-LONG.617"],"source":"https://dblp.org/rec/conf/acl/ZhangLTWW25","documentPage":"https://doi.org/10.18653/V1/2025.ACL-LONG.617","type":"Inproceedings","doi":"https://doi.org/10.18653/V1/2025.ACL-LONG.617","authorSignatures":[{}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/acl/ZhangLTWW25","documentUrl":"https://doi.org/10.18653/V1/2025.ACL-LONG.617"},{"key":"conf/eccv/ChenQWYLHW24","title":"PromptIQA: Boosting the Performance and Generalization for No-Reference Image Quality Assessment via Prompts.","year":2025,"yearOfEvent":2024,"venue":"ECCV (1)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1007/978-3-031-73232-4_14"],"source":"https://dblp.org/rec/conf/eccv/ChenQWYLHW24","documentPage":"https://doi.org/10.1007/978-3-031-73232-4_14","type":"Inproceedings","doi":"https://doi.org/10.1007/978-3-031-73232-4_14","authorSignatures":[{}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/eccv/ChenQWYLHW24","documentUrl":"https://doi.org/10.1007/978-3-031-73232-4_14"},{"key":"conf/emnlp/LiuCDSWWW25","title":"Attention-guided Self-reflection for Zero-shot Hallucination Detection in Large Language Models.","year":2025,"yearOfEvent":2025,"venue":"EMNLP","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.18653/V1/2025.EMNLP-MAIN.1063"],"source":"https://dblp.org/rec/conf/emnlp/LiuCDSWWW25","documentPage":"https://doi.org/10.18653/V1/2025.EMNLP-MAIN.1063","type":"Inproceedings","doi":"https://doi.org/10.18653/V1/2025.EMNLP-MAIN.1063","authorSignatures":[{}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/emnlp/LiuCDSWWW25","documentUrl":"https://doi.org/10.18653/V1/2025.EMNLP-MAIN.1063"},{"key":"conf/emnlp/WuDLXHSLWWT25","title":"SHARP: Steering Hallucination in LVLMs via Representation Engineering.","year":2025,"yearOfEvent":2025,"venue":"EMNLP","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.18653/V1/2025.EMNLP-MAIN.725"],"source":"https://dblp.org/rec/conf/emnlp/WuDLXHSLWWT25","documentPage":"https://doi.org/10.18653/V1/2025.EMNLP-MAIN.725","type":"Inproceedings","doi":"https://doi.org/10.18653/V1/2025.EMNLP-MAIN.725","authorSignatures":[{}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/emnlp/WuDLXHSLWWT25","documentUrl":"https://doi.org/10.18653/V1/2025.EMNLP-MAIN.725"},{"key":"conf/emnlp/YeLGYSFZLW25","title":"GenPilot: A Multi-Agent System for Test-Time Prompt Optimization in Image Generation.","year":2025,"yearOfEvent":2025,"venue":"EMNLP (Findings)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.18653/V1/2025.FINDINGS-EMNLP.49"],"source":"https://dblp.org/rec/conf/emnlp/YeLGYSFZLW25","documentPage":"https://doi.org/10.18653/V1/2025.FINDINGS-EMNLP.49","type":"Inproceedings","doi":"https://doi.org/10.18653/V1/2025.FINDINGS-EMNLP.49","authorSignatures":[{}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/emnlp/YeLGYSFZLW25","documentUrl":"https://doi.org/10.18653/V1/2025.FINDINGS-EMNLP.49"},{"key":"conf/emnlp/ZhangFLYWRCW25","title":"KELE: Residual Knowledge Erasure for Enhanced Multi-hop Reasoning in Knowledge Editing.","year":2025,"yearOfEvent":2025,"venue":"EMNLP (Findings)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.18653/V1/2025.FINDINGS-EMNLP.1334"],"source":"https://dblp.org/rec/conf/emnlp/ZhangFLYWRCW25","documentPage":"https://doi.org/10.18653/V1/2025.FINDINGS-EMNLP.1334","type":"Inproceedings","doi":"https://doi.org/10.18653/V1/2025.FINDINGS-EMNLP.1334","authorSignatures":[{}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/emnlp/ZhangFLYWRCW25","documentUrl":"https://doi.org/10.18653/V1/2025.FINDINGS-EMNLP.1334"},{"key":"conf/emnlp/ZhongLXLLWZWT25","title":"REACT: Representation Extraction And Controllable Tuning to Overcome Overfitting in LLM Knowledge Editing.","year":2025,"yearOfEvent":2025,"venue":"EMNLP","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.18653/V1/2025.EMNLP-MAIN.860"],"source":"https://dblp.org/rec/conf/emnlp/ZhongLXLLWZWT25","documentPage":"https://doi.org/10.18653/V1/2025.EMNLP-MAIN.860","type":"Inproceedings","doi":"https://doi.org/10.18653/V1/2025.EMNLP-MAIN.860","authorSignatures":[{}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/emnlp/ZhongLXLLWZWT25","documentUrl":"https://doi.org/10.18653/V1/2025.EMNLP-MAIN.860"},{"key":"conf/iccv/XiSWYZWWC25","title":"Player-Centric Multimodal Prompt Generation for Large Language Model Based Identity-Aware Basketball Video Captioning.","year":2025,"yearOfEvent":2025,"venue":"ICCV","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/ICCV51701.2025.02255"],"source":"https://dblp.org/rec/conf/iccv/XiSWYZWWC25","documentPage":"https://doi.org/10.1109/ICCV51701.2025.02255","type":"Inproceedings","doi":"https://doi.org/10.1109/ICCV51701.2025.02255","authorSignatures":[{"inst":"https://dblp.org/inst/11/691","instLabel":"Chinese Academy of Sciences (CAS)"}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/XiSWYZWWC25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.02255"},{"key":"conf/iclr/0004ZTFZWLWW00025","title":"MME-RealWorld: Could Your Multimodal LLM Challenge High-Resolution Real-World Scenarios that are Difficult for Humans?","year":2025,"yearOfEvent":2025,"venue":"ICLR","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/iclr/0004ZTFZWLWW00025","documentPage":"https://openreview.net/forum?id=k5VHHgsRbi","type":"Inproceedings","doi":null,"authorSignatures":[{}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iclr/0004ZTFZWLWW00025","documentUrl":"https://openreview.net/forum?id=k5VHHgsRbi"},{"key":"conf/iclr/0056L0ZLW025","title":"MolSpectra: Pre-training 3D Molecular Representation with Multi-modal Energy Spectra.","year":2025,"yearOfEvent":2025,"venue":"ICLR","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/iclr/0056L0ZLW025","documentPage":"https://openreview.net/forum?id=xJDxVDG3x2","type":"Inproceedings","doi":null,"authorSignatures":[{}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iclr/0056L0ZLW025","documentUrl":"https://openreview.net/forum?id=xJDxVDG3x2"},{"key":"conf/iclr/ZhouXLHGWLZWM25","title":"Integrating Protein Dynamics into Structure-Based Drug Design via Full-Atom Stochastic Flows.","year":2025,"yearOfEvent":2025,"venue":"ICLR","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/iclr/ZhouXLHGWLZWM25","documentPage":"https://openreview.net/forum?id=9qS3HzSDNv","type":"Inproceedings","doi":null,"authorSignatures":[{}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iclr/ZhouXLHGWLZWM25","documentUrl":"https://openreview.net/forum?id=9qS3HzSDNv"},{"key":"conf/icml/0004Y0FLZX0ZW0H25","title":"MM-RLHF: The Next Step Forward in Multimodal LLM Alignment.","year":2025,"yearOfEvent":2025,"venue":"ICML","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/icml/0004Y0FLZX0ZW0H25","documentPage":"https://proceedings.mlr.press/v267/zhang25cs.html","type":"Inproceedings","doi":null,"authorSignatures":[{}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/icml/0004Y0FLZX0ZW0H25","documentUrl":"https://proceedings.mlr.press/v267/zhang25cs.html"},{"key":"conf/nips/DongZSW25","title":"AuroRA: Breaking Low-Rank Bottleneck of LoRA with Nonlinear Mapping.","year":2025,"yearOfEvent":2025,"venue":"NeurIPS","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/nips/DongZSW25","documentPage":"http://papers.nips.cc/paper_files/paper/2025/hash/34aae5b7991a4fb4fe3081ca4f94549c-Abstract-Conference.html","type":"Inproceedings","doi":null,"authorSignatures":[{}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/nips/DongZSW25","documentUrl":"http://papers.nips.cc/paper_files/paper/2025/hash/34aae5b7991a4fb4fe3081ca4f94549c-Abstract-Conference.html"},{"key":"conf/nips/GaoLLLGYXWSLS25","title":"GOOD: Training-Free Guided Diffusion Sampling for Out-of-Distribution Detection.","year":2025,"yearOfEvent":2025,"venue":"NeurIPS","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/nips/GaoLLLGYXWSLS25","documentPage":"http://papers.nips.cc/paper_files/paper/2025/hash/123fd8a56501194823c8e0dca00733df-Abstract-Conference.html","type":"Inproceedings","doi":null,"authorSignatures":[{}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/nips/GaoLLLGYXWSLS25","documentUrl":"http://papers.nips.cc/paper_files/paper/2025/hash/123fd8a56501194823c8e0dca00733df-Abstract-Conference.html"},{"key":"conf/nips/LiCWMWHWKT25","title":"BridgeVLA: Input-Output Alignment for Efficient 3D Manipulation Learning with Vision-Language Models.","year":2025,"yearOfEvent":2025,"venue":"NeurIPS","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/nips/LiCWMWHWKT25","documentPage":"http://papers.nips.cc/paper_files/paper/2025/hash/5c1a8aa04c1a2cf5013f28831870dafa-Abstract-Conference.html","type":"Inproceedings","doi":null,"authorSignatures":[{}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/nips/LiCWMWHWKT25","documentUrl":"http://papers.nips.cc/paper_files/paper/2025/hash/5c1a8aa04c1a2cf5013f28831870dafa-Abstract-Conference.html"},{"key":"conf/nips/LiuLNZHW25","title":"DAA: Amplifying Unknown Discrepancy for Test-Time Discovery.","year":2025,"yearOfEvent":2025,"venue":"NeurIPS","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/nips/LiuLNZHW25","documentPage":"http://papers.nips.cc/paper_files/paper/2025/hash/5cdf0bed49f637448eb8d18f40e14de0-Abstract-Conference.html","type":"Inproceedings","doi":null,"authorSignatures":[{}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/nips/LiuLNZHW25","documentUrl":"http://papers.nips.cc/paper_files/paper/2025/hash/5cdf0bed49f637448eb8d18f40e14de0-Abstract-Conference.html"},{"key":"conf/nips/ShiWXZZZLFWLZCZ25","title":"MME-VideoOCR: Evaluating OCR-Based Capabilities of Multimodal LLMs in Video Scenarios.","year":2025,"yearOfEvent":2025,"venue":"NeurIPS","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/nips/ShiWXZZZLFWLZCZ25","documentPage":"http://papers.nips.cc/paper_files/paper/2025/hash/779efd29bc0236b07df1da5a548d0bba-Abstract-Datasets_and_Benchmarks_Track.html","type":"Inproceedings","doi":null,"authorSignatures":[{}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/nips/ShiWXZZZLFWLZCZ25","documentUrl":"http://papers.nips.cc/paper_files/paper/2025/hash/779efd29bc0236b07df1da5a548d0bba-Abstract-Datasets_and_Benchmarks_Track.html"},{"key":"conf/nips/WuGFLWWWT25","title":"Reinforcing Spatial Reasoning in Vision-Language Models with Interwoven Thinking and Visual Drawing.","year":2025,"yearOfEvent":2025,"venue":"NeurIPS","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/nips/WuGFLWWWT25","documentPage":"http://papers.nips.cc/paper_files/paper/2025/hash/d2f2ca2c305e1a9c29bf00a676f0a500-Abstract-Conference.html","type":"Inproceedings","doi":null,"authorSignatures":[{}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/nips/WuGFLWWWT25","documentUrl":"http://papers.nips.cc/paper_files/paper/2025/hash/d2f2ca2c305e1a9c29bf00a676f0a500-Abstract-Conference.html"},{"key":"conf/nips/ZhangSLWFH25","title":"QBasicVSR: Temporal Awareness Adaptation Quantization for Video Super-Resolution.","year":2025,"yearOfEvent":2025,"venue":"NeurIPS","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/nips/ZhangSLWFH25","documentPage":"http://papers.nips.cc/paper_files/paper/2025/hash/c17f3035898a7044194fe45c5df6c6e8-Abstract-Conference.html","type":"Inproceedings","doi":null,"authorSignatures":[{}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/nips/ZhangSLWFH25","documentUrl":"http://papers.nips.cc/paper_files/paper/2025/hash/c17f3035898a7044194fe45c5df6c6e8-Abstract-Conference.html"},{"key":"journals/corr/abs-2501-09997","title":"Attention-guided Self-reflection for Zero-shot Hallucination Detection in Large Language Models.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2501.09997"],"source":"https://dblp.org/rec/journals/corr/abs-2501-09997","documentPage":"https://doi.org/10.48550/ARXIV.2501.09997","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2501.09997","authorSignatures":[{}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2501-09997","documentUrl":"https://doi.org/10.48550/ARXIV.2501.09997"},{"key":"journals/corr/abs-2501-15142","title":"DAGPrompT: Pushing the Limits of Graph Prompting with a Distribution-aware Graph Prompt Tuning Approach.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2501.15142"],"source":"https://dblp.org/rec/journals/corr/abs-2501-15142","documentPage":"https://doi.org/10.48550/ARXIV.2501.15142","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2501.15142","authorSignatures":[{}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2501-15142","documentUrl":"https://doi.org/10.48550/ARXIV.2501.15142"},{"key":"journals/corr/abs-2502-02998","title":"Conformal Uncertainty Indicator for Continual Test-Time Adaptation.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2502.02998"],"source":"https://dblp.org/rec/journals/corr/abs-2502-02998","documentPage":"https://doi.org/10.48550/ARXIV.2502.02998","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2502.02998","authorSignatures":[{}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2502-02998","documentUrl":"https://doi.org/10.48550/ARXIV.2502.02998"},{"key":"journals/corr/abs-2502-09511","title":"Diffusion Models for Molecules: A Survey of Methods and Tasks.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2502.09511"],"source":"https://dblp.org/rec/journals/corr/abs-2502-09511","documentPage":"https://doi.org/10.48550/ARXIV.2502.09511","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2502.09511","authorSignatures":[{}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2502-09511","documentUrl":"https://doi.org/10.48550/ARXIV.2502.09511"},{"key":"journals/corr/abs-2502-09967","title":"VicKAM: Visual Conceptual Knowledge Guided Action Map for Weakly Supervised Group Activity Recognition.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2502.09967"],"source":"https://dblp.org/rec/journals/corr/abs-2502-09967","documentPage":"https://doi.org/10.48550/ARXIV.2502.09967","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2502.09967","authorSignatures":[{}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2502-09967","documentUrl":"https://doi.org/10.48550/ARXIV.2502.09967"},{"key":"journals/corr/abs-2502-10391","title":"MM-RLHF: The Next Step Forward in Multimodal LLM Alignment.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2502.10391"],"source":"https://dblp.org/rec/journals/corr/abs-2502-10391","documentPage":"https://doi.org/10.48550/ARXIV.2502.10391","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2502.10391","authorSignatures":[{}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2502-10391","documentUrl":"https://doi.org/10.48550/ARXIV.2502.10391"},{"key":"journals/corr/abs-2502-11959","title":"STRIVE: Structured Reasoning for Self-Improvement in Claim Verification.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2502.11959"],"source":"https://dblp.org/rec/journals/corr/abs-2502-11959","documentPage":"https://doi.org/10.48550/ARXIV.2502.11959","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2502.11959","authorSignatures":[{}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2502-11959","documentUrl":"https://doi.org/10.48550/ARXIV.2502.11959"},{"key":"journals/corr/abs-2502-16284","title":"MolSpectra: Pre-training 3D Molecular Representation with Multi-modal Energy Spectra.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2502.16284"],"source":"https://dblp.org/rec/journals/corr/abs-2502-16284","documentPage":"https://doi.org/10.48550/ARXIV.2502.16284","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2502.16284","authorSignatures":[{}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2502-16284","documentUrl":"https://doi.org/10.48550/ARXIV.2502.16284"},{"key":"journals/corr/abs-2503-03989","title":"Integrating Protein Dynamics into Structure-Based Drug Design via Full-Atom Stochastic Flows.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2503.03989"],"source":"https://dblp.org/rec/journals/corr/abs-2503-03989","documentPage":"https://doi.org/10.48550/ARXIV.2503.03989","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2503.03989","authorSignatures":[{}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-03989","documentUrl":"https://doi.org/10.48550/ARXIV.2503.03989"},{"key":"journals/corr/abs-2503-05213","title":"Personalized Text Generation with Contrastive Activation Steering.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2503.05213"],"source":"https://dblp.org/rec/journals/corr/abs-2503-05213","documentPage":"https://doi.org/10.48550/ARXIV.2503.05213","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2503.05213","authorSignatures":[{}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-05213","documentUrl":"https://doi.org/10.48550/ARXIV.2503.05213"},{"key":"journals/corr/abs-2503-10699","title":"Test-Time Discovery via Hashing Memory.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2503.10699"],"source":"https://dblp.org/rec/journals/corr/abs-2503-10699","documentPage":"https://doi.org/10.48550/ARXIV.2503.10699","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2503.10699","authorSignatures":[{}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-10699","documentUrl":"https://doi.org/10.48550/ARXIV.2503.10699"},{"key":"journals/corr/abs-2503-14504","title":"Aligning Multimodal LLM with Human Preference: A Survey.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2503.14504"],"source":"https://dblp.org/rec/journals/corr/abs-2503-14504","documentPage":"https://doi.org/10.48550/ARXIV.2503.14504","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2503.14504","authorSignatures":[{}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-14504","documentUrl":"https://doi.org/10.48550/ARXIV.2503.14504"},{"key":"journals/corr/abs-2503-22136","title":"Beyond Background Shift: Rethinking Instance Replay in Continual Semantic Segmentation.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2503.22136"],"source":"https://dblp.org/rec/journals/corr/abs-2503-22136","documentPage":"https://doi.org/10.48550/ARXIV.2503.22136","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2503.22136","authorSignatures":[{}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-22136","documentUrl":"https://doi.org/10.48550/ARXIV.2503.22136"},{"key":"journals/corr/abs-2504-03641","title":"MME-Unify: A Comprehensive Benchmark for Unified Multimodal Understanding and Generation Models.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2504.03641"],"source":"https://dblp.org/rec/journals/corr/abs-2504-03641","documentPage":"https://doi.org/10.48550/ARXIV.2504.03641","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2504.03641","authorSignatures":[{}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2504-03641","documentUrl":"https://doi.org/10.48550/ARXIV.2504.03641"},{"key":"journals/corr/abs-2504-04809","title":"Select Me! When You Need a Tool: A Black-box Text Attack on Tool Selection.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2504.04809"],"source":"https://dblp.org/rec/journals/corr/abs-2504-04809","documentPage":"https://doi.org/10.48550/ARXIV.2504.04809","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2504.04809","authorSignatures":[{}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2504-04809","documentUrl":"https://doi.org/10.48550/ARXIV.2504.04809"},{"key":"journals/corr/abs-2504-07135","title":"SINCon: Mitigate LLM-Generated Malicious Message Injection Attack for Rumor Detection.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2504.07135"],"source":"https://dblp.org/rec/journals/corr/abs-2504-07135","documentPage":"https://doi.org/10.48550/ARXIV.2504.07135","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2504.07135","authorSignatures":[{}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2504-07135","documentUrl":"https://doi.org/10.48550/ARXIV.2504.07135"},{"key":"journals/corr/abs-2504-15037","title":"A Call for New Recipes to Enhance Spatial Reasoning in MLLMs.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2504.15037"],"source":"https://dblp.org/rec/journals/corr/abs-2504-15037","documentPage":"https://doi.org/10.48550/ARXIV.2504.15037","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2504.15037","authorSignatures":[{}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2504-15037","documentUrl":"https://doi.org/10.48550/ARXIV.2504.15037"},{"key":"journals/corr/abs-2505-02835","title":"R1-Reward: Training Multimodal Reward Model Through Stable Reinforcement Learning.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2505.02835"],"source":"https://dblp.org/rec/journals/corr/abs-2505-02835","documentPage":"https://doi.org/10.48550/ARXIV.2505.02835","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2505.02835","authorSignatures":[{}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-02835","documentUrl":"https://doi.org/10.48550/ARXIV.2505.02835"},{"key":"journals/corr/abs-2505-04956","title":"Graffe: Graph Representation Learning via Diffusion Probabilistic Models.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2505.04956"],"source":"https://dblp.org/rec/journals/corr/abs-2505-04956","documentPage":"https://doi.org/10.48550/ARXIV.2505.04956","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2505.04956","authorSignatures":[{}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-04956","documentUrl":"https://doi.org/10.48550/ARXIV.2505.04956"},{"key":"journals/corr/abs-2505-12574","title":"PoisonArena: Uncovering Competing Poisoning Attacks in Retrieval-Augmented Generation.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2505.12574"],"source":"https://dblp.org/rec/journals/corr/abs-2505-12574","documentPage":"https://doi.org/10.48550/ARXIV.2505.12574","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2505.12574","authorSignatures":[{}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-12574","documentUrl":"https://doi.org/10.48550/ARXIV.2505.12574"},{"key":"journals/corr/abs-2505-16379","title":"Materials Generation in the Era of Artificial Intelligence: A Comprehensive Survey.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2505.16379"],"source":"https://dblp.org/rec/journals/corr/abs-2505-16379","documentPage":"https://doi.org/10.48550/ARXIV.2505.16379","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2505.16379","authorSignatures":[{}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-16379","documentUrl":"https://doi.org/10.48550/ARXIV.2505.16379"},{"key":"journals/corr/abs-2505-18738","title":"AuroRA: Breaking Low-Rank Bottleneck of LoRA with Nonlinear Mapping.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2505.18738"],"source":"https://dblp.org/rec/journals/corr/abs-2505-18738","documentPage":"https://doi.org/10.48550/ARXIV.2505.18738","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2505.18738","authorSignatures":[{}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-18738","documentUrl":"https://doi.org/10.48550/ARXIV.2505.18738"},{"key":"journals/corr/abs-2505-18933","title":"REACT: Representation Extraction And Controllable Tuning to Overcome Overfitting in LLM Knowledge Editing.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2505.18933"],"source":"https://dblp.org/rec/journals/corr/abs-2505-18933","documentPage":"https://doi.org/10.48550/ARXIV.2505.18933","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2505.18933","authorSignatures":[{}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-18933","documentUrl":"https://doi.org/10.48550/ARXIV.2505.18933"},{"key":"journals/corr/abs-2505-20049","title":"Data-Free Class-Incremental Gesture Recognition with Prototype-Guided Pseudo Feature Replay.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2505.20049"],"source":"https://dblp.org/rec/journals/corr/abs-2505-20049","documentPage":"https://doi.org/10.48550/ARXIV.2505.20049","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2505.20049","authorSignatures":[{}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-20049","documentUrl":"https://doi.org/10.48550/ARXIV.2505.20049"},{"key":"journals/corr/abs-2505-20871","title":"Divide-Then-Align: Honest Alignment based on the Knowledge Boundary of RAG.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2505.20871"],"source":"https://dblp.org/rec/journals/corr/abs-2505-20871","documentPage":"https://doi.org/10.48550/ARXIV.2505.20871","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2505.20871","authorSignatures":[{}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-20871","documentUrl":"https://doi.org/10.48550/ARXIV.2505.20871"},{"key":"journals/corr/abs-2505-21333","title":"MME-VideoOCR: Evaluating OCR-Based Capabilities of Multimodal LLMs in Video Scenarios.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2505.21333"],"source":"https://dblp.org/rec/journals/corr/abs-2505-21333","documentPage":"https://doi.org/10.48550/ARXIV.2505.21333","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2505.21333","authorSignatures":[{}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-21333","documentUrl":"https://doi.org/10.48550/ARXIV.2505.21333"},{"key":"journals/corr/abs-2505-21493","title":"Reinforcing General Reasoning without Verifiers.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2505.21493"],"source":"https://dblp.org/rec/journals/corr/abs-2505-21493","documentPage":"https://doi.org/10.48550/ARXIV.2505.21493","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2505.21493","authorSignatures":[{}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-21493","documentUrl":"https://doi.org/10.48550/ARXIV.2505.21493"},{"key":"journals/corr/abs-2506-07961","title":"BridgeVLA: Input-Output Alignment for Efficient 3D Manipulation Learning with Vision-Language Models.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2506.07961"],"source":"https://dblp.org/rec/journals/corr/abs-2506-07961","documentPage":"https://doi.org/10.48550/ARXIV.2506.07961","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2506.07961","authorSignatures":[{}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-07961","documentUrl":"https://doi.org/10.48550/ARXIV.2506.07961"},{"key":"journals/corr/abs-2506-09079","title":"VersaVid-R1: A Versatile Video Understanding and Reasoning Model from Question Answering to Captioning Tasks.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2506.09079"],"source":"https://dblp.org/rec/journals/corr/abs-2506-09079","documentPage":"https://doi.org/10.48550/ARXIV.2506.09079","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2506.09079","authorSignatures":[{}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-09079","documentUrl":"https://doi.org/10.48550/ARXIV.2506.09079"},{"key":"journals/corr/abs-2506-09965","title":"Reinforcing Spatial Reasoning in Vision-Language Models with Interwoven Thinking and Visual Drawing.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2506.09965"],"source":"https://dblp.org/rec/journals/corr/abs-2506-09965","documentPage":"https://doi.org/10.48550/ARXIV.2506.09965","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2506.09965","authorSignatures":[{}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-09965","documentUrl":"https://doi.org/10.48550/ARXIV.2506.09965"},{"key":"journals/corr/abs-2507-06224","title":"EC-Flow: Enabling Versatile Robotic Manipulation from Action-Unlabeled Videos via Embodiment-Centric Flow.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2507.06224"],"source":"https://dblp.org/rec/journals/corr/abs-2507-06224","documentPage":"https://doi.org/10.48550/ARXIV.2507.06224","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2507.06224","authorSignatures":[{}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2507-06224","documentUrl":"https://doi.org/10.48550/ARXIV.2507.06224"},{"key":"journals/corr/abs-2507-06853","title":"DiffSpectra: Molecular Structure Elucidation from Spectra using Diffusion Models.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2507.06853"],"source":"https://dblp.org/rec/journals/corr/abs-2507-06853","documentPage":"https://doi.org/10.48550/ARXIV.2507.06853","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2507.06853","authorSignatures":[{}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2507-06853","documentUrl":"https://doi.org/10.48550/ARXIV.2507.06853"},{"key":"journals/corr/abs-2507-20163","title":"Player-Centric Multimodal Prompt Generation for Large Language Model Based Identity-Aware Basketball Video Captioning.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2507.20163"],"source":"https://dblp.org/rec/journals/corr/abs-2507-20163","documentPage":"https://doi.org/10.48550/ARXIV.2507.20163","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2507.20163","authorSignatures":[{}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2507-20163","documentUrl":"https://doi.org/10.48550/ARXIV.2507.20163"},{"key":"journals/corr/abs-2507-23237","title":"Ambiguity-Guided Learnable Distribution Calibration for Semi-Supervised Few-Shot Class-Incremental Learning.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2507.23237"],"source":"https://dblp.org/rec/journals/corr/abs-2507-23237","documentPage":"https://doi.org/10.48550/ARXIV.2507.23237","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2507.23237","authorSignatures":[{}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2507-23237","documentUrl":"https://doi.org/10.48550/ARXIV.2507.23237"},{"key":"journals/corr/abs-2508-03469","title":"IKOD: Mitigating Visual Attention Degradation in Large Vision-Language Models.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2508.03469"],"source":"https://dblp.org/rec/journals/corr/abs-2508-03469","documentPage":"https://doi.org/10.48550/ARXIV.2508.03469","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2508.03469","authorSignatures":[{}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-03469","documentUrl":"https://doi.org/10.48550/ARXIV.2508.03469"},{"key":"journals/corr/abs-2508-04047","title":"DTPA: Dynamic Token-level Prefix Augmentation for Controllable Text Generation.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2508.04047"],"source":"https://dblp.org/rec/journals/corr/abs-2508-04047","documentPage":"https://doi.org/10.48550/ARXIV.2508.04047","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2508.04047","authorSignatures":[{}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-04047","documentUrl":"https://doi.org/10.48550/ARXIV.2508.04047"},{"key":"journals/corr/abs-2508-04482","title":"OS Agents: A Survey on MLLM-based Agents for General Computing Devices Use.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2508.04482"],"source":"https://dblp.org/rec/journals/corr/abs-2508-04482","documentPage":"https://doi.org/10.48550/ARXIV.2508.04482","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2508.04482","authorSignatures":[{}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-04482","documentUrl":"https://doi.org/10.48550/ARXIV.2508.04482"},{"key":"journals/corr/abs-2508-07992","title":"Mining the Social Fabric: Unveiling Communities for Fake News Detection in Short Videos.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2508.07992"],"source":"https://dblp.org/rec/journals/corr/abs-2508-07992","documentPage":"https://doi.org/10.48550/ARXIV.2508.07992","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2508.07992","authorSignatures":[{}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-07992","documentUrl":"https://doi.org/10.48550/ARXIV.2508.07992"},{"key":"journals/corr/abs-2508-08441","title":"Language Models Can Understand Spectra: A Multimodal Model for Molecular Structure Elucidation.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2508.08441"],"source":"https://dblp.org/rec/journals/corr/abs-2508-08441","documentPage":"https://doi.org/10.48550/ARXIV.2508.08441","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2508.08441","authorSignatures":[{}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-08441","documentUrl":"https://doi.org/10.48550/ARXIV.2508.08441"},{"key":"journals/corr/abs-2508-11630","title":"Thyme: Think Beyond Images.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2508.11630"],"source":"https://dblp.org/rec/journals/corr/abs-2508-11630","documentPage":"https://doi.org/10.48550/ARXIV.2508.11630","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2508.11630","authorSignatures":[{}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-11630","documentUrl":"https://doi.org/10.48550/ARXIV.2508.11630"},{"key":"journals/corr/abs-2508-12586","title":"Foundation Model for Skeleton-Based Human Action Understanding.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2508.12586"],"source":"https://dblp.org/rec/journals/corr/abs-2508-12586","documentPage":"https://doi.org/10.48550/ARXIV.2508.12586","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2508.12586","authorSignatures":[{}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-12586","documentUrl":"https://doi.org/10.48550/ARXIV.2508.12586"},{"key":"journals/corr/abs-2508-15232","title":"AeroDuo: Aerial Duo for UAV-based Vision and Language Navigation.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2508.15232"],"source":"https://dblp.org/rec/journals/corr/abs-2508-15232","documentPage":"https://doi.org/10.48550/ARXIV.2508.15232","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2508.15232","authorSignatures":[{}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-15232","documentUrl":"https://doi.org/10.48550/ARXIV.2508.15232"},{"key":"journals/corr/abs-2509-00419","title":"LightVLM: Acceleraing Large Multimodal Models with Pyramid Token Merging and KV Cache Compression.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2509.00419"],"source":"https://dblp.org/rec/journals/corr/abs-2509-00419","documentPage":"https://doi.org/10.48550/ARXIV.2509.00419","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2509.00419","authorSignatures":[{}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-00419","documentUrl":"https://doi.org/10.48550/ARXIV.2509.00419"},{"key":"journals/corr/abs-2509-02993","title":"SPENet: Self-guided Prototype Enhancement Network for Few-shot Medical Image Segmentation.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2509.02993"],"source":"https://dblp.org/rec/journals/corr/abs-2509-02993","documentPage":"https://doi.org/10.48550/ARXIV.2509.02993","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2509.02993","authorSignatures":[{}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-02993","documentUrl":"https://doi.org/10.48550/ARXIV.2509.02993"},{"key":"journals/corr/abs-2509-11569","title":"D2HScore: Reasoning-Aware Hallucination Detection via Semantic Breadth and Depth Analysis in LLMs.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2509.11569"],"source":"https://dblp.org/rec/journals/corr/abs-2509-11569","documentPage":"https://doi.org/10.48550/ARXIV.2509.11569","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2509.11569","authorSignatures":[{}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-11569","documentUrl":"https://doi.org/10.48550/ARXIV.2509.11569"},{"key":"journals/corr/abs-2509-16127","title":"BaseReward: A Strong Baseline for Multimodal Reward Model.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2509.16127"],"source":"https://dblp.org/rec/journals/corr/abs-2509-16127","documentPage":"https://doi.org/10.48550/ARXIV.2509.16127","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2509.16127","authorSignatures":[{}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-16127","documentUrl":"https://doi.org/10.48550/ARXIV.2509.16127"},{"key":"journals/corr/abs-2509-17044","title":"AgriDoctor: A Multimodal Intelligent Assistant for Agriculture.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2509.17044"],"source":"https://dblp.org/rec/journals/corr/abs-2509-17044","documentPage":"https://doi.org/10.48550/ARXIV.2509.17044","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2509.17044","authorSignatures":[{}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-17044","documentUrl":"https://doi.org/10.48550/ARXIV.2509.17044"},{"key":"journals/corr/abs-2509-19719","title":"Frequency-domain Multi-modal Fusion for Language-guided Medical Image Segmentation.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2509.19719"],"source":"https://dblp.org/rec/journals/corr/abs-2509-19719","documentPage":"https://doi.org/10.48550/ARXIV.2509.19719","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2509.19719","authorSignatures":[{}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-19719","documentUrl":"https://doi.org/10.48550/ARXIV.2509.19719"},{"key":"journals/corr/abs-2509-22578","title":"EgoDemoGen: Novel Egocentric Demonstration Generation Enables Viewpoint-Robust Manipulation.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2509.22578"],"source":"https://dblp.org/rec/journals/corr/abs-2509-22578","documentPage":"https://doi.org/10.48550/ARXIV.2509.22578","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2509.22578","authorSignatures":[{}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-22578","documentUrl":"https://doi.org/10.48550/ARXIV.2509.22578"},{"key":"journals/corr/abs-2509-22637","title":"Variational Reasoning for Language Models.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2509.22637"],"source":"https://dblp.org/rec/journals/corr/abs-2509-22637","documentPage":"https://doi.org/10.48550/ARXIV.2509.22637","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2509.22637","authorSignatures":[{}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-22637","documentUrl":"https://doi.org/10.48550/ARXIV.2509.22637"},{"key":"journals/corr/abs-2509-24900","title":"OpenGPT-4o-Image: A Comprehensive Dataset for Advanced Image Generation and Editing.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2509.24900"],"source":"https://dblp.org/rec/journals/corr/abs-2509-24900","documentPage":"https://doi.org/10.48550/ARXIV.2509.24900","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2509.24900","authorSignatures":[{}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-24900","documentUrl":"https://doi.org/10.48550/ARXIV.2509.24900"},{"key":"journals/corr/abs-2510-07217","title":"GenPilot: A Multi-Agent System for Test-Time Prompt Optimization in Image Generation.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2510.07217"],"source":"https://dblp.org/rec/journals/corr/abs-2510-07217","documentPage":"https://doi.org/10.48550/ARXIV.2510.07217","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2510.07217","authorSignatures":[{}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-07217","documentUrl":"https://doi.org/10.48550/ARXIV.2510.07217"},{"key":"journals/corr/abs-2510-10395","title":"AVoCaDO: An Audiovisual Video Captioner Driven by Temporal Orchestration.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2510.10395"],"source":"https://dblp.org/rec/journals/corr/abs-2510-10395","documentPage":"https://doi.org/10.48550/ARXIV.2510.10395","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2510.10395","authorSignatures":[{}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-10395","documentUrl":"https://doi.org/10.48550/ARXIV.2510.10395"},{"key":"journals/corr/abs-2510-17131","title":"GOOD: Training-Free Guided Diffusion Sampling for Out-of-Distribution Detection.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2510.17131"],"source":"https://dblp.org/rec/journals/corr/abs-2510-17131","documentPage":"https://doi.org/10.48550/ARXIV.2510.17131","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2510.17131","authorSignatures":[{}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-17131","documentUrl":"https://doi.org/10.48550/ARXIV.2510.17131"},{"key":"journals/corr/abs-2510-21333","title":"CausalRec: A CausalBoost Attention Model for Sequential Recommendation.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2510.21333"],"source":"https://dblp.org/rec/journals/corr/abs-2510-21333","documentPage":"https://doi.org/10.48550/ARXIV.2510.21333","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2510.21333","authorSignatures":[{}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-21333","documentUrl":"https://doi.org/10.48550/ARXIV.2510.21333"},{"key":"journals/corr/abs-2510-24514","title":"Latent Sketchpad: Sketching Visual Thoughts to Elicit Multimodal Reasoning in MLLMs.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2510.24514"],"source":"https://dblp.org/rec/journals/corr/abs-2510-24514","documentPage":"https://doi.org/10.48550/ARXIV.2510.24514","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2510.24514","authorSignatures":[{}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-24514","documentUrl":"https://doi.org/10.48550/ARXIV.2510.24514"},{"key":"journals/corr/abs-2511-00010","title":"PlotCraft: Pushing the Limits of LLMs for Complex and Interactive Data Visualization.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2511.00010"],"source":"https://dblp.org/rec/journals/corr/abs-2511-00010","documentPage":"https://doi.org/10.48550/ARXIV.2511.00010","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2511.00010","authorSignatures":[{}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2511-00010","documentUrl":"https://doi.org/10.48550/ARXIV.2511.00010"},{"key":"journals/corr/abs-2511-23369","title":"SimScale: Learning to Drive via Real-World Simulation at Scale.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2511.23369"],"source":"https://dblp.org/rec/journals/corr/abs-2511-23369","documentPage":"https://doi.org/10.48550/ARXIV.2511.23369","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2511.23369","authorSignatures":[{}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2511-23369","documentUrl":"https://doi.org/10.48550/ARXIV.2511.23369"},{"key":"journals/corr/abs-2512-04082","title":"PosterCopilot: Toward Layout Reasoning and Controllable Editing for Professional Graphic Design.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2512.04082"],"source":"https://dblp.org/rec/journals/corr/abs-2512-04082","documentPage":"https://doi.org/10.48550/ARXIV.2512.04082","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2512.04082","authorSignatures":[{}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-04082","documentUrl":"https://doi.org/10.48550/ARXIV.2512.04082"},{"key":"journals/corr/abs-2512-10999","title":"KBQA-R1: Reinforcing Large Language Models for Knowledge Base Question Answering.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2512.10999"],"source":"https://dblp.org/rec/journals/corr/abs-2512-10999","documentPage":"https://doi.org/10.48550/ARXIV.2512.10999","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2512.10999","authorSignatures":[{}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-10999","documentUrl":"https://doi.org/10.48550/ARXIV.2512.10999"},{"key":"journals/corr/abs-2512-16724","title":"VERM: Leveraging Foundation Models to Create a Virtual Eye for Efficient 3D Robotic Manipulation.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2512.16724"],"source":"https://dblp.org/rec/journals/corr/abs-2512-16724","documentPage":"https://doi.org/10.48550/ARXIV.2512.16724","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2512.16724","authorSignatures":[{}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-16724","documentUrl":"https://doi.org/10.48550/ARXIV.2512.16724"},{"key":"journals/corr/abs-2512-21857","title":"Fast Inference of Visual Autoregressive Model with Adjacency-Adaptive Dynamical Draft Trees.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2512.21857"],"source":"https://dblp.org/rec/journals/corr/abs-2512-21857","documentPage":"https://doi.org/10.48550/ARXIV.2512.21857","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2512.21857","authorSignatures":[{}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-21857","documentUrl":"https://doi.org/10.48550/ARXIV.2512.21857"},{"key":"journals/ijon/XiaTWLWZ25","title":"MPE3: Learning meta-prompt with entity-enhanced semantics for few-shot named entity recognition.","year":2025,"yearOfEvent":null,"venue":"Neurocomputing","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1016/J.NEUCOM.2024.129031"],"source":"https://dblp.org/rec/journals/ijon/XiaTWLWZ25","documentPage":"https://doi.org/10.1016/J.NEUCOM.2024.129031","type":"Article","doi":"https://doi.org/10.1016/J.NEUCOM.2024.129031","authorSignatures":[{"inst":"https://dblp.org/inst/11/691","instLabel":"Chinese Academy of Sciences (CAS)"},{"inst":"https://dblp.org/inst/12/068","instLabel":"Shandong Institute of Automation"},{"inst":"https://dblp.org/inst/12/115","instLabel":"Beijing Academy of Artificial Intelligence (BAAI)"},{"inst":"https://dblp.org/inst/5/099","instLabel":"University of the Chinese Academy of Sciences (UCAS)"}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/ijon/XiaTWLWZ25","documentUrl":"https://doi.org/10.1016/J.NEUCOM.2024.129031"}],"retrievedAt":"2026-10-19","querySource":"https://sparql.dblp.org/","method":"DBLP yearOfPublication=2025; Article + Inproceedings; excludes Informal/CoRR and explicit editorial/correction/erratum/preface; unique DBLP record keys within person.","verifiedLowerBound2025":27,"conferenceLowerBound2025":10,"journalLowerBound2025":17,"sourceWarning":true,"labName":"多模态人工智能系统全国重点实验室","labUrl":null,"labEvidence":"中国科学院大学本人教师页明确记载其任该全国重点实验室副主任；这是公开机构归属，不等同于其个人合作记录覆盖整个实验室。","labSourceUrl":"https://people.ucas.ac.cn/~wangliang","affiliationZh":"中科院自动化研究所","knownPreprintMinimum2025":null,"excludedMisattributed":[{"key":"conf/www/0025XYDK00YX025","title":"Learning against Non-credible Second-Price Auctions.","year":2025,"yearOfEvent":2025,"venue":"WWW","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1145/3696410.3714847"],"source":"https://dblp.org/rec/conf/www/0025XYDK00YX025","documentPage":"https://doi.org/10.1145/3696410.3714847","type":"Inproceedings","doi":"https://doi.org/10.1145/3696410.3714847","authorSignatures":[{"orcid":"https://orcid.org/0000-0001-5353-7803","inst":"https://dblp.org/inst/12/039","instLabel":"Alibaba Group"}],"exclusionReason":"Crossref identifies Alibaba Liang Wang, ORCID 0000-0001-5353-7803, not CASIA Wang Liang.","exclusionSource":"https://api.crossref.org/works/10.1145/3696410.3714847","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/www/0025XYDK00YX025","documentUrl":"https://doi.org/10.1145/3696410.3714847"},{"key":"conf/www/ChenW0S25","title":"DAGPrompT: Pushing the Limits of Graph Prompting with a Distribution-aware Graph Prompt Tuning Approach.","year":2025,"yearOfEvent":2025,"venue":"WWW","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1145/3696410.3714917"],"source":"https://dblp.org/rec/conf/www/ChenW0S25","documentPage":"https://doi.org/10.1145/3696410.3714917","type":"Inproceedings","doi":"https://doi.org/10.1145/3696410.3714917","authorSignatures":[{"orcid":"https://orcid.org/0000-0001-5353-7803","inst":"https://dblp.org/inst/12/039","instLabel":"Alibaba Group"}],"exclusionReason":"Crossref identifies Alibaba Liang Wang, ORCID 0000-0001-5353-7803, not CASIA Wang Liang.","exclusionSource":"https://api.crossref.org/works/10.1145/3696410.3714917","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/www/ChenW0S25","documentUrl":"https://doi.org/10.1145/3696410.3714917"},{"key":"journals/eswa/GaoZHSWF25","title":"A structure-based disentangled network with contrastive regularization for sign language recognition.","year":2025,"yearOfEvent":null,"venue":"Expert Syst. Appl.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1016/J.ESWA.2025.126623"],"source":"https://dblp.org/rec/journals/eswa/GaoZHSWF25","documentPage":"https://doi.org/10.1016/J.ESWA.2025.126623","type":"Article","doi":"https://doi.org/10.1016/J.ESWA.2025.126623","authorSignatures":[{"inst":"https://dblp.org/inst/2/152","instLabel":"Tianjin University (TJU)"}],"exclusionReason":"Crossref author family name is Wan (not Wang); DBLP signature identifies Tianjin University.","exclusionSource":"https://api.crossref.org/works/10.1016/J.ESWA.2025.126623","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/eswa/GaoZHSWF25","documentUrl":"https://doi.org/10.1016/J.ESWA.2025.126623"},{"key":"journals/pr/GaoWHHLSSF25","title":"A large-scale combinatorial benchmark for sign language recognition.","year":2025,"yearOfEvent":null,"venue":"Pattern Recognit.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1016/J.PATCOG.2024.111246"],"source":"https://dblp.org/rec/journals/pr/GaoWHHLSSF25","documentPage":"https://doi.org/10.1016/J.PATCOG.2024.111246","type":"Article","doi":"https://doi.org/10.1016/J.PATCOG.2024.111246","authorSignatures":[{"inst":"https://dblp.org/inst/2/152","instLabel":"Tianjin University (TJU)"}],"exclusionReason":"Crossref author family name is Wan (not Wang); DBLP signature identifies Tianjin University.","exclusionSource":"https://api.crossref.org/works/10.1016/J.PATCOG.2024.111246","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/pr/GaoWHHLSSF25","documentUrl":"https://doi.org/10.1016/J.PATCOG.2024.111246"},{"key":"journals/tip/HuangTJZWG25","title":"C-NeRF: Representing Scene Changes as Directional Consistency Difference-Based NeRF.","year":2025,"yearOfEvent":null,"venue":"IEEE Trans. Image Process.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1109/TIP.2025.3622374"],"source":"https://dblp.org/rec/journals/tip/HuangTJZWG25","documentPage":"https://doi.org/10.1109/TIP.2025.3622374","type":"Article","doi":"https://doi.org/10.1109/TIP.2025.3622374","authorSignatures":[{"orcid":"https://orcid.org/0000-0001-5501-9575","inst":"https://dblp.org/inst/2/152","instLabel":"Tianjin University (TJU)"}],"exclusionReason":"Crossref author family name is Wan (not Wang), Tianjin University, ORCID 0000-0001-5501-9575.","exclusionSource":"https://api.crossref.org/works/10.1109/TIP.2025.3622374","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/tip/HuangTJZWG25","documentUrl":"https://doi.org/10.1109/TIP.2025.3622374"}],"knownMinimum2025":27,"displayNotes":"该 DBLP 档案混有其他同名作者，已排除 5 条明确的同名记录；其余候选尚未逐篇核完，全年总数暂不给出。目前已逐篇核实 27 条，只作下界参考，不进入合计、中位数或排序。另有一篇候选（BridgeVLA）的项目页标注了中科院自动化所与国科大的归属，尚未完成复核，暂不计入下界。","labDisplayNotes":"国科大本人教师页写明其任多模态人工智能系统全国重点实验室副主任。这是大型机构，命名只表示公开归属；论文数仍为空缺，不画柱。"},{"index":87,"name":"Liyuan Wang","nameZh":"王立元","affiliation":"Tsinghua University","source":"DBLP Knowledge Graph official SPARQL API","profileUrl":"https://dblp.org/pid/121/6094","identifier":"121/6094","identityEvidence":[{"url":"https://lywang3081.github.io/","evidence":"Personal site identifies 王立元/Liyuan Wang at Tsinghua, neuroscience and continual learning. DBLP PID is an unresolved mixed-name page."},{"url":"https://orcid.org/0009-0002-7797-325X","evidence":"ORCID profile links directly to lywang3081.github.io; used to confirm the TVCG paper."}],"count2025":null,"conference2025":null,"journal2025":null,"preprint2025":null,"status":"partial_identity_review","notes":"Counts are DBLP indexed coauthored records, not first-author counts, laboratory totals, unique scientific discoveries, or quality assessments. DBLP yearOfPublication=2025; yearOfEvent retained and can differ. Conference workshops are included. Preprints are separate and may overlap formal versions. Mixed / unassigned DBLP profile. Main counts withheld pending review of every remaining candidate; retained papers establish a verified lower bound only. Do not present this lower bound as an exact annual total.","papers":[{"key":"conf/eccv/ZhouWZSLLL24","title":"MAGR: Manifold-Aligned Graph Regularization for Continual Action Quality Assessment.","year":2025,"yearOfEvent":2024,"venue":"ECCV (11)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1007/978-3-031-73247-8_22"],"source":"https://dblp.org/rec/conf/eccv/ZhouWZSLLL24","documentPage":"https://doi.org/10.1007/978-3-031-73247-8_22","type":"Inproceedings","doi":"https://doi.org/10.1007/978-3-031-73247-8_22","authorSignatures":[{"inst":"https://dblp.org/inst/1/155","instLabel":"Tsinghua University (THU)"},{"inst":"https://dblp.org/inst/12/205","instLabel":"Bosch"}],"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/eccv/ZhouWZSLLL24","documentUrl":"https://doi.org/10.1007/978-3-031-73247-8_22"},{"key":"conf/iclr/KangWZA25","title":"Advancing Prompt-Based Methods for Replay-Independent General Continual Learning.","year":2025,"yearOfEvent":2025,"venue":"ICLR","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/iclr/KangWZA25","documentPage":"https://openreview.net/forum?id=V6uxd8MEqw","type":"Inproceedings","doi":null,"authorSignatures":[{}],"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iclr/KangWZA25","documentUrl":"https://openreview.net/forum?id=V6uxd8MEqw"},{"key":"conf/icml/SunYW0LZ25","title":"Right Time to Learn: Promoting Generalization via Bio-inspired Spacing Effect in Knowledge Distillation.","year":2025,"yearOfEvent":2025,"venue":"ICML","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/icml/SunYW0LZ25","documentPage":"https://proceedings.mlr.press/v267/sun25w.html","type":"Inproceedings","doi":null,"authorSignatures":[{}],"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/icml/SunYW0LZ25","documentUrl":"https://proceedings.mlr.press/v267/sun25w.html"},{"key":"journals/pami/WangXZSZ25","title":"HiDe-PET: Continual Learning via Hierarchical Decomposition of Parameter-Efficient Tuning.","year":2025,"yearOfEvent":null,"venue":"IEEE Trans. Pattern Anal. Mach. Intell.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1109/TPAMI.2025.3562534"],"source":"https://dblp.org/rec/journals/pami/WangXZSZ25","documentPage":"https://doi.org/10.1109/TPAMI.2025.3562534","type":"Article","doi":"https://doi.org/10.1109/TPAMI.2025.3562534","authorSignatures":[{"orcid":"https://orcid.org/0000-0002-3869-8155","inst":"https://dblp.org/inst/1/155","instLabel":"Tsinghua University (THU)"},{"orcid":"https://orcid.org/0000-0002-3869-8155","inst":"https://dblp.org/inst/12/205","instLabel":"Bosch"}],"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/pami/WangXZSZ25","documentUrl":"https://doi.org/10.1109/TPAMI.2025.3562534"},{"key":"journals/tvcg/ZhouHWL25","title":"Adaptive Score Alignment Learning for Continual Perceptual Quality Assessment of 360-Degree Videos in Virtual Reality.","year":2025,"yearOfEvent":null,"venue":"IEEE Trans. Vis. Comput. Graph.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1109/TVCG.2025.3549179"],"source":"https://dblp.org/rec/journals/tvcg/ZhouHWL25","documentPage":"https://doi.org/10.1109/TVCG.2025.3549179","type":"Article","doi":"https://doi.org/10.1109/TVCG.2025.3549179","authorSignatures":[{"orcid":"https://orcid.org/0009-0002-7797-325X","inst":"https://dblp.org/inst/1/155","instLabel":"Tsinghua University (THU)"}],"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/tvcg/ZhouHWL25","documentUrl":"https://doi.org/10.1109/TVCG.2025.3549179"}],"preprints":[{"key":"journals/corr/abs-2502-06192","title":"Right Time to Learn:Promoting Generalization via Bio-inspired Spacing Effect in Knowledge Distillation.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2502.06192"],"source":"https://dblp.org/rec/journals/corr/abs-2502-06192","documentPage":"https://doi.org/10.48550/ARXIV.2502.06192","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2502.06192","authorSignatures":[{}],"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2502-06192","documentUrl":"https://doi.org/10.48550/ARXIV.2502.06192","arxivId":"2502.06192","arxivUrl":"https://arxiv.org/abs/2502.06192"},{"key":"journals/corr/abs-2503-00677","title":"Advancing Prompt-Based Methods for Replay-Independent General Continual Learning.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2503.00677"],"source":"https://dblp.org/rec/journals/corr/abs-2503-00677","documentPage":"https://doi.org/10.48550/ARXIV.2503.00677","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2503.00677","authorSignatures":[{}],"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-00677","documentUrl":"https://doi.org/10.48550/ARXIV.2503.00677","arxivId":"2503.00677","arxivUrl":"https://arxiv.org/abs/2503.00677"},{"key":"journals/corr/abs-2505-22306","title":"Versatile Cardiovascular Signal Generation with a Unified Diffusion Transformer.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2505.22306"],"source":"https://dblp.org/rec/journals/corr/abs-2505-22306","documentPage":"https://doi.org/10.48550/ARXIV.2505.22306","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2505.22306","authorSignatures":[{}],"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-22306","documentUrl":"https://doi.org/10.48550/ARXIV.2505.22306","arxivId":"2505.22306","arxivUrl":"https://arxiv.org/abs/2505.22306"},{"key":"journals/corr/abs-2510-06842","title":"Continual Action Quality Assessment via Adaptive Manifold-Aligned Graph Regularization.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2510.06842"],"source":"https://dblp.org/rec/journals/corr/abs-2510-06842","documentPage":"https://doi.org/10.48550/ARXIV.2510.06842","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2510.06842","authorSignatures":[{}],"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-06842","documentUrl":"https://doi.org/10.48550/ARXIV.2510.06842","arxivId":"2510.06842","arxivUrl":"https://arxiv.org/abs/2510.06842"},{"key":"journals/corr/abs-2510-16914","title":"Domain Generalizable Continual Learning.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2510.16914"],"source":"https://dblp.org/rec/journals/corr/abs-2510-16914","documentPage":"https://doi.org/10.48550/ARXIV.2510.16914","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2510.16914","authorSignatures":[{}],"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-16914","documentUrl":"https://doi.org/10.48550/ARXIV.2510.16914","arxivId":"2510.16914","arxivUrl":"https://arxiv.org/abs/2510.16914"}],"excludedFormal":[],"excludedOther":[],"excludedHomonyms":[],"unassignedCandidates":[{"key":"conf/iclr/WangWLZ25","title":"HeadMap: Locating and Enhancing Knowledge Circuits in LLMs.","year":2025,"yearOfEvent":2025,"venue":"ICLR","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/iclr/WangWLZ25","documentPage":"https://openreview.net/forum?id=jUsrbOuQ5e","type":"Inproceedings","doi":null,"authorSignatures":[{}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iclr/WangWLZ25","documentUrl":"https://openreview.net/forum?id=jUsrbOuQ5e"},{"key":"conf/iecon/GuZLWX25","title":"Hybrid Energy Storage Power Allocation Strategy Based on Improved Kalman Filtering and Variational Mode Decomposition.","year":2025,"yearOfEvent":2025,"venue":"IECON","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/IECON58223.2025.11221624"],"source":"https://dblp.org/rec/conf/iecon/GuZLWX25","documentPage":"https://doi.org/10.1109/IECON58223.2025.11221624","type":"Inproceedings","doi":"https://doi.org/10.1109/IECON58223.2025.11221624","authorSignatures":[{"inst":"https://dblp.org/inst/7/869","instLabel":"Northeast Dianli University (NEDU)"}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iecon/GuZLWX25","documentUrl":"https://doi.org/10.1109/IECON58223.2025.11221624"},{"key":"conf/iecon/QiZWZ25","title":"Improved Super-Twisting Nonsingular Terminal Sliding Mode Control for Capacitive Energy Transfer DC/DC Converter.","year":2025,"yearOfEvent":2025,"venue":"IECON","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/IECON58223.2025.11221039"],"source":"https://dblp.org/rec/conf/iecon/QiZWZ25","documentPage":"https://doi.org/10.1109/IECON58223.2025.11221039","type":"Inproceedings","doi":"https://doi.org/10.1109/IECON58223.2025.11221039","authorSignatures":[{"inst":"https://dblp.org/inst/7/869","instLabel":"Northeast Dianli University (NEDU)"}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iecon/QiZWZ25","documentUrl":"https://doi.org/10.1109/IECON58223.2025.11221039"},{"key":"conf/iecon/WangDZWLX25","title":"Collaborative Bidding Strategy for Wind and Storage Power Plants in Dual Markets Based on Electricity Price Forecasting and Dynamic Risk Management.","year":2025,"yearOfEvent":2025,"venue":"IECON","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/IECON58223.2025.11221893"],"source":"https://dblp.org/rec/conf/iecon/WangDZWLX25","documentPage":"https://doi.org/10.1109/IECON58223.2025.11221893","type":"Inproceedings","doi":"https://doi.org/10.1109/IECON58223.2025.11221893","authorSignatures":[{"inst":"https://dblp.org/inst/7/869","instLabel":"Northeast Dianli University (NEDU)"}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iecon/WangDZWLX25","documentUrl":"https://doi.org/10.1109/IECON58223.2025.11221893"},{"key":"conf/infocom/LinWSC25","title":"Optimizing Freshness of Machine Learning Model: A Timing (Multi-Armed) Bandit Approach.","year":2025,"yearOfEvent":2025,"venue":"INFOCOM WKSHPS","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/INFOCOMWKSHPS65812.2025.11152781"],"source":"https://dblp.org/rec/conf/infocom/LinWSC25","documentPage":"https://doi.org/10.1109/INFOCOMWKSHPS65812.2025.11152781","type":"Inproceedings","doi":"https://doi.org/10.1109/INFOCOMWKSHPS65812.2025.11152781","authorSignatures":[{"inst":"https://dblp.org/inst/8/375","instLabel":"City University of Hong Kong"}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/infocom/LinWSC25","documentUrl":"https://doi.org/10.1109/INFOCOMWKSHPS65812.2025.11152781"},{"key":"conf/nips/LiCWZ25","title":"Audio Super-Resolution with Latent Bridge Models.","year":2025,"yearOfEvent":2025,"venue":"NeurIPS","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/nips/LiCWZ25","documentPage":"http://papers.nips.cc/paper_files/paper/2025/hash/4572bc2f514e627914cbe60d0398a2d1-Abstract-Conference.html","type":"Inproceedings","doi":null,"authorSignatures":[{}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/nips/LiCWZ25","documentUrl":"http://papers.nips.cc/paper_files/paper/2025/hash/4572bc2f514e627914cbe60d0398a2d1-Abstract-Conference.html"},{"key":"conf/nips/YinWZZH25","title":"Vertical Federated Feature Screening.","year":2025,"yearOfEvent":2025,"venue":"NeurIPS","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/nips/YinWZZH25","documentPage":"http://papers.nips.cc/paper_files/paper/2025/hash/172946488c60421563ecad4ee2d4235d-Abstract-Conference.html","type":"Inproceedings","doi":null,"authorSignatures":[{}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/nips/YinWZZH25","documentUrl":"http://papers.nips.cc/paper_files/paper/2025/hash/172946488c60421563ecad4ee2d4235d-Abstract-Conference.html"},{"key":"journals/access/WangZML25","title":"Frequency Enhanced Dynamic Graph Convolutional Networks for Traffic Flow Forecasting.","year":2025,"yearOfEvent":null,"venue":"IEEE Access","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1109/ACCESS.2025.3579334"],"source":"https://dblp.org/rec/journals/access/WangZML25","documentPage":"https://doi.org/10.1109/ACCESS.2025.3579334","type":"Article","doi":"https://doi.org/10.1109/ACCESS.2025.3579334","authorSignatures":[{}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/access/WangZML25","documentUrl":"https://doi.org/10.1109/ACCESS.2025.3579334"},{"key":"journals/apin/WangZKZML25","title":"Harmful data enhanced anomaly detection for quasi-periodic multivariate time series.","year":2025,"yearOfEvent":null,"venue":"Appl. Intell.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1007/S10489-025-06461-X"],"source":"https://dblp.org/rec/journals/apin/WangZKZML25","documentPage":"https://doi.org/10.1007/S10489-025-06461-X","type":"Article","doi":"https://doi.org/10.1007/S10489-025-06461-X","authorSignatures":[{"inst":"https://dblp.org/inst/5/326","instLabel":"Southwest Petroleum University (SWPU)"}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/apin/WangZKZML25","documentUrl":"https://doi.org/10.1007/S10489-025-06461-X"},{"key":"journals/bib/WuXWLHLHLY24","title":"scGO: interpretable deep neural network for cell status annotation and disease diagnosis.","year":2025,"yearOfEvent":null,"venue":"Briefings Bioinform.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1093/BIB/BBAF018"],"source":"https://dblp.org/rec/journals/bib/WuXWLHLHLY24","documentPage":"https://doi.org/10.1093/BIB/BBAF018","type":"Article","doi":"https://doi.org/10.1093/BIB/BBAF018","authorSignatures":[{"orcid":"https://orcid.org/0000-0002-8996-6842","inst":"https://dblp.org/inst/9/595","instLabel":"Shanghai Jiao Tong University (SJTU)"}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/bib/WuXWLHLHLY24","documentUrl":"https://doi.org/10.1093/BIB/BBAF018"},{"key":"journals/cn/LinZZW25","title":"Trust evaluation mechanism for the internet of vehicles based on filtering algorithm.","year":2025,"yearOfEvent":null,"venue":"Comput. Networks","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1016/J.COMNET.2025.111583"],"source":"https://dblp.org/rec/journals/cn/LinZZW25","documentPage":"https://doi.org/10.1016/J.COMNET.2025.111583","type":"Article","doi":"https://doi.org/10.1016/J.COMNET.2025.111583","authorSignatures":[{}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/cn/LinZZW25","documentUrl":"https://doi.org/10.1016/J.COMNET.2025.111583"},{"key":"journals/cnsns/WangCG25","title":"Nonlinear stochastic vibration of GPRMF cylindrical shell with harmonic and white noise excitations.","year":2025,"yearOfEvent":null,"venue":"Commun. Nonlinear Sci. Numer. Simul.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1016/J.CNSNS.2025.108592"],"source":"https://dblp.org/rec/journals/cnsns/WangCG25","documentPage":"https://doi.org/10.1016/J.CNSNS.2025.108592","type":"Article","doi":"https://doi.org/10.1016/J.CNSNS.2025.108592","authorSignatures":[{"inst":"https://dblp.org/inst/12/027","instLabel":"Jiangsu University of Science and Technology (JUST)"}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/cnsns/WangCG25","documentUrl":"https://doi.org/10.1016/J.CNSNS.2025.108592"},{"key":"journals/corr/abs-2502-19644","title":"Adaptive Score Alignment Learning for Continual Perceptual Quality Assessment of 360-Degree Videos in Virtual Reality.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2502.19644"],"source":"https://dblp.org/rec/journals/corr/abs-2502-19644","documentPage":"https://doi.org/10.48550/ARXIV.2502.19644","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2502.19644","authorSignatures":[{}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2502-19644","documentUrl":"https://doi.org/10.48550/ARXIV.2502.19644"},{"key":"journals/corr/abs-2504-07433","title":"From Token to Line: Enhancing Code Generation with a Long-Term Perspective.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2504.07433"],"source":"https://dblp.org/rec/journals/corr/abs-2504-07433","documentPage":"https://doi.org/10.48550/ARXIV.2504.07433","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2504.07433","authorSignatures":[{}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2504-07433","documentUrl":"https://doi.org/10.48550/ARXIV.2504.07433"},{"key":"journals/corr/abs-2504-19979","title":"Transfer Learning Under High-Dimensional Network Convolutional Regression Model.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2504.19979"],"source":"https://dblp.org/rec/journals/corr/abs-2504-19979","documentPage":"https://doi.org/10.48550/ARXIV.2504.19979","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2504.19979","authorSignatures":[{}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2504-19979","documentUrl":"https://doi.org/10.48550/ARXIV.2504.19979"},{"key":"journals/corr/abs-2508-17198","title":"From reactive to cognitive: brain-inspired spatial intelligence for embodied agents.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2508.17198"],"source":"https://dblp.org/rec/journals/corr/abs-2508-17198","documentPage":"https://doi.org/10.48550/ARXIV.2508.17198","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2508.17198","authorSignatures":[{}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-17198","documentUrl":"https://doi.org/10.48550/ARXIV.2508.17198"},{"key":"journals/corr/abs-2509-17609","title":"Audio Super-Resolution with Latent Bridge Models.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2509.17609"],"source":"https://dblp.org/rec/journals/corr/abs-2509-17609","documentPage":"https://doi.org/10.48550/ARXIV.2509.17609","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2509.17609","authorSignatures":[{}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-17609","documentUrl":"https://doi.org/10.48550/ARXIV.2509.17609"},{"key":"journals/cphysics/ZhangJCWLLXW25","title":"Combining physics-informed graph neural network and finite difference for solving forward and inverse spatiotemporal PDEs.","year":2025,"yearOfEvent":null,"venue":"Comput. Phys. Commun.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1016/J.CPC.2024.109462"],"source":"https://dblp.org/rec/journals/cphysics/ZhangJCWLLXW25","documentPage":"https://doi.org/10.1016/J.CPC.2024.109462","type":"Article","doi":"https://doi.org/10.1016/J.CPC.2024.109462","authorSignatures":[{"orcid":"https://orcid.org/0000-0002-3768-8668","inst":"https://dblp.org/inst/12/733","instLabel":"China Academy of Engineering Physics (CAEP)"}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/cphysics/ZhangJCWLLXW25","documentUrl":"https://doi.org/10.1016/J.CPC.2024.109462"},{"key":"journals/gsis/XiaoSGYW25","title":"An intelligent partial charging navigation strategy for electric vehicles.","year":2025,"yearOfEvent":null,"venue":"Geo spatial Inf. Sci.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1080/10095020.2024.2336596"],"source":"https://dblp.org/rec/journals/gsis/XiaoSGYW25","documentPage":"https://doi.org/10.1080/10095020.2024.2336596","type":"Article","doi":"https://doi.org/10.1080/10095020.2024.2336596","authorSignatures":[{}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/gsis/XiaoSGYW25","documentUrl":"https://doi.org/10.1080/10095020.2024.2336596"},{"key":"journals/iotj/XingMWYGC25","title":"Toward Visual Interaction: Hand Segmentation by Combining 3-D Graph Deep Learning and Laser Point Cloud for Intelligent Rehabilitation.","year":2025,"yearOfEvent":null,"venue":"IEEE Internet Things J.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1109/JIOT.2025.3546874"],"source":"https://dblp.org/rec/journals/iotj/XingMWYGC25","documentPage":"https://doi.org/10.1109/JIOT.2025.3546874","type":"Article","doi":"https://doi.org/10.1109/JIOT.2025.3546874","authorSignatures":[{"inst":"https://dblp.org/inst/7/465","instLabel":"Kunming Medical University (KMU)"}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/iotj/XingMWYGC25","documentUrl":"https://doi.org/10.1109/JIOT.2025.3546874"},{"key":"journals/prl/LiuXDZWDZS25","title":"RobustPrompt: Learning to defend against adversarial attacks with adaptive visual prompts.","year":2025,"yearOfEvent":null,"venue":"Pattern Recognit. Lett.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1016/J.PATREC.2025.02.015"],"source":"https://dblp.org/rec/journals/prl/LiuXDZWDZS25","documentPage":"https://doi.org/10.1016/J.PATREC.2025.02.015","type":"Article","doi":"https://doi.org/10.1016/J.PATREC.2025.02.015","authorSignatures":[{"inst":"https://dblp.org/inst/1/155","instLabel":"Tsinghua University (THU)"}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/prl/LiuXDZWDZS25","documentUrl":"https://doi.org/10.1016/J.PATREC.2025.02.015"},{"key":"journals/tits/LinWDSC25","title":"Optimizing Ride-Sharing Routing: A Demand-Aware Approach.","year":2025,"yearOfEvent":null,"venue":"IEEE Trans. Intell. Transp. Syst.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1109/TITS.2025.3582629"],"source":"https://dblp.org/rec/journals/tits/LinWDSC25","documentPage":"https://doi.org/10.1109/TITS.2025.3582629","type":"Article","doi":"https://doi.org/10.1109/TITS.2025.3582629","authorSignatures":[{"inst":"https://dblp.org/inst/8/375","instLabel":"City University of Hong Kong"}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/tits/LinWDSC25","documentUrl":"https://doi.org/10.1109/TITS.2025.3582629"},{"key":"journals/tjs/QiWFGG25","title":"Improved qARM algorithm for frequent itemsets search in large-scale data sets.","year":2025,"yearOfEvent":null,"venue":"J. Supercomput.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1007/S11227-025-07209-7"],"source":"https://dblp.org/rec/journals/tjs/QiWFGG25","documentPage":"https://doi.org/10.1007/S11227-025-07209-7","type":"Article","doi":"https://doi.org/10.1007/S11227-025-07209-7","authorSignatures":[{"inst":"https://dblp.org/inst/6/582","instLabel":"Shenyang Aerospace University (SAU)"}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/tjs/QiWFGG25","documentUrl":"https://doi.org/10.1007/S11227-025-07209-7"},{"key":"journals/tog/ZhongZWYLLZ25","title":"Waste-to-Value: Reutilized Material Maximization for Additive and Subtractive Hybrid Remanufacturing.","year":2025,"yearOfEvent":null,"venue":"ACM Trans. Graph.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1145/3763313"],"source":"https://dblp.org/rec/journals/tog/ZhongZWYLLZ25","documentPage":"https://doi.org/10.1145/3763313","type":"Article","doi":"https://doi.org/10.1145/3763313","authorSignatures":[{"orcid":"https://orcid.org/0009-0003-5533-4315","inst":"https://dblp.org/inst/1/678","instLabel":"Shandong University (SDU)"}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/tog/ZhongZWYLLZ25","documentUrl":"https://doi.org/10.1145/3763313"}],"retrievedAt":"2026-10-19","querySource":"https://sparql.dblp.org/","method":"DBLP yearOfPublication=2025; Article + Inproceedings; excludes Informal/CoRR and explicit editorial/correction/erratum/preface; unique DBLP record keys within person.","verifiedLowerBound2025":5,"conferenceLowerBound2025":3,"journalLowerBound2025":2,"labName":null,"labUrl":null,"labEvidence":"本人主页及本轮清华官方资料仅出现本人课题组，未取得可核实的当前实验室专名；不把本科暑研导师实验室当作当前组。","labSourceUrl":"https://lywang3081.github.io/","affiliationZh":"清华大学","sourceWarning":false,"knownPreprintMinimum2025":5,"excludedMisattributed":[],"knownMinimum2025":5,"displayNotes":"该 DBLP 档案混有其他同名作者，剩余候选尚未逐篇核完，全年总数暂不给出。目前已逐篇核实 5 条，只作下界参考，不进入合计、中位数或排序。","labDisplayNotes":"本人主页与清华资料只提到其课题组，未见专名；本科暑期科研导师的实验室不作为当前团队。图中以「姓名及合作者」单列。"},{"index":88,"name":"Pengshuai Wang","nameZh":"王鹏帅","affiliation":"Peking University","source":"DBLP Knowledge Graph official SPARQL API","profileUrl":"https://dblp.org/pid/171/6817","identifier":"171/6817","identityEvidence":[{"url":"https://dblp.org/pid/171/6817","evidence":"DBLP curated profile affiliations: Microsoft Research Asia, Beijing, China; Peking University, Institute of Computer Technology, Beijing, China; Tsinghua University, Institute for Advanced Study, Beijing, China."},{"url":"https://dblp.org/pid/171/6817","evidence":"DBLP curated profile homepages: https://wang-ps.github.io/."}],"count2025":5,"conference2025":3,"journal2025":2,"preprint2025":3,"status":"verified","notes":"Counts are DBLP indexed coauthored records, not first-author counts, laboratory totals, unique scientific discoveries, or quality assessments. DBLP yearOfPublication=2025; yearOfEvent retained and can differ. Conference workshops are included. Preprints are separate and may overlap formal versions.","papers":[{"key":"conf/siggraph/WeiWZCW25","title":"OctGPT: Octree-based Multiscale Autoregressive Models for 3D Shape Generation.","year":2025,"yearOfEvent":2025,"venue":"SIGGRAPH (Conference Paper Track)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1145/3721238.3730601"],"source":"https://dblp.org/rec/conf/siggraph/WeiWZCW25","documentPage":"https://doi.org/10.1145/3721238.3730601","type":"Inproceedings","doi":"https://doi.org/10.1145/3721238.3730601","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/siggraph/WeiWZCW25","documentUrl":"https://doi.org/10.1145/3721238.3730601"},{"key":"conf/siggraph/ZhongWWLZ25","title":"DeepMill: Neural Accessibility Learning for Subtractive Manufacturing.","year":2025,"yearOfEvent":2025,"venue":"SIGGRAPH (Conference Paper Track)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1145/3721238.3730657"],"source":"https://dblp.org/rec/conf/siggraph/ZhongWWLZ25","documentPage":"https://doi.org/10.1145/3721238.3730657","type":"Inproceedings","doi":"https://doi.org/10.1145/3721238.3730657","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/siggraph/ZhongWWLZ25","documentUrl":"https://doi.org/10.1145/3721238.3730657"},{"key":"conf/siggrapha/WangTCW25","title":"Neural Visibility of Point Sets.","year":2025,"yearOfEvent":2025,"venue":"SIGGRAPH Asia","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1145/3757377.3763869"],"source":"https://dblp.org/rec/conf/siggrapha/WangTCW25","documentPage":"https://doi.org/10.1145/3757377.3763869","type":"Inproceedings","doi":"https://doi.org/10.1145/3757377.3763869","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/siggrapha/WangTCW25","documentUrl":"https://doi.org/10.1145/3757377.3763869"},{"key":"journals/cgf/XiongWZCLW25","title":"OctFusion: Octree-based Diffusion Models for 3D Shape Generation.","year":2025,"yearOfEvent":null,"venue":"Comput. Graph. Forum","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1111/CGF.70198"],"source":"https://dblp.org/rec/journals/cgf/XiongWZCLW25","documentPage":"https://doi.org/10.1111/CGF.70198","type":"Article","doi":"https://doi.org/10.1111/CGF.70198","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/cgf/XiongWZCLW25","documentUrl":"https://doi.org/10.1111/CGF.70198"},{"key":"journals/cvm/YangGXLPWTG25","title":"Swin3D: A Pretrained Transformer Backbone for 3D Indoor Scene Understanding.","year":2025,"yearOfEvent":null,"venue":"Comput. Vis. Media","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.26599/CVM.2025.9450383"],"source":"https://dblp.org/rec/journals/cvm/YangGXLPWTG25","documentPage":"https://doi.org/10.26599/CVM.2025.9450383","type":"Article","doi":"https://doi.org/10.26599/CVM.2025.9450383","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/cvm/YangGXLPWTG25","documentUrl":"https://doi.org/10.26599/CVM.2025.9450383"}],"preprints":[{"key":"journals/corr/abs-2502-06093","title":"DeepMill: Neural Accessibility Learning for Subtractive Manufacturing.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2502.06093"],"source":"https://dblp.org/rec/journals/corr/abs-2502-06093","documentPage":"https://doi.org/10.48550/ARXIV.2502.06093","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2502.06093","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2502-06093","documentUrl":"https://doi.org/10.48550/ARXIV.2502.06093","arxivId":"2502.06093","arxivUrl":"https://arxiv.org/abs/2502.06093"},{"key":"journals/corr/abs-2504-09975","title":"OctGPT: Octree-based Multiscale Autoregressive Models for 3D Shape Generation.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2504.09975"],"source":"https://dblp.org/rec/journals/corr/abs-2504-09975","documentPage":"https://doi.org/10.48550/ARXIV.2504.09975","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2504.09975","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2504-09975","documentUrl":"https://doi.org/10.48550/ARXIV.2504.09975","arxivId":"2504.09975","arxivUrl":"https://arxiv.org/abs/2504.09975"},{"key":"journals/corr/abs-2509-24150","title":"Neural Visibility of Point Sets.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2509.24150"],"source":"https://dblp.org/rec/journals/corr/abs-2509-24150","documentPage":"https://doi.org/10.48550/ARXIV.2509.24150","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2509.24150","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-24150","documentUrl":"https://doi.org/10.48550/ARXIV.2509.24150","arxivId":"2509.24150","arxivUrl":"https://arxiv.org/abs/2509.24150"}],"excludedFormal":[],"excludedOther":[],"excludedHomonyms":[],"unassignedCandidates":[],"retrievedAt":"2026-10-19","querySource":"https://sparql.dblp.org/","method":"DBLP yearOfPublication=2025; Article + Inproceedings; excludes Informal/CoRR and explicit editorial/correction/erratum/preface; unique DBLP record keys within person.","labName":"Spatial Intelligence Group（SIG）","labUrl":null,"labEvidence":"本人主页明确表示自己领导北京大学 Spatial Intelligence Group (SIG)。未见单独实验室首页，链接留空。","labSourceUrl":"https://wang-ps.github.io/","affiliationZh":"北京大学","sourceWarning":false,"knownPreprintMinimum2025":null,"excludedMisattributed":[],"displayNotes":"身份已经个人或机构主页核对。2025 年正式记录 5 条（会议 3、期刊 2），所有作者位置均计入；预印本 3 条单列，不加总。","labDisplayNotes":"本人主页写明其领导北京大学 Spatial Intelligence Group（SIG），据此归组；未见独立网址。它与 CMU Minchen Li 的 Simulation Intelligence Group 是不同团队。"},{"index":89,"name":"Xinggang Wang","nameZh":"王兴刚","affiliation":"Huazhong University of Science and Technology","source":"DBLP Knowledge Graph official SPARQL API","profileUrl":"https://dblp.org/pid/95/3056","identifier":"95/3056","identityEvidence":[{"url":"https://dblp.org/pid/95/3056","evidence":"DBLP curated profile homepages: https://openreview.net/profile?id=~Xinggang_Wang1."},{"url":"https://xwcv.github.io","evidence":"Personal site links directly to DBLP PID 95/3056 and ORCID 0000-0001-6732-7823."},{"url":"https://sites.google.com/site/cvxwang/home","evidence":"Personal faculty page identifies HUST professor Xinggang Wang."},{"url":"https://dblp.org/rec/conf/cvpr/YaoYW25","evidence":"DBLP paper author signature connects this profile to Huazhong University of Science and Technology (HUST)."},{"url":"https://dblp.org/rec/journals/ijcv/LiaoCZJZLHW25","evidence":"DBLP paper author signature connects this profile to Huazhong University of Science and Technology (HUST) and https://orcid.org/0000-0001-6732-7823."}],"count2025":36,"conference2025":23,"journal2025":13,"preprint2025":39,"status":"verified","notes":"Counts are DBLP indexed coauthored records, not first-author counts, laboratory totals, unique scientific discoveries, or quality assessments. DBLP yearOfPublication=2025; yearOfEvent retained and can differ. Conference workshops are included. Preprints are separate and may overlap formal versions.","papers":[{"key":"conf/aaai/LiaoWZZH25","title":"ViG: Linear-complexity Visual Sequence Learning with Gated Linear Attention.","year":2025,"yearOfEvent":2025,"venue":"AAAI","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1609/AAAI.V39I5.32550"],"source":"https://dblp.org/rec/conf/aaai/LiaoWZZH25","documentPage":"https://doi.org/10.1609/AAAI.V39I5.32550","type":"Inproceedings","doi":"https://doi.org/10.1609/AAAI.V39I5.32550","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/aaai/LiaoWZZH25","documentUrl":"https://doi.org/10.1609/AAAI.V39I5.32550"},{"key":"conf/aaai/XuZ0W25","title":"GaraMoSt: Parallel Multi-Granularity Motion and Structural Modeling for Efficient Multi-Frame Interpolation in DSA Images.","year":2025,"yearOfEvent":2025,"venue":"AAAI","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1609/AAAI.V39I27.35076"],"source":"https://dblp.org/rec/conf/aaai/XuZ0W25","documentPage":"https://doi.org/10.1609/AAAI.V39I27.35076","type":"Inproceedings","doi":"https://doi.org/10.1609/AAAI.V39I27.35076","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/aaai/XuZ0W25","documentUrl":"https://doi.org/10.1609/AAAI.V39I27.35076"},{"key":"conf/cvpr/JiangLCWLS0W25","title":"GaussTR: Foundation Model-Aligned Gaussian Transformer for Self-Supervised 3D Spatial Understanding.","year":2025,"yearOfEvent":2025,"venue":"CVPR","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/CVPR52734.2025.01117"],"source":"https://dblp.org/rec/conf/cvpr/JiangLCWLS0W25","documentPage":"https://openaccess.thecvf.com/content/CVPR2025/html/Jiang_GaussTR_Foundation_Model-Aligned_Gaussian_Transformer_for_Self-Supervised_3D_Spatial_Understanding_CVPR_2025_paper.html","type":"Inproceedings","doi":"https://doi.org/10.1109/CVPR52734.2025.01117","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/JiangLCWLS0W25","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Jiang_GaussTR_Foundation_Model-Aligned_Gaussian_Transformer_for_Self-Supervised_3D_Spatial_Understanding_CVPR_2025_paper.html"},{"key":"conf/cvpr/LiaoCY0WYZLZZW25","title":"DiffusionDrive: Truncated Diffusion Model for End-to-End Autonomous Driving.","year":2025,"yearOfEvent":2025,"venue":"CVPR","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/CVPR52734.2025.01124"],"source":"https://dblp.org/rec/conf/cvpr/LiaoCY0WYZLZZW25","documentPage":"https://openaccess.thecvf.com/content/CVPR2025/html/Liao_DiffusionDrive_Truncated_Diffusion_Model_for_End-to-End_Autonomous_Driving_CVPR_2025_paper.html","type":"Inproceedings","doi":"https://doi.org/10.1109/CVPR52734.2025.01124","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/LiaoCY0WYZLZZW25","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Liao_DiffusionDrive_Truncated_Diffusion_Model_for_End-to-End_Autonomous_Driving_CVPR_2025_paper.html"},{"key":"conf/cvpr/LiC00W25","title":"Mask-Adapter: The Devil is in the Masks for Open-Vocabulary Segmentation.","year":2025,"yearOfEvent":2025,"venue":"CVPR","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/CVPR52734.2025.01397"],"source":"https://dblp.org/rec/conf/cvpr/LiC00W25","documentPage":"https://openaccess.thecvf.com/content/CVPR2025/html/Li_Mask-Adapter_The_Devil_is_in_the_Masks_for_Open-Vocabulary_Segmentation_CVPR_2025_paper.html","type":"Inproceedings","doi":"https://doi.org/10.1109/CVPR52734.2025.01397","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/LiC00W25","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Li_Mask-Adapter_The_Devil_is_in_the_Masks_for_Open-Vocabulary_Segmentation_CVPR_2025_paper.html"},{"key":"conf/cvpr/YaoYW25","title":"Reconstruction vs. Generation: Taming Optimization Dilemma in Latent Diffusion Models.","year":2025,"yearOfEvent":2025,"venue":"CVPR","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/CVPR52734.2025.01464"],"source":"https://dblp.org/rec/conf/cvpr/YaoYW25","documentPage":"https://openaccess.thecvf.com/content/CVPR2025/html/Yao_Reconstruction_vs._Generation_Taming_Optimization_Dilemma_in_Latent_Diffusion_Models_CVPR_2025_paper.html","type":"Inproceedings","doi":"https://doi.org/10.1109/CVPR52734.2025.01464","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/YaoYW25","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Yao_Reconstruction_vs._Generation_Taming_Optimization_Dilemma_in_Latent_Diffusion_Models_CVPR_2025_paper.html"},{"key":"conf/cvpr/ZhuHLLYFW25","title":"DiG: Scalable and Efficient Diffusion Models with Gated Linear Attention.","year":2025,"yearOfEvent":2025,"venue":"CVPR","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/CVPR52734.2025.00718"],"source":"https://dblp.org/rec/conf/cvpr/ZhuHLLYFW25","documentPage":"https://openaccess.thecvf.com/content/CVPR2025/html/Zhu_DiG_Scalable_and_Efficient_Diffusion_Models_with_Gated_Linear_Attention_CVPR_2025_paper.html","type":"Inproceedings","doi":"https://doi.org/10.1109/CVPR52734.2025.00718","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/ZhuHLLYFW25","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Zhu_DiG_Scalable_and_Efficient_Diffusion_Models_with_Gated_Linear_Attention_CVPR_2025_paper.html"},{"key":"conf/eccv/ChenFHYZXWDXT24","title":"Cascade-Zero123: One Image to Highly Consistent 3D with Self-prompted Nearby Views.","year":2025,"yearOfEvent":2024,"venue":"ECCV (41)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1007/978-3-031-72940-9_18"],"source":"https://dblp.org/rec/conf/eccv/ChenFHYZXWDXT24","documentPage":"https://doi.org/10.1007/978-3-031-72940-9_18","type":"Inproceedings","doi":"https://doi.org/10.1007/978-3-031-72940-9_18","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/eccv/ChenFHYZXWDXT24","documentUrl":"https://doi.org/10.1007/978-3-031-72940-9_18"},{"key":"conf/eccv/LiaoCJCZLHW24","title":"Lane Graph as Path: Continuity-Preserving Path-Wise Modeling for Online Lane Graph Construction.","year":2025,"yearOfEvent":2024,"venue":"ECCV (44)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1007/978-3-031-72784-9_19"],"source":"https://dblp.org/rec/conf/eccv/LiaoCJCZLHW24","documentPage":"https://doi.org/10.1007/978-3-031-72784-9_19","type":"Inproceedings","doi":"https://doi.org/10.1007/978-3-031-72784-9_19","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/eccv/LiaoCJCZLHW24","documentUrl":"https://doi.org/10.1007/978-3-031-72784-9_19"},{"key":"conf/eccv/ShiCZLW24","title":"Occupancy as Set of Points.","year":2025,"yearOfEvent":2024,"venue":"ECCV (61)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1007/978-3-031-73030-6_5"],"source":"https://dblp.org/rec/conf/eccv/ShiCZLW24","documentPage":"https://doi.org/10.1007/978-3-031-73030-6_5","type":"Inproceedings","doi":"https://doi.org/10.1007/978-3-031-73030-6_5","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/eccv/ShiCZLW24","documentUrl":"https://doi.org/10.1007/978-3-031-73030-6_5"},{"key":"conf/eccv/WangMZWFXX24","title":"Towards Dual Transparent Liquid Level Estimation in Biomedical Lab: Dataset, Methods and Practices.","year":2025,"yearOfEvent":2024,"venue":"ECCV (65)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1007/978-3-031-73650-6_12"],"source":"https://dblp.org/rec/conf/eccv/WangMZWFXX24","documentPage":"https://doi.org/10.1007/978-3-031-73650-6_12","type":"Inproceedings","doi":"https://doi.org/10.1007/978-3-031-73650-6_12","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/eccv/WangMZWFXX24","documentUrl":"https://doi.org/10.1007/978-3-031-73650-6_12"},{"key":"conf/eccv/WuHZW24","title":"Co-Student: Collaborating Strong and Weak Students for Sparsely Annotated Object Detection.","year":2025,"yearOfEvent":2024,"venue":"ECCV (47)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1007/978-3-031-72970-6_26"],"source":"https://dblp.org/rec/conf/eccv/WuHZW24","documentPage":"https://doi.org/10.1007/978-3-031-72970-6_26","type":"Inproceedings","doi":"https://doi.org/10.1007/978-3-031-72970-6_26","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/eccv/WuHZW24","documentUrl":"https://doi.org/10.1007/978-3-031-72970-6_26"},{"key":"conf/eccv/XiongFWL24","title":"Causality-Inspired Discriminative Feature Learning in Triple Domains for Gait Recognition.","year":2025,"yearOfEvent":2024,"venue":"ECCV (54)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1007/978-3-031-72949-2_15"],"source":"https://dblp.org/rec/conf/eccv/XiongFWL24","documentPage":"https://doi.org/10.1007/978-3-031-72949-2_15","type":"Inproceedings","doi":"https://doi.org/10.1007/978-3-031-72949-2_15","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/eccv/XiongFWL24","documentUrl":"https://doi.org/10.1007/978-3-031-72949-2_15"},{"key":"conf/eccv/ZhuLGLWWHYY24","title":"Visual Text Generation in the Wild.","year":2025,"yearOfEvent":2024,"venue":"ECCV (53)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1007/978-3-031-73668-1_6"],"source":"https://dblp.org/rec/conf/eccv/ZhuLGLWWHYY24","documentPage":"https://doi.org/10.1007/978-3-031-73668-1_6","type":"Inproceedings","doi":"https://doi.org/10.1007/978-3-031-73668-1_6","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/eccv/ZhuLGLWWHYY24","documentUrl":"https://doi.org/10.1007/978-3-031-73668-1_6"},{"key":"conf/iccv/HuZZCLLRCLW25","title":"GroundingSuite: Measuring Complex Multi-Granular Pixel Grounding.","year":2025,"yearOfEvent":2025,"venue":"ICCV","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/ICCV51701.2025.02145"],"source":"https://dblp.org/rec/conf/iccv/HuZZCLLRCLW25","documentPage":"https://doi.org/10.1109/ICCV51701.2025.02145","type":"Inproceedings","doi":"https://doi.org/10.1109/ICCV51701.2025.02145","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/HuZZCLLRCLW25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.02145"},{"key":"conf/iccv/LiLLW25","title":"MaTVLM: Hybrid Mamba-Transformer for Efficient Vision-Language Modeling.","year":2025,"yearOfEvent":2025,"venue":"ICCV","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/ICCV51701.2025.01941"],"source":"https://dblp.org/rec/conf/iccv/LiLLW25","documentPage":"https://doi.org/10.1109/ICCV51701.2025.01941","type":"Inproceedings","doi":"https://doi.org/10.1109/ICCV51701.2025.01941","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/LiLLW25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.01941"},{"key":"conf/iclr/LiCCSSR00W25","title":"ControlAR: Controllable Image Generation with Autoregressive Models.","year":2025,"yearOfEvent":2025,"venue":"ICLR","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/iclr/LiCCSSR00W25","documentPage":"https://openreview.net/forum?id=BWuBDdXVnH","type":"Inproceedings","doi":null,"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iclr/LiCCSSR00W25","documentUrl":"https://openreview.net/forum?id=BWuBDdXVnH"},{"key":"conf/iclr/ZhuWW25","title":"JudgeLM: Fine-tuned Large Language Models are Scalable Judges.","year":2025,"yearOfEvent":2025,"venue":"ICLR","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/iclr/ZhuWW25","documentPage":"https://openreview.net/forum?id=xsELpEPn4A","type":"Inproceedings","doi":null,"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iclr/ZhuWW25","documentUrl":"https://openreview.net/forum?id=xsELpEPn4A"},{"key":"conf/icmcs/DengXFWL25","title":"STP4D: Spatio-Temporal-Prompt Consistent Modeling for Text-To-4D Gaussian Splatting.","year":2025,"yearOfEvent":2025,"venue":"ICME","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/ICME59968.2025.11209788"],"source":"https://dblp.org/rec/conf/icmcs/DengXFWL25","documentPage":"https://doi.org/10.1109/ICME59968.2025.11209788","type":"Inproceedings","doi":"https://doi.org/10.1109/ICME59968.2025.11209788","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/icmcs/DengXFWL25","documentUrl":"https://doi.org/10.1109/ICME59968.2025.11209788"},{"key":"conf/mm/ZhangWXW0025","title":"Dynamic 2D Gaussians: Geometrically Accurate Radiance Fields for Dynamic Objects.","year":2025,"yearOfEvent":2025,"venue":"ACM Multimedia","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1145/3746027.3755328"],"source":"https://dblp.org/rec/conf/mm/ZhangWXW0025","documentPage":"https://doi.org/10.1145/3746027.3755328","type":"Inproceedings","doi":"https://doi.org/10.1145/3746027.3755328","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/mm/ZhangWXW0025","documentUrl":"https://doi.org/10.1145/3746027.3755328"},{"key":"conf/nips/GaoCJLSGPYLZZLZ25","title":"RAD: Training an End-to-End Driving Policy via Large-Scale 3DGS-based Reinforcement Learning.","year":2025,"yearOfEvent":2025,"venue":"NeurIPS","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/nips/GaoCJLSGPYLZZLZ25","documentPage":"http://papers.nips.cc/paper_files/paper/2025/hash/2ed3a566a0af6dcec424b988f1880ecc-Abstract-Conference.html","type":"Inproceedings","doi":null,"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/nips/GaoCJLSGPYLZZLZ25","documentUrl":"http://papers.nips.cc/paper_files/paper/2025/hash/2ed3a566a0af6dcec424b988f1880ecc-Abstract-Conference.html"},{"key":"conf/nips/GuoWXXZXXSWCYLW25","title":"Genesis: Multimodal Driving Scene Generation with Spatio-Temporal and Cross-Modal Consistency.","year":2025,"yearOfEvent":2025,"venue":"NeurIPS","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/nips/GuoWXXZXXSWCYLW25","documentPage":"http://papers.nips.cc/paper_files/paper/2025/hash/571082ea18d30060177dfcaf662ff0e5-Abstract-Conference.html","type":"Inproceedings","doi":null,"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/nips/GuoWXXZXXSWCYLW25","documentUrl":"http://papers.nips.cc/paper_files/paper/2025/hash/571082ea18d30060177dfcaf662ff0e5-Abstract-Conference.html"},{"key":"conf/nips/ZhaoHFW25","title":"SuperCLIP: CLIP with Simple Classification Supervision.","year":2025,"yearOfEvent":2025,"venue":"NeurIPS","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/nips/ZhaoHFW25","documentPage":"http://papers.nips.cc/paper_files/paper/2025/hash/aadaedf7fc275bf68ad217bf1b38626e-Abstract-Conference.html","type":"Inproceedings","doi":null,"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/nips/ZhaoHFW25","documentUrl":"http://papers.nips.cc/paper_files/paper/2025/hash/aadaedf7fc275bf68ad217bf1b38626e-Abstract-Conference.html"},{"key":"journals/ijcv/LiaoCZJZLHW25","title":"MapTRv2: An End-to-End Framework for Online Vectorized HD Map Construction.","year":2025,"yearOfEvent":null,"venue":"Int. J. Comput. Vis.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1007/S11263-024-02235-Z"],"source":"https://dblp.org/rec/journals/ijcv/LiaoCZJZLHW25","documentPage":"https://doi.org/10.1007/S11263-024-02235-Z","type":"Article","doi":"https://doi.org/10.1007/S11263-024-02235-Z","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/ijcv/LiaoCZJZLHW25","documentUrl":"https://doi.org/10.1007/S11263-024-02235-Z"},{"key":"journals/ijcv/ZhangCLWH25","title":"Mamba Capsule Routing Towards Part-Whole Relational Camouflaged Object Detection.","year":2025,"yearOfEvent":null,"venue":"Int. J. Comput. Vis.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1007/S11263-025-02530-3"],"source":"https://dblp.org/rec/journals/ijcv/ZhangCLWH25","documentPage":"https://doi.org/10.1007/S11263-025-02530-3","type":"Article","doi":"https://doi.org/10.1007/S11263-025-02530-3","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/ijcv/ZhangCLWH25","documentUrl":"https://doi.org/10.1007/S11263-025-02530-3"},{"key":"journals/ijcv/ZhaoHZYDWWLF25","title":"Skim then Focus: Integrating Contextual and Fine-grained Views for Repetitive Action Counting.","year":2025,"yearOfEvent":null,"venue":"Int. J. Comput. Vis.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1007/S11263-025-02471-X"],"source":"https://dblp.org/rec/journals/ijcv/ZhaoHZYDWWLF25","documentPage":"https://doi.org/10.1007/S11263-025-02471-X","type":"Article","doi":"https://doi.org/10.1007/S11263-025-02471-X","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/ijcv/ZhaoHZYDWWLF25","documentUrl":"https://doi.org/10.1007/S11263-025-02471-X"},{"key":"journals/ijcv/ZhuWFCLJZH25","title":"WeakCLIP: Adapting CLIP for Weakly-Supervised Semantic Segmentation.","year":2025,"yearOfEvent":null,"venue":"Int. J. Comput. Vis.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1007/S11263-024-02224-2"],"source":"https://dblp.org/rec/journals/ijcv/ZhuWFCLJZH25","documentPage":"https://doi.org/10.1007/S11263-024-02224-2","type":"Article","doi":"https://doi.org/10.1007/S11263-024-02224-2","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/ijcv/ZhuWFCLJZH25","documentUrl":"https://doi.org/10.1007/S11263-024-02224-2"},{"key":"journals/ijcv/ZouLZLW25","title":"MIM4D: Masked Modeling with Multi-View Video for Autonomous Driving Representation Learning.","year":2025,"yearOfEvent":null,"venue":"Int. J. Comput. Vis.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1007/S11263-025-02464-W"],"source":"https://dblp.org/rec/journals/ijcv/ZouLZLW25","documentPage":"https://doi.org/10.1007/S11263-025-02464-W","type":"Article","doi":"https://doi.org/10.1007/S11263-025-02464-W","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/ijcv/ZouLZLW25","documentUrl":"https://doi.org/10.1007/S11263-025-02464-W"},{"key":"journals/ivc/ChenWCZHL25","title":"PolarDETR: Polar Parametrization for vision-based surround-view 3D detection.","year":2025,"yearOfEvent":null,"venue":"Image Vis. Comput.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1016/J.IMAVIS.2025.105438"],"source":"https://dblp.org/rec/journals/ivc/ChenWCZHL25","documentPage":"https://doi.org/10.1016/J.IMAVIS.2025.105438","type":"Article","doi":"https://doi.org/10.1016/J.IMAVIS.2025.105438","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/ivc/ChenWCZHL25","documentUrl":"https://doi.org/10.1016/J.IMAVIS.2025.105438"},{"key":"journals/ivc/XiongFWWL25","title":"MambaGait: Gait recognition approach combining explicit representation and implicit state space model.","year":2025,"yearOfEvent":null,"venue":"Image Vis. Comput.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1016/J.IMAVIS.2025.105597"],"source":"https://dblp.org/rec/journals/ivc/XiongFWWL25","documentPage":"https://doi.org/10.1016/J.IMAVIS.2025.105597","type":"Article","doi":"https://doi.org/10.1016/J.IMAVIS.2025.105597","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/ivc/XiongFWWL25","documentUrl":"https://doi.org/10.1016/J.IMAVIS.2025.105597"},{"key":"journals/mva/ChengWLL25","title":"Cross-layer attentive feature upsampling for low-latency semantic segmentation.","year":2025,"yearOfEvent":null,"venue":"Mach. Vis. Appl.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1007/S00138-024-01631-2"],"source":"https://dblp.org/rec/journals/mva/ChengWLL25","documentPage":"https://doi.org/10.1007/S00138-024-01631-2","type":"Article","doi":"https://doi.org/10.1007/S00138-024-01631-2","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/mva/ChengWLL25","documentUrl":"https://doi.org/10.1007/S00138-024-01631-2"},{"key":"journals/mva/HuWL25","title":"Personvit: large-scale self-supervised vision transformer for person re-identification.","year":2025,"yearOfEvent":null,"venue":"Mach. Vis. Appl.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1007/S00138-025-01659-Y"],"source":"https://dblp.org/rec/journals/mva/HuWL25","documentPage":"https://doi.org/10.1007/S00138-025-01659-Y","type":"Article","doi":"https://doi.org/10.1007/S00138-025-01659-Y","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/mva/HuWL25","documentUrl":"https://doi.org/10.1007/S00138-025-01659-Y"},{"key":"journals/npjdm/YaoWSZMCLW25","title":"EVA-X: a foundation model for general chest x-ray analysis with self-supervised learning.","year":2025,"yearOfEvent":null,"venue":"npj Digit. Medicine","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1038/S41746-025-02032-Z"],"source":"https://dblp.org/rec/journals/npjdm/YaoWSZMCLW25","documentPage":"https://doi.org/10.1038/S41746-025-02032-Z","type":"Article","doi":"https://doi.org/10.1038/S41746-025-02032-Z","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/npjdm/YaoWSZMCLW25","documentUrl":"https://doi.org/10.1038/S41746-025-02032-Z"},{"key":"journals/ral/ZhangYHWWZL25","title":"M${}^{3}$Bench: Benchmarking Whole-Body Motion Generation for Mobile Manipulation in 3D Scenes.","year":2025,"yearOfEvent":null,"venue":"IEEE Robotics Autom. Lett.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1109/LRA.2025.3575013"],"source":"https://dblp.org/rec/journals/ral/ZhangYHWWZL25","documentPage":"https://doi.org/10.1109/LRA.2025.3575013","type":"Article","doi":"https://doi.org/10.1109/LRA.2025.3575013","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/ral/ZhangYHWWZL25","documentUrl":"https://doi.org/10.1109/LRA.2025.3575013"},{"key":"journals/tcsv/LiuWWLB25","title":"SparseTrack: Multi-Object Tracking by Performing Scene Decomposition Based on Pseudo-Depth.","year":2025,"yearOfEvent":null,"venue":"IEEE Trans. Circuits Syst. Video Technol.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1109/TCSVT.2024.3524670"],"source":"https://dblp.org/rec/journals/tcsv/LiuWWLB25","documentPage":"https://doi.org/10.1109/TCSVT.2024.3524670","type":"Article","doi":"https://doi.org/10.1109/TCSVT.2024.3524670","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/tcsv/LiuWWLB25","documentUrl":"https://doi.org/10.1109/TCSVT.2024.3524670"},{"key":"journals/titb/ZhangZZWZWL25","title":"TOGS: Gaussian Splatting With Temporal Opacity Offset for Real-Time 4D DSA Rendering.","year":2025,"yearOfEvent":null,"venue":"IEEE J. Biomed. Health Informatics","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1109/JBHI.2025.3575613"],"source":"https://dblp.org/rec/journals/titb/ZhangZZWZWL25","documentPage":"https://doi.org/10.1109/JBHI.2025.3575613","type":"Article","doi":"https://doi.org/10.1109/JBHI.2025.3575613","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/titb/ZhangZZWZWL25","documentUrl":"https://doi.org/10.1109/JBHI.2025.3575613"}],"preprints":[{"key":"journals/corr/abs-2501-01423","title":"Reconstruction vs. Generation: Taming Optimization Dilemma in Latent Diffusion Models.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2501.01423"],"source":"https://dblp.org/rec/journals/corr/abs-2501-01423","documentPage":"https://doi.org/10.48550/ARXIV.2501.01423","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2501.01423","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2501-01423","documentUrl":"https://doi.org/10.48550/ARXIV.2501.01423","arxivId":"2501.01423","arxivUrl":"https://arxiv.org/abs/2501.01423"},{"key":"journals/corr/abs-2501-02962","title":"SceneVTG++: Controllable Multilingual Visual Text Generation in the Wild.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2501.02962"],"source":"https://dblp.org/rec/journals/corr/abs-2501-02962","documentPage":"https://doi.org/10.48550/ARXIV.2501.02962","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2501.02962","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2501-02962","documentUrl":"https://doi.org/10.48550/ARXIV.2501.02962","arxivId":"2501.02962","arxivUrl":"https://arxiv.org/abs/2501.02962"},{"key":"journals/corr/abs-2502-13144","title":"RAD: Training an End-to-End Driving Policy via Large-Scale 3DGS-based Reinforcement Learning.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2502.13144"],"source":"https://dblp.org/rec/journals/corr/abs-2502-13144","documentPage":"https://doi.org/10.48550/ARXIV.2502.13144","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2502.13144","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2502-13144","documentUrl":"https://doi.org/10.48550/ARXIV.2502.13144","arxivId":"2502.13144","arxivUrl":"https://arxiv.org/abs/2502.13144"},{"key":"journals/corr/abs-2502-13145","title":"Multimodal Mamba: Decoder-only Multimodal State Space Model via Quadratic to Linear Distillation.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2502.13145"],"source":"https://dblp.org/rec/journals/corr/abs-2502-13145","documentPage":"https://doi.org/10.48550/ARXIV.2502.13145","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2502.13145","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2502-13145","documentUrl":"https://doi.org/10.48550/ARXIV.2502.13145","arxivId":"2502.13145","arxivUrl":"https://arxiv.org/abs/2502.13145"},{"key":"journals/corr/abs-2503-07608","title":"AlphaDrive: Unleashing the Power of VLMs in Autonomous Driving via Reinforcement Learning and Reasoning.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2503.07608"],"source":"https://dblp.org/rec/journals/corr/abs-2503-07608","documentPage":"https://doi.org/10.48550/ARXIV.2503.07608","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2503.07608","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-07608","documentUrl":"https://doi.org/10.48550/ARXIV.2503.07608","arxivId":"2503.07608","arxivUrl":"https://arxiv.org/abs/2503.07608"},{"key":"journals/corr/abs-2503-08686","title":"OmniMamba: Efficient and Unified Multimodal Understanding and Generation via State Space Models.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2503.08686"],"source":"https://dblp.org/rec/journals/corr/abs-2503-08686","documentPage":"https://doi.org/10.48550/ARXIV.2503.08686","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2503.08686","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-08686","documentUrl":"https://doi.org/10.48550/ARXIV.2503.08686","arxivId":"2503.08686","arxivUrl":"https://arxiv.org/abs/2503.08686"},{"key":"journals/corr/abs-2503-10322","title":"Towards Fast, Memory-based and Data-Efficient Vision-Language Policy.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2503.10322"],"source":"https://dblp.org/rec/journals/corr/abs-2503-10322","documentPage":"https://doi.org/10.48550/ARXIV.2503.10322","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2503.10322","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-10322","documentUrl":"https://doi.org/10.48550/ARXIV.2503.10322","arxivId":"2503.10322","arxivUrl":"https://arxiv.org/abs/2503.10322"},{"key":"journals/corr/abs-2503-10596","title":"GroundingSuite: Measuring Complex Multi-Granular Pixel Grounding.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2503.10596"],"source":"https://dblp.org/rec/journals/corr/abs-2503-10596","documentPage":"https://doi.org/10.48550/ARXIV.2503.10596","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2503.10596","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-10596","documentUrl":"https://doi.org/10.48550/ARXIV.2503.10596","arxivId":"2503.10596","arxivUrl":"https://arxiv.org/abs/2503.10596"},{"key":"journals/corr/abs-2503-13440","title":"MaTVLM: Hybrid Mamba-Transformer for Efficient Vision-Language Modeling.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2503.13440"],"source":"https://dblp.org/rec/journals/corr/abs-2503-13440","documentPage":"https://doi.org/10.48550/ARXIV.2503.13440","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2503.13440","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-13440","documentUrl":"https://doi.org/10.48550/ARXIV.2503.13440","arxivId":"2503.13440","arxivUrl":"https://arxiv.org/abs/2503.13440"},{"key":"journals/corr/abs-2504-18318","title":"STP4D: Spatio-Temporal-Prompt Consistent Modeling for Text-to-4D Gaussian Splatting.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2504.18318"],"source":"https://dblp.org/rec/journals/corr/abs-2504-18318","documentPage":"https://doi.org/10.48550/ARXIV.2504.18318","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2504.18318","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2504-18318","documentUrl":"https://doi.org/10.48550/ARXIV.2504.18318","arxivId":"2504.18318","arxivUrl":"https://arxiv.org/abs/2504.18318"},{"key":"journals/corr/abs-2504-20438","title":"PixelHacker: Image Inpainting with Structural and Semantic Consistency.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2504.20438"],"source":"https://dblp.org/rec/journals/corr/abs-2504-20438","documentPage":"https://doi.org/10.48550/ARXIV.2504.20438","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2504.20438","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2504-20438","documentUrl":"https://doi.org/10.48550/ARXIV.2504.20438","arxivId":"2504.20438","arxivUrl":"https://arxiv.org/abs/2504.20438"},{"key":"journals/corr/abs-2506-07497","title":"Genesis: Multimodal Driving Scene Generation with Spatio-Temporal and Cross-Modal Consistency.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2506.07497"],"source":"https://dblp.org/rec/journals/corr/abs-2506-07497","documentPage":"https://doi.org/10.48550/ARXIV.2506.07497","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2506.07497","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-07497","documentUrl":"https://doi.org/10.48550/ARXIV.2506.07497","arxivId":"2506.07497","arxivUrl":"https://arxiv.org/abs/2506.07497"},{"key":"journals/corr/abs-2506-08052","title":"ReCogDrive: A Reinforced Cognitive Framework for End-to-End Autonomous Driving.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2506.08052"],"source":"https://dblp.org/rec/journals/corr/abs-2506-08052","documentPage":"https://doi.org/10.48550/ARXIV.2506.08052","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2506.08052","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-08052","documentUrl":"https://doi.org/10.48550/ARXIV.2506.08052","arxivId":"2506.08052","arxivUrl":"https://arxiv.org/abs/2506.08052"},{"key":"journals/corr/abs-2507-19493","title":"From Bench to Bedside: A DeepSeek-Powered AI System for Automated Chest Radiograph Interpretation in Clinical Practice.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2507.19493"],"source":"https://dblp.org/rec/journals/corr/abs-2507-19493","documentPage":"https://doi.org/10.48550/ARXIV.2507.19493","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2507.19493","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2507-19493","documentUrl":"https://doi.org/10.48550/ARXIV.2507.19493","arxivId":"2507.19493","arxivUrl":"https://arxiv.org/abs/2507.19493"},{"key":"journals/corr/abs-2508-03643","title":"Uni3R: Unified 3D Reconstruction and Semantic Understanding via Generalizable Gaussian Splatting from Unposed Multi-View Images.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2508.03643"],"source":"https://dblp.org/rec/journals/corr/abs-2508-03643","documentPage":"https://doi.org/10.48550/ARXIV.2508.03643","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2508.03643","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-03643","documentUrl":"https://doi.org/10.48550/ARXIV.2508.03643","arxivId":"2508.03643","arxivUrl":"https://arxiv.org/abs/2508.03643"},{"key":"journals/corr/abs-2508-09136","title":"Turbo-VAED: Fast and Stable Transfer of Video-VAEs to Mobile Devices.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2508.09136"],"source":"https://dblp.org/rec/journals/corr/abs-2508-09136","documentPage":"https://doi.org/10.48550/ARXIV.2508.09136","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2508.09136","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-09136","documentUrl":"https://doi.org/10.48550/ARXIV.2508.09136","arxivId":"2508.09136","arxivUrl":"https://arxiv.org/abs/2508.09136"},{"key":"journals/corr/abs-2508-13515","title":"2D Gaussians Meet Visual Tokenizer.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2508.13515"],"source":"https://dblp.org/rec/journals/corr/abs-2508-13515","documentPage":"https://doi.org/10.48550/ARXIV.2508.13515","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2508.13515","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-13515","documentUrl":"https://doi.org/10.48550/ARXIV.2508.13515","arxivId":"2508.13515","arxivUrl":"https://arxiv.org/abs/2508.13515"},{"key":"journals/corr/abs-2508-14153","title":"LENS: Learning to Segment Anything with Unified Reinforced Reasoning.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2508.14153"],"source":"https://dblp.org/rec/journals/corr/abs-2508-14153","documentPage":"https://doi.org/10.48550/ARXIV.2508.14153","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2508.14153","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-14153","documentUrl":"https://doi.org/10.48550/ARXIV.2508.14153","arxivId":"2508.14153","arxivUrl":"https://arxiv.org/abs/2508.14153"},{"key":"journals/corr/abs-2508-14814","title":"TransLight: Image-Guided Customized Lighting Control with Generative Decoupling.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2508.14814"],"source":"https://dblp.org/rec/journals/corr/abs-2508-14814","documentPage":"https://doi.org/10.48550/ARXIV.2508.14814","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2508.14814","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-14814","documentUrl":"https://doi.org/10.48550/ARXIV.2508.14814","arxivId":"2508.14814","arxivUrl":"https://arxiv.org/abs/2508.14814"},{"key":"journals/corr/abs-2508-14892","title":"Snap-Snap: Taking Two Images to Reconstruct 3D Human Gaussians in Milliseconds.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2508.14892"],"source":"https://dblp.org/rec/journals/corr/abs-2508-14892","documentPage":"https://doi.org/10.48550/ARXIV.2508.14892","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2508.14892","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-14892","documentUrl":"https://doi.org/10.48550/ARXIV.2508.14892","arxivId":"2508.14892","arxivUrl":"https://arxiv.org/abs/2508.14892"},{"key":"journals/corr/abs-2509-04406","title":"Few-step Flow for 3D Generation via Marginal-Data Transport Distillation.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2509.04406"],"source":"https://dblp.org/rec/journals/corr/abs-2509-04406","documentPage":"https://doi.org/10.48550/ARXIV.2509.04406","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2509.04406","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-04406","documentUrl":"https://doi.org/10.48550/ARXIV.2509.04406","arxivId":"2509.04406","arxivUrl":"https://arxiv.org/abs/2509.04406"},{"key":"journals/corr/abs-2509-25079","title":"UniLat3D: Geometry-Appearance Unified Latents for Single-Stage 3D Generation.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2509.25079"],"source":"https://dblp.org/rec/journals/corr/abs-2509-25079","documentPage":"https://doi.org/10.48550/ARXIV.2509.25079","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2509.25079","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-25079","documentUrl":"https://doi.org/10.48550/ARXIV.2509.25079","arxivId":"2509.25079","arxivUrl":"https://arxiv.org/abs/2509.25079"},{"key":"journals/corr/abs-2510-08562","title":"ResAD: Normalized Residual Trajectory Modeling for End-to-End Autonomous Driving.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2510.08562"],"source":"https://dblp.org/rec/journals/corr/abs-2510-08562","documentPage":"https://doi.org/10.48550/ARXIV.2510.08562","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2510.08562","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-08562","documentUrl":"https://doi.org/10.48550/ARXIV.2510.08562","arxivId":"2510.08562","arxivUrl":"https://arxiv.org/abs/2510.08562"},{"key":"journals/corr/abs-2511-06245","title":"Gait Recognition via Collaborating Discriminative and Generative Diffusion Models.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2511.06245"],"source":"https://dblp.org/rec/journals/corr/abs-2511-06245","documentPage":"https://doi.org/10.48550/ARXIV.2511.06245","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2511.06245","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2511-06245","documentUrl":"https://doi.org/10.48550/ARXIV.2511.06245","arxivId":"2511.06245","arxivUrl":"https://arxiv.org/abs/2511.06245"},{"key":"journals/corr/abs-2511-11077","title":"Phys-Liquid: A Physics-Informed Dataset for Estimating 3D Geometry and Volume of Transparent Deformable Liquids.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2511.11077"],"source":"https://dblp.org/rec/journals/corr/abs-2511-11077","documentPage":"https://doi.org/10.48550/ARXIV.2511.11077","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2511.11077","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2511-11077","documentUrl":"https://doi.org/10.48550/ARXIV.2511.11077","arxivId":"2511.11077","arxivUrl":"https://arxiv.org/abs/2511.11077"},{"key":"journals/corr/abs-2511-17300","title":"MolSight: Optical Chemical Structure Recognition with SMILES Pretraining, Multi-Granularity Learning and Reinforcement Learning.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2511.17300"],"source":"https://dblp.org/rec/journals/corr/abs-2511-17300","documentPage":"https://doi.org/10.48550/ARXIV.2511.17300","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2511.17300","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2511-17300","documentUrl":"https://doi.org/10.48550/ARXIV.2511.17300","arxivId":"2511.17300","arxivUrl":"https://arxiv.org/abs/2511.17300"},{"key":"journals/corr/abs-2511-20410","title":"Image-Free Timestep Distillation via Continuous-Time Consistency with Trajectory-Sampled Pairs.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2511.20410"],"source":"https://dblp.org/rec/journals/corr/abs-2511-20410","documentPage":"https://doi.org/10.48550/ARXIV.2511.20410","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2511.20410","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2511-20410","documentUrl":"https://doi.org/10.48550/ARXIV.2511.20410","arxivId":"2511.20410","arxivUrl":"https://arxiv.org/abs/2511.20410"},{"key":"journals/corr/abs-2511-21475","title":"MobileI2V: Fast and High-Resolution Image-to-Video on Mobile Devices.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2511.21475"],"source":"https://dblp.org/rec/journals/corr/abs-2511-21475","documentPage":"https://doi.org/10.48550/ARXIV.2511.21475","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2511.21475","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2511-21475","documentUrl":"https://doi.org/10.48550/ARXIV.2511.21475","arxivId":"2511.21475","arxivUrl":"https://arxiv.org/abs/2511.21475"},{"key":"journals/corr/abs-2511-23386","title":"VQRAE: Representation Quantization Autoencoders for Multimodal Understanding, Generation and Reconstruction.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2511.23386"],"source":"https://dblp.org/rec/journals/corr/abs-2511-23386","documentPage":"https://doi.org/10.48550/ARXIV.2511.23386","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2511.23386","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2511-23386","documentUrl":"https://doi.org/10.48550/ARXIV.2511.23386","arxivId":"2511.23386","arxivUrl":"https://arxiv.org/abs/2511.23386"},{"key":"journals/corr/abs-2511-23469","title":"Visual Generation Tuning.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2511.23469"],"source":"https://dblp.org/rec/journals/corr/abs-2511-23469","documentPage":"https://doi.org/10.48550/ARXIV.2511.23469","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2511.23469","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2511-23469","documentUrl":"https://doi.org/10.48550/ARXIV.2511.23469","arxivId":"2511.23469","arxivUrl":"https://arxiv.org/abs/2511.23469"},{"key":"journals/corr/abs-2512-05060","title":"4DLangVGGT: 4D Language-Visual Geometry Grounded Transformer.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2512.05060"],"source":"https://dblp.org/rec/journals/corr/abs-2512-05060","documentPage":"https://doi.org/10.48550/ARXIV.2512.05060","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2512.05060","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-05060","documentUrl":"https://doi.org/10.48550/ARXIV.2512.05060","arxivId":"2512.05060","arxivUrl":"https://arxiv.org/abs/2512.05060"},{"key":"journals/corr/abs-2512-07745","title":"DiffusionDriveV2: Reinforcement Learning-Constrained Truncated Diffusion Modeling in End-to-End Autonomous Driving.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2512.07745"],"source":"https://dblp.org/rec/journals/corr/abs-2512-07745","documentPage":"https://doi.org/10.48550/ARXIV.2512.07745","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2512.07745","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-07745","documentUrl":"https://doi.org/10.48550/ARXIV.2512.07745","arxivId":"2512.07745","arxivUrl":"https://arxiv.org/abs/2512.07745"},{"key":"journals/corr/abs-2512-08829","title":"InfiniteVL: Synergizing Linear and Sparse Attention for Highly-Efficient, Unlimited-Input Vision-Language Models.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2512.08829"],"source":"https://dblp.org/rec/journals/corr/abs-2512-08829","documentPage":"https://doi.org/10.48550/ARXIV.2512.08829","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2512.08829","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-08829","documentUrl":"https://doi.org/10.48550/ARXIV.2512.08829","arxivId":"2512.08829","arxivUrl":"https://arxiv.org/abs/2512.08829"},{"key":"journals/corr/abs-2512-13687","title":"Towards Scalable Pre-training of Visual Tokenizers for Generation.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2512.13687"],"source":"https://dblp.org/rec/journals/corr/abs-2512-13687","documentPage":"https://doi.org/10.48550/ARXIV.2512.13687","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2512.13687","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-13687","documentUrl":"https://doi.org/10.48550/ARXIV.2512.13687","arxivId":"2512.13687","arxivUrl":"https://arxiv.org/abs/2512.13687"},{"key":"journals/corr/abs-2512-14480","title":"SuperCLIP: CLIP with Simple Classification Supervision.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2512.14480"],"source":"https://dblp.org/rec/journals/corr/abs-2512-14480","documentPage":"https://doi.org/10.48550/ARXIV.2512.14480","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2512.14480","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-14480","documentUrl":"https://doi.org/10.48550/ARXIV.2512.14480","arxivId":"2512.14480","arxivUrl":"https://arxiv.org/abs/2512.14480"},{"key":"journals/corr/abs-2512-15713","title":"DiffusionVL: Translating Any Autoregressive Models into Diffusion Vision Language Models.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2512.15713"],"source":"https://dblp.org/rec/journals/corr/abs-2512-15713","documentPage":"https://doi.org/10.48550/ARXIV.2512.15713","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2512.15713","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-15713","documentUrl":"https://doi.org/10.48550/ARXIV.2512.15713","arxivId":"2512.15713","arxivUrl":"https://arxiv.org/abs/2512.15713"},{"key":"journals/corr/abs-2512-19331","title":"DeltaMIL: Gated Memory Integration for Efficient and Discriminative Whole Slide Image Analysis.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2512.19331"],"source":"https://dblp.org/rec/journals/corr/abs-2512-19331","documentPage":"https://doi.org/10.48550/ARXIV.2512.19331","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2512.19331","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-19331","documentUrl":"https://doi.org/10.48550/ARXIV.2512.19331","arxivId":"2512.19331","arxivUrl":"https://arxiv.org/abs/2512.19331"},{"key":"journals/corr/abs-2512-20344","title":"A DeepSeek-Powered AI System for Automated Chest Radiograph Interpretation in Clinical Practice.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2512.20344"],"source":"https://dblp.org/rec/journals/corr/abs-2512-20344","documentPage":"https://doi.org/10.48550/ARXIV.2512.20344","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2512.20344","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-20344","documentUrl":"https://doi.org/10.48550/ARXIV.2512.20344","arxivId":"2512.20344","arxivUrl":"https://arxiv.org/abs/2512.20344"},{"key":"journals/corr/abs-2512-23421","title":"DriveLaW:Unifying Planning and Video Generation in a Latent Driving World.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2512.23421"],"source":"https://dblp.org/rec/journals/corr/abs-2512-23421","documentPage":"https://doi.org/10.48550/ARXIV.2512.23421","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2512.23421","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-23421","documentUrl":"https://doi.org/10.48550/ARXIV.2512.23421","arxivId":"2512.23421","arxivUrl":"https://arxiv.org/abs/2512.23421"}],"excludedFormal":[{"key":"journals/tcsv/WangZWYC25","title":"Guest Editorial Introduction to the Special Issue on Segment Anything for Videos and Beyond.","year":2025,"yearOfEvent":null,"venue":"IEEE Trans. Circuits Syst. Video Technol.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1109/TCSVT.2025.3551468"],"source":"https://dblp.org/rec/journals/tcsv/WangZWYC25","documentPage":"https://doi.org/10.1109/TCSVT.2025.3551468","type":"Article","doi":"https://doi.org/10.1109/TCSVT.2025.3551468","exclusionReason":"Explicit editorial, correction, erratum or preface; excluded from research-paper count.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/tcsv/WangZWYC25","documentUrl":"https://doi.org/10.1109/TCSVT.2025.3551468"}],"excludedOther":[],"excludedHomonyms":[],"unassignedCandidates":[],"retrievedAt":"2026-10-19","querySource":"https://sparql.dblp.org/","method":"DBLP yearOfPublication=2025; Article + Inproceedings; excludes Informal/CoRR and explicit editorial/correction/erratum/preface; unique DBLP record keys within person.","labName":"HUST Vision Lab","labUrl":"https://hustvl.github.io/","labEvidence":"已缓存的实验室自述明确写明 HUST Vision Lab 由 Xinggang Wang 领导。","labSourceUrl":"https://hustvl.github.io/","affiliationZh":"华中科技大学","sourceWarning":false,"knownPreprintMinimum2025":null,"excludedMisattributed":[],"displayNotes":"身份已经个人或机构主页核对。2025 年正式记录 36 条（会议 23、期刊 13），所有作者位置均计入，不表示主导或贡献份额；预印本 39 条单列，不加总。","labDisplayNotes":"实验室的自我介绍写明 HUST Vision Lab 由其领导，据此归组；分组只含本人参与的记录。"},{"index":90,"name":"Baoyuan Wu","nameZh":"吴保元","affiliation":"The Chinese University of Hong Kong, Shenzhen","source":"DBLP Knowledge Graph official SPARQL API","profileUrl":"https://dblp.org/pid/73/7781","identifier":"73/7781","identityEvidence":[{"url":"https://dblp.org/pid/73/7781","evidence":"DBLP curated profile affiliations: Chinese Academy of Sciences, Institute of Automation, National Laboratory of Pattern Recognition, Beijing, China; Chinese University of Hong Kong, School of Data Science, Shenzhen,China."},{"url":"https://dblp.org/pid/73/7781","evidence":"DBLP curated profile homepages: https://openreview.net/profile?id=~Baoyuan_Wu1; https://sites.google.com/site/baoyuanwu2015/home."}],"count2025":18,"conference2025":12,"journal2025":6,"preprint2025":14,"status":"verified","notes":"Counts are DBLP indexed coauthored records, not first-author counts, laboratory totals, unique scientific discoveries, or quality assessments. DBLP yearOfPublication=2025; yearOfEvent retained and can differ. Conference workshops are included. Preprints are separate and may overlap formal versions.","papers":[{"key":"conf/aaai/MaZZZWHHW25","title":"Spurious Feature Eraser: Stabilizing Test-Time Adaptation for Vision-Language Foundation Model.","year":2025,"yearOfEvent":2025,"venue":"AAAI","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1609/AAAI.V39I18.34124"],"source":"https://dblp.org/rec/conf/aaai/MaZZZWHHW25","documentPage":"https://doi.org/10.1609/AAAI.V39I18.34124","type":"Inproceedings","doi":"https://doi.org/10.1609/AAAI.V39I18.34124","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/aaai/MaZZZWHHW25","documentUrl":"https://doi.org/10.1609/AAAI.V39I18.34124"},{"key":"conf/aaai/TanTLGWZW25","title":"C2P-CLIP: Injecting Category Common Prompt in CLIP to Enhance Generalization in Deepfake Detection.","year":2025,"yearOfEvent":2025,"venue":"AAAI","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1609/AAAI.V39I7.32772"],"source":"https://dblp.org/rec/conf/aaai/TanTLGWZW25","documentPage":"https://doi.org/10.1609/AAAI.V39I7.32772","type":"Inproceedings","doi":"https://doi.org/10.1609/AAAI.V39I7.32772","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/aaai/TanTLGWZW25","documentUrl":"https://doi.org/10.1609/AAAI.V39I7.32772"},{"key":"conf/acl/WangGWY25","title":"MorphMark: Flexible Adaptive Watermarking for Large Language Models.","year":2025,"yearOfEvent":2025,"venue":"ACL (1)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.18653/V1/2025.ACL-LONG.240"],"source":"https://dblp.org/rec/conf/acl/WangGWY25","documentPage":"https://doi.org/10.18653/V1/2025.ACL-LONG.240","type":"Inproceedings","doi":"https://doi.org/10.18653/V1/2025.ACL-LONG.240","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/acl/WangGWY25","documentUrl":"https://doi.org/10.18653/V1/2025.ACL-LONG.240"},{"key":"conf/acl/WangWDY25","title":"Robust and Minimally Invasive Watermarking for EaaS.","year":2025,"yearOfEvent":2025,"venue":"ACL (Findings)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.18653/V1/2025.FINDINGS-ACL.112"],"source":"https://dblp.org/rec/conf/acl/WangWDY25","documentPage":"https://doi.org/10.18653/V1/2025.FINDINGS-ACL.112","type":"Inproceedings","doi":"https://doi.org/10.18653/V1/2025.FINDINGS-ACL.112","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/acl/WangWDY25","documentUrl":"https://doi.org/10.18653/V1/2025.FINDINGS-ACL.112"},{"key":"conf/cvpr/HuangHLH00W0C25","title":"SIDA: Social Media Image Deepfake Detection, Localization and Explanation with Large Multimodal Model.","year":2025,"yearOfEvent":2025,"venue":"CVPR","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/CVPR52734.2025.02685"],"source":"https://dblp.org/rec/conf/cvpr/HuangHLH00W0C25","documentPage":"https://openaccess.thecvf.com/content/CVPR2025/html/Huang_SIDA_Social_Media_Image_Deepfake_Detection_Localization_and_Explanation_with_CVPR_2025_paper.html","type":"Inproceedings","doi":"https://doi.org/10.1109/CVPR52734.2025.02685","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/HuangHLH00W0C25","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Huang_SIDA_Social_Media_Image_Deepfake_Detection_Localization_and_Explanation_with_CVPR_2025_paper.html"},{"key":"conf/icassp/ZengLLDWL25","title":"Reliable Imputed-Sample Assisted Vertical Federated Learning.","year":2025,"yearOfEvent":2025,"venue":"ICASSP","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/ICASSP49660.2025.10888109"],"source":"https://dblp.org/rec/conf/icassp/ZengLLDWL25","documentPage":"https://doi.org/10.1109/ICASSP49660.2025.10888109","type":"Inproceedings","doi":"https://doi.org/10.1109/ICASSP49660.2025.10888109","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/icassp/ZengLLDWL25","documentUrl":"https://doi.org/10.1109/ICASSP49660.2025.10888109"},{"key":"conf/iccv/WangZOCTWW25","title":"BadVideo: Stealthy Backdoor Attack Against Text-to-Video Generation.","year":2025,"yearOfEvent":2025,"venue":"ICCV","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/ICCV51701.2025.01773"],"source":"https://dblp.org/rec/conf/iccv/WangZOCTWW25","documentPage":"https://doi.org/10.1109/ICCV51701.2025.01773","type":"Inproceedings","doi":"https://doi.org/10.1109/ICCV51701.2025.01773","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/WangZOCTWW25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.01773"},{"key":"conf/iclr/YuanZWLW25","title":"Activation Gradient based Poisoned Sample Detection Against Backdoor Attacks.","year":2025,"yearOfEvent":2025,"venue":"ICLR","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/iclr/YuanZWLW25","documentPage":"https://openreview.net/forum?id=VNMJfBBUd5","type":"Inproceedings","doi":null,"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iclr/YuanZWLW25","documentUrl":"https://openreview.net/forum?id=VNMJfBBUd5"},{"key":"conf/icml/0002WJZLCYDW025","title":"Orthogonal Subspace Decomposition for Generalizable AI-Generated Image Detection.","year":2025,"yearOfEvent":2025,"venue":"ICML","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/icml/0002WJZLCYDW025","documentPage":"https://proceedings.mlr.press/v267/yan25b.html","type":"Inproceedings","doi":null,"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/icml/0002WJZLCYDW025","documentUrl":"https://proceedings.mlr.press/v267/yan25b.html"},{"key":"conf/mm/LiHWHLWC25","title":"RAIDX: A Retrieval-Augmented Generation and GRPO Reinforcement Learning Framework for Explainable Deepfake Detection.","year":2025,"yearOfEvent":2025,"venue":"ACM Multimedia","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1145/3746027.3754798"],"source":"https://dblp.org/rec/conf/mm/LiHWHLWC25","documentPage":"https://doi.org/10.1145/3746027.3754798","type":"Inproceedings","doi":"https://doi.org/10.1145/3746027.3754798","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/mm/LiHWHLWC25","documentUrl":"https://doi.org/10.1145/3746027.3754798"},{"key":"conf/nips/ChenYCZLW25","title":"X2-DFD: A framework for explainable and extendable Deepfake Detection.","year":2025,"yearOfEvent":2025,"venue":"NeurIPS","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/nips/ChenYCZLW25","documentPage":"http://papers.nips.cc/paper_files/paper/2025/hash/78a2ed8e7da1829d64fb3561adbd706b-Abstract-Conference.html","type":"Inproceedings","doi":null,"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/nips/ChenYCZLW25","documentUrl":"http://papers.nips.cc/paper_files/paper/2025/hash/78a2ed8e7da1829d64fb3561adbd706b-Abstract-Conference.html"},{"key":"conf/wacv/LiLWWZD25","title":"Texture, Shape and Order Matter: A New Transformer Design for Sequential DeepFake Detection.","year":2025,"yearOfEvent":2025,"venue":"WACV","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/WACV61041.2025.00030"],"source":"https://dblp.org/rec/conf/wacv/LiLWWZD25","documentPage":"https://doi.org/10.1109/WACV61041.2025.00030","type":"Inproceedings","doi":"https://doi.org/10.1109/WACV61041.2025.00030","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/wacv/LiLWWZD25","documentUrl":"https://doi.org/10.1109/WACV61041.2025.00030"},{"key":"journals/ftsec/MaGWWWSDXCZHLWZZBLWQZHL25","title":"Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety.","year":2025,"yearOfEvent":null,"venue":"Found. Trends Priv. Secur.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1561/3300000051"],"source":"https://dblp.org/rec/journals/ftsec/MaGWWWSDXCZHLWZZBLWQZHL25","documentPage":"https://doi.org/10.1561/3300000051","type":"Article","doi":"https://doi.org/10.1561/3300000051","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/ftsec/MaGWWWSDXCZHLWZZBLWQZHL25","documentUrl":"https://doi.org/10.1561/3300000051"},{"key":"journals/ijcv/WuCZZWYZWLS25","title":"BackdoorBench: A Comprehensive Benchmark and Analysis of Backdoor Learning.","year":2025,"yearOfEvent":null,"venue":"Int. J. Comput. Vis.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1007/S11263-025-02447-X"],"source":"https://dblp.org/rec/journals/ijcv/WuCZZWYZWLS25","documentPage":"https://doi.org/10.1007/S11263-025-02447-X","type":"Article","doi":"https://doi.org/10.1007/S11263-025-02447-X","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/ijcv/WuCZZWYZWLS25","documentUrl":"https://doi.org/10.1007/S11263-025-02447-X"},{"key":"journals/pami/ZhengYZCW25","title":"BlackboxBench: A Comprehensive Benchmark of Black-Box Adversarial Attacks.","year":2025,"yearOfEvent":null,"venue":"IEEE Trans. Pattern Anal. Mach. Intell.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1109/TPAMI.2025.3574432"],"source":"https://dblp.org/rec/journals/pami/ZhengYZCW25","documentPage":"https://doi.org/10.1109/TPAMI.2025.3574432","type":"Article","doi":"https://doi.org/10.1109/TPAMI.2025.3574432","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/pami/ZhengYZCW25","documentUrl":"https://doi.org/10.1109/TPAMI.2025.3574432"},{"key":"journals/tdsc/ZhuLWZWL25","title":"Hiding Faces in Plain Sight: Defending DeepFakes by Disrupting Face Detection.","year":2025,"yearOfEvent":null,"venue":"IEEE Trans. Dependable Secur. Comput.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1109/TDSC.2025.3592230"],"source":"https://dblp.org/rec/journals/tdsc/ZhuLWZWL25","documentPage":"https://doi.org/10.1109/TDSC.2025.3592230","type":"Article","doi":"https://doi.org/10.1109/TDSC.2025.3592230","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/tdsc/ZhuLWZWL25","documentUrl":"https://doi.org/10.1109/TDSC.2025.3592230"},{"key":"journals/tfs/DaiZGWZ25","title":"Hierarchical Fuzzy Stochastic Configuration Network Based on Canonical Correlation Analysis for Multiview Pulse Signal Fusion.","year":2025,"yearOfEvent":null,"venue":"IEEE Trans. Fuzzy Syst.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1109/TFUZZ.2025.3576112"],"source":"https://dblp.org/rec/journals/tfs/DaiZGWZ25","documentPage":"https://doi.org/10.1109/TFUZZ.2025.3576112","type":"Article","doi":"https://doi.org/10.1109/TFUZZ.2025.3576112","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/tfs/DaiZGWZ25","documentUrl":"https://doi.org/10.1109/TFUZZ.2025.3576112"},{"key":"journals/tip/XiePLWZ25","title":"3DFACENet: 3D Facial Attractiveness Computation and Enhancement Network.","year":2025,"yearOfEvent":null,"venue":"IEEE Trans. Image Process.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1109/TIP.2025.3607629"],"source":"https://dblp.org/rec/journals/tip/XiePLWZ25","documentPage":"https://doi.org/10.1109/TIP.2025.3607629","type":"Article","doi":"https://doi.org/10.1109/TIP.2025.3607629","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/tip/XiePLWZ25","documentUrl":"https://doi.org/10.1109/TIP.2025.3607629"}],"preprints":[{"key":"journals/corr/abs-2501-06429","title":"Reliable Imputed-Sample Assisted Vertical Federated Learning.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2501.06429"],"source":"https://dblp.org/rec/journals/corr/abs-2501-06429","documentPage":"https://doi.org/10.48550/ARXIV.2501.06429","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2501.06429","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2501-06429","documentUrl":"https://doi.org/10.48550/ARXIV.2501.06429","arxivId":"2501.06429","arxivUrl":"https://arxiv.org/abs/2501.06429"},{"key":"journals/corr/abs-2502-05206","title":"Safety at Scale: A Comprehensive Survey of Large Model Safety.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2502.05206"],"source":"https://dblp.org/rec/journals/corr/abs-2502-05206","documentPage":"https://doi.org/10.48550/ARXIV.2502.05206","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2502.05206","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2502-05206","documentUrl":"https://doi.org/10.48550/ARXIV.2502.05206","arxivId":"2502.05206","arxivUrl":"https://arxiv.org/abs/2502.05206"},{"key":"journals/corr/abs-2502-12202","title":"BoT: Breaking Long Thought Processes of o1-like Large Language Models through Backdoor Attack.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2502.12202"],"source":"https://dblp.org/rec/journals/corr/abs-2502-12202","documentPage":"https://doi.org/10.48550/ARXIV.2502.12202","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2502.12202","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2502-12202","documentUrl":"https://doi.org/10.48550/ARXIV.2502.12202","arxivId":"2502.12202","arxivUrl":"https://arxiv.org/abs/2502.12202"},{"key":"journals/corr/abs-2502-18520","title":"Class-Conditional Neural Polarizer: A Lightweight and Effective Backdoor Defense by Purifying Poisoned Features.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2502.18520"],"source":"https://dblp.org/rec/journals/corr/abs-2502-18520","documentPage":"https://doi.org/10.48550/ARXIV.2502.18520","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2502.18520","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2502-18520","documentUrl":"https://doi.org/10.48550/ARXIV.2502.18520","arxivId":"2502.18520","arxivUrl":"https://arxiv.org/abs/2502.18520"},{"key":"journals/corr/abs-2504-16474","title":"Seeking Flat Minima over Diverse Surrogates for Improved Adversarial Transferability: A Theoretical Framework and Algorithmic Instantiation.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2504.16474"],"source":"https://dblp.org/rec/journals/corr/abs-2504-16474","documentPage":"https://doi.org/10.48550/ARXIV.2504.16474","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2504.16474","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2504-16474","documentUrl":"https://doi.org/10.48550/ARXIV.2504.16474","arxivId":"2504.16474","arxivUrl":"https://arxiv.org/abs/2504.16474"},{"key":"journals/corr/abs-2504-16907","title":"BadVideo: Stealthy Backdoor Attack against Text-to-Video Generation.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2504.16907"],"source":"https://dblp.org/rec/journals/corr/abs-2504-16907","documentPage":"https://doi.org/10.48550/ARXIV.2504.16907","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2504.16907","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2504-16907","documentUrl":"https://doi.org/10.48550/ARXIV.2504.16907","arxivId":"2504.16907","arxivUrl":"https://arxiv.org/abs/2504.16907"},{"key":"journals/corr/abs-2505-08294","title":"FauForensics: Boosting Audio-Visual Deepfake Detection with Facial Action Units.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2505.08294"],"source":"https://dblp.org/rec/journals/corr/abs-2505-08294","documentPage":"https://doi.org/10.48550/ARXIV.2505.08294","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2505.08294","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-08294","documentUrl":"https://doi.org/10.48550/ARXIV.2505.08294","arxivId":"2505.08294","arxivUrl":"https://arxiv.org/abs/2505.08294"},{"key":"journals/corr/abs-2505-11541","title":"MorphMark: Flexible Adaptive Watermarking for Large Language Models.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2505.11541"],"source":"https://dblp.org/rec/journals/corr/abs-2505-11541","documentPage":"https://doi.org/10.48550/ARXIV.2505.11541","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2505.11541","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-11541","documentUrl":"https://doi.org/10.48550/ARXIV.2505.11541","arxivId":"2505.11541","arxivUrl":"https://arxiv.org/abs/2505.11541"},{"key":"journals/corr/abs-2505-12620","title":"BusterX: MLLM-Powered AI-Generated Video Forgery Detection and Explanation.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2505.12620"],"source":"https://dblp.org/rec/journals/corr/abs-2505-12620","documentPage":"https://doi.org/10.48550/ARXIV.2505.12620","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2505.12620","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-12620","documentUrl":"https://doi.org/10.48550/ARXIV.2505.12620","arxivId":"2505.12620","arxivUrl":"https://arxiv.org/abs/2505.12620"},{"key":"journals/corr/abs-2506-22930","title":"Towards Explainable Bilingual Multimodal Misinformation Detection and Localization.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2506.22930"],"source":"https://dblp.org/rec/journals/corr/abs-2506-22930","documentPage":"https://doi.org/10.48550/ARXIV.2506.22930","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2506.22930","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-22930","documentUrl":"https://doi.org/10.48550/ARXIV.2506.22930","arxivId":"2506.22930","arxivUrl":"https://arxiv.org/abs/2506.22930"},{"key":"journals/corr/abs-2508-04524","title":"RAIDX: A Retrieval-Augmented Generation and GRPO Reinforcement Learning Framework for Explainable Deepfake Detection.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2508.04524"],"source":"https://dblp.org/rec/journals/corr/abs-2508-04524","documentPage":"https://doi.org/10.48550/ARXIV.2508.04524","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2508.04524","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-04524","documentUrl":"https://doi.org/10.48550/ARXIV.2508.04524","arxivId":"2508.04524","arxivUrl":"https://arxiv.org/abs/2508.04524"},{"key":"journals/corr/abs-2509-24269","title":"AdvChain: Adversarial Chain-of-Thought Tuning for Robust Safety Alignment of Large Reasoning Models.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2509.24269"],"source":"https://dblp.org/rec/journals/corr/abs-2509-24269","documentPage":"https://doi.org/10.48550/ARXIV.2509.24269","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2509.24269","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-24269","documentUrl":"https://doi.org/10.48550/ARXIV.2509.24269","arxivId":"2509.24269","arxivUrl":"https://arxiv.org/abs/2509.24269"},{"key":"journals/corr/abs-2510-22622","title":"DeepfakeBench-MM: A Comprehensive Benchmark for Multimodal Deepfake Detection.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2510.22622"],"source":"https://dblp.org/rec/journals/corr/abs-2510-22622","documentPage":"https://doi.org/10.48550/ARXIV.2510.22622","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2510.22622","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-22622","documentUrl":"https://doi.org/10.48550/ARXIV.2510.22622","arxivId":"2510.22622","arxivUrl":"https://arxiv.org/abs/2510.22622"},{"key":"journals/corr/abs-2512-05651","title":"Self-Supervised AI-Generated Image Detection: A Camera Metadata Perspective.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2512.05651"],"source":"https://dblp.org/rec/journals/corr/abs-2512-05651","documentPage":"https://doi.org/10.48550/ARXIV.2512.05651","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2512.05651","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-05651","documentUrl":"https://doi.org/10.48550/ARXIV.2512.05651","arxivId":"2512.05651","arxivUrl":"https://arxiv.org/abs/2512.05651"}],"excludedFormal":[],"excludedOther":[],"excludedHomonyms":[],"unassignedCandidates":[],"retrievedAt":"2026-10-19","querySource":"https://sparql.dblp.org/","method":"DBLP yearOfPublication=2025; Article + Inproceedings; excludes Informal/CoRR and explicit editorial/correction/erratum/preface; unique DBLP record keys within person.","labName":"龙岗区智能数字经济安全重点实验室（iDES）","labUrl":null,"labEvidence":"本人当前主页明确写其担任 Longgang District Key Laboratory of Intelligent Digital Economy Security 主任，并给出中文名与 iDES 简称。","labSourceUrl":"https://sites.google.com/site/baoyuanwu2015/","affiliationZh":"香港中文大学（深圳）","sourceWarning":false,"knownPreprintMinimum2025":null,"excludedMisattributed":[],"displayNotes":"身份已经个人或机构主页核对。2025 年正式记录 18 条（会议 12、期刊 6），所有作者位置均计入，不表示主导或贡献份额；预印本 14 条单列，不加总。","labDisplayNotes":"本人主页写明其任龙岗区智能数字经济安全重点实验室（iDES）主任，据此归组。这是区级重点实验室，分组只含本人参与的记录。"},{"index":91,"name":"Tong Wu","nameZh":"吴桐","affiliation":"Fudan University","source":"DBLP Knowledge Graph official SPARQL API","profileUrl":"https://dblp.org/pid/75/5056","identifier":"75/5056","identityEvidence":[{"url":"https://wutong16.github.io/","evidence":"Personal site identifies 吴桐, Fudan, previously Stanford postdoc and CUHK MMLab PhD; specific titles matched to DBLP mixed PID 75/5056. PID 75/5056-2 is a different CUHK power-systems researcher and was rejected."}],"count2025":null,"conference2025":null,"journal2025":null,"preprint2025":null,"status":"partial_identity_review","notes":"Counts are DBLP indexed coauthored records, not first-author counts, laboratory totals, unique scientific discoveries, or quality assessments. DBLP yearOfPublication=2025; yearOfEvent retained and can differ. Conference workshops are included. Preprints are separate and may overlap formal versions. Mixed / unassigned DBLP profile. Main counts withheld pending review of every remaining candidate; retained papers establish a verified lower bound only. Do not present this lower bound as an exact annual total.","papers":[{"key":"conf/cvpr/0009TDCHL0XWSPL25","title":"3DTopia-XL: Scaling High-quality 3D Asset Generation via Primitive Diffusion.","year":2025,"yearOfEvent":2025,"venue":"CVPR","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/CVPR52734.2025.02475"],"source":"https://dblp.org/rec/conf/cvpr/0009TDCHL0XWSPL25","documentPage":"https://openaccess.thecvf.com/content/CVPR2025/html/Chen_3DTopia-XL_Scaling_High-quality_3D_Asset_Generation_via_Primitive_Diffusion_CVPR_2025_paper.html","type":"Inproceedings","doi":"https://doi.org/10.1109/CVPR52734.2025.02475","authorSignatures":[{"inst":"https://dblp.org/inst/1/452","instLabel":"Chinese University of Hong Kong (CUHK)"},{"inst":"https://dblp.org/inst/12/399","instLabel":"Shanghai Artificial Intelligence Laboratory"},{"inst":"https://dblp.org/inst/12/695","instLabel":"ShangHai JiAi Genetics & IVF Institute"}],"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/0009TDCHL0XWSPL25","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Chen_3DTopia-XL_Scaling_High-quality_3D_Asset_Generation_via_Primitive_Diffusion_CVPR_2025_paper.html"},{"key":"conf/eccv/ChenWWPJL24","title":"ComboVerse: Compositional 3D Assets Creation Using Spatially-Aware Diffusion Guidance.","year":2025,"yearOfEvent":2024,"venue":"ECCV (24)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1007/978-3-031-72691-0_8"],"source":"https://dblp.org/rec/conf/eccv/ChenWWPJL24","documentPage":"https://doi.org/10.1007/978-3-031-72691-0_8","type":"Inproceedings","doi":"https://doi.org/10.1007/978-3-031-72691-0_8","authorSignatures":[{"inst":"https://dblp.org/inst/11/304","instLabel":"The Chinese University of Hong Kong, Shenzhen (CUHK-SZ)"}],"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/eccv/ChenWWPJL24","documentUrl":"https://doi.org/10.1007/978-3-031-72691-0_8"},{"key":"conf/eccv/ZhangWWWLL24","title":"Omni6D: Large-Vocabulary 3D Object Dataset for Category-Level 6D Object Pose Estimation.","year":2025,"yearOfEvent":2024,"venue":"ECCV (25)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1007/978-3-031-72698-9_13"],"source":"https://dblp.org/rec/conf/eccv/ZhangWWWLL24","documentPage":"https://doi.org/10.1007/978-3-031-72698-9_13","type":"Inproceedings","doi":"https://doi.org/10.1007/978-3-031-72698-9_13","authorSignatures":[{"inst":"https://dblp.org/inst/1/452","instLabel":"Chinese University of Hong Kong (CUHK)"}],"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/eccv/ZhangWWWLL24","documentUrl":"https://doi.org/10.1007/978-3-031-72698-9_13"},{"key":"conf/iccv/SunWZZDXLW25","title":"Bootstrap3D: Improving Multi-View Diffusion Model with Synthetic Data.","year":2025,"yearOfEvent":2025,"venue":"ICCV","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/ICCV51701.2025.01458"],"source":"https://dblp.org/rec/conf/iccv/SunWZZDXLW25","documentPage":"https://doi.org/10.1109/ICCV51701.2025.01458","type":"Inproceedings","doi":"https://doi.org/10.1109/ICCV51701.2025.01458","authorSignatures":[{"inst":"https://dblp.org/inst/1/055","instLabel":"Stanford University (SU)"}],"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/SunWZZDXLW25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.01458"},{"key":"conf/iccv/ZhangWTLWL25","title":"GenDoP: Auto-regressive Camera Trajectory Generation as a Director of Photography.","year":2025,"yearOfEvent":2025,"venue":"ICCV","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/ICCV51701.2025.01694"],"source":"https://dblp.org/rec/conf/iccv/ZhangWTLWL25","documentPage":"https://doi.org/10.1109/ICCV51701.2025.01694","type":"Inproceedings","doi":"https://doi.org/10.1109/ICCV51701.2025.01694","authorSignatures":[{"inst":"https://dblp.org/inst/1/055","instLabel":"Stanford University (SU)"}],"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/ZhangWTLWL25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.01694"},{"key":"conf/iccv/ZhouBLZWHLDZCRWN25","title":"Light-a-Video: Training-Free Video Relighting via Progressive Light Fusion.","year":2025,"yearOfEvent":2025,"venue":"ICCV","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/ICCV51701.2025.01237"],"source":"https://dblp.org/rec/conf/iccv/ZhouBLZWHLDZCRWN25","documentPage":"https://doi.org/10.1109/ICCV51701.2025.01237","type":"Inproceedings","doi":"https://doi.org/10.1109/ICCV51701.2025.01237","authorSignatures":[{"inst":"https://dblp.org/inst/1/055","instLabel":"Stanford University (SU)"}],"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/ZhouBLZWHLDZCRWN25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.01237"},{"key":"conf/iclr/LingB0DZWC0025","title":"MotionClone: Training-Free Motion Cloning for Controllable Video Generation.","year":2025,"yearOfEvent":2025,"venue":"ICLR","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/iclr/LingB0DZWC0025","documentPage":"https://openreview.net/forum?id=aY3L65HgHJ","type":"Inproceedings","doi":null,"authorSignatures":[{}],"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iclr/LingB0DZWC0025","documentUrl":"https://openreview.net/forum?id=aY3L65HgHJ"},{"key":"conf/iclr/LiW000L25","title":"IDArb: Intrinsic Decomposition for Arbitrary Number of Input Views and Illuminations.","year":2025,"yearOfEvent":2025,"venue":"ICLR","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/iclr/LiW000L25","documentPage":"https://openreview.net/forum?id=uuef1HP6X7","type":"Inproceedings","doi":null,"authorSignatures":[{}],"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iclr/LiW000L25","documentUrl":"https://openreview.net/forum?id=uuef1HP6X7"},{"key":"conf/iclr/YeZHZBKHLWW0CLH25","title":"LOKI: A Comprehensive Synthetic Data Detection Benchmark using Large Multimodal Models.","year":2025,"yearOfEvent":2025,"venue":"ICLR","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/iclr/YeZHZBKHLWW0CLH25","documentPage":"https://openreview.net/forum?id=z8sxoCYgmd","type":"Inproceedings","doi":null,"authorSignatures":[{}],"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iclr/YeZHZBKHLWW0CLH25","documentUrl":"https://openreview.net/forum?id=z8sxoCYgmd"},{"key":"conf/nips/BuLZZWDZCLW25","title":"HiFlow: Training-free High-Resolution Image Generation with Flow-Aligned Guidance.","year":2025,"yearOfEvent":2025,"venue":"NeurIPS","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/nips/BuLZZWDZCLW25","documentPage":"http://papers.nips.cc/paper_files/paper/2025/hash/d4ecde5d18d36150c529d1b9c5f0d727-Abstract-Conference.html","type":"Inproceedings","doi":null,"authorSignatures":[{}],"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/nips/BuLZZWDZCLW25","documentUrl":"http://papers.nips.cc/paper_files/paper/2025/hash/d4ecde5d18d36150c529d1b9c5f0d727-Abstract-Conference.html"},{"key":"conf/nips/TanYWHGLL25","title":"Imagine360: Immersive 360 Video Generation from Perspective Anchor.","year":2025,"yearOfEvent":2025,"venue":"NeurIPS","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/nips/TanYWHGLL25","documentPage":"http://papers.nips.cc/paper_files/paper/2025/hash/cc83e97320000f4e08cb9e293b12cf7e-Abstract-Conference.html","type":"Inproceedings","doi":null,"authorSignatures":[{}],"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/nips/TanYWHGLL25","documentUrl":"http://papers.nips.cc/paper_files/paper/2025/hash/cc83e97320000f4e08cb9e293b12cf7e-Abstract-Conference.html"},{"key":"conf/nips/WuYPXLLW25","title":"Video World Models with Long-term Spatial Memory.","year":2025,"yearOfEvent":2025,"venue":"NeurIPS","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/nips/WuYPXLLW25","documentPage":"http://papers.nips.cc/paper_files/paper/2025/hash/467655d26fcc207bca08915dc91964c6-Abstract-Conference.html","type":"Inproceedings","doi":null,"authorSignatures":[{}],"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/nips/WuYPXLLW25","documentUrl":"http://papers.nips.cc/paper_files/paper/2025/hash/467655d26fcc207bca08915dc91964c6-Abstract-Conference.html"},{"key":"conf/nips/ZhangZCWLPLL25","title":"Hi3DEval: Advancing 3D Generation Evaluation with Hierarchical Validity.","year":2025,"yearOfEvent":2025,"venue":"NeurIPS","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/nips/ZhangZCWLPLL25","documentPage":"http://papers.nips.cc/paper_files/paper/2025/hash/42ffaddcc6edc9fb05ff9f9b49fca700-Abstract-Datasets_and_Benchmarks_Track.html","type":"Inproceedings","doi":null,"authorSignatures":[{}],"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/nips/ZhangZCWLPLL25","documentUrl":"http://papers.nips.cc/paper_files/paper/2025/hash/42ffaddcc6edc9fb05ff9f9b49fca700-Abstract-Datasets_and_Benchmarks_Track.html"},{"key":"conf/siggraph/Yang00WW0L25","title":"LayerPano3D: Layered 3D Panorama for Hyper-Immersive Scene Generation.","year":2025,"yearOfEvent":2025,"venue":"SIGGRAPH (Conference Paper Track)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1145/3721238.3730643"],"source":"https://dblp.org/rec/conf/siggraph/Yang00WW0L25","documentPage":"https://doi.org/10.1145/3721238.3730643","type":"Inproceedings","doi":"https://doi.org/10.1145/3721238.3730643","authorSignatures":[{"orcid":"https://orcid.org/0000-0001-5557-0623","inst":"https://dblp.org/inst/1/452","instLabel":"Chinese University of Hong Kong (CUHK)"}],"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/siggraph/Yang00WW0L25","documentUrl":"https://doi.org/10.1145/3721238.3730643"},{"key":"journals/tog/LiZWTWL25","title":"SS4D: Native 4D Generative Model via Structured Spacetime Latents.","year":2025,"yearOfEvent":null,"venue":"ACM Trans. Graph.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1145/3763302"],"source":"https://dblp.org/rec/journals/tog/LiZWTWL25","documentPage":"https://doi.org/10.1145/3763302","type":"Article","doi":"https://doi.org/10.1145/3763302","authorSignatures":[{"orcid":"https://orcid.org/0000-0001-5557-0623","inst":"https://dblp.org/inst/1/055","instLabel":"Stanford University (SU)"}],"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/tog/LiZWTWL25","documentUrl":"https://doi.org/10.1145/3763302"}],"preprints":[{"key":"journals/corr/abs-2501-16330","title":"RelightVid: Temporal-Consistent Diffusion Model for Video Relighting.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2501.16330"],"source":"https://dblp.org/rec/journals/corr/abs-2501-16330","documentPage":"https://doi.org/10.48550/ARXIV.2501.16330","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2501.16330","authorSignatures":[{}],"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2501-16330","documentUrl":"https://doi.org/10.48550/ARXIV.2501.16330","arxivId":"2501.16330","arxivUrl":"https://arxiv.org/abs/2501.16330"},{"key":"journals/corr/abs-2502-08590","title":"Light-A-Video: Training-free Video Relighting via Progressive Light Fusion.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2502.08590"],"source":"https://dblp.org/rec/journals/corr/abs-2502-08590","documentPage":"https://doi.org/10.48550/ARXIV.2502.08590","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2502.08590","authorSignatures":[{}],"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2502-08590","documentUrl":"https://doi.org/10.48550/ARXIV.2502.08590","arxivId":"2502.08590","arxivUrl":"https://arxiv.org/abs/2502.08590"},{"key":"journals/corr/abs-2504-06232","title":"HiFlow: Training-free High-Resolution Image Generation with Flow-Aligned Guidance.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2504.06232"],"source":"https://dblp.org/rec/journals/corr/abs-2504-06232","documentPage":"https://doi.org/10.48550/ARXIV.2504.06232","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2504.06232","authorSignatures":[{}],"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2504-06232","documentUrl":"https://doi.org/10.48550/ARXIV.2504.06232","arxivId":"2504.06232","arxivUrl":"https://arxiv.org/abs/2504.06232"},{"key":"journals/corr/abs-2504-07083","title":"GenDoP: Auto-regressive Camera Trajectory Generation as a Director of Photography.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2504.07083"],"source":"https://dblp.org/rec/journals/corr/abs-2504-07083","documentPage":"https://doi.org/10.48550/ARXIV.2504.07083","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2504.07083","authorSignatures":[{}],"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2504-07083","documentUrl":"https://doi.org/10.48550/ARXIV.2504.07083","arxivId":"2504.07083","arxivUrl":"https://arxiv.org/abs/2504.07083"},{"key":"journals/corr/abs-2506-05210","title":"Towards Vision-Language-Garment Models for Web Knowledge Garment Understanding and Generation.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2506.05210"],"source":"https://dblp.org/rec/journals/corr/abs-2506-05210","documentPage":"https://doi.org/10.48550/ARXIV.2506.05210","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2506.05210","authorSignatures":[{}],"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-05210","documentUrl":"https://doi.org/10.48550/ARXIV.2506.05210","arxivId":"2506.05210","arxivUrl":"https://arxiv.org/abs/2506.05210"},{"key":"journals/corr/abs-2506-05284","title":"Video World Models with Long-term Spatial Memory.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2506.05284"],"source":"https://dblp.org/rec/journals/corr/abs-2506-05284","documentPage":"https://doi.org/10.48550/ARXIV.2506.05284","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2506.05284","authorSignatures":[{}],"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-05284","documentUrl":"https://doi.org/10.48550/ARXIV.2506.05284","arxivId":"2506.05284","arxivUrl":"https://arxiv.org/abs/2506.05284"},{"key":"journals/corr/abs-2508-04700","title":"SEAgent: Self-Evolving Computer Use Agent with Autonomous Learning from Experience.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2508.04700"],"source":"https://dblp.org/rec/journals/corr/abs-2508-04700","documentPage":"https://doi.org/10.48550/ARXIV.2508.04700","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2508.04700","authorSignatures":[{}],"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-04700","documentUrl":"https://doi.org/10.48550/ARXIV.2508.04700","arxivId":"2508.04700","arxivUrl":"https://arxiv.org/abs/2508.04700"},{"key":"journals/corr/abs-2508-05609","title":"Hi3DEval: Advancing 3D Generation Evaluation with Hierarchical Validity.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2508.05609"],"source":"https://dblp.org/rec/journals/corr/abs-2508-05609","documentPage":"https://doi.org/10.48550/ARXIV.2508.05609","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2508.05609","authorSignatures":[{}],"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-05609","documentUrl":"https://doi.org/10.48550/ARXIV.2508.05609","arxivId":"2508.05609","arxivUrl":"https://arxiv.org/abs/2508.05609"},{"key":"journals/corr/abs-2512-03036","title":"ViSAudio: End-to-End Video-Driven Binaural Spatial Audio Generation.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2512.03036"],"source":"https://dblp.org/rec/journals/corr/abs-2512-03036","documentPage":"https://doi.org/10.48550/ARXIV.2512.03036","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2512.03036","authorSignatures":[{}],"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-03036","documentUrl":"https://doi.org/10.48550/ARXIV.2512.03036","arxivId":"2512.03036","arxivUrl":"https://arxiv.org/abs/2512.03036"},{"key":"journals/corr/abs-2512-05076","title":"BulletTime: Decoupled Control of Time and Camera Pose for Video Generation.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2512.05076"],"source":"https://dblp.org/rec/journals/corr/abs-2512-05076","documentPage":"https://doi.org/10.48550/ARXIV.2512.05076","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2512.05076","authorSignatures":[{}],"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-05076","documentUrl":"https://doi.org/10.48550/ARXIV.2512.05076","arxivId":"2512.05076","arxivUrl":"https://arxiv.org/abs/2512.05076"},{"key":"journals/corr/abs-2512-11799","title":"V-RGBX: Video Editing with Accurate Controls over Intrinsic Properties.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2512.11799"],"source":"https://dblp.org/rec/journals/corr/abs-2512-11799","documentPage":"https://doi.org/10.48550/ARXIV.2512.11799","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2512.11799","authorSignatures":[{}],"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-11799","documentUrl":"https://doi.org/10.48550/ARXIV.2512.11799","arxivId":"2512.11799","arxivUrl":"https://arxiv.org/abs/2512.11799"},{"key":"journals/corr/abs-2512-14284","title":"SS4D: Native 4D Generative Model via Structured Spacetime Latents.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2512.14284"],"source":"https://dblp.org/rec/journals/corr/abs-2512-14284","documentPage":"https://doi.org/10.48550/ARXIV.2512.14284","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2512.14284","authorSignatures":[{}],"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-14284","documentUrl":"https://doi.org/10.48550/ARXIV.2512.14284","arxivId":"2512.14284","arxivUrl":"https://arxiv.org/abs/2512.14284"}],"excludedFormal":[],"excludedOther":[],"excludedHomonyms":[],"unassignedCandidates":[{"key":"conf/aaai/FanHGR0WZZ25","title":"EventPillars: Pillar-based Efficient Representations for Event Data.","year":2025,"yearOfEvent":2025,"venue":"AAAI","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1609/AAAI.V39I3.32292"],"source":"https://dblp.org/rec/conf/aaai/FanHGR0WZZ25","documentPage":"https://doi.org/10.1609/AAAI.V39I3.32292","type":"Inproceedings","doi":"https://doi.org/10.1609/AAAI.V39I3.32292","authorSignatures":[{}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/aaai/FanHGR0WZZ25","documentUrl":"https://doi.org/10.1609/AAAI.V39I3.32292"},{"key":"conf/aaai/JiangW0H25","title":"Sensing Surface Patches in Volume Rendering for Inferring Signed Distance Functions.","year":2025,"yearOfEvent":2025,"venue":"AAAI","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1609/AAAI.V39I4.32426"],"source":"https://dblp.org/rec/conf/aaai/JiangW0H25","documentPage":"https://doi.org/10.1609/AAAI.V39I4.32426","type":"Inproceedings","doi":"https://doi.org/10.1609/AAAI.V39I4.32426","authorSignatures":[{}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/aaai/JiangW0H25","documentUrl":"https://doi.org/10.1609/AAAI.V39I4.32426"},{"key":"conf/acl/JiaWQS25","title":"The Task Shield: Enforcing Task Alignment to Defend Against Indirect Prompt Injection in LLM Agents.","year":2025,"yearOfEvent":2025,"venue":"ACL (1)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.18653/V1/2025.ACL-LONG.1435"],"source":"https://dblp.org/rec/conf/acl/JiaWQS25","documentPage":"https://doi.org/10.18653/V1/2025.ACL-LONG.1435","type":"Inproceedings","doi":"https://doi.org/10.18653/V1/2025.ACL-LONG.1435","authorSignatures":[{}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/acl/JiaWQS25","documentUrl":"https://doi.org/10.18653/V1/2025.ACL-LONG.1435"},{"key":"conf/bdicn/WangLWYWG25","title":"The Influence of Marine Pollution Cognition on Seafood Consumption Resistance: The Moderating Role of Regulatory Focus in Big Data Analysis.","year":2025,"yearOfEvent":2025,"venue":"BDICN","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1145/3727353.3727414"],"source":"https://dblp.org/rec/conf/bdicn/WangLWYWG25","documentPage":"https://doi.org/10.1145/3727353.3727414","type":"Inproceedings","doi":"https://doi.org/10.1145/3727353.3727414","authorSignatures":[{"orcid":"https://orcid.org/0009-0000-1149-8703","inst":"https://dblp.org/inst/2/283","instLabel":"Xiamen University (XMU)"}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/bdicn/WangLWYWG25","documentUrl":"https://doi.org/10.1145/3727353.3727414"},{"key":"conf/cgi/WuWP24","title":"Automated Data Exploration and Analysis.","year":2025,"yearOfEvent":2024,"venue":"CGI (2)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1007/978-3-031-82021-2_27"],"source":"https://dblp.org/rec/conf/cgi/WuWP24","documentPage":"https://doi.org/10.1007/978-3-031-82021-2_27","type":"Inproceedings","doi":"https://doi.org/10.1007/978-3-031-82021-2_27","authorSignatures":[{"orcid":"https://orcid.org/0009-0005-7333-4727","inst":"https://dblp.org/inst/12/043","instLabel":"Southwest University of Science and Technology (SWUST)"}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/cgi/WuWP24","documentUrl":"https://doi.org/10.1007/978-3-031-82021-2_27"},{"key":"conf/chi/LuoWJDLLFHT25","title":"RemapVR: An Immersive Authoring Tool for Rapid Prototyping of Remapped Interaction in VR.","year":2025,"yearOfEvent":2025,"venue":"CHI","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1145/3706598.3714201"],"source":"https://dblp.org/rec/conf/chi/LuoWJDLLFHT25","documentPage":"https://doi.org/10.1145/3706598.3714201","type":"Inproceedings","doi":"https://doi.org/10.1145/3706598.3714201","authorSignatures":[{"orcid":"https://orcid.org/0009-0007-8720-7598","inst":"https://dblp.org/inst/11/691","instLabel":"Chinese Academy of Sciences (CAS)"},{"orcid":"https://orcid.org/0009-0007-8720-7598","inst":"https://dblp.org/inst/12/221","instLabel":"Institute of Software (IOS)"}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/chi/LuoWJDLLFHT25","documentUrl":"https://doi.org/10.1145/3706598.3714201"},{"key":"conf/chi/MartinezHSWZ25","title":"Generative Dreams: Rethinking GenAI Design Through a Community-based Approach with Recently Incarcerated, Gang Affiliated, and At-risk Young Adults at a Trauma Informed Arts Center.","year":2025,"yearOfEvent":2025,"venue":"CHI Extended Abstracts","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1145/3706599.3706679"],"source":"https://dblp.org/rec/conf/chi/MartinezHSWZ25","documentPage":"https://doi.org/10.1145/3706599.3706679","type":"Inproceedings","doi":"https://doi.org/10.1145/3706599.3706679","authorSignatures":[{"orcid":"https://orcid.org/0009-0000-6836-6699","inst":"https://dblp.org/inst/11/711","instLabel":"Google"}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/chi/MartinezHSWZ25","documentUrl":"https://doi.org/10.1145/3706599.3706679"},{"key":"conf/cikm/ChengWHGE25","title":"VideoAVE: A Multi-Attribute Video-to-Text Attribute Value Extraction Dataset and Benchmark Models.","year":2025,"yearOfEvent":2025,"venue":"CIKM","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1145/3746252.3761621"],"source":"https://dblp.org/rec/conf/cikm/ChengWHGE25","documentPage":"https://doi.org/10.1145/3746252.3761621","type":"Inproceedings","doi":"https://doi.org/10.1145/3746252.3761621","authorSignatures":[{"orcid":"https://orcid.org/0009-0004-8310-6501","inst":"https://dblp.org/inst/1/401","instLabel":"Virginia Tech"}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/cikm/ChengWHGE25","documentUrl":"https://doi.org/10.1145/3746252.3761621"},{"key":"conf/coling/JiangJWSXY25","title":"Automated Progressive Red Teaming.","year":2025,"yearOfEvent":2025,"venue":"COLING","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/coling/JiangJWSXY25","documentPage":"https://aclanthology.org/2025.coling-main.260/","type":"Inproceedings","doi":null,"authorSignatures":[{}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/coling/JiangJWSXY25","documentUrl":"https://aclanthology.org/2025.coling-main.260/"},{"key":"conf/cscwd/HeWW25","title":"IEDA4Med: Iterative EDA Method for Medical Examination Data Based on Diagnostic Text.","year":2025,"yearOfEvent":2025,"venue":"CSCWD","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/CSCWD64889.2025.11033313"],"source":"https://dblp.org/rec/conf/cscwd/HeWW25","documentPage":"https://doi.org/10.1109/CSCWD64889.2025.11033313","type":"Inproceedings","doi":"https://doi.org/10.1109/CSCWD64889.2025.11033313","authorSignatures":[{"inst":"https://dblp.org/inst/12/043","instLabel":"Southwest University of Science and Technology (SWUST)"}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/cscwd/HeWW25","documentUrl":"https://doi.org/10.1109/CSCWD64889.2025.11033313"},{"key":"conf/cscwd/PengWWL25","title":"Multimodal Interaction-Driven User Intent Perception Model and Application.","year":2025,"yearOfEvent":2025,"venue":"CSCWD","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/CSCWD64889.2025.11033301"],"source":"https://dblp.org/rec/conf/cscwd/PengWWL25","documentPage":"https://doi.org/10.1109/CSCWD64889.2025.11033301","type":"Inproceedings","doi":"https://doi.org/10.1109/CSCWD64889.2025.11033301","authorSignatures":[{"inst":"https://dblp.org/inst/12/043","instLabel":"Southwest University of Science and Technology (SWUST)"}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/cscwd/PengWWL25","documentUrl":"https://doi.org/10.1109/CSCWD64889.2025.11033301"},{"key":"conf/cvpr/BuL0WDZCL025","title":"ByTheWay: Boost Your Text-to-Video Generation Model to Higher Quality in a Training-free Way.","year":2025,"yearOfEvent":2025,"venue":"CVPR","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/CVPR52734.2025.01213"],"source":"https://dblp.org/rec/conf/cvpr/BuL0WDZCL025","documentPage":"https://openaccess.thecvf.com/content/CVPR2025/html/Bu_ByTheWay_Boost_Your_Text-to-Video_Generation_Model_to_Higher_Quality_in_CVPR_2025_paper.html","type":"Inproceedings","doi":"https://doi.org/10.1109/CVPR52734.2025.01213","authorSignatures":[{"inst":"https://dblp.org/inst/1/449","instLabel":"University of Hong Kong (HKU)"},{"inst":"https://dblp.org/inst/1/452","instLabel":"Chinese University of Hong Kong (CUHK)"}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/BuL0WDZCL025","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Bu_ByTheWay_Boost_Your_Text-to-Video_Generation_Model_to_Higher_Quality_in_CVPR_2025_paper.html"},{"key":"conf/cvpr/Wang0WLB025","title":"FSFM: A Generalizable Face Security Foundation Model via Self-Supervised Facial Representation Learning.","year":2025,"yearOfEvent":2025,"venue":"CVPR","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/CVPR52734.2025.02269"],"source":"https://dblp.org/rec/conf/cvpr/Wang0WLB025","documentPage":"https://openaccess.thecvf.com/content/CVPR2025/html/Wang_FSFM_A_Generalizable_Face_Security_Foundation_Model_via_Self-Supervised_Facial_CVPR_2025_paper.html","type":"Inproceedings","doi":"https://doi.org/10.1109/CVPR52734.2025.02269","authorSignatures":[{"inst":"https://dblp.org/inst/1/584","instLabel":"Zhejiang University (ZJU)"}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/Wang0WLB025","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Wang_FSFM_A_Generalizable_Face_Security_Foundation_Model_via_Self-Supervised_Facial_CVPR_2025_paper.html"},{"key":"conf/cvpr/WangWCW0Z25","title":"OmniMMI: A Comprehensive Multi-modal Interaction Benchmark in Streaming Video Contexts.","year":2025,"yearOfEvent":2025,"venue":"CVPR","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/CVPR52734.2025.01763"],"source":"https://dblp.org/rec/conf/cvpr/WangWCW0Z25","documentPage":"https://openaccess.thecvf.com/content/CVPR2025/html/Wang_OmniMMI_A_Comprehensive_Multi-modal_Interaction_Benchmark_in_Streaming_Video_Contexts_CVPR_2025_paper.html","type":"Inproceedings","doi":"https://doi.org/10.1109/CVPR52734.2025.01763","authorSignatures":[{"inst":"https://dblp.org/inst/12/115","instLabel":"Beijing Academy of Artificial Intelligence (BAAI)"}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/WangWCW0Z25","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Wang_OmniMMI_A_Comprehensive_Multi-modal_Interaction_Benchmark_in_Streaming_Video_Contexts_CVPR_2025_paper.html"},{"key":"conf/dsa/WuXYMH25","title":"A Collision-Induced Evaluation Framework for End-to-End Autonomous Driving Model.","year":2025,"yearOfEvent":2025,"venue":"DSA","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/DSA66321.2025.00052"],"source":"https://dblp.org/rec/conf/dsa/WuXYMH25","documentPage":"https://doi.org/10.1109/DSA66321.2025.00052","type":"Inproceedings","doi":"https://doi.org/10.1109/DSA66321.2025.00052","authorSignatures":[{"inst":"https://dblp.org/inst/1/155","instLabel":"Tsinghua University (THU)"}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/dsa/WuXYMH25","documentUrl":"https://doi.org/10.1109/DSA66321.2025.00052"},{"key":"conf/eilm/OuyangYWZ25","title":"TalkPersonaDiff: High-Fidelity Speech-Driven 3D Facial Animation Generation via Unified Multimodal Synergistic Encoding and Dual-Style Modulation.","year":2025,"yearOfEvent":2025,"venue":"EILM","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1145/3788731.3788741"],"source":"https://dblp.org/rec/conf/eilm/OuyangYWZ25","documentPage":"https://doi.org/10.1145/3788731.3788741","type":"Inproceedings","doi":"https://doi.org/10.1145/3788731.3788741","authorSignatures":[{"orcid":"https://orcid.org/0009-0002-4263-3650","inst":"https://dblp.org/inst/2/008","instLabel":"Beijing University of Posts and Telecommunications (BUPT)"}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/eilm/OuyangYWZ25","documentUrl":"https://doi.org/10.1145/3788731.3788741"},{"key":"conf/hpca/YangHWYW00SF25","title":"GoPIM: GCN-Oriented Pipeline Optimization for PIM Accelerators.","year":2025,"yearOfEvent":2025,"venue":"HPCA","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/HPCA61900.2025.00056"],"source":"https://dblp.org/rec/conf/hpca/YangHWYW00SF25","documentPage":"https://doi.org/10.1109/HPCA61900.2025.00056","type":"Inproceedings","doi":"https://doi.org/10.1109/HPCA61900.2025.00056","authorSignatures":[{"inst":"https://dblp.org/inst/1/584","instLabel":"Zhejiang University (ZJU)"},{"inst":"https://dblp.org/inst/12/021","instLabel":"Zhejiang Lab"}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/hpca/YangHWYW00SF25","documentUrl":"https://doi.org/10.1109/HPCA61900.2025.00056"},{"key":"conf/icaie/WangLWWY25","title":"The Design and Teaching Application of the Comprehensive Experimental Platform for Modular Embedded Intelligent Vehicles.","year":2025,"yearOfEvent":2025,"venue":"ICAIE","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1145/3797552.3797700"],"source":"https://dblp.org/rec/conf/icaie/WangLWWY25","documentPage":"https://doi.org/10.1145/3797552.3797700","type":"Inproceedings","doi":"https://doi.org/10.1145/3797552.3797700","authorSignatures":[{"orcid":"https://orcid.org/0009-0000-0446-1574","inst":"https://dblp.org/inst/2/471","instLabel":"Jilin University"}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/icaie/WangLWWY25","documentUrl":"https://doi.org/10.1145/3797552.3797700"},{"key":"conf/icassp/Jiang0YL0WLZ25","title":"CoMT: Chain-of-Medical-Thought Reduces Hallucination in Medical Report Generation.","year":2025,"yearOfEvent":2025,"venue":"ICASSP","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/ICASSP49660.2025.10887699"],"source":"https://dblp.org/rec/conf/icassp/Jiang0YL0WLZ25","documentPage":"https://doi.org/10.1109/ICASSP49660.2025.10887699","type":"Inproceedings","doi":"https://doi.org/10.1109/ICASSP49660.2025.10887699","authorSignatures":[{"inst":"https://dblp.org/inst/12/029","instLabel":"Tencent"},{"inst":"https://dblp.org/inst/2/283","instLabel":"Xiamen University (XMU)"}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/icassp/Jiang0YL0WLZ25","documentUrl":"https://doi.org/10.1109/ICASSP49660.2025.10887699"},{"key":"conf/iccip/QinL0XW25","title":"Lightweight Intelligent Task Classification Model for Heterogeneous Data in Non-Terrestrial Networks.","year":2025,"yearOfEvent":2025,"venue":"ICCIP","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1145/3784833.3784923"],"source":"https://dblp.org/rec/conf/iccip/QinL0XW25","documentPage":"https://doi.org/10.1145/3784833.3784923","type":"Inproceedings","doi":"https://doi.org/10.1145/3784833.3784923","authorSignatures":[{"orcid":"https://orcid.org/0009-0007-5485-2232"}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iccip/QinL0XW25","documentUrl":"https://doi.org/10.1145/3784833.3784923"},{"key":"conf/iccv/SunCZWZDXLW25","title":"X-Prompt: Generalizable Auto-Regressive Visual Learning with In-Context Prompting.","year":2025,"yearOfEvent":2025,"venue":"ICCV","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/ICCV51701.2025.01604"],"source":"https://dblp.org/rec/conf/iccv/SunCZWZDXLW25","documentPage":"https://doi.org/10.1109/ICCV51701.2025.01604","type":"Inproceedings","doi":"https://doi.org/10.1109/ICCV51701.2025.01604","authorSignatures":[{}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/SunCZWZDXLW25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.01604"},{"key":"conf/iccv/ZengLGFWWL25","title":"An Efficient Hybrid Vision Transformer for Tinyml Applications.","year":2025,"yearOfEvent":2025,"venue":"ICCV","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/ICCV51701.2025.01852"],"source":"https://dblp.org/rec/conf/iccv/ZengLGFWWL25","documentPage":"https://doi.org/10.1109/ICCV51701.2025.01852","type":"Inproceedings","doi":"https://doi.org/10.1109/ICCV51701.2025.01852","authorSignatures":[{"inst":"https://dblp.org/inst/1/778","instLabel":"Xidian University"}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/ZengLGFWWL25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.01852"},{"key":"conf/icer/ManeshW0025","title":"Understanding and Improving Student Note-Taking in Live Coding Lectures.","year":2025,"yearOfEvent":2025,"venue":"ICER (1)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1145/3702652.3744224"],"source":"https://dblp.org/rec/conf/icer/ManeshW0025","documentPage":"https://doi.org/10.1145/3702652.3744224","type":"Inproceedings","doi":"https://doi.org/10.1145/3702652.3744224","authorSignatures":[{"orcid":"https://orcid.org/0009-0004-8310-6501","inst":"https://dblp.org/inst/1/401","instLabel":"Virginia Tech"}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/icer/ManeshW0025","documentUrl":"https://doi.org/10.1145/3702652.3744224"},{"key":"conf/icip/WuK25","title":"Geometric Mean Improves Loss For Few-Shot Learning.","year":2025,"yearOfEvent":2025,"venue":"ICIP","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/ICIP55913.2025.11084713"],"source":"https://dblp.org/rec/conf/icip/WuK25","documentPage":"https://doi.org/10.1109/ICIP55913.2025.11084713","type":"Inproceedings","doi":"https://doi.org/10.1109/ICIP55913.2025.11084713","authorSignatures":[{"inst":"https://dblp.org/inst/3/455","instLabel":"University of Tsukuba"}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/icip/WuK25","documentUrl":"https://doi.org/10.1109/ICIP55913.2025.11084713"},{"key":"conf/icis/Wu25","title":"User Engagement with Online Deals: The Role of Discounts and Poster Status.","year":2025,"yearOfEvent":2025,"venue":"ICIS","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/icis/Wu25","documentPage":"https://aisel.aisnet.org/icis2025/user_behav/user_behav/1","type":"Inproceedings","doi":null,"authorSignatures":[{}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/icis/Wu25","documentUrl":"https://aisel.aisnet.org/icis2025/user_behav/user_behav/1"},{"key":"conf/iclr/WuZSXZAI0MZ25","title":"Instructional Segment Embedding: Improving LLM Safety with Instruction Hierarchy.","year":2025,"yearOfEvent":2025,"venue":"ICLR","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/iclr/WuZSXZAI0MZ25","documentPage":"https://openreview.net/forum?id=sjWG7B8dvt","type":"Inproceedings","doi":null,"authorSignatures":[{}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iclr/WuZSXZAI0MZ25","documentUrl":"https://openreview.net/forum?id=sjWG7B8dvt"},{"key":"conf/icmcs/LiLSWC25","title":"Trustworthy Localized Corrections-guided Mutual Learning for Multi-View Learning.","year":2025,"yearOfEvent":2025,"venue":"ICME","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/ICME59968.2025.11209409"],"source":"https://dblp.org/rec/conf/icmcs/LiLSWC25","documentPage":"https://doi.org/10.1109/ICME59968.2025.11209409","type":"Inproceedings","doi":"https://doi.org/10.1109/ICME59968.2025.11209409","authorSignatures":[{"inst":"https://dblp.org/inst/6/924","instLabel":"University of Electronic Science and Technology of China (UESTC)"}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/icmcs/LiLSWC25","documentUrl":"https://doi.org/10.1109/ICME59968.2025.11209409"},{"key":"conf/icmcs/WuWLWLZ25","title":"Multimodal Causal Reasoning-Guided Intrinsic Goals for Efficient Task Completion in Reinforcement Learning.","year":2025,"yearOfEvent":2025,"venue":"ICME","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/ICME59968.2025.11210033"],"source":"https://dblp.org/rec/conf/icmcs/WuWLWLZ25","documentPage":"https://doi.org/10.1109/ICME59968.2025.11210033","type":"Inproceedings","doi":"https://doi.org/10.1109/ICME59968.2025.11210033","authorSignatures":[{"orcid":"https://orcid.org/0009-0000-7406-5358","inst":"https://dblp.org/inst/6/924","instLabel":"University of Electronic Science and Technology of China (UESTC)"}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/icmcs/WuWLWLZ25","documentUrl":"https://doi.org/10.1109/ICME59968.2025.11210033"},{"key":"conf/icml/WuJ0025","title":"Label Distribution Propagation-based Label Completion for Crowdsourcing.","year":2025,"yearOfEvent":2025,"venue":"ICML","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/icml/WuJ0025","documentPage":"https://proceedings.mlr.press/v267/wu25n.html","type":"Inproceedings","doi":null,"authorSignatures":[{}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/icml/WuJ0025","documentUrl":"https://proceedings.mlr.press/v267/wu25n.html"},{"key":"conf/icml/WuSJ0Z25","title":"TokenSwift: Lossless Acceleration of Ultra Long Sequence Generation.","year":2025,"yearOfEvent":2025,"venue":"ICML","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/icml/WuSJ0Z25","documentPage":"https://proceedings.mlr.press/v267/wu25z.html","type":"Inproceedings","doi":null,"authorSignatures":[{}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/icml/WuSJ0Z25","documentUrl":"https://proceedings.mlr.press/v267/wu25z.html"},{"key":"conf/iconip/WuLY24","title":"CRA-Eformer: Cross-Scale Residual Attention-Based Edge-Guide Transformer for Low-Dose CT Denoising.","year":2025,"yearOfEvent":2024,"venue":"ICONIP (5)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1007/978-981-96-6588-4_9"],"source":"https://dblp.org/rec/conf/iconip/WuLY24","documentPage":"https://doi.org/10.1007/978-981-96-6588-4_9","type":"Inproceedings","doi":"https://doi.org/10.1007/978-981-96-6588-4_9","authorSignatures":[{"inst":"https://dblp.org/inst/1/464","instLabel":"Auckland University of Technology (AUT)"}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iconip/WuLY24","documentUrl":"https://doi.org/10.1007/978-981-96-6588-4_9"},{"key":"conf/icra/LiHGWZZD25","title":"Chemistry3D: Robotic Interaction Toolkit for Chemistry Experiments.","year":2025,"yearOfEvent":2025,"venue":"ICRA","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/ICRA55743.2025.11128846"],"source":"https://dblp.org/rec/conf/icra/LiHGWZZD25","documentPage":"https://doi.org/10.1109/ICRA55743.2025.11128846","type":"Inproceedings","doi":"https://doi.org/10.1109/ICRA55743.2025.11128846","authorSignatures":[{"inst":"https://dblp.org/inst/1/155","instLabel":"Tsinghua University (THU)"},{"inst":"https://dblp.org/inst/12/357","instLabel":"University Town of Shenzhen"}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/icra/LiHGWZZD25","documentUrl":"https://doi.org/10.1109/ICRA55743.2025.11128846"},{"key":"conf/icws/LiuSWA25","title":"A Verifiable and Low-Latency Cross-Chain IoT Service Query Scheme with Collaborative Indexing.","year":2025,"yearOfEvent":2025,"venue":"ICWS","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/ICWS67624.2025.00073"],"source":"https://dblp.org/rec/conf/icws/LiuSWA25","documentPage":"https://doi.org/10.1109/ICWS67624.2025.00073","type":"Inproceedings","doi":"https://doi.org/10.1109/ICWS67624.2025.00073","authorSignatures":[{"inst":"https://dblp.org/inst/2/496","instLabel":"University of Science and Technology Beijing (USTB)"},{"inst":"https://dblp.org/inst/9/410","instLabel":"Beijing Information Science & Technology University (BISTU)"}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/icws/LiuSWA25","documentUrl":"https://doi.org/10.1109/ICWS67624.2025.00073"},{"key":"conf/icws/LiuSWA25a","title":"Cross-Chain Iot Service Composition: an Adaptive QoS Constraint-Based Approach.","year":2025,"yearOfEvent":2025,"venue":"ICWS","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/ICWS67624.2025.00086"],"source":"https://dblp.org/rec/conf/icws/LiuSWA25a","documentPage":"https://doi.org/10.1109/ICWS67624.2025.00086","type":"Inproceedings","doi":"https://doi.org/10.1109/ICWS67624.2025.00086","authorSignatures":[{"inst":"https://dblp.org/inst/2/496","instLabel":"University of Science and Technology Beijing (USTB)"}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/icws/LiuSWA25a","documentUrl":"https://doi.org/10.1109/ICWS67624.2025.00086"},{"key":"conf/iros/ZhouZWZZ25","title":"HAC-LOCO: Learning Hierarchical Active Compliance Control for Quadruped Locomotion under Continuous External Disturbances.","year":2025,"yearOfEvent":2025,"venue":"IROS","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/IROS60139.2025.11247775"],"source":"https://dblp.org/rec/conf/iros/ZhouZWZZ25","documentPage":"https://doi.org/10.1109/IROS60139.2025.11247775","type":"Inproceedings","doi":"https://doi.org/10.1109/IROS60139.2025.11247775","authorSignatures":[{"inst":"https://dblp.org/inst/1/557","instLabel":"Harbin Institute of Technology (HIT)"}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iros/ZhouZWZZ25","documentUrl":"https://doi.org/10.1109/IROS60139.2025.11247775"},{"key":"conf/isscc/LinWLCZKCH25","title":"2.9 STEP: An 8K-60fps Space-Time Resolution-Enhancement Neural-Network Processor for Next-Generation Display and Streaming.","year":2025,"yearOfEvent":2025,"venue":"ISSCC","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/ISSCC49661.2025.10904700"],"source":"https://dblp.org/rec/conf/isscc/LinWLCZKCH25","documentPage":"https://doi.org/10.1109/ISSCC49661.2025.10904700","type":"Inproceedings","doi":"https://doi.org/10.1109/ISSCC49661.2025.10904700","authorSignatures":[{"inst":"https://dblp.org/inst/1/340","instLabel":"National Tsing Hua University (NTHU)"}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/isscc/LinWLCZKCH25","documentUrl":"https://doi.org/10.1109/ISSCC49661.2025.10904700"},{"key":"conf/micad2/AliWMH24","title":"Synth-to-Segment: MRI Brain Tumor Segmentation with Diffusion Transformers and Attention U-Net.","year":2025,"yearOfEvent":2024,"venue":"MICAD","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1007/978-981-96-3863-5_12"],"source":"https://dblp.org/rec/conf/micad2/AliWMH24","documentPage":"https://doi.org/10.1007/978-981-96-3863-5_12","type":"Inproceedings","doi":"https://doi.org/10.1007/978-981-96-3863-5_12","authorSignatures":[{"inst":"https://dblp.org/inst/1/584","instLabel":"Zhejiang University (ZJU)"},{"inst":"https://dblp.org/inst/1/657","instLabel":"University of Illinois Urbana-Champaign (UIUC)"}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/micad2/AliWMH24","documentUrl":"https://doi.org/10.1007/978-981-96-3863-5_12"},{"key":"conf/nips/ShenIWXMK25","title":"ReliabilityRAG: Effective and Provably Robust Defense for RAG-based Web-Search.","year":2025,"yearOfEvent":2025,"venue":"NeurIPS","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/nips/ShenIWXMK25","documentPage":"http://papers.nips.cc/paper_files/paper/2025/hash/41457d56a2fdd20b4c072190290a549b-Abstract-Conference.html","type":"Inproceedings","doi":null,"authorSignatures":[{}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/nips/ShenIWXMK25","documentUrl":"http://papers.nips.cc/paper_files/paper/2025/hash/41457d56a2fdd20b4c072190290a549b-Abstract-Conference.html"},{"key":"conf/nips/WangMWX25","title":"Towards a Golden Classifier-Free Guidance Path via Foresight Fixed Point Iterations.","year":2025,"yearOfEvent":2025,"venue":"NeurIPS","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/nips/WangMWX25","documentPage":"http://papers.nips.cc/paper_files/paper/2025/hash/b56d827a2b8433517e722e0272c7f464-Abstract-Conference.html","type":"Inproceedings","doi":null,"authorSignatures":[{}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/nips/WangMWX25","documentUrl":"http://papers.nips.cc/paper_files/paper/2025/hash/b56d827a2b8433517e722e0272c7f464-Abstract-Conference.html"},{"key":"conf/nips/ZhaoWWXYLWWZH25","title":"Absolute Zero: Reinforced Self-play Reasoning with Zero Data.","year":2025,"yearOfEvent":2025,"venue":"NeurIPS","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/nips/ZhaoWWXYLWWZH25","documentPage":"http://papers.nips.cc/paper_files/paper/2025/hash/9837dc00ff67d176373268ed48042d49-Abstract-Conference.html","type":"Inproceedings","doi":null,"authorSignatures":[{}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/nips/ZhaoWWXYLWWZH25","documentUrl":"http://papers.nips.cc/paper_files/paper/2025/hash/9837dc00ff67d176373268ed48042d49-Abstract-Conference.html"},{"key":"conf/sigcse/WuTWCSC25","title":"The Impact of Group Discussion and Formation on Student Performance: An Experience Report in a Large CS1 Course.","year":2025,"yearOfEvent":2025,"venue":"SIGCSE (1)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1145/3641554.3701973"],"source":"https://dblp.org/rec/conf/sigcse/WuTWCSC25","documentPage":"https://doi.org/10.1145/3641554.3701973","type":"Inproceedings","doi":"https://doi.org/10.1145/3641554.3701973","authorSignatures":[{"orcid":"https://orcid.org/0009-0004-8310-6501","inst":"https://dblp.org/inst/1/401","instLabel":"Virginia Tech"}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/sigcse/WuTWCSC25","documentUrl":"https://doi.org/10.1145/3641554.3701973"},{"key":"conf/smc/ZhuWZW25","title":"Auto-Visualization Driven Visual Analytics for Elderly Care Institutions.","year":2025,"yearOfEvent":2025,"venue":"SMC","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/SMC58881.2025.11343460"],"source":"https://dblp.org/rec/conf/smc/ZhuWZW25","documentPage":"https://doi.org/10.1109/SMC58881.2025.11343460","type":"Inproceedings","doi":"https://doi.org/10.1109/SMC58881.2025.11343460","authorSignatures":[{"inst":"https://dblp.org/inst/12/043","instLabel":"Southwest University of Science and Technology (SWUST)"}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/smc/ZhuWZW25","documentUrl":"https://doi.org/10.1109/SMC58881.2025.11343460"},{"key":"conf/uai/CaiWX25","title":"Fast Non-convex Matrix Sensing with Optimal Sample Complexity.","year":2025,"yearOfEvent":2025,"venue":"UAI","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/uai/CaiWX25","documentPage":"https://proceedings.mlr.press/v286/cai25b.html","type":"Inproceedings","doi":null,"authorSignatures":[{}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/uai/CaiWX25","documentUrl":"https://proceedings.mlr.press/v286/cai25b.html"},{"key":"conf/vr/LiWHSLH0ZZ0W25","title":"A Dual-Stick Controller for Enhancing Raycasting Interactions with Virtual Objects.","year":2025,"yearOfEvent":2025,"venue":"VR","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/VR59515.2025.00062"],"source":"https://dblp.org/rec/conf/vr/LiWHSLH0ZZ0W25","documentPage":"https://doi.org/10.1109/VR59515.2025.00062","type":"Inproceedings","doi":"https://doi.org/10.1109/VR59515.2025.00062","authorSignatures":[{"inst":"https://dblp.org/inst/11/691","instLabel":"Chinese Academy of Sciences (CAS)"},{"inst":"https://dblp.org/inst/12/221","instLabel":"Institute of Software (IOS)"}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/vr/LiWHSLH0ZZ0W25","documentUrl":"https://doi.org/10.1109/VR59515.2025.00062"},{"key":"conf/vtc/SuLWZHWZ25","title":"A Novel Scenario Reconstruction Method Based on 3D Point Cloud Data and RT Channel Modeling for 6G Indoor Communications.","year":2025,"yearOfEvent":2025,"venue":"VTC2025-Fall","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/VTC2025-FALL65116.2025.11310383"],"source":"https://dblp.org/rec/conf/vtc/SuLWZHWZ25","documentPage":"https://doi.org/10.1109/VTC2025-FALL65116.2025.11310383","type":"Inproceedings","doi":"https://doi.org/10.1109/VTC2025-FALL65116.2025.11310383","authorSignatures":[{"inst":"https://dblp.org/inst/2/470","instLabel":"Southeast University (SEU)"}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/vtc/SuLWZHWZ25","documentUrl":"https://doi.org/10.1109/VTC2025-FALL65116.2025.11310383"},{"key":"conf/wacv/YaoZPWX25","title":"DepthSSC: Monocular 3D Semantic Scene Completion via Depth-Spatial Alignment and Voxel Adaptation.","year":2025,"yearOfEvent":2025,"venue":"WACV","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/WACV61041.2025.00216"],"source":"https://dblp.org/rec/conf/wacv/YaoZPWX25","documentPage":"https://doi.org/10.1109/WACV61041.2025.00216","type":"Inproceedings","doi":"https://doi.org/10.1109/WACV61041.2025.00216","authorSignatures":[{"inst":"https://dblp.org/inst/1/064","instLabel":"University of Washington (UW)"}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/wacv/YaoZPWX25","documentUrl":"https://doi.org/10.1109/WACV61041.2025.00216"},{"key":"journals/access/DengWW25","title":"Research on the Classification of Electromagnetic Radiation Safety Levels of Mobile Communication Terminals Using Unsupervised Learning Models.","year":2025,"yearOfEvent":null,"venue":"IEEE Access","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1109/ACCESS.2025.3585928"],"source":"https://dblp.org/rec/journals/access/DengWW25","documentPage":"https://doi.org/10.1109/ACCESS.2025.3585928","type":"Article","doi":"https://doi.org/10.1109/ACCESS.2025.3585928","authorSignatures":[{"orcid":"https://orcid.org/0000-0002-1920-5044"}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/access/DengWW25","documentUrl":"https://doi.org/10.1109/ACCESS.2025.3585928"},{"key":"journals/access/ZhouWZLPZSLH25","title":"Non-Staggered Hexagonal Meta-Atom-Based Metasurface for Broadband and Multipolarized OAM Generation.","year":2025,"yearOfEvent":null,"venue":"IEEE Access","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1109/ACCESS.2025.3625214"],"source":"https://dblp.org/rec/journals/access/ZhouWZLPZSLH25","documentPage":"https://doi.org/10.1109/ACCESS.2025.3625214","type":"Article","doi":"https://doi.org/10.1109/ACCESS.2025.3625214","authorSignatures":[{"orcid":"https://orcid.org/0009-0008-3513-8073","inst":"https://dblp.org/inst/2/468","instLabel":"Nanjing University of Aeronautics and Astronautics (NUAA)"}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/access/ZhouWZLPZSLH25","documentUrl":"https://doi.org/10.1109/ACCESS.2025.3625214"},{"key":"journals/asc/WuL25","title":"Tensor idempotent representation with auto-weighted exponential tensor nuclear norm minimization for multi-view clustering.","year":2025,"yearOfEvent":null,"venue":"Appl. Soft Comput.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1016/J.ASOC.2025.113103"],"source":"https://dblp.org/rec/journals/asc/WuL25","documentPage":"https://doi.org/10.1016/J.ASOC.2025.113103","type":"Article","doi":"https://doi.org/10.1016/J.ASOC.2025.113103","authorSignatures":[{"orcid":"https://orcid.org/0009-0001-7417-5781","inst":"https://dblp.org/inst/7/754","instLabel":"Anhui Polytechnic University (AUTS)"}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/asc/WuL25","documentUrl":"https://doi.org/10.1016/J.ASOC.2025.113103"},{"key":"journals/cmc/WuZ25","title":"Research on Fault Probability Based on Hamming Weight in Fault Injection Attack.","year":2025,"yearOfEvent":null,"venue":"Comput. Mater. Continua","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.32604/CMC.2025.066525"],"source":"https://dblp.org/rec/journals/cmc/WuZ25","documentPage":"https://doi.org/10.32604/CMC.2025.066525","type":"Article","doi":"https://doi.org/10.32604/CMC.2025.066525","authorSignatures":[{}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/cmc/WuZ25","documentUrl":"https://doi.org/10.32604/CMC.2025.066525"},{"key":"journals/cmc/XiongWSHY25","title":"Thermodynamics Calculation of Reaction Synthesis Pathways for Ag-Al2O3 Powder By First-Principles Calculations.","year":2025,"yearOfEvent":null,"venue":"Comput. Mater. Continua","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.32604/CMC.2025.067722"],"source":"https://dblp.org/rec/journals/cmc/XiongWSHY25","documentPage":"https://doi.org/10.32604/CMC.2025.067722","type":"Article","doi":"https://doi.org/10.32604/CMC.2025.067722","authorSignatures":[{}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/cmc/XiongWSHY25","documentUrl":"https://doi.org/10.32604/CMC.2025.067722"},{"key":"journals/cmig/AliWHLXZJYY25","title":"A review of the Segment Anything Model (SAM) for medical image analysis: Accomplishments and perspectives.","year":2025,"yearOfEvent":null,"venue":"Comput. Medical Imaging Graph.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1016/J.COMPMEDIMAG.2024.102473"],"source":"https://dblp.org/rec/journals/cmig/AliWHLXZJYY25","documentPage":"https://doi.org/10.1016/J.COMPMEDIMAG.2024.102473","type":"Article","doi":"https://doi.org/10.1016/J.COMPMEDIMAG.2024.102473","authorSignatures":[{"inst":"https://dblp.org/inst/1/584","instLabel":"Zhejiang University (ZJU)"},{"inst":"https://dblp.org/inst/1/657","instLabel":"University of Illinois Urbana-Champaign (UIUC)"}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/cmig/AliWHLXZJYY25","documentUrl":"https://doi.org/10.1016/J.COMPMEDIMAG.2024.102473"},{"key":"journals/corr/abs-2501-01696","title":"Guaranteed Nonconvex Low-Rank Tensor Estimation via Scaled Gradient Descent.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2501.01696"],"source":"https://dblp.org/rec/journals/corr/abs-2501-01696","documentPage":"https://doi.org/10.48550/ARXIV.2501.01696","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2501.01696","authorSignatures":[{}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2501-01696","documentUrl":"https://doi.org/10.48550/ARXIV.2501.01696"},{"key":"journals/corr/abs-2501-08680","title":"Digital Twin Online Channel Modeling: Challenges,Principles, and Applications.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2501.08680"],"source":"https://dblp.org/rec/journals/corr/abs-2501-08680","documentPage":"https://doi.org/10.48550/ARXIV.2501.08680","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2501.08680","authorSignatures":[{}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2501-08680","documentUrl":"https://doi.org/10.48550/ARXIV.2501.08680"},{"key":"journals/corr/abs-2501-14593","title":"Geometric Mean Improves Loss For Few-Shot Learning.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2501.14593"],"source":"https://dblp.org/rec/journals/corr/abs-2501-14593","documentPage":"https://doi.org/10.48550/ARXIV.2501.14593","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2501.14593","authorSignatures":[{}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2501-14593","documentUrl":"https://doi.org/10.48550/ARXIV.2501.14593"},{"key":"journals/corr/abs-2502-18890","title":"From Hours to Minutes: Lossless Acceleration of Ultra Long Sequence Generation up to 100K Tokens.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2502.18890"],"source":"https://dblp.org/rec/journals/corr/abs-2502-18890","documentPage":"https://doi.org/10.48550/ARXIV.2502.18890","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2502.18890","authorSignatures":[{}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2502-18890","documentUrl":"https://doi.org/10.48550/ARXIV.2502.18890"},{"key":"journals/corr/abs-2503-01177","title":"Scalable Connectivity for Ising Machines: Dense to Sparse.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2503.01177"],"source":"https://dblp.org/rec/journals/corr/abs-2503-01177","documentPage":"https://doi.org/10.48550/ARXIV.2503.01177","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2503.01177","authorSignatures":[{}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-01177","documentUrl":"https://doi.org/10.48550/ARXIV.2503.01177"},{"key":"journals/corr/abs-2503-21745","title":"3DGen-Bench: Comprehensive Benchmark Suite for 3D Generative Models.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2503.21745"],"source":"https://dblp.org/rec/journals/corr/abs-2503-21745","documentPage":"https://doi.org/10.48550/ARXIV.2503.21745","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2503.21745","authorSignatures":[{}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-21745","documentUrl":"https://doi.org/10.48550/ARXIV.2503.21745"},{"key":"journals/corr/abs-2503-22952","title":"OmniMMI: A Comprehensive Multi-modal Interaction Benchmark in Streaming Video Contexts.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2503.22952"],"source":"https://dblp.org/rec/journals/corr/abs-2503-22952","documentPage":"https://doi.org/10.48550/ARXIV.2503.22952","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2503.22952","authorSignatures":[{}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-22952","documentUrl":"https://doi.org/10.48550/ARXIV.2503.22952"},{"key":"journals/corr/abs-2503-24370","title":"Effectively Controlling Reasoning Models through Thinking Intervention.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2503.24370"],"source":"https://dblp.org/rec/journals/corr/abs-2503-24370","documentPage":"https://doi.org/10.48550/ARXIV.2503.24370","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2503.24370","authorSignatures":[{}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-24370","documentUrl":"https://doi.org/10.48550/ARXIV.2503.24370"},{"key":"journals/corr/abs-2504-19194","title":"VTire: A Bimodal Visuotactile Tire with High-Resolution Sensing Capability.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2504.19194"],"source":"https://dblp.org/rec/journals/corr/abs-2504-19194","documentPage":"https://doi.org/10.48550/ARXIV.2504.19194","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2504.19194","authorSignatures":[{}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2504-19194","documentUrl":"https://doi.org/10.48550/ARXIV.2504.19194"},{"key":"journals/corr/abs-2505-03335","title":"Absolute Zero: Reinforced Self-play Reasoning with Zero Data.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2505.03335"],"source":"https://dblp.org/rec/journals/corr/abs-2505-03335","documentPage":"https://doi.org/10.48550/ARXIV.2505.03335","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2505.03335","authorSignatures":[{}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-03335","documentUrl":"https://doi.org/10.48550/ARXIV.2505.03335"},{"key":"journals/corr/abs-2505-13308","title":"Seek in the Dark: Reasoning via Test-Time Instance-Level Policy Gradient in Latent Space.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2505.13308"],"source":"https://dblp.org/rec/journals/corr/abs-2505-13308","documentPage":"https://doi.org/10.48550/ARXIV.2505.13308","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2505.13308","authorSignatures":[{}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-13308","documentUrl":"https://doi.org/10.48550/ARXIV.2505.13308"},{"key":"journals/corr/abs-2505-19487","title":"SpikeStereoNet: A Brain-Inspired Framework for Stereo Depth Estimation from Spike Streams.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2505.19487"],"source":"https://dblp.org/rec/journals/corr/abs-2505-19487","documentPage":"https://doi.org/10.48550/ARXIV.2505.19487","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2505.19487","authorSignatures":[{}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-19487","documentUrl":"https://doi.org/10.48550/ARXIV.2505.19487"},{"key":"journals/corr/abs-2507-15185","title":"On Subsample Size of Quantile-Based Randomized Kaczmarz.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2507.15185"],"source":"https://dblp.org/rec/journals/corr/abs-2507-15185","documentPage":"https://doi.org/10.48550/ARXIV.2507.15185","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2507.15185","authorSignatures":[{}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2507-15185","documentUrl":"https://doi.org/10.48550/ARXIV.2507.15185"},{"key":"journals/corr/abs-2507-15974","title":"Does More Inference-Time Compute Really Help Robustness?","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2507.15974"],"source":"https://dblp.org/rec/journals/corr/abs-2507-15974","documentPage":"https://doi.org/10.48550/ARXIV.2507.15974","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2507.15974","authorSignatures":[{}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2507-15974","documentUrl":"https://doi.org/10.48550/ARXIV.2507.15974"},{"key":"journals/corr/abs-2508-11801","title":"VideoAVE: A Multi-Attribute Video-to-Text Attribute Value Extraction Dataset and Benchmark Models.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2508.11801"],"source":"https://dblp.org/rec/journals/corr/abs-2508-11801","documentPage":"https://doi.org/10.48550/ARXIV.2508.11801","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2508.11801","authorSignatures":[{}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-11801","documentUrl":"https://doi.org/10.48550/ARXIV.2508.11801"},{"key":"journals/corr/abs-2508-17356","title":"DiCache: Let Diffusion Model Determine Its Own Cache.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2508.17356"],"source":"https://dblp.org/rec/journals/corr/abs-2508-17356","documentPage":"https://doi.org/10.48550/ARXIV.2508.17356","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2508.17356","authorSignatures":[{}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-17356","documentUrl":"https://doi.org/10.48550/ARXIV.2508.17356"},{"key":"journals/corr/abs-2509-03808","title":"EGTM: Event-guided Efficient Turbulence Mitigation.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2509.03808"],"source":"https://dblp.org/rec/journals/corr/abs-2509-03808","documentPage":"https://doi.org/10.48550/ARXIV.2509.03808","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2509.03808","authorSignatures":[{}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-03808","documentUrl":"https://doi.org/10.48550/ARXIV.2509.03808"},{"key":"journals/corr/abs-2509-10999","title":"Real-Time Defense Against Coordinated Cyber-Physical Attacks: A Robust Constrained Reinforcement Learning Approach.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2509.10999"],"source":"https://dblp.org/rec/journals/corr/abs-2509-10999","documentPage":"https://doi.org/10.48550/ARXIV.2509.10999","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2509.10999","authorSignatures":[{}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-10999","documentUrl":"https://doi.org/10.48550/ARXIV.2509.10999"},{"key":"journals/corr/abs-2509-13776","title":"Morphology-optimized Multi-Scale Fusion: Combining Local Artifacts and Mesoscopic Semantics for Deepfake Detection and Localization.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2509.13776"],"source":"https://dblp.org/rec/journals/corr/abs-2509-13776","documentPage":"https://doi.org/10.48550/ARXIV.2509.13776","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2509.13776","authorSignatures":[{}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-13776","documentUrl":"https://doi.org/10.48550/ARXIV.2509.13776"},{"key":"journals/corr/abs-2509-23519","title":"ReliabilityRAG: Effective and Provably Robust Defense for RAG-based Web-Search.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2509.23519"],"source":"https://dblp.org/rec/journals/corr/abs-2509-23519","documentPage":"https://doi.org/10.48550/ARXIV.2509.23519","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2509.23519","authorSignatures":[{}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-23519","documentUrl":"https://doi.org/10.48550/ARXIV.2509.23519"},{"key":"journals/corr/abs-2509-25852","title":"Reinforced Embodied Planning with Verifiable Reward for Real-World Robotic Manipulation.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2509.25852"],"source":"https://dblp.org/rec/journals/corr/abs-2509-25852","documentPage":"https://doi.org/10.48550/ARXIV.2509.25852","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2509.25852","authorSignatures":[{}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-25852","documentUrl":"https://doi.org/10.48550/ARXIV.2509.25852"},{"key":"journals/corr/abs-2510-02359","title":"Emission-GPT: A domain-specific language model agent for knowledge retrieval, emission inventory and data analysis.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2510.02359"],"source":"https://dblp.org/rec/journals/corr/abs-2510-02359","documentPage":"https://doi.org/10.48550/ARXIV.2510.02359","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2510.02359","authorSignatures":[{}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-02359","documentUrl":"https://doi.org/10.48550/ARXIV.2510.02359"},{"key":"journals/corr/abs-2510-10663","title":"Scalable Face Security Vision Foundation Model for Deepfake, Diffusion, and Spoofing Detection.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2510.10663"],"source":"https://dblp.org/rec/journals/corr/abs-2510-10663","documentPage":"https://doi.org/10.48550/ARXIV.2510.10663","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2510.10663","authorSignatures":[{}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-10663","documentUrl":"https://doi.org/10.48550/ARXIV.2510.10663"},{"key":"journals/corr/abs-2510-21512","title":"Towards a Golden Classifier-Free Guidance Path via Foresight Fixed Point Iterations.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2510.21512"],"source":"https://dblp.org/rec/journals/corr/abs-2510-21512","documentPage":"https://doi.org/10.48550/ARXIV.2510.21512","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2510.21512","authorSignatures":[{}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-21512","documentUrl":"https://doi.org/10.48550/ARXIV.2510.21512"},{"key":"journals/corr/abs-2510-24944","title":"Interpolated Discrepancy Data Assimilation for PDEs with Sparse Observations.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2510.24944"],"source":"https://dblp.org/rec/journals/corr/abs-2510-24944","documentPage":"https://doi.org/10.48550/ARXIV.2510.24944","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2510.24944","authorSignatures":[{}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-24944","documentUrl":"https://doi.org/10.48550/ARXIV.2510.24944"},{"key":"journals/corr/abs-2511-05393","title":"PreResQ-R1: Towards Fine-Grained Rank-and-Score Reinforcement Learning for Visual Quality Assessment via Preference-Response Disentangled Policy Optimization.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2511.05393"],"source":"https://dblp.org/rec/journals/corr/abs-2511-05393","documentPage":"https://doi.org/10.48550/ARXIV.2511.05393","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2511.05393","authorSignatures":[{}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2511-05393","documentUrl":"https://doi.org/10.48550/ARXIV.2511.05393"},{"key":"journals/corr/abs-2511-09323","title":"Mixture-of-Channels: Exploiting Sparse FFNs for Efficient LLMs Pre-Training and Inference.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2511.09323"],"source":"https://dblp.org/rec/journals/corr/abs-2511-09323","documentPage":"https://doi.org/10.48550/ARXIV.2511.09323","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2511.09323","authorSignatures":[{}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2511-09323","documentUrl":"https://doi.org/10.48550/ARXIV.2511.09323"},{"key":"journals/corr/abs-2511-14139","title":"FlexiCup: Wireless Multimodal Suction Cup with Dual-Zone Vision-Tactile Sensing.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2511.14139"],"source":"https://dblp.org/rec/journals/corr/abs-2511-14139","documentPage":"https://doi.org/10.48550/ARXIV.2511.14139","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2511.14139","authorSignatures":[{}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2511-14139","documentUrl":"https://doi.org/10.48550/ARXIV.2511.14139"},{"key":"journals/corr/abs-2512-00136","title":"An Empirical Study on the Security Vulnerabilities of GPTs.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2512.00136"],"source":"https://dblp.org/rec/journals/corr/abs-2512-00136","documentPage":"https://doi.org/10.48550/ARXIV.2512.00136","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2512.00136","authorSignatures":[{}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-00136","documentUrl":"https://doi.org/10.48550/ARXIV.2512.00136"},{"key":"journals/corr/abs-2512-07461","title":"Native Parallel Reasoner: Reasoning in Parallelism via Self-Distilled Reinforcement Learning.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2512.07461"],"source":"https://dblp.org/rec/journals/corr/abs-2512-07461","documentPage":"https://doi.org/10.48550/ARXIV.2512.07461","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2512.07461","authorSignatures":[{}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-07461","documentUrl":"https://doi.org/10.48550/ARXIV.2512.07461"},{"key":"journals/corr/abs-2512-24503","title":"Can Small Training Runs Reliably Guide Data Curation? Rethinking Proxy-Model Practice.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2512.24503"],"source":"https://dblp.org/rec/journals/corr/abs-2512-24503","documentPage":"https://doi.org/10.48550/ARXIV.2512.24503","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2512.24503","authorSignatures":[{}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-24503","documentUrl":"https://doi.org/10.48550/ARXIV.2512.24503"},{"key":"journals/eaai/LiuWWSL25","title":"A self-attention enhanced generative adversarial autoencoder for anomaly detection of self-discharge of lithium-ion batteries.","year":2025,"yearOfEvent":null,"venue":"Eng. Appl. Artif. Intell.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1016/J.ENGAPPAI.2025.111495"],"source":"https://dblp.org/rec/journals/eaai/LiuWWSL25","documentPage":"https://doi.org/10.1016/J.ENGAPPAI.2025.111495","type":"Article","doi":"https://doi.org/10.1016/J.ENGAPPAI.2025.111495","authorSignatures":[{"inst":"https://dblp.org/inst/5/702","instLabel":"Hefei University of Technology (HFUT)"}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/eaai/LiuWWSL25","documentUrl":"https://doi.org/10.1016/J.ENGAPPAI.2025.111495"},{"key":"journals/entropy/WangWW25","title":"LOMDP: Maximizing Desired Opinions in Social Networks by Considering User Expression Intentions.","year":2025,"yearOfEvent":null,"venue":"Entropy","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.3390/E27040360"],"source":"https://dblp.org/rec/journals/entropy/WangWW25","documentPage":"https://doi.org/10.3390/E27040360","type":"Article","doi":"https://doi.org/10.3390/E27040360","authorSignatures":[{"inst":"https://dblp.org/inst/2/008","instLabel":"Beijing University of Posts and Telecommunications (BUPT)"}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/entropy/WangWW25","documentUrl":"https://doi.org/10.3390/E27040360"},{"key":"journals/icl/ZhangJSWLC25","title":"Metaheuristic-Based Beam Scheduling Strategies for LEO Multibeam Satellite: A Comparison.","year":2025,"yearOfEvent":null,"venue":"IEEE Commun. Lett.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1109/LCOMM.2025.3535631"],"source":"https://dblp.org/rec/journals/icl/ZhangJSWLC25","documentPage":"https://doi.org/10.1109/LCOMM.2025.3535631","type":"Article","doi":"https://doi.org/10.1109/LCOMM.2025.3535631","authorSignatures":[{"inst":"https://dblp.org/inst/9/595","instLabel":"Shanghai Jiao Tong University (SJTU)"}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/icl/ZhangJSWLC25","documentUrl":"https://doi.org/10.1109/LCOMM.2025.3535631"},{"key":"journals/ijcisys/WuLLFHB25","title":"SIP Flooding Attack Detection Technology of Multi-agent System Covert Network Based on BiGRU Algorithm.","year":2025,"yearOfEvent":null,"venue":"Int. J. Comput. Intell. Syst.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1007/S44196-025-00864-X"],"source":"https://dblp.org/rec/journals/ijcisys/WuLLFHB25","documentPage":"https://doi.org/10.1007/S44196-025-00864-X","type":"Article","doi":"https://doi.org/10.1007/S44196-025-00864-X","authorSignatures":[{"inst":"https://dblp.org/inst/2/544","instLabel":"Northeastern University (NEU)"}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/ijcisys/WuLLFHB25","documentUrl":"https://doi.org/10.1007/S44196-025-00864-X"},{"key":"journals/ijon/HuWHLXL25","title":"Multi-view clustering via view-specific consensus kernelized graph learning.","year":2025,"yearOfEvent":null,"venue":"Neurocomputing","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1016/J.NEUCOM.2025.129766"],"source":"https://dblp.org/rec/journals/ijon/HuWHLXL25","documentPage":"https://doi.org/10.1016/J.NEUCOM.2025.129766","type":"Article","doi":"https://doi.org/10.1016/J.NEUCOM.2025.129766","authorSignatures":[{"inst":"https://dblp.org/inst/7/754","instLabel":"Anhui Polytechnic University (AUTS)"}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/ijon/HuWHLXL25","documentUrl":"https://doi.org/10.1016/J.NEUCOM.2025.129766"},{"key":"journals/ijon/WuLH25","title":"Auto-weighted exponential tensor nuclear norm minimization for multi-attribute low-dimensional subspace clustering.","year":2025,"yearOfEvent":null,"venue":"Neurocomputing","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1016/J.NEUCOM.2025.130394"],"source":"https://dblp.org/rec/journals/ijon/WuLH25","documentPage":"https://doi.org/10.1016/J.NEUCOM.2025.130394","type":"Article","doi":"https://doi.org/10.1016/J.NEUCOM.2025.130394","authorSignatures":[{"inst":"https://dblp.org/inst/7/754","instLabel":"Anhui Polytechnic University (AUTS)"}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/ijon/WuLH25","documentUrl":"https://doi.org/10.1016/J.NEUCOM.2025.130394"},{"key":"journals/isci/WuL25","title":"Tensorized diversity and consistency with Laplacian manifold for multi-view clustering.","year":2025,"yearOfEvent":null,"venue":"Inf. Sci.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1016/J.INS.2024.121575"],"source":"https://dblp.org/rec/journals/isci/WuL25","documentPage":"https://doi.org/10.1016/J.INS.2024.121575","type":"Article","doi":"https://doi.org/10.1016/J.INS.2024.121575","authorSignatures":[{"orcid":"https://orcid.org/0009-0001-7417-5781","inst":"https://dblp.org/inst/7/754","instLabel":"Anhui Polytechnic University (AUTS)"}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/isci/WuL25","documentUrl":"https://doi.org/10.1016/J.INS.2024.121575"},{"key":"journals/jfi/WuY25","title":"Dynamic periodic event-triggered control for nonlinear multi-agent systems under DoS attacks.","year":2025,"yearOfEvent":null,"venue":"J. Frankl. Inst.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1016/J.JFRANKLIN.2025.108011"],"source":"https://dblp.org/rec/journals/jfi/WuY25","documentPage":"https://doi.org/10.1016/J.JFRANKLIN.2025.108011","type":"Article","doi":"https://doi.org/10.1016/J.JFRANKLIN.2025.108011","authorSignatures":[{"inst":"https://dblp.org/inst/12/163","instLabel":"Shanghai Electric"},{"inst":"https://dblp.org/inst/2/544","instLabel":"Northeastern University (NEU)"}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/jfi/WuY25","documentUrl":"https://doi.org/10.1016/J.JFRANKLIN.2025.108011"},{"key":"journals/jssc/LinLLWWH25","title":"VISTA: A Memory-Efficient CNN Processor for Video and Image Spatial/Temporal Interpolation Acceleration.","year":2025,"yearOfEvent":null,"venue":"IEEE J. Solid State Circuits","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1109/JSSC.2025.3547982"],"source":"https://dblp.org/rec/journals/jssc/LinLLWWH25","documentPage":"https://doi.org/10.1109/JSSC.2025.3547982","type":"Article","doi":"https://doi.org/10.1109/JSSC.2025.3547982","authorSignatures":[{"inst":"https://dblp.org/inst/1/340","instLabel":"National Tsing Hua University (NTHU)"}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/jssc/LinLLWWH25","documentUrl":"https://doi.org/10.1109/JSSC.2025.3547982"},{"key":"journals/pacmhci/WangWLBC25","title":"Generative Co-Learners: Enhancing Cognitive and Social Presence of Students in Asynchronous Learning with Generative AI.","year":2025,"yearOfEvent":null,"venue":"Proc. ACM Hum. Comput. Interact.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1145/3701198"],"source":"https://dblp.org/rec/journals/pacmhci/WangWLBC25","documentPage":"https://doi.org/10.1145/3701198","type":"Article","doi":"https://doi.org/10.1145/3701198","authorSignatures":[{"orcid":"https://orcid.org/0009-0004-8310-6501","inst":"https://dblp.org/inst/1/401","instLabel":"Virginia Tech"}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/pacmhci/WangWLBC25","documentUrl":"https://doi.org/10.1145/3701198"},{"key":"journals/pami/CaoHWPL25","title":"DiffTF++: 3D-Aware Diffusion Transformer for Large-Vocabulary 3D Generation.","year":2025,"yearOfEvent":null,"venue":"IEEE Trans. Pattern Anal. Mach. Intell.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1109/TPAMI.2025.3528247"],"source":"https://dblp.org/rec/journals/pami/CaoHWPL25","documentPage":"https://doi.org/10.1109/TPAMI.2025.3528247","type":"Article","doi":"https://doi.org/10.1109/TPAMI.2025.3528247","authorSignatures":[{"inst":"https://dblp.org/inst/1/452","instLabel":"Chinese University of Hong Kong (CUHK)"}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/pami/CaoHWPL25","documentUrl":"https://doi.org/10.1109/TPAMI.2025.3528247"},{"key":"journals/pr/CaiLGW25","title":"Tensorized latent representation with automatic dimensionality selection for multi-view clustering.","year":2025,"yearOfEvent":null,"venue":"Pattern Recognit.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1016/J.PATCOG.2024.111192"],"source":"https://dblp.org/rec/journals/pr/CaiLGW25","documentPage":"https://doi.org/10.1016/J.PATCOG.2024.111192","type":"Article","doi":"https://doi.org/10.1016/J.PATCOG.2024.111192","authorSignatures":[{"inst":"https://dblp.org/inst/7/754","instLabel":"Anhui Polytechnic University (AUTS)"}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/pr/CaiLGW25","documentUrl":"https://doi.org/10.1016/J.PATCOG.2024.111192"},{"key":"journals/prl/AliHWMLZJ25","title":"Segmentation of MRI tumors and pelvic anatomy via cGAN-synthesized data and attention-enhanced U-Net.","year":2025,"yearOfEvent":null,"venue":"Pattern Recognit. Lett.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1016/J.PATREC.2024.11.003"],"source":"https://dblp.org/rec/journals/prl/AliHWMLZJ25","documentPage":"https://doi.org/10.1016/J.PATREC.2024.11.003","type":"Article","doi":"https://doi.org/10.1016/J.PATREC.2024.11.003","authorSignatures":[{"inst":"https://dblp.org/inst/1/657","instLabel":"University of Illinois Urbana-Champaign (UIUC)"}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/prl/AliHWMLZJ25","documentUrl":"https://doi.org/10.1016/J.PATREC.2024.11.003"},{"key":"journals/sigpro/WuL25","title":"Specific and coupled double consistency multi-view subspace clustering with low-rank tensor learning.","year":2025,"yearOfEvent":null,"venue":"Signal Process.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1016/J.SIGPRO.2024.109803"],"source":"https://dblp.org/rec/journals/sigpro/WuL25","documentPage":"https://doi.org/10.1016/J.SIGPRO.2024.109803","type":"Article","doi":"https://doi.org/10.1016/J.SIGPRO.2024.109803","authorSignatures":[{"orcid":"https://orcid.org/0009-0001-7417-5781","inst":"https://dblp.org/inst/7/754","instLabel":"Anhui Polytechnic University (AUTS)"}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/sigpro/WuL25","documentUrl":"https://doi.org/10.1016/J.SIGPRO.2024.109803"},{"key":"journals/staeors/WuLNZZW25","title":"Two-Stage Target Detection for Compact HFSWR With Space-to-Depth YOLOv8 and Multiframe ViT.","year":2025,"yearOfEvent":null,"venue":"IEEE J. Sel. Top. Appl. Earth Obs. Remote. Sens.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1109/JSTARS.2025.3556138"],"source":"https://dblp.org/rec/journals/staeors/WuLNZZW25","documentPage":"https://doi.org/10.1109/JSTARS.2025.3556138","type":"Article","doi":"https://doi.org/10.1109/JSTARS.2025.3556138","authorSignatures":[{"orcid":"https://orcid.org/0009-0003-8397-5566","inst":"https://dblp.org/inst/1/853","instLabel":"Ocean University of China (OUC)"}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/staeors/WuLNZZW25","documentUrl":"https://doi.org/10.1109/JSTARS.2025.3556138"},{"key":"journals/systems/ChenLWXWLL25","title":"Port Investment Optimization and Its Application Under Differentiated Port and Industrial Risks Along the Maritime Silk Road.","year":2025,"yearOfEvent":null,"venue":"Syst.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.3390/SYSTEMS13090794"],"source":"https://dblp.org/rec/journals/systems/ChenLWXWLL25","documentPage":"https://doi.org/10.3390/SYSTEMS13090794","type":"Article","doi":"https://doi.org/10.3390/SYSTEMS13090794","authorSignatures":[{"inst":"https://dblp.org/inst/6/556","instLabel":"Ningbo University (NBU)"}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/systems/ChenLWXWLL25","documentUrl":"https://doi.org/10.3390/SYSTEMS13090794"},{"key":"journals/tcsv/LiZLWGZZ25","title":"TinyFusionDet: Hardware-Efficient LiDAR-Camera Fusion Framework for 3D Object Detection at Edge.","year":2025,"yearOfEvent":null,"venue":"IEEE Trans. Circuits Syst. Video Technol.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1109/TCSVT.2025.3556711"],"source":"https://dblp.org/rec/journals/tcsv/LiZLWGZZ25","documentPage":"https://doi.org/10.1109/TCSVT.2025.3556711","type":"Article","doi":"https://doi.org/10.1109/TCSVT.2025.3556711","authorSignatures":[{"orcid":"https://orcid.org/0009-0000-2766-1966","inst":"https://dblp.org/inst/1/778","instLabel":"Xidian University"}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/tcsv/LiZLWGZZ25","documentUrl":"https://doi.org/10.1109/TCSVT.2025.3556711"},{"key":"journals/tgrs/HongWXZ25","title":"Depth2Elevation: Scale Modulation With Depth Anything Model for Single-View Remote Sensing Image Height Estimation.","year":2025,"yearOfEvent":null,"venue":"IEEE Trans. Geosci. Remote. Sens.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1109/TGRS.2025.3564820"],"source":"https://dblp.org/rec/journals/tgrs/HongWXZ25","documentPage":"https://doi.org/10.1109/TGRS.2025.3564820","type":"Article","doi":"https://doi.org/10.1109/TGRS.2025.3564820","authorSignatures":[{"orcid":"https://orcid.org/0000-0002-2888-275X","inst":"https://dblp.org/inst/1/132","instLabel":"University of Bristol"},{"orcid":"https://orcid.org/0000-0002-2888-275X","inst":"https://dblp.org/inst/1/464","instLabel":"Auckland University of Technology (AUT)"}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/tgrs/HongWXZ25","documentUrl":"https://doi.org/10.1109/TGRS.2025.3564820"},{"key":"journals/tmlr/JiaLKWWWWZSLQLHZZ25","title":"The AI Hippocampus: How Far are We From Human Memory?","year":2025,"yearOfEvent":null,"venue":"Trans. Mach. Learn. Res.","types":["https://dblp.org/rdf/schema#Article"],"dois":[],"source":"https://dblp.org/rec/journals/tmlr/JiaLKWWWWZSLQLHZZ25","documentPage":"https://openreview.net/forum?id=Sk7pwmLuAY","type":"Article","doi":null,"authorSignatures":[{}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/tmlr/JiaLKWWWWZSLQLHZZ25","documentUrl":"https://openreview.net/forum?id=Sk7pwmLuAY"},{"key":"journals/tnn/CuiQGZXWLSZL25","title":"SinKD: Sinkhorn Distance Minimization for Knowledge Distillation.","year":2025,"yearOfEvent":null,"venue":"IEEE Trans. Neural Networks Learn. Syst.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1109/TNNLS.2024.3501335"],"source":"https://dblp.org/rec/journals/tnn/CuiQGZXWLSZL25","documentPage":"https://doi.org/10.1109/TNNLS.2024.3501335","type":"Article","doi":"https://doi.org/10.1109/TNNLS.2024.3501335","authorSignatures":[{"inst":"https://dblp.org/inst/12/029","instLabel":"Tencent"}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/tnn/CuiQGZXWLSZL25","documentUrl":"https://doi.org/10.1109/TNNLS.2024.3501335"},{"key":"journals/tomccap/WuZZL25","title":"RESIST: Rationale-Enhanced and Reward Model-Based End-to-End Social Influence Dialogue System.","year":2025,"yearOfEvent":null,"venue":"ACM Trans. Multim. Comput. Commun. Appl.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1145/3736580"],"source":"https://dblp.org/rec/journals/tomccap/WuZZL25","documentPage":"https://doi.org/10.1145/3736580","type":"Article","doi":"https://doi.org/10.1145/3736580","authorSignatures":[{"orcid":"https://orcid.org/0009-0002-5870-4556","inst":"https://dblp.org/inst/1/937","instLabel":"Anhui University"}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/tomccap/WuZZL25","documentUrl":"https://doi.org/10.1145/3736580"},{"key":"journals/vtm/LiWHQW25","title":"Digital Twin Online Channel Modeling: Challenges, Principles, and Applications.","year":2025,"yearOfEvent":null,"venue":"IEEE Veh. Technol. Mag.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1109/MVT.2025.3527729"],"source":"https://dblp.org/rec/journals/vtm/LiWHQW25","documentPage":"https://doi.org/10.1109/MVT.2025.3527729","type":"Article","doi":"https://doi.org/10.1109/MVT.2025.3527729","authorSignatures":[{"inst":"https://dblp.org/inst/2/470","instLabel":"Southeast University (SEU)"}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/vtm/LiWHQW25","documentUrl":"https://doi.org/10.1109/MVT.2025.3527729"}],"retrievedAt":"2026-10-19","querySource":"https://sparql.dblp.org/","method":"DBLP yearOfPublication=2025; Article + Inproceedings; excludes Informal/CoRR and explicit editorial/correction/erratum/preface; unique DBLP record keys within person.","verifiedLowerBound2025":15,"conferenceLowerBound2025":14,"journalLowerBound2025":1,"labName":null,"labUrl":null,"labEvidence":"本轮复旦研究院资料只明确其所属研究院；研究院由两个实验室联合创建，不足以断定其属于哪一个。CUHK MMLab为旧博士经历。","labSourceUrl":"https://wutong16.github.io/","affiliationZh":"复旦大学","sourceWarning":false,"knownPreprintMinimum2025":12,"excludedMisattributed":[],"knownMinimum2025":15,"displayNotes":"该 DBLP 档案混有其他同名作者，剩余候选尚未逐篇核完，全年总数暂不给出。目前已逐篇核实 15 条，只作下界参考，不进入合计、中位数或排序。","labDisplayNotes":"复旦资料只写明其所属研究院，而该研究院由两个实验室联合创建，无法断定其属于哪一个；港中文 MMLab 是其博士阶段经历。图中以「姓名及合作者」单列。"},{"index":92,"name":"Jun Xia","nameZh":"夏俊","affiliation":"Hong Kong University of Science and Technology (Guangzhou)","source":"DBLP Knowledge Graph official SPARQL API","profileUrl":"https://dblp.org/pid/22/3650-1","identifier":"22/3650-1","identityEvidence":[{"url":"https://dblp.org/pid/22/3650-1","evidence":"DBLP curated profile affiliations: Hong Kong University of Science and Technology, Guangzhou, China; Hong Kong University of Science and Technology, Hong Kong; Westlake University, School of Engineering, AI Lab, Hangzhou, China; Zhejiang University, Hangzhou, China."}],"count2025":12,"conference2025":9,"journal2025":3,"preprint2025":9,"status":"verified","notes":"Counts are DBLP indexed coauthored records, not first-author counts, laboratory totals, unique scientific discoveries, or quality assessments. DBLP yearOfPublication=2025; yearOfEvent retained and can differ. Conference workshops are included. Preprints are separate and may overlap formal versions.","papers":[{"key":"conf/iclr/0012CGW000HL25","title":"MeToken: Uniform Micro-environment Token Boosts Post-Translational Modification Prediction.","year":2025,"yearOfEvent":2025,"venue":"ICLR","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/iclr/0012CGW000HL25","documentPage":"https://openreview.net/forum?id=noUF58SMra","type":"Inproceedings","doi":null,"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iclr/0012CGW000HL25","documentUrl":"https://openreview.net/forum?id=noUF58SMra"},{"key":"conf/iclr/Chen0ZZGH0DL25","title":"ReNovo: Retrieval-Based \\emph{De Novo} Mass Spectrometry Peptide Sequencing.","year":2025,"yearOfEvent":2025,"venue":"ICLR","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/iclr/Chen0ZZGH0DL25","documentPage":"https://openreview.net/forum?id=uQnvYP7yX9","type":"Inproceedings","doi":null,"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iclr/Chen0ZZGH0DL25","documentUrl":"https://openreview.net/forum?id=uQnvYP7yX9"},{"key":"conf/iclr/XiaLZCX00L25","title":"Bridging the Gap between Database Search and De Novo Peptide Sequencing with SearchNovo.","year":2025,"yearOfEvent":2025,"venue":"ICLR","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/iclr/XiaLZCX00L25","documentPage":"https://openreview.net/forum?id=SjMtxqdQ73","type":"Inproceedings","doi":null,"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iclr/XiaLZCX00L25","documentUrl":"https://openreview.net/forum?id=SjMtxqdQ73"},{"key":"conf/ijcai/Chi0ZC0L25","title":"GRAPE: Heterogeneous Graph Representation Learning for Genetic Perturbation with Coding and Non-Coding Biotype.","year":2025,"yearOfEvent":2025,"venue":"IJCAI","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.24963/IJCAI.2025/551"],"source":"https://dblp.org/rec/conf/ijcai/Chi0ZC0L25","documentPage":"https://doi.org/10.24963/IJCAI.2025/551","type":"Inproceedings","doi":"https://doi.org/10.24963/IJCAI.2025/551","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/ijcai/Chi0ZC0L25","documentUrl":"https://doi.org/10.24963/IJCAI.2025/551"},{"key":"conf/ijcai/LiDXWWYW25","title":"MTGIB-UNet: A Multi-Task Graph Information Bottleneck and Uncertainty Weighted Network for ADMET Prediction.","year":2025,"yearOfEvent":2025,"venue":"IJCAI","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.24963/IJCAI.2025/836"],"source":"https://dblp.org/rec/conf/ijcai/LiDXWWYW25","documentPage":"https://doi.org/10.24963/IJCAI.2025/836","type":"Inproceedings","doi":"https://doi.org/10.24963/IJCAI.2025/836","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/ijcai/LiDXWWYW25","documentUrl":"https://doi.org/10.24963/IJCAI.2025/836"},{"key":"conf/ijcai/XiangXJDZZ25","title":"Electron Density-enhanced Molecular Geometry Learning.","year":2025,"yearOfEvent":2025,"venue":"IJCAI","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.24963/IJCAI.2025/872"],"source":"https://dblp.org/rec/conf/ijcai/XiangXJDZZ25","documentPage":"https://doi.org/10.24963/IJCAI.2025/872","type":"Inproceedings","doi":"https://doi.org/10.24963/IJCAI.2025/872","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/ijcai/XiangXJDZZ25","documentUrl":"https://doi.org/10.24963/IJCAI.2025/872"},{"key":"conf/ijcai/XiaZCLL25","title":"A Comprehensive and Systematic Review for Deep Learning-Based De Novo Peptide Sequencing.","year":2025,"yearOfEvent":2025,"venue":"IJCAI","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.24963/IJCAI.2025/1191"],"source":"https://dblp.org/rec/conf/ijcai/XiaZCLL25","documentPage":"https://doi.org/10.24963/IJCAI.2025/1191","type":"Inproceedings","doi":"https://doi.org/10.24963/IJCAI.2025/1191","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/ijcai/XiaZCLL25","documentUrl":"https://doi.org/10.24963/IJCAI.2025/1191"},{"key":"conf/nips/ChengCZXX25","title":"PRESCRIBE: Predicting Single-Cell Responses with Bayesian Estimation.","year":2025,"yearOfEvent":2025,"venue":"NeurIPS","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/nips/ChengCZXX25","documentPage":"http://papers.nips.cc/paper_files/paper/2025/hash/d6383e7643415842b48a5077a1b09c98-Abstract-Conference.html","type":"Inproceedings","doi":null,"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/nips/ChengCZXX25","documentUrl":"http://papers.nips.cc/paper_files/paper/2025/hash/d6383e7643415842b48a5077a1b09c98-Abstract-Conference.html"},{"key":"conf/nips/XiangLLCYDXZJZ25","title":"EDBench: Large-Scale Electron Density Data for Molecular Modeling.","year":2025,"yearOfEvent":2025,"venue":"NeurIPS","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/nips/XiangLLCYDXZJZ25","documentPage":"http://papers.nips.cc/paper_files/paper/2025/hash/d412ba5c76774f921762644e82515da3-Abstract-Datasets_and_Benchmarks_Track.html","type":"Inproceedings","doi":null,"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/nips/XiangLLCYDXZJZ25","documentUrl":"http://papers.nips.cc/paper_files/paper/2025/hash/d412ba5c76774f921762644e82515da3-Abstract-Datasets_and_Benchmarks_Track.html"},{"key":"journals/bib/XuZHYTXL24","title":"Complex hierarchical structures analysis in single-cell data with Poincaré deep manifold transformation.","year":2025,"yearOfEvent":null,"venue":"Briefings Bioinform.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1093/BIB/BBAE687"],"source":"https://dblp.org/rec/journals/bib/XuZHYTXL24","documentPage":"https://doi.org/10.1093/BIB/BBAE687","type":"Article","doi":"https://doi.org/10.1093/BIB/BBAE687","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/bib/XuZHYTXL24","documentUrl":"https://doi.org/10.1093/BIB/BBAE687"},{"key":"journals/bioinformatics/LiuLX0L25","title":"SP-DTI: subpocket-informed transformer for drug-target interaction prediction.","year":2025,"yearOfEvent":null,"venue":"Bioinform.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1093/BIOINFORMATICS/BTAF011"],"source":"https://dblp.org/rec/journals/bioinformatics/LiuLX0L25","documentPage":"https://doi.org/10.1093/BIOINFORMATICS/BTAF011","type":"Article","doi":"https://doi.org/10.1093/BIOINFORMATICS/BTAF011","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/bioinformatics/LiuLX0L25","documentUrl":"https://doi.org/10.1093/BIOINFORMATICS/BTAF011"},{"key":"journals/bioinformatics/XiangLHJWXDYFYZX25","title":"An image-based protein-ligand binding representation learning framework via multi-level flexible dynamics trajectory pre-training.","year":2025,"yearOfEvent":null,"venue":"Bioinform.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1093/BIOINFORMATICS/BTAF535"],"source":"https://dblp.org/rec/journals/bioinformatics/XiangLHJWXDYFYZX25","documentPage":"https://doi.org/10.1093/BIOINFORMATICS/BTAF535","type":"Article","doi":"https://doi.org/10.1093/BIOINFORMATICS/BTAF535","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/bioinformatics/XiangLHJWXDYFYZX25","documentUrl":"https://doi.org/10.1093/BIOINFORMATICS/BTAF535"}],"preprints":[{"key":"journals/corr/abs-2501-18492","title":"GuardReasoner: Towards Reasoning-based LLM Safeguards.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2501.18492"],"source":"https://dblp.org/rec/journals/corr/abs-2501-18492","documentPage":"https://doi.org/10.48550/ARXIV.2501.18492","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2501.18492","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2501-18492","documentUrl":"https://doi.org/10.48550/ARXIV.2501.18492","arxivId":"2501.18492","arxivUrl":"https://arxiv.org/abs/2501.18492"},{"key":"journals/corr/abs-2503-03211","title":"NodeReg: Mitigating the Imbalance and Distribution Shift Effects in Semi-Supervised Node Classification via Norm Consistency.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2503.03211"],"source":"https://dblp.org/rec/journals/corr/abs-2503-03211","documentPage":"https://doi.org/10.48550/ARXIV.2503.03211","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2503.03211","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-03211","documentUrl":"https://doi.org/10.48550/ARXIV.2503.03211","arxivId":"2503.03211","arxivUrl":"https://arxiv.org/abs/2503.03211"},{"key":"journals/corr/abs-2504-00540","title":"Adversarial Curriculum Graph-Free Knowledge Distillation for Graph Neural Networks.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2504.00540"],"source":"https://dblp.org/rec/journals/corr/abs-2504-00540","documentPage":"https://doi.org/10.48550/ARXIV.2504.00540","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2504.00540","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2504-00540","documentUrl":"https://doi.org/10.48550/ARXIV.2504.00540","arxivId":"2504.00540","arxivUrl":"https://arxiv.org/abs/2504.00540"},{"key":"journals/corr/abs-2505-03853","title":"GRAPE: Heterogeneous Graph Representation Learning for Genetic Perturbation with Coding and Non-Coding Biotype.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2505.03853"],"source":"https://dblp.org/rec/journals/corr/abs-2505-03853","documentPage":"https://doi.org/10.48550/ARXIV.2505.03853","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2505.03853","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-03853","documentUrl":"https://doi.org/10.48550/ARXIV.2505.03853","arxivId":"2505.03853","arxivUrl":"https://arxiv.org/abs/2505.03853"},{"key":"journals/corr/abs-2505-09262","title":"EDBench: Large-Scale Electron Density Data for Molecular Modeling.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2505.09262"],"source":"https://dblp.org/rec/journals/corr/abs-2505-09262","documentPage":"https://doi.org/10.48550/ARXIV.2505.09262","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2505.09262","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-09262","documentUrl":"https://doi.org/10.48550/ARXIV.2505.09262","arxivId":"2505.09262","arxivUrl":"https://arxiv.org/abs/2505.09262"},{"key":"journals/corr/abs-2506-21107","title":"Unlasting: Unpaired Single-Cell Multi-Perturbation Estimation by Dual Conditional Diffusion Implicit Bridges.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2506.21107"],"source":"https://dblp.org/rec/journals/corr/abs-2506-21107","documentPage":"https://doi.org/10.48550/ARXIV.2506.21107","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2506.21107","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-21107","documentUrl":"https://doi.org/10.48550/ARXIV.2506.21107","arxivId":"2506.21107","arxivUrl":"https://arxiv.org/abs/2506.21107"},{"key":"journals/corr/abs-2509-11782","title":"Multimodal Regression for Enzyme Turnover Rates Prediction.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2509.11782"],"source":"https://dblp.org/rec/journals/corr/abs-2509-11782","documentPage":"https://doi.org/10.48550/ARXIV.2509.11782","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2509.11782","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-11782","documentUrl":"https://doi.org/10.48550/ARXIV.2509.11782","arxivId":"2509.11782","arxivUrl":"https://arxiv.org/abs/2509.11782"},{"key":"journals/corr/abs-2510-07964","title":"PRESCRIBE: Predicting Single-Cell Responses with Bayesian Estimation.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2510.07964"],"source":"https://dblp.org/rec/journals/corr/abs-2510-07964","documentPage":"https://doi.org/10.48550/ARXIV.2510.07964","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2510.07964","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-07964","documentUrl":"https://doi.org/10.48550/ARXIV.2510.07964","arxivId":"2510.07964","arxivUrl":"https://arxiv.org/abs/2510.07964"},{"key":"journals/corr/abs-2511-13124","title":"Departures: Distributional Transport for Single-Cell Perturbation Prediction with Neural Schrödinger Bridges.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2511.13124"],"source":"https://dblp.org/rec/journals/corr/abs-2511-13124","documentPage":"https://doi.org/10.48550/ARXIV.2511.13124","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2511.13124","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2511-13124","documentUrl":"https://doi.org/10.48550/ARXIV.2511.13124","arxivId":"2511.13124","arxivUrl":"https://arxiv.org/abs/2511.13124"}],"excludedFormal":[],"excludedOther":[],"excludedHomonyms":[],"unassignedCandidates":[],"retrievedAt":"2026-10-19","querySource":"https://sparql.dblp.org/","method":"DBLP yearOfPublication=2025; Article + Inproceedings; excludes Informal/CoRR and explicit editorial/correction/erratum/preface; unique DBLP record keys within person.","labName":"AI for Multimodality and Science Lab（AIMS Lab）","labUrl":"https://junxia97.github.io/","labEvidence":"港科大广州官方教师页与本人当前主页均明确称夏俊领导 AIMS Lab；当前任职已为 HKUST(GZ)，不能将原名单中的西湖大学机构与当前组名拼成一个2025实验室。","labSourceUrl":"https://facultyprofiles.hkust-gz.edu.cn/faculty-personal-page/XIA-Jun/junxia","affiliationZh":"香港科技大学（广州）","sourceWarning":false,"knownPreprintMinimum2025":null,"excludedMisattributed":[],"displayNotes":"身份已经个人或机构主页核对。2025 年正式记录 12 条（会议 9、期刊 3），所有作者位置均计入，不表示主导或贡献份额；预印本 9 条单列，不加总。","labDisplayNotes":"港科大（广州）官方教师页与本人主页都写明其领导 AIMS Lab，据此归组。其现任职已在港科大（广州），原名单所列为西湖大学；不把两者拼成一个 2025 年的团队。"},{"index":93,"name":"Yuliang Xiu","nameZh":"修宇亮","affiliation":"Westlake University","source":"DBLP Knowledge Graph official SPARQL API","profileUrl":"https://dblp.org/pid/215/3940","identifier":"215/3940","identityEvidence":[{"url":"https://en.westlake.edu.cn/faculty/yuliang-xiu.html","evidence":"School profile identifies 修宇亮 and lists representative works ICON, ECON, Pose Flow; DBLP profile uses ORCID 0000-0003-0165-5909 and matching papers."},{"url":"https://dblp.org/rec/conf/iccv/ChenCXGC25","evidence":"DBLP paper author signature connects this profile to Max Planck Institute for Intelligent Systems (MPI-IS)."},{"url":"https://dblp.org/rec/phd/dnb/Xiu25","evidence":"DBLP paper author signature connects this profile to University of Tübingen."},{"url":"https://dblp.org/rec/conf/iccv/LiFCBX25","evidence":"DBLP paper author signature connects this profile to Westlake University (WIAS)."}],"count2025":5,"conference2025":5,"journal2025":0,"preprint2025":6,"status":"verified","notes":"Counts are DBLP indexed coauthored records, not first-author counts, laboratory totals, unique scientific discoveries, or quality assessments. DBLP yearOfPublication=2025; yearOfEvent retained and can differ. Conference workshops are included. Preprints are separate and may overlap formal versions.","papers":[{"key":"conf/cvpr/BianXX00LB025","title":"ChatGarment: Garment Estimation, Generation and Editing via Large Language Models.","year":2025,"yearOfEvent":2025,"venue":"CVPR","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/CVPR52734.2025.00278"],"source":"https://dblp.org/rec/conf/cvpr/BianXX00LB025","documentPage":"https://openaccess.thecvf.com/content/CVPR2025/html/Bian_ChatGarment_Garment_Estimation_Generation_and_Editing_via_Large_Language_Models_CVPR_2025_paper.html","type":"Inproceedings","doi":"https://doi.org/10.1109/CVPR52734.2025.00278","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/BianXX00LB025","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Bian_ChatGarment_Garment_Estimation_Generation_and_Editing_via_Large_Language_Models_CVPR_2025_paper.html"},{"key":"conf/cvpr/ChenCCPX25","title":"Feat2GS: Probing Visual Foundation Models with Gaussian Splatting.","year":2025,"yearOfEvent":2025,"venue":"CVPR","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/CVPR52734.2025.00595"],"source":"https://dblp.org/rec/conf/cvpr/ChenCCPX25","documentPage":"https://openaccess.thecvf.com/content/CVPR2025/html/Chen_Feat2GS_Probing_Visual_Foundation_Models_with_Gaussian_Splatting_CVPR_2025_paper.html","type":"Inproceedings","doi":"https://doi.org/10.1109/CVPR52734.2025.00595","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/ChenCCPX25","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Chen_Feat2GS_Probing_Visual_Foundation_Models_with_Gaussian_Splatting_CVPR_2025_paper.html"},{"key":"conf/iccv/ChenCXGC25","title":"Easi3R: Estimating Disentangled Motion from DUSt3R Without Training.","year":2025,"yearOfEvent":2025,"venue":"ICCV","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/ICCV51701.2025.00856"],"source":"https://dblp.org/rec/conf/iccv/ChenCXGC25","documentPage":"https://doi.org/10.1109/ICCV51701.2025.00856","type":"Inproceedings","doi":"https://doi.org/10.1109/ICCV51701.2025.00856","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/ChenCXGC25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.00856"},{"key":"conf/iccv/LiFCBX25","title":"ETCH: Generalizing Body Fitting to Clothed Humans Via Equivariant Tightness.","year":2025,"yearOfEvent":2025,"venue":"ICCV","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/ICCV51701.2025.00774"],"source":"https://dblp.org/rec/conf/iccv/LiFCBX25","documentPage":"https://doi.org/10.1109/ICCV51701.2025.00774","type":"Inproceedings","doi":"https://doi.org/10.1109/ICCV51701.2025.00774","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/LiFCBX25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.00774"},{"key":"conf/siggraph/LiaoZXK00025","title":"SOAP: Style-Omniscient Animatable Portraits.","year":2025,"yearOfEvent":2025,"venue":"SIGGRAPH (Conference Paper Track)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1145/3721238.3730691"],"source":"https://dblp.org/rec/conf/siggraph/LiaoZXK00025","documentPage":"https://doi.org/10.1145/3721238.3730691","type":"Inproceedings","doi":"https://doi.org/10.1145/3721238.3730691","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/siggraph/LiaoZXK00025","documentUrl":"https://doi.org/10.1145/3721238.3730691"}],"preprints":[{"key":"journals/corr/abs-2503-10624","title":"ETCH: Generalizing Body Fitting to Clothed Humans via Equivariant Tightness.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2503.10624"],"source":"https://dblp.org/rec/journals/corr/abs-2503-10624","documentPage":"https://doi.org/10.48550/ARXIV.2503.10624","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2503.10624","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-10624","documentUrl":"https://doi.org/10.48550/ARXIV.2503.10624","arxivId":"2503.10624","arxivUrl":"https://arxiv.org/abs/2503.10624"},{"key":"journals/corr/abs-2503-24391","title":"Easi3R: Estimating Disentangled Motion from DUSt3R Without Training.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2503.24391"],"source":"https://dblp.org/rec/journals/corr/abs-2503-24391","documentPage":"https://doi.org/10.48550/ARXIV.2503.24391","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2503.24391","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-24391","documentUrl":"https://doi.org/10.48550/ARXIV.2503.24391","arxivId":"2503.24391","arxivUrl":"https://arxiv.org/abs/2503.24391"},{"key":"journals/corr/abs-2505-05022","title":"SOAP: Style-Omniscient Animatable Portraits.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2505.05022"],"source":"https://dblp.org/rec/journals/corr/abs-2505-05022","documentPage":"https://doi.org/10.48550/ARXIV.2505.05022","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2505.05022","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-05022","documentUrl":"https://doi.org/10.48550/ARXIV.2505.05022","arxivId":"2505.05022","arxivUrl":"https://arxiv.org/abs/2505.05022"},{"key":"journals/corr/abs-2509-24817","title":"UP2You: Fast Reconstruction of Yourself from Unconstrained Photo Collections.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2509.24817"],"source":"https://dblp.org/rec/journals/corr/abs-2509-24817","documentPage":"https://doi.org/10.48550/ARXIV.2509.24817","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2509.24817","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-24817","documentUrl":"https://doi.org/10.48550/ARXIV.2509.24817","arxivId":"2509.24817","arxivUrl":"https://arxiv.org/abs/2509.24817"},{"key":"journals/corr/abs-2509-26645","title":"TTT3R: 3D Reconstruction as Test-Time Training.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2509.26645"],"source":"https://dblp.org/rec/journals/corr/abs-2509-26645","documentPage":"https://doi.org/10.48550/ARXIV.2509.26645","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2509.26645","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-26645","documentUrl":"https://doi.org/10.48550/ARXIV.2509.26645","arxivId":"2509.26645","arxivUrl":"https://arxiv.org/abs/2509.26645"},{"key":"journals/corr/abs-2510-06219","title":"Human3R: Everyone Everywhere All at Once.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2510.06219"],"source":"https://dblp.org/rec/journals/corr/abs-2510-06219","documentPage":"https://doi.org/10.48550/ARXIV.2510.06219","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2510.06219","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-06219","documentUrl":"https://doi.org/10.48550/ARXIV.2510.06219","arxivId":"2510.06219","arxivUrl":"https://arxiv.org/abs/2510.06219"}],"excludedFormal":[],"excludedOther":[{"key":"phd/dnb/Xiu25","title":"Democratizing 3D Human Digitization.","year":2025,"yearOfEvent":null,"venue":null,"types":["https://dblp.org/rdf/schema#Book"],"dois":["https://doi.org/10.15496/PUBLIKATION-104690"],"source":"https://dblp.org/rec/phd/dnb/Xiu25","documentPage":"https://doi.org/10.15496/PUBLIKATION-104690","type":"other","doi":"https://doi.org/10.15496/PUBLIKATION-104690","exclusionReason":"Not DBLP Article, Inproceedings, or Informal; outside the requested publication types.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/phd/dnb/Xiu25","documentUrl":"https://doi.org/10.15496/PUBLIKATION-104690"}],"excludedHomonyms":[],"unassignedCandidates":[],"retrievedAt":"2026-10-19","querySource":"https://sparql.dblp.org/","method":"DBLP yearOfPublication=2025; Article + Inproceedings; excludes Informal/CoRR and explicit editorial/correction/erratum/preface; unique DBLP record keys within person.","labName":"Endless AI Lab（远兮实验室）","labUrl":"https://endless.do","labEvidence":"西湖大学教师介绍明确列出 Endless AI Lab，并称其为 founding PI；本人主页也写明以 PI 身份领导远兮实验室，链接 endless.do。","labSourceUrl":"https://en.westlake.edu.cn/faculty/yuliang-xiu.html","affiliationZh":"西湖大学","sourceWarning":false,"knownPreprintMinimum2025":null,"excludedMisattributed":[],"displayNotes":"身份已经个人或机构主页核对。2025 年正式记录 5 条，均为会议论文，所有作者位置均计入；预印本 6 条单列，不加总。","labDisplayNotes":"西湖大学教师页列出 Endless AI Lab，并称其为创始 PI；本人主页也写明其领导远兮实验室，据此归组。"},{"index":94,"name":"Feng Xu","nameZh":"徐枫","affiliation":"Tsinghua University","source":"DBLP Knowledge Graph official SPARQL API","profileUrl":"https://dblp.org/pid/03/2611-5","identifier":"03/2611-5","identityEvidence":[{"url":"https://dblp.org/pid/03/2611-5","evidence":"DBLP curated profile affiliations: Microsoft Research, Beijing, China; Tsinghua University, BNRIst, Beijing, China; Tsinghua University, School of Software / TNList, Beijing, China."}],"count2025":18,"conference2025":9,"journal2025":9,"preprint2025":11,"status":"verified","notes":"Counts are DBLP indexed coauthored records, not first-author counts, laboratory totals, unique scientific discoveries, or quality assessments. DBLP yearOfPublication=2025; yearOfEvent retained and can differ. Conference workshops are included. Preprints are separate and may overlap formal versions.","papers":[{"key":"conf/apsipa/ZhangHLLX24","title":"PRTGaussian: Efficient Relighting Using 3D Gaussians with Precomputed Radiance Transfer.","year":2025,"yearOfEvent":2024,"venue":"APSIPA","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/APSIPAASC63619.2025.10849016"],"source":"https://dblp.org/rec/conf/apsipa/ZhangHLLX24","documentPage":"https://doi.org/10.1109/APSIPAASC63619.2025.10849016","type":"Inproceedings","doi":"https://doi.org/10.1109/APSIPAASC63619.2025.10849016","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/apsipa/ZhangHLLX24","documentUrl":"https://doi.org/10.1109/APSIPAASC63619.2025.10849016"},{"key":"conf/bibm/DongGLHYPLX25","title":"Refined Mamba-Based Lower Limbs Motor Estimator for Parkinson's Disease Diagnostic.","year":2025,"yearOfEvent":2025,"venue":"BIBM","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/BIBM66473.2025.11356357"],"source":"https://dblp.org/rec/conf/bibm/DongGLHYPLX25","documentPage":"https://doi.org/10.1109/BIBM66473.2025.11356357","type":"Inproceedings","doi":"https://doi.org/10.1109/BIBM66473.2025.11356357","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/bibm/DongGLHYPLX25","documentUrl":"https://doi.org/10.1109/BIBM66473.2025.11356357"},{"key":"conf/bibm/YeGLHLPX25","title":"A Noise-Resistant 3D Hand Motion Estimator Framework for Parkinson's Tremor Assessment.","year":2025,"yearOfEvent":2025,"venue":"BIBM","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/BIBM66473.2025.11357216"],"source":"https://dblp.org/rec/conf/bibm/YeGLHLPX25","documentPage":"https://doi.org/10.1109/BIBM66473.2025.11357216","type":"Inproceedings","doi":"https://doi.org/10.1109/BIBM66473.2025.11357216","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/bibm/YeGLHLPX25","documentUrl":"https://doi.org/10.1109/BIBM66473.2025.11357216"},{"key":"conf/eccv/MingLLZX24","title":"High-Quality Mesh Blendshape Generation from Face Videos via Neural Inverse Rendering.","year":2025,"yearOfEvent":2024,"venue":"ECCV (70)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1007/978-3-031-72897-6_7"],"source":"https://dblp.org/rec/conf/eccv/MingLLZX24","documentPage":"https://doi.org/10.1007/978-3-031-72897-6_7","type":"Inproceedings","doi":"https://doi.org/10.1007/978-3-031-72897-6_7","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/eccv/MingLLZX24","documentUrl":"https://doi.org/10.1007/978-3-031-72897-6_7"},{"key":"conf/iccv/ShaoYYGYX25","title":"MagShield: Towards Better Robustness in Sparse Inertial Motion Capture Under Magnetic Disturbances.","year":2025,"yearOfEvent":2025,"venue":"ICCV","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/ICCV51701.2025.02695"],"source":"https://dblp.org/rec/conf/iccv/ShaoYYGYX25","documentPage":"https://doi.org/10.1109/ICCV51701.2025.02695","type":"Inproceedings","doi":"https://doi.org/10.1109/ICCV51701.2025.02695","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/ShaoYYGYX25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.02695"},{"key":"conf/iccv/ZhengLWWX25","title":"Teeth Reconstruction and Performance Capture Using a Phone Camera.","year":2025,"yearOfEvent":2025,"venue":"ICCV","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/ICCV51701.2025.00932"],"source":"https://dblp.org/rec/conf/iccv/ZhengLWWX25","documentPage":"https://doi.org/10.1109/ICCV51701.2025.00932","type":"Inproceedings","doi":"https://doi.org/10.1109/ICCV51701.2025.00932","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/ZhengLWWX25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.00932"},{"key":"conf/mm/0001LLTPM0025","title":"MotionRefineNet: Fine-Grained Pose Sequence Smoothing and Refinement.","year":2025,"yearOfEvent":2025,"venue":"ACM Multimedia","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1145/3746027.3754506"],"source":"https://dblp.org/rec/conf/mm/0001LLTPM0025","documentPage":"https://doi.org/10.1145/3746027.3754506","type":"Inproceedings","doi":"https://doi.org/10.1145/3746027.3754506","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/mm/0001LLTPM0025","documentUrl":"https://doi.org/10.1145/3746027.3754506"},{"key":"conf/siggraph/HuangLZ025","title":"Guiding-Based Importance Sampling for Walk on Stars.","year":2025,"yearOfEvent":2025,"venue":"SIGGRAPH (Conference Paper Track)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1145/3721238.3730593"],"source":"https://dblp.org/rec/conf/siggraph/HuangLZ025","documentPage":"https://doi.org/10.1145/3721238.3730593","type":"Inproceedings","doi":"https://doi.org/10.1145/3721238.3730593","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/siggraph/HuangLZ025","documentUrl":"https://doi.org/10.1145/3721238.3730593"},{"key":"conf/uist/ZhangYX25","title":"BaroPoser: Real-time Human Motion Tracking from IMUs and Barometers in Everyday Devices.","year":2025,"yearOfEvent":2025,"venue":"UIST","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1145/3746059.3747731"],"source":"https://dblp.org/rec/conf/uist/ZhangYX25","documentPage":"https://doi.org/10.1145/3746059.3747731","type":"Inproceedings","doi":"https://doi.org/10.1145/3746059.3747731","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/uist/ZhangYX25","documentUrl":"https://doi.org/10.1145/3746059.3747731"},{"key":"journals/cee/XuZBLGX25","title":"Diagnosing tic disorders from videos using multi-phase learning.","year":2025,"yearOfEvent":null,"venue":"Comput. Electr. Eng.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1016/J.COMPELECENG.2025.110216"],"source":"https://dblp.org/rec/journals/cee/XuZBLGX25","documentPage":"https://doi.org/10.1016/J.COMPELECENG.2025.110216","type":"Article","doi":"https://doi.org/10.1016/J.COMPELECENG.2025.110216","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/cee/XuZBLGX25","documentUrl":"https://doi.org/10.1016/J.COMPELECENG.2025.110216"},{"key":"journals/patterns/TangGLHLLX25","title":"S2S: A deep learning method for the radiological diagnosis of fine-grained diseases spanning screening to subtyping.","year":2025,"yearOfEvent":null,"venue":"Patterns","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1016/J.PATTER.2025.101294"],"source":"https://dblp.org/rec/journals/patterns/TangGLHLLX25","documentPage":"https://doi.org/10.1016/J.PATTER.2025.101294","type":"Article","doi":"https://doi.org/10.1016/J.PATTER.2025.101294","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/patterns/TangGLHLLX25","documentUrl":"https://doi.org/10.1016/J.PATTER.2025.101294"},{"key":"journals/tim/ZhuZHWQZYX25","title":"Progressive Inertial Poser: Progressive Real-Time Kinematic Chain Estimation for 3-D Full-Body Pose From Three IMU Sensors.","year":2025,"yearOfEvent":null,"venue":"IEEE Trans. Instrum. Meas.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1109/TIM.2025.3570339"],"source":"https://dblp.org/rec/journals/tim/ZhuZHWQZYX25","documentPage":"https://doi.org/10.1109/TIM.2025.3570339","type":"Article","doi":"https://doi.org/10.1109/TIM.2025.3570339","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/tim/ZhuZHWQZYX25","documentUrl":"https://doi.org/10.1109/TIM.2025.3570339"},{"key":"journals/tog/HanLSQZXX25","title":"Facial Appearance Capture at Home with Patch-Level Reflectance Prior.","year":2025,"yearOfEvent":null,"venue":"ACM Trans. Graph.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1145/3730825"],"source":"https://dblp.org/rec/journals/tog/HanLSQZXX25","documentPage":"https://doi.org/10.1145/3730825","type":"Article","doi":"https://doi.org/10.1145/3730825","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/tog/HanLSQZXX25","documentUrl":"https://doi.org/10.1145/3730825"},{"key":"journals/tog/YinSWYXG25","title":"Shape-aware Inertial Poser: Motion Tracking for Humans with Diverse Shapes Using Sparse Inertial Sensors.","year":2025,"yearOfEvent":null,"venue":"ACM Trans. Graph.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1145/3763311"],"source":"https://dblp.org/rec/journals/tog/YinSWYXG25","documentPage":"https://doi.org/10.1145/3763311","type":"Article","doi":"https://doi.org/10.1145/3763311","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/tog/YinSWYXG25","documentUrl":"https://doi.org/10.1145/3763311"},{"key":"journals/tog/YiPX25","title":"Improving Global Motion Estimation in Sparse IMU-based Motion Capture with Physics.","year":2025,"yearOfEvent":null,"venue":"ACM Trans. Graph.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1145/3730822"],"source":"https://dblp.org/rec/journals/tog/YiPX25","documentPage":"https://doi.org/10.1145/3730822","type":"Article","doi":"https://doi.org/10.1145/3730822","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/tog/YiPX25","documentUrl":"https://doi.org/10.1145/3730822"},{"key":"journals/tog/ZuoHJYSCYXGQ25","title":"Transformer IMU Calibrator: Dynamic On-body IMU Calibration for Inertial Motion Capture.","year":2025,"yearOfEvent":null,"venue":"ACM Trans. Graph.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1145/3730937"],"source":"https://dblp.org/rec/journals/tog/ZuoHJYSCYXGQ25","documentPage":"https://doi.org/10.1145/3730937","type":"Article","doi":"https://doi.org/10.1145/3730937","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/tog/ZuoHJYSCYXGQ25","documentUrl":"https://doi.org/10.1145/3730937"},{"key":"journals/tvcg/PanYZJZ0025","title":"DiffCap: Diffusion-Based Real-Time Human Motion Capture Using Sparse IMUs and a Monocular Camera.","year":2025,"yearOfEvent":null,"venue":"IEEE Trans. Vis. Comput. Graph.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1109/TVCG.2025.3596403"],"source":"https://dblp.org/rec/journals/tvcg/PanYZJZ0025","documentPage":"https://doi.org/10.1109/TVCG.2025.3596403","type":"Article","doi":"https://doi.org/10.1109/TVCG.2025.3596403","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/tvcg/PanYZJZ0025","documentUrl":"https://doi.org/10.1109/TVCG.2025.3596403"},{"key":"journals/tvcg/WangXLXPG25","title":"GaussianHead: High-Fidelity Head Avatars With Learnable Gaussian Derivation.","year":2025,"yearOfEvent":null,"venue":"IEEE Trans. Vis. Comput. Graph.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1109/TVCG.2025.3561794"],"source":"https://dblp.org/rec/journals/tvcg/WangXLXPG25","documentPage":"https://doi.org/10.1109/TVCG.2025.3561794","type":"Article","doi":"https://doi.org/10.1109/TVCG.2025.3561794","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/tvcg/WangXLXPG25","documentUrl":"https://doi.org/10.1109/TVCG.2025.3561794"}],"preprints":[{"key":"journals/corr/abs-2505-05010","title":"Improving Global Motion Estimation in Sparse IMU-based Motion Capture with Physics.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2505.05010"],"source":"https://dblp.org/rec/journals/corr/abs-2505-05010","documentPage":"https://doi.org/10.48550/ARXIV.2505.05010","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2505.05010","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-05010","documentUrl":"https://doi.org/10.48550/ARXIV.2505.05010","arxivId":"2505.05010","arxivUrl":"https://arxiv.org/abs/2505.05010"},{"key":"journals/corr/abs-2505-05336","title":"Progressive Inertial Poser: Progressive Real-Time Kinematic Chain Estimation for 3D Full-Body Pose from Three IMU Sensors.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2505.05336"],"source":"https://dblp.org/rec/journals/corr/abs-2505-05336","documentPage":"https://doi.org/10.48550/ARXIV.2505.05336","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2505.05336","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-05336","documentUrl":"https://doi.org/10.48550/ARXIV.2505.05336","arxivId":"2505.05336","arxivUrl":"https://arxiv.org/abs/2505.05336"},{"key":"journals/corr/abs-2506-03478","title":"Facial Appearance Capture at Home with Patch-Level Reflectance Prior.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2506.03478"],"source":"https://dblp.org/rec/journals/corr/abs-2506-03478","documentPage":"https://doi.org/10.48550/ARXIV.2506.03478","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2506.03478","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-03478","documentUrl":"https://doi.org/10.48550/ARXIV.2506.03478","arxivId":"2506.03478","arxivUrl":"https://arxiv.org/abs/2506.03478"},{"key":"journals/corr/abs-2506-10580","title":"Transformer IMU Calibrator: Dynamic On-body IMU Calibration for Inertial Motion Capture.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2506.10580"],"source":"https://dblp.org/rec/journals/corr/abs-2506-10580","documentPage":"https://doi.org/10.48550/ARXIV.2506.10580","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2506.10580","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-10580","documentUrl":"https://doi.org/10.48550/ARXIV.2506.10580","arxivId":"2506.10580","arxivUrl":"https://arxiv.org/abs/2506.10580"},{"key":"journals/corr/abs-2506-22907","title":"MagShield: Towards Better Robustness in Sparse Inertial Motion Capture Under Magnetic Disturbances.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2506.22907"],"source":"https://dblp.org/rec/journals/corr/abs-2506-22907","documentPage":"https://doi.org/10.48550/ARXIV.2506.22907","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2506.22907","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-22907","documentUrl":"https://doi.org/10.48550/ARXIV.2506.22907","arxivId":"2506.22907","arxivUrl":"https://arxiv.org/abs/2506.22907"},{"key":"journals/corr/abs-2508-03313","title":"BaroPoser: Real-time Human Motion Tracking from IMUs and Barometers in Everyday Devices.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2508.03313"],"source":"https://dblp.org/rec/journals/corr/abs-2508-03313","documentPage":"https://doi.org/10.48550/ARXIV.2508.03313","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2508.03313","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-03313","documentUrl":"https://doi.org/10.48550/ARXIV.2508.03313","arxivId":"2508.03313","arxivUrl":"https://arxiv.org/abs/2508.03313"},{"key":"journals/corr/abs-2508-06139","title":"DiffCap: Diffusion-based Real-time Human Motion Capture using Sparse IMUs and a Monocular Camera.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2508.06139"],"source":"https://dblp.org/rec/journals/corr/abs-2508-06139","documentPage":"https://doi.org/10.48550/ARXIV.2508.06139","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2508.06139","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-06139","documentUrl":"https://doi.org/10.48550/ARXIV.2508.06139","arxivId":"2508.06139","arxivUrl":"https://arxiv.org/abs/2508.06139"},{"key":"journals/corr/abs-2509-12742","title":"Effective Gaussian Management for High-fidelity Object Reconstruction.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2509.12742"],"source":"https://dblp.org/rec/journals/corr/abs-2509-12742","documentPage":"https://doi.org/10.48550/ARXIV.2509.12742","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2509.12742","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-12742","documentUrl":"https://doi.org/10.48550/ARXIV.2509.12742","arxivId":"2509.12742","arxivUrl":"https://arxiv.org/abs/2509.12742"},{"key":"journals/corr/abs-2510-17101","title":"Shape-aware Inertial Poser: Motion Tracking for Humans with Diverse Shapes Using Sparse Inertial Sensors.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2510.17101"],"source":"https://dblp.org/rec/journals/corr/abs-2510-17101","documentPage":"https://doi.org/10.48550/ARXIV.2510.17101","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2510.17101","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-17101","documentUrl":"https://doi.org/10.48550/ARXIV.2510.17101","arxivId":"2510.17101","arxivUrl":"https://arxiv.org/abs/2510.17101"},{"key":"journals/corr/abs-2511-20366","title":"VGGTFace: Topologically Consistent Facial Geometry Reconstruction in the Wild.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2511.20366"],"source":"https://dblp.org/rec/journals/corr/abs-2511-20366","documentPage":"https://doi.org/10.48550/ARXIV.2511.20366","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2511.20366","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2511-20366","documentUrl":"https://doi.org/10.48550/ARXIV.2511.20366","arxivId":"2511.20366","arxivUrl":"https://arxiv.org/abs/2511.20366"},{"key":"journals/corr/abs-2512-11237","title":"WildCap: Facial Appearance Capture in the Wild via Hybrid Inverse Rendering.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2512.11237"],"source":"https://dblp.org/rec/journals/corr/abs-2512-11237","documentPage":"https://doi.org/10.48550/ARXIV.2512.11237","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2512.11237","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-11237","documentUrl":"https://doi.org/10.48550/ARXIV.2512.11237","arxivId":"2512.11237","arxivUrl":"https://arxiv.org/abs/2512.11237"}],"excludedFormal":[],"excludedOther":[],"excludedHomonyms":[],"unassignedCandidates":[],"retrievedAt":"2026-10-19","querySource":"https://sparql.dblp.org/","method":"DBLP yearOfPublication=2025; Article + Inproceedings; excludes Informal/CoRR and explicit editorial/correction/erratum/preface; unique DBLP record keys within person.","labName":null,"labUrl":null,"labEvidence":"本人机构教师页和主页索引未给出可核实的当前Lab专名；直接主页取回遇证书错误，未知留空。","labSourceUrl":"https://www.thss.tsinghua.edu.cn/en/faculty/fengxu.htm","affiliationZh":"清华大学","sourceWarning":false,"knownPreprintMinimum2025":null,"excludedMisattributed":[],"displayNotes":"身份已经个人或机构主页核对。2025 年正式记录 18 条（会议 9、期刊 9），所有作者位置均计入，不表示主导或贡献份额；预印本 11 条单列，不加总。","labDisplayNotes":"清华软件学院教师页与本人主页索引都未见实验室专名；直接访问主页遇到证书错误。图中以「姓名及合作者」单列。"},{"index":95,"name":"Huazhe Xu","nameZh":"许华哲","affiliation":"Tsinghua University","source":"DBLP Knowledge Graph official SPARQL API","profileUrl":"https://dblp.org/pid/164/9006","identifier":"164/9006","identityEvidence":[{"url":"https://iiis.tsinghua.edu.cn/en/People/Faculty/XuHuazhe.htm","evidence":"School profile identifies Huazhe Xu, IIIS Tsinghua, robotics / reinforcement learning."},{"url":"https://www.khoury.northeastern.edu/home/lsw/papers/cvpr2025-mating.pdf","evidence":"2025 CVPR paper Two by Two lists Huazhe Xu with IIIS Tsinghua / Shanghai Qi Zhi Institute and is present in DBLP PID 164/9006."},{"url":"https://dblp.org/rec/conf/iccv/HouZFGHYZX25","evidence":"DBLP paper author signature connects this profile to Peking University (PKU)."},{"url":"https://dblp.org/rec/conf/iccv/HouZFGHYZX25","evidence":"DBLP paper author signature connects this profile to Shanghai Artificial Intelligence Laboratory."},{"url":"https://dblp.org/rec/conf/icra/ZhangLCZX25","evidence":"DBLP paper author signature connects this profile to ShangHai JiAi Genetics & IVF Institute."}],"count2025":16,"conference2025":14,"journal2025":2,"preprint2025":20,"status":"verified","notes":"Counts are DBLP indexed coauthored records, not first-author counts, laboratory totals, unique scientific discoveries, or quality assessments. DBLP yearOfPublication=2025; yearOfEvent retained and can differ. Conference workshops are included. Preprints are separate and may overlap formal versions.","papers":[{"key":"conf/cvpr/QiJWCWX25","title":"Two by Two: Learning Multi-Task Pairwise Objects Assembly for Generalizable Robot Manipulation.","year":2025,"yearOfEvent":2025,"venue":"CVPR","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/CVPR52734.2025.01620"],"source":"https://dblp.org/rec/conf/cvpr/QiJWCWX25","documentPage":"https://openaccess.thecvf.com/content/CVPR2025/html/Qi_Two_by_Two_Learning_Multi-Task_Pairwise_Objects_Assembly_for_Generalizable_CVPR_2025_paper.html","type":"Inproceedings","doi":"https://doi.org/10.1109/CVPR52734.2025.01620","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/QiJWCWX25","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Qi_Two_by_Two_Learning_Multi-Task_Pairwise_Objects_Assembly_for_Generalizable_CVPR_2025_paper.html"},{"key":"conf/eccv/HuangJZX24","title":"Diffusion Reward: Learning Rewards via Conditional Video Diffusion.","year":2025,"yearOfEvent":2024,"venue":"ECCV (42)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1007/978-3-031-72946-1_27"],"source":"https://dblp.org/rec/conf/eccv/HuangJZX24","documentPage":"https://doi.org/10.1007/978-3-031-72946-1_27","type":"Inproceedings","doi":"https://doi.org/10.1007/978-3-031-72946-1_27","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/eccv/HuangJZX24","documentUrl":"https://doi.org/10.1007/978-3-031-72946-1_27"},{"key":"conf/eccv/JuHZZJX24","title":"Robo-ABC: Affordance Generalization Beyond Categories via Semantic Correspondence for Robot Manipulation.","year":2025,"yearOfEvent":2024,"venue":"ECCV (41)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1007/978-3-031-72940-9_13"],"source":"https://dblp.org/rec/conf/eccv/JuHZZJX24","documentPage":"https://doi.org/10.1007/978-3-031-72940-9_13","type":"Inproceedings","doi":"https://doi.org/10.1007/978-3-031-72940-9_13","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/eccv/JuHZZJX24","documentUrl":"https://doi.org/10.1007/978-3-031-72940-9_13"},{"key":"conf/iccv/HouZFGHYZX25","title":"4D Visual Pre-Training for Robot Learning.","year":2025,"yearOfEvent":2025,"venue":"ICCV","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/ICCV51701.2025.00791"],"source":"https://dblp.org/rec/conf/iccv/HouZFGHYZX25","documentPage":"https://doi.org/10.1109/ICCV51701.2025.00791","type":"Inproceedings","doi":"https://doi.org/10.1109/ICCV51701.2025.00791","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/HouZFGHYZX25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.00791"},{"key":"conf/iclr/HeCXP25","title":"Looking Backward: Retrospective Backward Synthesis for Goal-Conditioned GFlowNets.","year":2025,"yearOfEvent":2025,"venue":"ICLR","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/iclr/HeCXP25","documentPage":"https://openreview.net/forum?id=fNMKqyvuZT","type":"Inproceedings","doi":null,"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iclr/HeCXP25","documentUrl":"https://openreview.net/forum?id=fNMKqyvuZT"},{"key":"conf/iclr/HuRHLHX25","title":"Stem-OB: Generalizable Visual Imitation Learning with Stem-Like Convergent Observation through Diffusion Inversion.","year":2025,"yearOfEvent":2025,"venue":"ICLR","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/iclr/HuRHLHX25","documentPage":"https://openreview.net/forum?id=xaYlO03tIk","type":"Inproceedings","doi":null,"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iclr/HuRHLHX25","documentUrl":"https://openreview.net/forum?id=xaYlO03tIk"},{"key":"conf/iclr/JiangSH0LX25","title":"Robots Pre-train Robots: Manipulation-Centric Robotic Representation from Large-Scale Robot Datasets.","year":2025,"yearOfEvent":2025,"venue":"ICLR","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/iclr/JiangSH0LX25","documentPage":"https://openreview.net/forum?id=yTEwmr1TJb","type":"Inproceedings","doi":null,"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iclr/JiangSH0LX25","documentUrl":"https://openreview.net/forum?id=yTEwmr1TJb"},{"key":"conf/iclr/ZhuJZWYHX25","title":"DenseMatcher: Learning 3D Semantic Correspondence for Category-Level Manipulation from a Single Demo.","year":2025,"yearOfEvent":2025,"venue":"ICLR","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/iclr/ZhuJZWYHX25","documentPage":"https://openreview.net/forum?id=8oFvUBvF1u","type":"Inproceedings","doi":null,"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iclr/ZhuJZWYHX25","documentUrl":"https://openreview.net/forum?id=8oFvUBvF1u"},{"key":"conf/icml/HuangZLXKL0XX25","title":"MENTOR: Mixture-of-Experts Network with Task-Oriented Perturbation for Visual Reinforcement Learning.","year":2025,"yearOfEvent":2025,"venue":"ICML","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/icml/HuangZLXKL0XX25","documentPage":"https://proceedings.mlr.press/v267/huang25av.html","type":"Inproceedings","doi":null,"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/icml/HuangZLXKL0XX25","documentUrl":"https://proceedings.mlr.press/v267/huang25av.html"},{"key":"conf/icml/KangHLYZX25","title":"A Forget-and-Grow Strategy for Deep Reinforcement Learning Scaling in Continuous Control.","year":2025,"yearOfEvent":2025,"venue":"ICML","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/icml/KangHLYZX25","documentPage":"https://proceedings.mlr.press/v267/kang25c.html","type":"Inproceedings","doi":null,"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/icml/KangHLYZX25","documentUrl":"https://proceedings.mlr.press/v267/kang25c.html"},{"key":"conf/icra/NaiYCCZXG25","title":"Fine-Tuning Hard-to-Simulate Objectives for Quadruped Locomotion: A Case Study on Total Power Saving.","year":2025,"yearOfEvent":2025,"venue":"ICRA","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/ICRA55743.2025.11128263"],"source":"https://dblp.org/rec/conf/icra/NaiYCCZXG25","documentPage":"https://doi.org/10.1109/ICRA55743.2025.11128263","type":"Inproceedings","doi":"https://doi.org/10.1109/ICRA55743.2025.11128263","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/icra/NaiYCCZXG25","documentUrl":"https://doi.org/10.1109/ICRA55743.2025.11128263"},{"key":"conf/icra/ZhangLCZX25","title":"Catch It! Learning to Catch in Flight with Mobile Dexterous Hands.","year":2025,"yearOfEvent":2025,"venue":"ICRA","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/ICRA55743.2025.11127596"],"source":"https://dblp.org/rec/conf/icra/ZhangLCZX25","documentPage":"https://doi.org/10.1109/ICRA55743.2025.11127596","type":"Inproceedings","doi":"https://doi.org/10.1109/ICRA55743.2025.11127596","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/icra/ZhangLCZX25","documentUrl":"https://doi.org/10.1109/ICRA55743.2025.11127596"},{"key":"conf/iros/XuWLZX25","title":"DTactive: A Vision-Based Tactile Sensor with Active Surface.","year":2025,"yearOfEvent":2025,"venue":"IROS","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/IROS60139.2025.11247152"],"source":"https://dblp.org/rec/conf/iros/XuWLZX25","documentPage":"https://doi.org/10.1109/IROS60139.2025.11247152","type":"Inproceedings","doi":"https://doi.org/10.1109/IROS60139.2025.11247152","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iros/XuWLZX25","documentUrl":"https://doi.org/10.1109/IROS60139.2025.11247152"},{"key":"conf/naacl/LiuHWLTLHX25","title":"World Models with Hints of Large Language Models for Goal Achieving.","year":2025,"yearOfEvent":2025,"venue":"NAACL (Long Papers)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.18653/V1/2025.NAACL-LONG.3"],"source":"https://dblp.org/rec/conf/naacl/LiuHWLTLHX25","documentPage":"https://doi.org/10.18653/V1/2025.NAACL-LONG.3","type":"Inproceedings","doi":"https://doi.org/10.18653/V1/2025.NAACL-LONG.3","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/naacl/LiuHWLTLHX25","documentUrl":"https://doi.org/10.18653/V1/2025.NAACL-LONG.3"},{"key":"journals/ijairr/ZhangYPYMCXZZ25","title":"Morpheus: A Neural-Driven Animatronic Face with Hybrid Actuation and Diverse Emotion Control.","year":2025,"yearOfEvent":null,"venue":"Int. J. Artif. Intell. Robotics Res.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1142/S2972335325500048"],"source":"https://dblp.org/rec/journals/ijairr/ZhangYPYMCXZZ25","documentPage":"https://doi.org/10.1142/S2972335325500048","type":"Article","doi":"https://doi.org/10.1142/S2972335325500048","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/ijairr/ZhangYPYMCXZZ25","documentUrl":"https://doi.org/10.1142/S2972335325500048"},{"key":"journals/ral/PanBYJJLPLX25","title":"RoboDuet: Learning a Cooperative Policy for Whole-Body Legged Loco-Manipulation.","year":2025,"yearOfEvent":null,"venue":"IEEE Robotics Autom. Lett.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1109/LRA.2025.3551230"],"source":"https://dblp.org/rec/journals/ral/PanBYJJLPLX25","documentPage":"https://doi.org/10.1109/LRA.2025.3551230","type":"Article","doi":"https://doi.org/10.1109/LRA.2025.3551230","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/ral/PanBYJJLPLX25","documentUrl":"https://doi.org/10.1109/LRA.2025.3551230"}],"preprints":[{"key":"journals/corr/abs-2502-07730","title":"DOGlove: Dexterous Manipulation with a Low-Cost Open-Source Haptic Force Feedback Glove.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2502.07730"],"source":"https://dblp.org/rec/journals/corr/abs-2502-07730","documentPage":"https://doi.org/10.48550/ARXIV.2502.07730","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2502.07730","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2502-07730","documentUrl":"https://doi.org/10.48550/ARXIV.2502.07730","arxivId":"2502.07730","arxivUrl":"https://arxiv.org/abs/2502.07730"},{"key":"journals/corr/abs-2502-10956","title":"Fine-Tuning Hard-to-Simulate Objectives for Quadruped Locomotion: A Case Study on Total Power Saving.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2502.10956"],"source":"https://dblp.org/rec/journals/corr/abs-2502-10956","documentPage":"https://doi.org/10.48550/ARXIV.2502.10956","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2502.10956","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2502-10956","documentUrl":"https://doi.org/10.48550/ARXIV.2502.10956","arxivId":"2502.10956","arxivUrl":"https://arxiv.org/abs/2502.10956"},{"key":"journals/corr/abs-2502-16932","title":"DemoGen: Synthetic Demonstration Generation for Data-Efficient Visuomotor Policy Learning.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2502.16932"],"source":"https://dblp.org/rec/journals/corr/abs-2502-16932","documentPage":"https://doi.org/10.48550/ARXIV.2502.16932","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2502.16932","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2502-16932","documentUrl":"https://doi.org/10.48550/ARXIV.2502.16932","arxivId":"2502.16932","arxivUrl":"https://arxiv.org/abs/2502.16932"},{"key":"journals/corr/abs-2503-02881","title":"Reactive Diffusion Policy: Slow-Fast Visual-Tactile Policy Learning for Contact-Rich Manipulation.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2503.02881"],"source":"https://dblp.org/rec/journals/corr/abs-2503-02881","documentPage":"https://doi.org/10.48550/ARXIV.2503.02881","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2503.02881","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-02881","documentUrl":"https://doi.org/10.48550/ARXIV.2503.02881","arxivId":"2503.02881","arxivUrl":"https://arxiv.org/abs/2503.02881"},{"key":"journals/corr/abs-2503-22444","title":"Scaling Laws of Scientific Discovery with AI and Robot Scientists.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2503.22444"],"source":"https://dblp.org/rec/journals/corr/abs-2503-22444","documentPage":"https://doi.org/10.48550/ARXIV.2503.22444","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2503.22444","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-22444","documentUrl":"https://doi.org/10.48550/ARXIV.2503.22444","arxivId":"2503.22444","arxivUrl":"https://arxiv.org/abs/2503.22444"},{"key":"journals/corr/abs-2504-06961","title":"Two by Two: Learning Multi-Task Pairwise Objects Assembly for Generalizable Robot Manipulation.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2504.06961"],"source":"https://dblp.org/rec/journals/corr/abs-2504-06961","documentPage":"https://doi.org/10.48550/ARXIV.2504.06961","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2504.06961","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2504-06961","documentUrl":"https://doi.org/10.48550/ARXIV.2504.06961","arxivId":"2504.06961","arxivUrl":"https://arxiv.org/abs/2504.06961"},{"key":"journals/corr/abs-2505-06883","title":"FACET: Force-Adaptive Control via Impedance Reference Tracking for Legged Robots.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2505.06883"],"source":"https://dblp.org/rec/journals/corr/abs-2505-06883","documentPage":"https://doi.org/10.48550/ARXIV.2505.06883","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2505.06883","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-06883","documentUrl":"https://doi.org/10.48550/ARXIV.2505.06883","arxivId":"2505.06883","arxivUrl":"https://arxiv.org/abs/2505.06883"},{"key":"journals/corr/abs-2505-07819","title":"H3DP: Triply-Hierarchical Diffusion Policy for Visuomotor Learning.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2505.07819"],"source":"https://dblp.org/rec/journals/corr/abs-2505-07819","documentPage":"https://doi.org/10.48550/ARXIV.2505.07819","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2505.07819","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-07819","documentUrl":"https://doi.org/10.48550/ARXIV.2505.07819","arxivId":"2505.07819","arxivUrl":"https://arxiv.org/abs/2505.07819"},{"key":"journals/corr/abs-2505-15692","title":"Thought-Augmented Policy Optimization: Bridging External Guidance and Internal Capabilities.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2505.15692"],"source":"https://dblp.org/rec/journals/corr/abs-2505-15692","documentPage":"https://doi.org/10.48550/ARXIV.2505.15692","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2505.15692","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-15692","documentUrl":"https://doi.org/10.48550/ARXIV.2505.15692","arxivId":"2505.15692","arxivUrl":"https://arxiv.org/abs/2505.15692"},{"key":"journals/corr/abs-2506-05064","title":"DemoSpeedup: Accelerating Visuomotor Policies via Entropy-Guided Demonstration Acceleration.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2506.05064"],"source":"https://dblp.org/rec/journals/corr/abs-2506-05064","documentPage":"https://doi.org/10.48550/ARXIV.2506.05064","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2506.05064","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-05064","documentUrl":"https://doi.org/10.48550/ARXIV.2506.05064","arxivId":"2506.05064","arxivUrl":"https://arxiv.org/abs/2506.05064"},{"key":"journals/corr/abs-2507-02712","title":"A Forget-and-Grow Strategy for Deep Reinforcement Learning Scaling in Continuous Control.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2507.02712"],"source":"https://dblp.org/rec/journals/corr/abs-2507-02712","documentPage":"https://doi.org/10.48550/ARXIV.2507.02712","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2507.02712","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2507-02712","documentUrl":"https://doi.org/10.48550/ARXIV.2507.02712","arxivId":"2507.02712","arxivUrl":"https://arxiv.org/abs/2507.02712"},{"key":"journals/corr/abs-2507-16645","title":"Morpheus: A Neural-driven Animatronic Face with Hybrid Actuation and Diverse Emotion Control.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2507.16645"],"source":"https://dblp.org/rec/journals/corr/abs-2507-16645","documentPage":"https://doi.org/10.48550/ARXIV.2507.16645","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2507.16645","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2507-16645","documentUrl":"https://doi.org/10.48550/ARXIV.2507.16645","arxivId":"2507.16645","arxivUrl":"https://arxiv.org/abs/2507.16645"},{"key":"journals/corr/abs-2508-17230","title":"4D Visual Pre-training for Robot Learning.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2508.17230"],"source":"https://dblp.org/rec/journals/corr/abs-2508-17230","documentPage":"https://doi.org/10.48550/ARXIV.2508.17230","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2508.17230","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-17230","documentUrl":"https://doi.org/10.48550/ARXIV.2508.17230","arxivId":"2508.17230","arxivUrl":"https://arxiv.org/abs/2508.17230"},{"key":"journals/corr/abs-2508-20085","title":"HERMES: Human-to-Robot Embodied Learning from Multi-Source Motion Data for Mobile Dexterous Manipulation.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2508.20085"],"source":"https://dblp.org/rec/journals/corr/abs-2508-20085","documentPage":"https://doi.org/10.48550/ARXIV.2508.20085","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2508.20085","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-20085","documentUrl":"https://doi.org/10.48550/ARXIV.2508.20085","arxivId":"2508.20085","arxivUrl":"https://arxiv.org/abs/2508.20085"},{"key":"journals/corr/abs-2509-00576","title":"Galaxea Open-World Dataset and G0 Dual-System VLA Model.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2509.00576"],"source":"https://dblp.org/rec/journals/corr/abs-2509-00576","documentPage":"https://doi.org/10.48550/ARXIV.2509.00576","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2509.00576","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-00576","documentUrl":"https://doi.org/10.48550/ARXIV.2509.00576","arxivId":"2509.00576","arxivUrl":"https://arxiv.org/abs/2509.00576"},{"key":"journals/corr/abs-2509-15273","title":"Embodied Arena: A Comprehensive, Unified, and Evolving Evaluation Platform for Embodied AI.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2509.15273"],"source":"https://dblp.org/rec/journals/corr/abs-2509-15273","documentPage":"https://doi.org/10.48550/ARXIV.2509.15273","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2509.15273","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-15273","documentUrl":"https://doi.org/10.48550/ARXIV.2509.15273","arxivId":"2509.15273","arxivUrl":"https://arxiv.org/abs/2509.15273"},{"key":"journals/corr/abs-2509-23721","title":"DA-MMP: Learning Coordinated and Accurate Throwing with Dynamics-Aware Motion Manifold Primitives.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2509.23721"],"source":"https://dblp.org/rec/journals/corr/abs-2509-23721","documentPage":"https://doi.org/10.48550/ARXIV.2509.23721","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2509.23721","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-23721","documentUrl":"https://doi.org/10.48550/ARXIV.2509.23721","arxivId":"2509.23721","arxivUrl":"https://arxiv.org/abs/2509.23721"},{"key":"journals/corr/abs-2510-08549","title":"Entropy Regularizing Activation: Boosting Continuous Control, Large Language Models, and Image Classification with Activation as Entropy Constraints.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2510.08549"],"source":"https://dblp.org/rec/journals/corr/abs-2510-08549","documentPage":"https://doi.org/10.48550/ARXIV.2510.08549","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2510.08549","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-08549","documentUrl":"https://doi.org/10.48550/ARXIV.2510.08549","arxivId":"2510.08549","arxivUrl":"https://arxiv.org/abs/2510.08549"},{"key":"journals/corr/abs-2510-14830","title":"RL-100: Performant Robotic Manipulation with Real-World Reinforcement Learning.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2510.14830"],"source":"https://dblp.org/rec/journals/corr/abs-2510-14830","documentPage":"https://doi.org/10.48550/ARXIV.2510.14830","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2510.14830","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-14830","documentUrl":"https://doi.org/10.48550/ARXIV.2510.14830","arxivId":"2510.14830","arxivUrl":"https://arxiv.org/abs/2510.14830"},{"key":"journals/corr/abs-2511-05007","title":"MoE-DP: An MoE-Enhanced Diffusion Policy for Robust Long-Horizon Robotic Manipulation with Skill Decomposition and Failure Recovery.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2511.05007"],"source":"https://dblp.org/rec/journals/corr/abs-2511-05007","documentPage":"https://doi.org/10.48550/ARXIV.2511.05007","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2511.05007","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2511-05007","documentUrl":"https://doi.org/10.48550/ARXIV.2511.05007","arxivId":"2511.05007","arxivUrl":"https://arxiv.org/abs/2511.05007"}],"excludedFormal":[],"excludedOther":[],"excludedHomonyms":[],"unassignedCandidates":[],"retrievedAt":"2026-10-19","querySource":"https://sparql.dblp.org/","method":"DBLP yearOfPublication=2025; Article + Inproceedings; excludes Informal/CoRR and explicit editorial/correction/erratum/preface; unique DBLP record keys within person.","labName":"Tsinghua Embodied AI Lab（TEA Lab）","labUrl":null,"labEvidence":"已缓存的本人主页明确表示其领导 Tsinghua Embodied AI Lab；缓存未提供可确认的独立实验室首页地址。","labSourceUrl":"https://hxu.rocks/","affiliationZh":"清华大学","sourceWarning":false,"knownPreprintMinimum2025":null,"excludedMisattributed":[],"displayNotes":"身份已经个人或机构主页核对。2025 年正式记录 16 条（会议 14、期刊 2），所有作者位置均计入，不表示主导或贡献份额；预印本 20 条单列，不加总。","labDisplayNotes":"本人主页写明其领导 Tsinghua Embodied AI Lab（TEA Lab），据此归组；未取得可确认的独立实验室网址。"},{"index":96,"name":"Kai Xu","nameZh":"徐凯","affiliation":"Institute of Industrial Artificial Intelligence, Chinese Academy of Sciences","source":"DBLP Knowledge Graph official SPARQL API","profileUrl":"https://dblp.org/pid/x/KaiXu4","identifier":"x/KaiXu4","identityEvidence":[{"url":"https://dblp.org/pid/x/KaiXu4","evidence":"DBLP curated profile affiliations: National University of Defense Technology, Changsha, China; National University of Defense Technology, School of Computer Science, Changsha, China; Princeton University, NJ, USA; Simon Fraser University, BC, Canada."},{"url":"https://dblp.org/pid/x/KaiXu4","evidence":"DBLP curated profile homepages: http://www.kevinkaixu.net."},{"url":"https://dh.fjut.edu.cn/2026/0622/c1430a269327/page.htm","evidence":"Host university biography identifies 徐凯 of CAS industrial AI institute as formerly NUDT professor, Princeton visiting scholar and SFU guest professor, matching DBLP Kai Xu 0004."}],"count2025":21,"conference2025":11,"journal2025":10,"preprint2025":18,"status":"verified","notes":"Counts are DBLP indexed coauthored records, not first-author counts, laboratory totals, unique scientific discoveries, or quality assessments. DBLP yearOfPublication=2025; yearOfEvent retained and can differ. Conference workshops are included. Preprints are separate and may overlap formal versions.","papers":[{"key":"conf/cvpr/GuoXL0LH25","title":"ArticulatedGS: Self-supervised Digital Twin Modeling of Articulated Objects using 3D Gaussian Splatting.","year":2025,"yearOfEvent":2025,"venue":"CVPR","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/CVPR52734.2025.02528"],"source":"https://dblp.org/rec/conf/cvpr/GuoXL0LH25","documentPage":"https://openaccess.thecvf.com/content/CVPR2025/html/Guo_ArticulatedGS_Self-supervised_Digital_Twin_Modeling_of_Articulated_Objects_using_3D_CVPR_2025_paper.html","type":"Inproceedings","doi":"https://doi.org/10.1109/CVPR52734.2025.02528","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/GuoXL0LH25","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Guo_ArticulatedGS_Self-supervised_Digital_Twin_Modeling_of_Articulated_Objects_using_3D_CVPR_2025_paper.html"},{"key":"conf/cvpr/TangZLGD0X25","title":"OnlineAnySeg: Online Zero-Shot 3D Segmentation by Visual Foundation Model Guided 2D Mask Merging.","year":2025,"yearOfEvent":2025,"venue":"CVPR","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/CVPR52734.2025.00348"],"source":"https://dblp.org/rec/conf/cvpr/TangZLGD0X25","documentPage":"https://openaccess.thecvf.com/content/CVPR2025/html/Tang_OnlineAnySeg_Online_Zero-Shot_3D_Segmentation_by_Visual_Foundation_Model_Guided_CVPR_2025_paper.html","type":"Inproceedings","doi":"https://doi.org/10.1109/CVPR52734.2025.00348","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/TangZLGD0X25","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Tang_OnlineAnySeg_Online_Zero-Shot_3D_Segmentation_by_Visual_Foundation_Model_Guided_CVPR_2025_paper.html"},{"key":"conf/cvpr/WangWMHXG25","title":"VideoDirector: Precise Video Editing via Text-to-Video Models.","year":2025,"yearOfEvent":2025,"venue":"CVPR","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/CVPR52734.2025.00247"],"source":"https://dblp.org/rec/conf/cvpr/WangWMHXG25","documentPage":"https://openaccess.thecvf.com/content/CVPR2025/html/Wang_VideoDirector_Precise_Video_Editing_via_Text-to-Video_Models_CVPR_2025_paper.html","type":"Inproceedings","doi":"https://doi.org/10.1109/CVPR52734.2025.00247","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/WangWMHXG25","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Wang_VideoDirector_Precise_Video_Editing_via_Text-to-Video_Models_CVPR_2025_paper.html"},{"key":"conf/cvpr/WangY00025","title":"VasTSD: Learning 3D Vascular Tree-state Space Diffusion Model for Angiography Synthesis.","year":2025,"yearOfEvent":2025,"venue":"CVPR","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/CVPR52734.2025.01463"],"source":"https://dblp.org/rec/conf/cvpr/WangY00025","documentPage":"https://openaccess.thecvf.com/content/CVPR2025/html/Wang_VasTSD_Learning_3D_Vascular_Tree-state_Space_Diffusion_Model_for_Angiography_CVPR_2025_paper.html","type":"Inproceedings","doi":"https://doi.org/10.1109/CVPR52734.2025.01463","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/WangY00025","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Wang_VasTSD_Learning_3D_Vascular_Tree-state_Space_Diffusion_Model_for_Angiography_CVPR_2025_paper.html"},{"key":"conf/cvpr/ZhaoAZXG25","title":"Progressive Correspondence Regenerator for Robust 3D Registration.","year":2025,"yearOfEvent":2025,"venue":"CVPR","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/CVPR52734.2025.00121"],"source":"https://dblp.org/rec/conf/cvpr/ZhaoAZXG25","documentPage":"https://openaccess.thecvf.com/content/CVPR2025/html/Zhao_Progressive_Correspondence_Regenerator_for_Robust_3D_Registration_CVPR_2025_paper.html","type":"Inproceedings","doi":"https://doi.org/10.1109/CVPR52734.2025.00121","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/ZhaoAZXG25","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Zhao_Progressive_Correspondence_Regenerator_for_Robust_3D_Registration_CVPR_2025_paper.html"},{"key":"conf/eccv/DaiLSHMHXH24","title":"InterFusion: Text-Driven Generation of 3D Human-Object Interaction.","year":2025,"yearOfEvent":2024,"venue":"ECCV (48)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1007/978-3-031-73195-2_2"],"source":"https://dblp.org/rec/conf/eccv/DaiLSHMHXH24","documentPage":"https://doi.org/10.1007/978-3-031-73195-2_2","type":"Inproceedings","doi":"https://doi.org/10.1007/978-3-031-73195-2_2","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/eccv/DaiLSHMHXH24","documentUrl":"https://doi.org/10.1007/978-3-031-73195-2_2"},{"key":"conf/eccv/SheZYHX24","title":"Learning Cross-Hand Policies of High-DOF Reaching and Grasping.","year":2025,"yearOfEvent":2024,"venue":"ECCV (30)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1007/978-3-031-73404-5_16"],"source":"https://dblp.org/rec/conf/eccv/SheZYHX24","documentPage":"https://doi.org/10.1007/978-3-031-73404-5_16","type":"Inproceedings","doi":"https://doi.org/10.1007/978-3-031-73404-5_16","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/eccv/SheZYHX24","documentUrl":"https://doi.org/10.1007/978-3-031-73404-5_16"},{"key":"conf/iccv/CaoZYLQZDX25","title":"CogNav: Cognitive Process Modeling for Object Goal Navigation with LLMs.","year":2025,"yearOfEvent":2025,"venue":"ICCV","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/ICCV51701.2025.00891"],"source":"https://dblp.org/rec/conf/iccv/CaoZYLQZDX25","documentPage":"https://doi.org/10.1109/ICCV51701.2025.00891","type":"Inproceedings","doi":"https://doi.org/10.1109/ICCV51701.2025.00891","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/CaoZYLQZDX25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.00891"},{"key":"conf/iccv/GaoYDZCZX25","title":"Curve-Aware Gaussian Splatting for 3D Parametric Curve Reconstruction.","year":2025,"yearOfEvent":2025,"venue":"ICCV","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/ICCV51701.2025.02556"],"source":"https://dblp.org/rec/conf/iccv/GaoYDZCZX25","documentPage":"https://doi.org/10.1109/ICCV51701.2025.02556","type":"Inproceedings","doi":"https://doi.org/10.1109/ICCV51701.2025.02556","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/GaoYDZCZX25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.02556"},{"key":"conf/iccv/GaoYHCZX25","title":"Self-Supervised Learning of Hybrid Part-Aware 3D Representations of 2D Gaussians and Superquadrics.","year":2025,"yearOfEvent":2025,"venue":"ICCV","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/ICCV51701.2025.00900"],"source":"https://dblp.org/rec/conf/iccv/GaoYHCZX25","documentPage":"https://doi.org/10.1109/ICCV51701.2025.00900","type":"Inproceedings","doi":"https://doi.org/10.1109/ICCV51701.2025.00900","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/GaoYHCZX25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.00900"},{"key":"conf/prcv/LiuXHYZ24","title":"MaskEditor: Instruct 3D Object Editing with Learned Masks.","year":2025,"yearOfEvent":2024,"venue":"PRCV (6)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1007/978-981-97-8508-7_20"],"source":"https://dblp.org/rec/conf/prcv/LiuXHYZ24","documentPage":"https://doi.org/10.1007/978-981-97-8508-7_20","type":"Inproceedings","doi":"https://doi.org/10.1007/978-981-97-8508-7_20","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/prcv/LiuXHYZ24","documentUrl":"https://doi.org/10.1007/978-981-97-8508-7_20"},{"key":"journals/cgf/LanZGZCYWX25","title":"BoxFusion: Reconstruction-Free Open-Vocabulary 3D Object Detection via Real-Time Multi-View Box Fusion.","year":2025,"yearOfEvent":null,"venue":"Comput. Graph. Forum","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1111/CGF.70254"],"source":"https://dblp.org/rec/journals/cgf/LanZGZCYWX25","documentPage":"https://doi.org/10.1111/CGF.70254","type":"Article","doi":"https://doi.org/10.1111/CGF.70254","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/cgf/LanZGZCYWX25","documentUrl":"https://doi.org/10.1111/CGF.70254"},{"key":"journals/cvgip/ZhaoYHYZX25","title":"DISCO: Efficient Diffusion Solver for large-scale Combinatorial Optimization problems.","year":2025,"yearOfEvent":null,"venue":"Graph. Model.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1016/J.GMOD.2025.101284"],"source":"https://dblp.org/rec/journals/cvgip/ZhaoYHYZX25","documentPage":"https://doi.org/10.1016/J.GMOD.2025.101284","type":"Article","doi":"https://doi.org/10.1016/J.GMOD.2025.101284","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/cvgip/ZhaoYHYZX25","documentUrl":"https://doi.org/10.1016/J.GMOD.2025.101284"},{"key":"journals/fcsc/WenZYWZX25","title":"CAD-NeRF: learning NeRFs from uncalibrated few-view images by CAD model retrieval.","year":2025,"yearOfEvent":null,"venue":"Frontiers Comput. Sci.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1007/S11704-024-40417-7"],"source":"https://dblp.org/rec/journals/fcsc/WenZYWZX25","documentPage":"https://doi.org/10.1007/S11704-024-40417-7","type":"Article","doi":"https://doi.org/10.1007/S11704-024-40417-7","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/fcsc/WenZYWZX25","documentUrl":"https://doi.org/10.1007/S11704-024-40417-7"},{"key":"journals/pami/WanSCX25","title":"Equivariant Diffusion Model With A5-Group Neurons for Joint Pose Estimation and Shape Reconstruction.","year":2025,"yearOfEvent":null,"venue":"IEEE Trans. Pattern Anal. Mach. Intell.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1109/TPAMI.2025.3540593"],"source":"https://dblp.org/rec/journals/pami/WanSCX25","documentPage":"https://doi.org/10.1109/TPAMI.2025.3540593","type":"Article","doi":"https://doi.org/10.1109/TPAMI.2025.3540593","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/pami/WanSCX25","documentUrl":"https://doi.org/10.1109/TPAMI.2025.3540593"},{"key":"journals/tcsv/GaoYZZCX25","title":"Generic Objects as Pose Probes for Few-Shot View Synthesis.","year":2025,"yearOfEvent":null,"venue":"IEEE Trans. Circuits Syst. Video Technol.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1109/TCSVT.2025.3551303"],"source":"https://dblp.org/rec/journals/tcsv/GaoYZZCX25","documentPage":"https://doi.org/10.1109/TCSVT.2025.3551303","type":"Article","doi":"https://doi.org/10.1109/TCSVT.2025.3551303","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/tcsv/GaoYZZCX25","documentUrl":"https://doi.org/10.1109/TCSVT.2025.3551303"},{"key":"journals/tcsv/ZhuYWZX25","title":"Relighting Scenes With Object Insertions in Neural Radiance Fields.","year":2025,"yearOfEvent":null,"venue":"IEEE Trans. Circuits Syst. Video Technol.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1109/TCSVT.2025.3535599"],"source":"https://dblp.org/rec/journals/tcsv/ZhuYWZX25","documentPage":"https://doi.org/10.1109/TCSVT.2025.3535599","type":"Article","doi":"https://doi.org/10.1109/TCSVT.2025.3535599","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/tcsv/ZhuYWZX25","documentUrl":"https://doi.org/10.1109/TCSVT.2025.3535599"},{"key":"journals/tmm/TianQYZX25","title":"Tensorformer: Normalized Matrix Attention Transformer for High-Quality Point Cloud Reconstruction.","year":2025,"yearOfEvent":null,"venue":"IEEE Trans. Multim.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1109/TMM.2023.3277271"],"source":"https://dblp.org/rec/journals/tmm/TianQYZX25","documentPage":"https://doi.org/10.1109/TMM.2023.3277271","type":"Article","doi":"https://doi.org/10.1109/TMM.2023.3277271","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/tmm/TianQYZX25","documentUrl":"https://doi.org/10.1109/TMM.2023.3277271"},{"key":"journals/tog/XiaoLZLX25","title":"Designing Pin-pression Gripper and Learning its Dexterous Grasping with Online In-hand Adjustment.","year":2025,"yearOfEvent":null,"venue":"ACM Trans. Graph.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1145/3730880"],"source":"https://dblp.org/rec/journals/tog/XiaoLZLX25","documentPage":"https://doi.org/10.1145/3730880","type":"Article","doi":"https://doi.org/10.1145/3730880","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/tog/XiaoLZLX25","documentUrl":"https://doi.org/10.1145/3730880"},{"key":"journals/tvcg/HuangZLX25","title":"Part-Aware Shape Generation With Latent 3D Diffusion of Neural Voxel Fields.","year":2025,"yearOfEvent":null,"venue":"IEEE Trans. Vis. Comput. Graph.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1109/TVCG.2025.3562871"],"source":"https://dblp.org/rec/journals/tvcg/HuangZLX25","documentPage":"https://doi.org/10.1109/TVCG.2025.3562871","type":"Article","doi":"https://doi.org/10.1109/TVCG.2025.3562871","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/tvcg/HuangZLX25","documentUrl":"https://doi.org/10.1109/TVCG.2025.3562871"},{"key":"journals/vc/WangYWZXH25","title":"Angio-Diff: learning a self-supervised adversarial diffusion model for angiographic geometry generation.","year":2025,"yearOfEvent":null,"venue":"Vis. Comput.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1007/S00371-025-04036-Y"],"source":"https://dblp.org/rec/journals/vc/WangYWZXH25","documentPage":"https://doi.org/10.1007/S00371-025-04036-Y","type":"Article","doi":"https://doi.org/10.1007/S00371-025-04036-Y","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/vc/WangYWZXH25","documentUrl":"https://doi.org/10.1007/S00371-025-04036-Y"}],"preprints":[{"key":"journals/corr/abs-2501-02519","title":"Layout2Scene: 3D Semantic Layout Guided Scene Generation via Geometry and Appearance Diffusion Priors.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2501.02519"],"source":"https://dblp.org/rec/journals/corr/abs-2501-02519","documentPage":"https://doi.org/10.48550/ARXIV.2501.02519","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2501.02519","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2501-02519","documentUrl":"https://doi.org/10.48550/ARXIV.2501.02519","arxivId":"2501.02519","arxivUrl":"https://arxiv.org/abs/2501.02519"},{"key":"journals/corr/abs-2502-02163","title":"Progressive Correspondence Regenerator for Robust 3D Registration.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2502.02163"],"source":"https://dblp.org/rec/journals/corr/abs-2502-02163","documentPage":"https://doi.org/10.48550/ARXIV.2502.02163","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2502.02163","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2502-02163","documentUrl":"https://doi.org/10.48550/ARXIV.2502.02163","arxivId":"2502.02163","arxivUrl":"https://arxiv.org/abs/2502.02163"},{"key":"journals/corr/abs-2503-01309","title":"OnlineAnySeg: Online Zero-Shot 3D Segmentation by Visual Foundation Model Guided 2D Mask Merging.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2503.01309"],"source":"https://dblp.org/rec/journals/corr/abs-2503-01309","documentPage":"https://doi.org/10.48550/ARXIV.2503.01309","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2503.01309","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-01309","documentUrl":"https://doi.org/10.48550/ARXIV.2503.01309","arxivId":"2503.01309","arxivUrl":"https://arxiv.org/abs/2503.01309"},{"key":"journals/corr/abs-2503-08135","title":"ArticulatedGS: Self-supervised Digital Twin Modeling of Articulated Objects using 3D Gaussian Splatting.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2503.08135"],"source":"https://dblp.org/rec/journals/corr/abs-2503-08135","documentPage":"https://doi.org/10.48550/ARXIV.2503.08135","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2503.08135","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-08135","documentUrl":"https://doi.org/10.48550/ARXIV.2503.08135","arxivId":"2503.08135","arxivUrl":"https://arxiv.org/abs/2503.08135"},{"key":"journals/corr/abs-2503-12758","title":"VasTSD: Learning 3D Vascular Tree-state Space Diffusion Model for Angiography Synthesis.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2503.12758"],"source":"https://dblp.org/rec/journals/corr/abs-2503-12758","documentPage":"https://doi.org/10.48550/ARXIV.2503.12758","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2503.12758","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-12758","documentUrl":"https://doi.org/10.48550/ARXIV.2503.12758","arxivId":"2503.12758","arxivUrl":"https://arxiv.org/abs/2503.12758"},{"key":"journals/corr/abs-2504-04421","title":"Deliberate Planning of 3D Bin Packing on Packing Configuration Trees.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2504.04421"],"source":"https://dblp.org/rec/journals/corr/abs-2504-04421","documentPage":"https://doi.org/10.48550/ARXIV.2504.04421","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2504.04421","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2504-04421","documentUrl":"https://doi.org/10.48550/ARXIV.2504.04421","arxivId":"2504.04421","arxivUrl":"https://arxiv.org/abs/2504.04421"},{"key":"journals/corr/abs-2504-16693","title":"PIN-WM: Learning Physics-INformed World Models for Non-Prehensile Manipulation.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2504.16693"],"source":"https://dblp.org/rec/journals/corr/abs-2504-16693","documentPage":"https://doi.org/10.48550/ARXIV.2504.16693","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2504.16693","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2504-16693","documentUrl":"https://doi.org/10.48550/ARXIV.2504.16693","arxivId":"2504.16693","arxivUrl":"https://arxiv.org/abs/2504.16693"},{"key":"journals/corr/abs-2505-11528","title":"LaDi-WM: A Latent Diffusion-based World Model for Predictive Manipulation.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2505.11528"],"source":"https://dblp.org/rec/journals/corr/abs-2505-11528","documentPage":"https://doi.org/10.48550/ARXIV.2505.11528","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2505.11528","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-11528","documentUrl":"https://doi.org/10.48550/ARXIV.2505.11528","arxivId":"2505.11528","arxivUrl":"https://arxiv.org/abs/2505.11528"},{"key":"journals/corr/abs-2505-18994","title":"Designing Pin-pression Gripper and Learning its Dexterous Grasping with Online In-hand Adjustment.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2505.18994"],"source":"https://dblp.org/rec/journals/corr/abs-2505-18994","documentPage":"https://doi.org/10.48550/ARXIV.2505.18994","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2505.18994","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-18994","documentUrl":"https://doi.org/10.48550/ARXIV.2505.18994","arxivId":"2505.18994","arxivUrl":"https://arxiv.org/abs/2505.18994"},{"key":"journals/corr/abs-2506-15610","title":"BoxFusion: Reconstruction-Free Open-Vocabulary 3D Object Detection via Real-Time Multi-View Box Fusion.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2506.15610"],"source":"https://dblp.org/rec/journals/corr/abs-2506-15610","documentPage":"https://doi.org/10.48550/ARXIV.2506.15610","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2506.15610","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-15610","documentUrl":"https://doi.org/10.48550/ARXIV.2506.15610","arxivId":"2506.15610","arxivUrl":"https://arxiv.org/abs/2506.15610"},{"key":"journals/corr/abs-2506-19455","title":"Angio-Diff: Learning a Self-Supervised Adversarial Diffusion Model for Angiographic Geometry Generation.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2506.19455"],"source":"https://dblp.org/rec/journals/corr/abs-2506-19455","documentPage":"https://doi.org/10.48550/ARXIV.2506.19455","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2506.19455","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-19455","documentUrl":"https://doi.org/10.48550/ARXIV.2506.19455","arxivId":"2506.19455","arxivUrl":"https://arxiv.org/abs/2506.19455"},{"key":"journals/corr/abs-2506-21401","title":"Curve-Aware Gaussian Splatting for 3D Parametric Curve Reconstruction.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2506.21401"],"source":"https://dblp.org/rec/journals/corr/abs-2506-21401","documentPage":"https://doi.org/10.48550/ARXIV.2506.21401","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2506.21401","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-21401","documentUrl":"https://doi.org/10.48550/ARXIV.2506.21401","arxivId":"2506.21401","arxivUrl":"https://arxiv.org/abs/2506.21401"},{"key":"journals/corr/abs-2506-24121","title":"TextMesh4D: High-Quality Text-to-4D Mesh Generation.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2506.24121"],"source":"https://dblp.org/rec/journals/corr/abs-2506-24121","documentPage":"https://doi.org/10.48550/ARXIV.2506.24121","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2506.24121","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-24121","documentUrl":"https://doi.org/10.48550/ARXIV.2506.24121","arxivId":"2506.24121","arxivUrl":"https://arxiv.org/abs/2506.24121"},{"key":"journals/corr/abs-2507-17594","title":"RemixFusion: Residual-based Mixed Representation for Large-scale Online RGB-D Reconstruction.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2507.17594"],"source":"https://dblp.org/rec/journals/corr/abs-2507-17594","documentPage":"https://doi.org/10.48550/ARXIV.2507.17594","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2507.17594","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2507-17594","documentUrl":"https://doi.org/10.48550/ARXIV.2507.17594","arxivId":"2507.17594","arxivUrl":"https://arxiv.org/abs/2507.17594"},{"key":"journals/corr/abs-2508-06625","title":"CycleDiff: Cycle Diffusion Models for Unpaired Image-to-image Translation.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2508.06625"],"source":"https://dblp.org/rec/journals/corr/abs-2508-06625","documentPage":"https://doi.org/10.48550/ARXIV.2508.06625","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2508.06625","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-06625","documentUrl":"https://doi.org/10.48550/ARXIV.2508.06625","arxivId":"2508.06625","arxivUrl":"https://arxiv.org/abs/2508.06625"},{"key":"journals/corr/abs-2512-03538","title":"AdaPower: Specializing World Foundation Models for Predictive Manipulation.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2512.03538"],"source":"https://dblp.org/rec/journals/corr/abs-2512-03538","documentPage":"https://doi.org/10.48550/ARXIV.2512.03538","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2512.03538","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-03538","documentUrl":"https://doi.org/10.48550/ARXIV.2512.03538","arxivId":"2512.03538","arxivUrl":"https://arxiv.org/abs/2512.03538"},{"key":"journals/corr/abs-2512-04415","title":"RoboBPP: Benchmarking Robotic Online Bin Packing with Physics-based Simulation.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2512.04415"],"source":"https://dblp.org/rec/journals/corr/abs-2512-04415","documentPage":"https://doi.org/10.48550/ARXIV.2512.04415","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2512.04415","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-04415","documentUrl":"https://doi.org/10.48550/ARXIV.2512.04415","arxivId":"2512.04415","arxivUrl":"https://arxiv.org/abs/2512.04415"},{"key":"journals/corr/abs-2512-14095","title":"AnchorHOI: Zero-shot Generation of 4D Human-Object Interaction via Anchor-based Prior Distillation.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2512.14095"],"source":"https://dblp.org/rec/journals/corr/abs-2512-14095","documentPage":"https://doi.org/10.48550/ARXIV.2512.14095","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2512.14095","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-14095","documentUrl":"https://doi.org/10.48550/ARXIV.2512.14095","arxivId":"2512.14095","arxivUrl":"https://arxiv.org/abs/2512.14095"}],"excludedFormal":[],"excludedOther":[],"excludedHomonyms":[],"unassignedCandidates":[],"retrievedAt":"2026-10-19","querySource":"https://sparql.dblp.org/","method":"DBLP yearOfPublication=2025; Article + Inproceedings; excludes Informal/CoRR and explicit editorial/correction/erratum/preface; unique DBLP record keys within person.","labName":"物理智能团队","labUrl":null,"labEvidence":"中国科学院工业人工智能研究所官网2026年资料明确称其为物理智能团队负责人；原国防科大团队不当作当前团队。","labSourceUrl":"https://iaii.cas.cn/kxpj/kpwz/202607/t20260715_8249001.html","affiliationZh":"中科院工业人工智能研究所","sourceWarning":false,"knownPreprintMinimum2025":null,"excludedMisattributed":[],"displayNotes":"身份已经个人或机构主页核对。2025 年正式记录 21 条（会议 11、期刊 10），所有作者位置均计入，不表示主导或贡献份额；预印本 18 条单列，不加总。","labDisplayNotes":"中科院工业人工智能研究所 2026 年的官网资料称其为物理智能团队负责人，据此归组；不采用其此前在国防科大的团队。"},{"index":97,"name":"Lan Xu","nameZh":"许岚","affiliation":"ShanghaiTech University","source":"DBLP Knowledge Graph official SPARQL API","profileUrl":"https://dblp.org/pid/41/4840-3","identifier":"41/4840-3","identityEvidence":[{"url":"https://dblp.org/pid/41/4840-3","evidence":"DBLP curated profile affiliations: ShanghaiTech University, Shanghai, China."}],"count2025":18,"conference2025":15,"journal2025":3,"preprint2025":18,"status":"verified","notes":"Counts are DBLP indexed coauthored records, not first-author counts, laboratory totals, unique scientific discoveries, or quality assessments. DBLP yearOfPublication=2025; yearOfEvent retained and can differ. Conference workshops are included. Preprints are separate and may overlap formal versions.","papers":[{"key":"conf/3dim/ZhengWLZSCZLZZWX25","title":"HeadGAP: Few-Shot 3D Head Avatar via Generalizable Gaussian Priors.","year":2025,"yearOfEvent":2025,"venue":"3DV","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/3DV66043.2025.00092"],"source":"https://dblp.org/rec/conf/3dim/ZhengWLZSCZLZZWX25","documentPage":"https://doi.org/10.1109/3DV66043.2025.00092","type":"Inproceedings","doi":"https://doi.org/10.1109/3DV66043.2025.00092","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/3dim/ZhengWLZSCZLZZWX25","documentUrl":"https://doi.org/10.1109/3DV66043.2025.00092"},{"key":"conf/aaai/LiuZRHYX25","title":"SCOPE: Sign Language Contextual Processing with Embedding from LLMs.","year":2025,"yearOfEvent":2025,"venue":"AAAI","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1609/AAAI.V39I6.32612"],"source":"https://dblp.org/rec/conf/aaai/LiuZRHYX25","documentPage":"https://doi.org/10.1609/AAAI.V39I6.32612","type":"Inproceedings","doi":"https://doi.org/10.1609/AAAI.V39I6.32612","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/aaai/LiuZRHYX25","documentUrl":"https://doi.org/10.1609/AAAI.V39I6.32612"},{"key":"conf/aaai/WangWZLPZZJZXWY25","title":"Capturing the Unseen: Vision-Free Facial Motion Capture Using Inertial Measurement Units.","year":2025,"yearOfEvent":2025,"venue":"AAAI","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1609/AAAI.V39I8.32873"],"source":"https://dblp.org/rec/conf/aaai/WangWZLPZZJZXWY25","documentPage":"https://doi.org/10.1609/AAAI.V39I8.32873","type":"Inproceedings","doi":"https://doi.org/10.1609/AAAI.V39I8.32873","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/aaai/WangWZLPZZJZXWY25","documentUrl":"https://doi.org/10.1609/AAAI.V39I8.32873"},{"key":"conf/cvpr/JiangSGH0ZHX25","title":"RePerformer: Immersive Human-centric Volumetric Videos from Playback to Photoreal Reperformance.","year":2025,"yearOfEvent":2025,"venue":"CVPR","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/CVPR52734.2025.01060"],"source":"https://dblp.org/rec/conf/cvpr/JiangSGH0ZHX25","documentPage":"https://openaccess.thecvf.com/content/CVPR2025/html/Jiang_RePerformer_Immersive_Human-centric_Volumetric_Videos_from_Playback_to_Photoreal_Reperformance_CVPR_2025_paper.html","type":"Inproceedings","doi":"https://doi.org/10.1109/CVPR52734.2025.01060","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/JiangSGH0ZHX25","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Jiang_RePerformer_Immersive_Human-centric_Volumetric_Videos_from_Playback_to_Photoreal_Reperformance_CVPR_2025_paper.html"},{"key":"conf/cvpr/YanLLFDZZMXWS025","title":"ClimbingCap: Multi-Modal Dataset and Method for Rock Climbing in World Coordinate.","year":2025,"yearOfEvent":2025,"venue":"CVPR","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/CVPR52734.2025.01149"],"source":"https://dblp.org/rec/conf/cvpr/YanLLFDZZMXWS025","documentPage":"https://openaccess.thecvf.com/content/CVPR2025/html/Yan_ClimbingCap_Multi-Modal_Dataset_and_Method_for_Rock_Climbing_in_World_CVPR_2025_paper.html","type":"Inproceedings","doi":"https://doi.org/10.1109/CVPR52734.2025.01149","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/YanLLFDZZMXWS025","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Yan_ClimbingCap_Multi-Modal_Dataset_and_Method_for_Rock_Climbing_in_World_CVPR_2025_paper.html"},{"key":"conf/iccv/JiSJCXMYW25","title":"Towards Immersive Human-X Interaction: A Real-Time Framework for Physically Plausible Motion Synthesis.","year":2025,"yearOfEvent":2025,"venue":"ICCV","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/ICCV51701.2025.00948"],"source":"https://dblp.org/rec/conf/iccv/JiSJCXMYW25","documentPage":"https://doi.org/10.1109/ICCV51701.2025.00948","type":"Inproceedings","doi":"https://doi.org/10.1109/ICCV51701.2025.00948","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/JiSJCXMYW25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.00948"},{"key":"conf/iccv/YangLWLWYSX25","title":"SMGDiff: Soccer Motion Generation using Diffusion Probabilistic Models.","year":2025,"yearOfEvent":2025,"venue":"ICCV","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/ICCV51701.2025.01098"],"source":"https://dblp.org/rec/conf/iccv/YangLWLWYSX25","documentPage":"https://doi.org/10.1109/ICCV51701.2025.01098","type":"Inproceedings","doi":"https://doi.org/10.1109/ICCV51701.2025.01098","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/YangLWLWYSX25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.01098"},{"key":"conf/icmcs/WuSHXYW25","title":"THOR: Text to Human-Object Interaction Diffusion via Relation Intervention.","year":2025,"yearOfEvent":2025,"venue":"ICME","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/ICME59968.2025.11209879"],"source":"https://dblp.org/rec/conf/icmcs/WuSHXYW25","documentPage":"https://doi.org/10.1109/ICME59968.2025.11209879","type":"Inproceedings","doi":"https://doi.org/10.1109/ICME59968.2025.11209879","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/icmcs/WuSHXYW25","documentUrl":"https://doi.org/10.1109/ICME59968.2025.11209879"},{"key":"conf/mm/HongWSGJZ00025","title":"BEAM: Bridging Physically-based Rendering and Gaussian Modeling for Relightable Volumetric Video.","year":2025,"yearOfEvent":2025,"venue":"ACM Multimedia","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1145/3746027.3755233"],"source":"https://dblp.org/rec/conf/mm/HongWSGJZ00025","documentPage":"https://doi.org/10.1145/3746027.3755233","type":"Inproceedings","doi":"https://doi.org/10.1145/3746027.3755233","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/mm/HongWSGJZ00025","documentUrl":"https://doi.org/10.1145/3746027.3755233"},{"key":"conf/mm/LongZOZ00025","title":"Generating 3D Hair Strands from Images with Diverse Styles and Viewpoints.","year":2025,"yearOfEvent":2025,"venue":"ACM Multimedia","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1145/3746027.3755802"],"source":"https://dblp.org/rec/conf/mm/LongZOZ00025","documentPage":"https://doi.org/10.1145/3746027.3755802","type":"Inproceedings","doi":"https://doi.org/10.1145/3746027.3755802","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/mm/LongZOZ00025","documentUrl":"https://doi.org/10.1145/3746027.3755802"},{"key":"conf/mmsp/ShenCLHWZZX25","title":"Dynamic Gaussian Streams for Volumetric Video via Codebook-Based Quantization.","year":2025,"yearOfEvent":2025,"venue":"MMSP","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/MMSP64401.2025.11324257"],"source":"https://dblp.org/rec/conf/mmsp/ShenCLHWZZX25","documentPage":"https://doi.org/10.1109/MMSP64401.2025.11324257","type":"Inproceedings","doi":"https://doi.org/10.1109/MMSP64401.2025.11324257","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/mmsp/ShenCLHWZZX25","documentUrl":"https://doi.org/10.1109/MMSP64401.2025.11324257"},{"key":"conf/nips/WangHLZXYG25","title":"PartNeXt: A Next-Generation Dataset for Fine-Grained and Hierarchical 3D Part Understanding.","year":2025,"yearOfEvent":2025,"venue":"NeurIPS","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/nips/WangHLZXYG25","documentPage":"http://papers.nips.cc/paper_files/paper/2025/hash/579636b69390b41fa2d39b744593bfbe-Abstract-Datasets_and_Benchmarks_Track.html","type":"Inproceedings","doi":null,"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/nips/WangHLZXYG25","documentUrl":"http://papers.nips.cc/paper_files/paper/2025/hash/579636b69390b41fa2d39b744593bfbe-Abstract-Datasets_and_Benchmarks_Track.html"},{"key":"conf/nips/ZhengWZTCXYZHZ25","title":"4DGCPro: Efficient Hierarchical 4D Gaussian Compression for Progressive Volumetric Video Streaming.","year":2025,"yearOfEvent":2025,"venue":"NeurIPS","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/nips/ZhengWZTCXYZHZ25","documentPage":"http://papers.nips.cc/paper_files/paper/2025/hash/923285deb805c3e14e1aeebc9854d644-Abstract-Conference.html","type":"Inproceedings","doi":null,"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/nips/ZhengWZTCXYZHZ25","documentUrl":"http://papers.nips.cc/paper_files/paper/2025/hash/923285deb805c3e14e1aeebc9854d644-Abstract-Conference.html"},{"key":"conf/siggrapha/JiangGWHZSZJ00H25","title":"Topology-Aware Optimization of Gaussian Primitives for Human-Centric Volumetric Videos.","year":2025,"yearOfEvent":2025,"venue":"SIGGRAPH Asia","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1145/3757377.3763975"],"source":"https://dblp.org/rec/conf/siggrapha/JiangGWHZSZJ00H25","documentPage":"https://doi.org/10.1145/3757377.3763975","type":"Inproceedings","doi":"https://doi.org/10.1145/3757377.3763975","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/siggrapha/JiangGWHZSZJ00H25","documentUrl":"https://doi.org/10.1145/3757377.3763975"},{"key":"conf/siggrapha/LiuZLCCZ00S0Z25","title":"CityGo: Lightweight Urban Modeling and Rendering with Proxy Buildings and Residual Gaussians.","year":2025,"yearOfEvent":2025,"venue":"SIGGRAPH Asia","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1145/3757377.3763866"],"source":"https://dblp.org/rec/conf/siggrapha/LiuZLCCZ00S0Z25","documentPage":"https://doi.org/10.1145/3757377.3763866","type":"Inproceedings","doi":"https://doi.org/10.1145/3757377.3763866","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/siggrapha/LiuZLCCZ00S0Z25","documentUrl":"https://doi.org/10.1145/3757377.3763866"},{"key":"journals/tog/HanLSQZXX25","title":"Facial Appearance Capture at Home with Patch-Level Reflectance Prior.","year":2025,"yearOfEvent":null,"venue":"ACM Trans. Graph.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1145/3730825"],"source":"https://dblp.org/rec/journals/tog/HanLSQZXX25","documentPage":"https://doi.org/10.1145/3730825","type":"Article","doi":"https://doi.org/10.1145/3730825","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/tog/HanLSQZXX25","documentUrl":"https://doi.org/10.1145/3730825"},{"key":"journals/tog/YaoZYZZXYGY25","title":"CAST: Component-Aligned 3D Scene Reconstruction from an RGB Image.","year":2025,"yearOfEvent":null,"venue":"ACM Trans. Graph.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1145/3730841"],"source":"https://dblp.org/rec/journals/tog/YaoZYZZXYGY25","documentPage":"https://doi.org/10.1145/3730841","type":"Article","doi":"https://doi.org/10.1145/3730841","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/tog/YaoZYZZXYGY25","documentUrl":"https://doi.org/10.1145/3730841"},{"key":"journals/tog/ZhangZJBYXY25","title":"BANG: Dividing 3D Assets via Generative Exploded Dynamics.","year":2025,"yearOfEvent":null,"venue":"ACM Trans. Graph.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1145/3730840"],"source":"https://dblp.org/rec/journals/tog/ZhangZJBYXY25","documentPage":"https://doi.org/10.1145/3730840","type":"Article","doi":"https://doi.org/10.1145/3730840","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/tog/ZhangZJBYXY25","documentUrl":"https://doi.org/10.1145/3730840"}],"preprints":[{"key":"journals/corr/abs-2502-06392","title":"TANGLED: Generating 3D Hair Strands from Images with Arbitrary Styles and Viewpoints.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2502.06392"],"source":"https://dblp.org/rec/journals/corr/abs-2502-06392","documentPage":"https://doi.org/10.48550/ARXIV.2502.06392","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2502.06392","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2502-06392","documentUrl":"https://doi.org/10.48550/ARXIV.2502.06392","arxivId":"2502.06392","arxivUrl":"https://arxiv.org/abs/2502.06392"},{"key":"journals/corr/abs-2502-08297","title":"BEAM: Bridging Physically-based Rendering and Gaussian Modeling for Relightable Volumetric Video.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2502.08297"],"source":"https://dblp.org/rec/journals/corr/abs-2502-08297","documentPage":"https://doi.org/10.48550/ARXIV.2502.08297","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2502.08297","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2502-08297","documentUrl":"https://doi.org/10.48550/ARXIV.2502.08297","arxivId":"2502.08297","arxivUrl":"https://arxiv.org/abs/2502.08297"},{"key":"journals/corr/abs-2502-12894","title":"CAST: Component-Aligned 3D Scene Reconstruction from an RGB Image.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2502.12894"],"source":"https://dblp.org/rec/journals/corr/abs-2502-12894","documentPage":"https://doi.org/10.48550/ARXIV.2502.12894","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2502.12894","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2502-12894","documentUrl":"https://doi.org/10.48550/ARXIV.2502.12894","arxivId":"2502.12894","arxivUrl":"https://arxiv.org/abs/2502.12894"},{"key":"journals/corr/abs-2502-16175","title":"Mojito: LLM-Aided Motion Instructor with Jitter-Reduced Inertial Tokens.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2502.16175"],"source":"https://dblp.org/rec/journals/corr/abs-2502-16175","documentPage":"https://doi.org/10.48550/ARXIV.2502.16175","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2502.16175","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2502-16175","documentUrl":"https://doi.org/10.48550/ARXIV.2502.16175","arxivId":"2502.16175","arxivUrl":"https://arxiv.org/abs/2502.16175"},{"key":"journals/corr/abs-2503-12242","title":"RePerformer: Immersive Human-centric Volumetric Videos from Playback to Photoreal Reperformance.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2503.12242"],"source":"https://dblp.org/rec/journals/corr/abs-2503-12242","documentPage":"https://doi.org/10.48550/ARXIV.2503.12242","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2503.12242","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-12242","documentUrl":"https://doi.org/10.48550/ARXIV.2503.12242","arxivId":"2503.12242","arxivUrl":"https://arxiv.org/abs/2503.12242"},{"key":"journals/corr/abs-2503-18349","title":"Human-Object Interaction with Vision-Language Model Guided Relative Movement Dynamics.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2503.18349"],"source":"https://dblp.org/rec/journals/corr/abs-2503-18349","documentPage":"https://doi.org/10.48550/ARXIV.2503.18349","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2503.18349","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-18349","documentUrl":"https://doi.org/10.48550/ARXIV.2503.18349","arxivId":"2503.18349","arxivUrl":"https://arxiv.org/abs/2503.18349"},{"key":"journals/corr/abs-2503-21268","title":"ClimbingCap: Multi-Modal Dataset and Method for Rock Climbing in World Coordinate.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2503.21268"],"source":"https://dblp.org/rec/journals/corr/abs-2503-21268","documentPage":"https://doi.org/10.48550/ARXIV.2503.21268","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2503.21268","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-21268","documentUrl":"https://doi.org/10.48550/ARXIV.2503.21268","arxivId":"2503.21268","arxivUrl":"https://arxiv.org/abs/2503.21268"},{"key":"journals/corr/abs-2505-21041","title":"CityGo: Lightweight Urban Modeling and Rendering with Proxy Buildings and Residual Gaussians.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2505.21041"],"source":"https://dblp.org/rec/journals/corr/abs-2505-21041","documentPage":"https://doi.org/10.48550/ARXIV.2505.21041","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2505.21041","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-21041","documentUrl":"https://doi.org/10.48550/ARXIV.2505.21041","arxivId":"2505.21041","arxivUrl":"https://arxiv.org/abs/2505.21041"},{"key":"journals/corr/abs-2506-03478","title":"Facial Appearance Capture at Home with Patch-Level Reflectance Prior.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2506.03478"],"source":"https://dblp.org/rec/journals/corr/abs-2506-03478","documentPage":"https://doi.org/10.48550/ARXIV.2506.03478","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2506.03478","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-03478","documentUrl":"https://doi.org/10.48550/ARXIV.2506.03478","arxivId":"2506.03478","arxivUrl":"https://arxiv.org/abs/2506.03478"},{"key":"journals/corr/abs-2507-21493","title":"BANG: Dividing 3D Assets via Generative Exploded Dynamics.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2507.21493"],"source":"https://dblp.org/rec/journals/corr/abs-2507-21493","documentPage":"https://doi.org/10.48550/ARXIV.2507.21493","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2507.21493","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2507-21493","documentUrl":"https://doi.org/10.48550/ARXIV.2507.21493","arxivId":"2507.21493","arxivUrl":"https://arxiv.org/abs/2507.21493"},{"key":"journals/corr/abs-2508-02106","title":"Towards Immersive Human-X Interaction: A Real-Time Framework for Physically Plausible Motion Synthesis.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2508.02106"],"source":"https://dblp.org/rec/journals/corr/abs-2508-02106","documentPage":"https://doi.org/10.48550/ARXIV.2508.02106","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2508.02106","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-02106","documentUrl":"https://doi.org/10.48550/ARXIV.2508.02106","arxivId":"2508.02106","arxivUrl":"https://arxiv.org/abs/2508.02106"},{"key":"journals/corr/abs-2509-07653","title":"Topology-Aware Optimization of Gaussian Primitives for Human-Centric Volumetric Videos.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2509.07653"],"source":"https://dblp.org/rec/journals/corr/abs-2509-07653","documentPage":"https://doi.org/10.48550/ARXIV.2509.07653","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2509.07653","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-07653","documentUrl":"https://doi.org/10.48550/ARXIV.2509.07653","arxivId":"2509.07653","arxivUrl":"https://arxiv.org/abs/2509.07653"},{"key":"journals/corr/abs-2509-17506","title":"4D-MoDe: Towards Editable and Scalable Volumetric Streaming via Motion-Decoupled 4D Gaussian Compression.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2509.17506"],"source":"https://dblp.org/rec/journals/corr/abs-2509-17506","documentPage":"https://doi.org/10.48550/ARXIV.2509.17506","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2509.17506","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-17506","documentUrl":"https://doi.org/10.48550/ARXIV.2509.17506","arxivId":"2509.17506","arxivUrl":"https://arxiv.org/abs/2509.17506"},{"key":"journals/corr/abs-2509-17513","title":"4DGCPro: Efficient Hierarchical 4D Gaussian Compression for Progressive Volumetric Video Streaming.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2509.17513"],"source":"https://dblp.org/rec/journals/corr/abs-2509-17513","documentPage":"https://doi.org/10.48550/ARXIV.2509.17513","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2509.17513","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-17513","documentUrl":"https://doi.org/10.48550/ARXIV.2509.17513","arxivId":"2509.17513","arxivUrl":"https://arxiv.org/abs/2509.17513"},{"key":"journals/corr/abs-2510-20155","title":"PartNeXt: A Next-Generation Dataset for Fine-Grained and Hierarchical 3D Part Understanding.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2510.20155"],"source":"https://dblp.org/rec/journals/corr/abs-2510-20155","documentPage":"https://doi.org/10.48550/ARXIV.2510.20155","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2510.20155","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-20155","documentUrl":"https://doi.org/10.48550/ARXIV.2510.20155","arxivId":"2510.20155","arxivUrl":"https://arxiv.org/abs/2510.20155"},{"key":"journals/corr/abs-2511-01294","title":"Kinematify: Open-Vocabulary Synthesis of High-DoF Articulated Objects.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2511.01294"],"source":"https://dblp.org/rec/journals/corr/abs-2511-01294","documentPage":"https://doi.org/10.48550/ARXIV.2511.01294","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2511.01294","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2511-01294","documentUrl":"https://doi.org/10.48550/ARXIV.2511.01294","arxivId":"2511.01294","arxivUrl":"https://arxiv.org/abs/2511.01294"},{"key":"journals/corr/abs-2512-07410","title":"InterAgent: Physics-based Multi-agent Command Execution via Diffusion on Interaction Graphs.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2512.07410"],"source":"https://dblp.org/rec/journals/corr/abs-2512-07410","documentPage":"https://doi.org/10.48550/ARXIV.2512.07410","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2512.07410","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-07410","documentUrl":"https://doi.org/10.48550/ARXIV.2512.07410","arxivId":"2512.07410","arxivUrl":"https://arxiv.org/abs/2512.07410"},{"key":"journals/corr/abs-2512-11237","title":"WildCap: Facial Appearance Capture in the Wild via Hybrid Inverse Rendering.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2512.11237"],"source":"https://dblp.org/rec/journals/corr/abs-2512-11237","documentPage":"https://doi.org/10.48550/ARXIV.2512.11237","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2512.11237","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-11237","documentUrl":"https://doi.org/10.48550/ARXIV.2512.11237","arxivId":"2512.11237","arxivUrl":"https://arxiv.org/abs/2512.11237"}],"excludedFormal":[],"excludedOther":[],"excludedHomonyms":[],"unassignedCandidates":[],"retrievedAt":"2026-10-19","querySource":"https://sparql.dblp.org/","method":"DBLP yearOfPublication=2025; Article + Inproceedings; excludes Informal/CoRR and explicit editorial/correction/erratum/preface; unique DBLP record keys within person.","labName":"多学科人工现实工作室（MARS）","labUrl":null,"labEvidence":"上海科技大学官方2025年讲座简介明确称许岚为 MARS 实验室主任；该校2020年官方报道写明 MARS 中文全名为多学科人工现实工作室。","labSourceUrl":"https://sist.shanghaitech.edu.cn/sist_en/2025/0304/c11304a1107935/page.htm","affiliationZh":"上海科技大学","sourceWarning":false,"knownPreprintMinimum2025":null,"excludedMisattributed":[],"displayNotes":"身份已经个人或机构主页核对。2025 年正式记录 18 条（会议 15、期刊 3），所有作者位置均计入，不表示主导或贡献份额；预印本 18 条单列，不加总。","labDisplayNotes":"上海科技大学 2025 年讲座简介称其为 MARS 实验室主任，学校 2020 年的报道给出中文全称「多学科人工现实工作室」，据此归组。它与武汉大学、清华的两个 MARS 是不同团队。"},{"index":98,"name":"Mengdi Xu","nameZh":"徐梦迪","affiliation":"Tsinghua University","source":"DBLP Knowledge Graph official SPARQL API","profileUrl":"https://dblp.org/pid/87/8693","identifier":"87/8693","identityEvidence":[{"url":"https://www.mengdixu.me/","evidence":"Personal website identifies Tsinghua IIIS assistant professor, formerly CMU PhD and Stanford postdoc, and lists the three retained 2025 titles. The other three formal records in unnumbered DBLP PID are homonyms."},{"url":"https://doi.org/10.1109/LRA.2025.3540391","evidence":"DBLP author signature for Dynamics as Prompts identifies Mengdi Xu with CMU and ORCID 0000-0001-9332-4175; separate homonyms use ORCID 0009-0009-7123-8001 or PLA Army Engineering University."}],"count2025":1,"conference2025":0,"journal2025":1,"preprint2025":2,"status":"verified_manual","notes":"Counts are DBLP indexed coauthored records, not first-author counts, laboratory totals, unique scientific discoveries, or quality assessments. DBLP yearOfPublication=2025; yearOfEvent retained and can differ. Conference workshops are included. Preprints are separate and may overlap formal versions. DBLP unnumbered profile is mixed. Retained records matched the personal publication list; three unrelated formal records were excluded with per-record ORCID/institution evidence.","papers":[{"key":"journals/ral/ZhangLHHLXZ25","title":"Dynamics as Prompts: In-Context Learning for Sim-to-Real System Identifications.","year":2025,"yearOfEvent":null,"venue":"IEEE Robotics Autom. Lett.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1109/LRA.2025.3540391"],"source":"https://dblp.org/rec/journals/ral/ZhangLHHLXZ25","documentPage":"https://doi.org/10.1109/LRA.2025.3540391","type":"Article","doi":"https://doi.org/10.1109/LRA.2025.3540391","authorSignatures":[{"orcid":"https://orcid.org/0000-0001-9332-4175","inst":"https://dblp.org/inst/1/118","instLabel":"Carnegie Mellon University (CMU)"}],"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/ral/ZhangLHHLXZ25","documentUrl":"https://doi.org/10.1109/LRA.2025.3540391"}],"preprints":[{"key":"journals/corr/abs-2505-24871","title":"MoDoMoDo: Multi-Domain Data Mixtures for Multimodal LLM Reinforcement Learning.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2505.24871"],"source":"https://dblp.org/rec/journals/corr/abs-2505-24871","documentPage":"https://doi.org/10.48550/ARXIV.2505.24871","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2505.24871","authorSignatures":[{}],"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-24871","documentUrl":"https://doi.org/10.48550/ARXIV.2505.24871","arxivId":"2505.24871","arxivUrl":"https://arxiv.org/abs/2505.24871"},{"key":"journals/corr/abs-2510-18316","title":"MoMaGen: Generating Demonstrations under Soft and Hard Constraints for Multi-Step Bimanual Mobile Manipulation.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2510.18316"],"source":"https://dblp.org/rec/journals/corr/abs-2510-18316","documentPage":"https://doi.org/10.48550/ARXIV.2510.18316","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2510.18316","authorSignatures":[{}],"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-18316","documentUrl":"https://doi.org/10.48550/ARXIV.2510.18316","arxivId":"2510.18316","arxivUrl":"https://arxiv.org/abs/2510.18316"}],"excludedFormal":[],"excludedOther":[],"excludedHomonyms":[{"key":"journals/eswa/XuZLLS25","title":"Dynamic Meta-Decoupler-inspired Single-Universal Domain Generalization for Intelligent Fault Diagnosis.","year":2025,"yearOfEvent":null,"venue":"Expert Syst. Appl.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1016/J.ESWA.2025.127528"],"source":"https://dblp.org/rec/journals/eswa/XuZLLS25","documentPage":"https://doi.org/10.1016/J.ESWA.2025.127528","type":"Article","doi":"https://doi.org/10.1016/J.ESWA.2025.127528","authorSignatures":[{"orcid":"https://orcid.org/0009-0009-7123-8001"}],"exclusionReason":"Different homonym, supported by DBLP author signature ORCID / institution and personal publication list.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/eswa/XuZLLS25","documentUrl":"https://doi.org/10.1016/J.ESWA.2025.127528"},{"key":"journals/jksucis/TuXMLX25","title":"Indoor environmental quality assessment based on Interval-Valued Intuitionistic Fuzzy Linguistic Term Set TOPSIS method.","year":2025,"yearOfEvent":null,"venue":"J. King Saud Univ. Comput. Inf. Sci.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1007/S44443-025-00188-Y"],"source":"https://dblp.org/rec/journals/jksucis/TuXMLX25","documentPage":"https://doi.org/10.1007/S44443-025-00188-Y","type":"Article","doi":"https://doi.org/10.1007/S44443-025-00188-Y","authorSignatures":[{"inst":"https://dblp.org/inst/12/025","instLabel":"PLA Army Engineering University (PLA UST)"}],"exclusionReason":"Different homonym, supported by DBLP author signature ORCID / institution and personal publication list.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/jksucis/TuXMLX25","documentUrl":"https://doi.org/10.1007/S44443-025-00188-Y"},{"key":"journals/kbs/XuZLLS25","title":"A novel domain-private-suppress meta-recognition network based universal domain generalization for machinery fault diagnosis.","year":2025,"yearOfEvent":null,"venue":"Knowl. Based Syst.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1016/J.KNOSYS.2024.112775"],"source":"https://dblp.org/rec/journals/kbs/XuZLLS25","documentPage":"https://doi.org/10.1016/J.KNOSYS.2024.112775","type":"Article","doi":"https://doi.org/10.1016/J.KNOSYS.2024.112775","authorSignatures":[{"orcid":"https://orcid.org/0009-0009-7123-8001","inst":"https://dblp.org/inst/1/894","instLabel":"Hunan University"}],"exclusionReason":"Different homonym, supported by DBLP author signature ORCID / institution and personal publication list.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/kbs/XuZLLS25","documentUrl":"https://doi.org/10.1016/J.KNOSYS.2024.112775"}],"unassignedCandidates":[],"retrievedAt":"2026-10-19","querySource":"https://sparql.dblp.org/","method":"DBLP yearOfPublication=2025; Article + Inproceedings; excludes Informal/CoRR and explicit editorial/correction/erratum/preface; unique DBLP record keys within person.","labName":null,"labUrl":null,"labEvidence":"本人主页仍只称my lab at Tsinghua IIIS，没有当前组专名；MIT-IBM/SVL/SafeAI均为既往经历。","labSourceUrl":"https://www.mengdixu.me/","affiliationZh":"清华大学","sourceWarning":true,"knownPreprintMinimum2025":null,"excludedMisattributed":[{"key":"journals/eswa/XuZLLS25","title":"Dynamic Meta-Decoupler-inspired Single-Universal Domain Generalization for Intelligent Fault Diagnosis.","year":2025,"yearOfEvent":null,"venue":"Expert Syst. Appl.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1016/J.ESWA.2025.127528"],"source":"https://dblp.org/rec/journals/eswa/XuZLLS25","documentPage":"https://doi.org/10.1016/J.ESWA.2025.127528","type":"Article","doi":"https://doi.org/10.1016/J.ESWA.2025.127528","authorSignatures":[{"orcid":"https://orcid.org/0009-0009-7123-8001"}],"exclusionReason":"Different homonym, supported by DBLP author signature ORCID / institution and personal publication list.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/eswa/XuZLLS25","documentUrl":"https://doi.org/10.1016/J.ESWA.2025.127528"},{"key":"journals/jksucis/TuXMLX25","title":"Indoor environmental quality assessment based on Interval-Valued Intuitionistic Fuzzy Linguistic Term Set TOPSIS method.","year":2025,"yearOfEvent":null,"venue":"J. King Saud Univ. Comput. Inf. Sci.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1007/S44443-025-00188-Y"],"source":"https://dblp.org/rec/journals/jksucis/TuXMLX25","documentPage":"https://doi.org/10.1007/S44443-025-00188-Y","type":"Article","doi":"https://doi.org/10.1007/S44443-025-00188-Y","authorSignatures":[{"inst":"https://dblp.org/inst/12/025","instLabel":"PLA Army Engineering University (PLA UST)"}],"exclusionReason":"Different homonym, supported by DBLP author signature ORCID / institution and personal publication list.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/jksucis/TuXMLX25","documentUrl":"https://doi.org/10.1007/S44443-025-00188-Y"},{"key":"journals/kbs/XuZLLS25","title":"A novel domain-private-suppress meta-recognition network based universal domain generalization for machinery fault diagnosis.","year":2025,"yearOfEvent":null,"venue":"Knowl. Based Syst.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1016/J.KNOSYS.2024.112775"],"source":"https://dblp.org/rec/journals/kbs/XuZLLS25","documentPage":"https://doi.org/10.1016/J.KNOSYS.2024.112775","type":"Article","doi":"https://doi.org/10.1016/J.KNOSYS.2024.112775","authorSignatures":[{"orcid":"https://orcid.org/0009-0009-7123-8001","inst":"https://dblp.org/inst/1/894","instLabel":"Hunan University"}],"exclusionReason":"Different homonym, supported by DBLP author signature ORCID / institution and personal publication list.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/kbs/XuZLLS25","documentUrl":"https://doi.org/10.1016/J.KNOSYS.2024.112775"}],"displayNotes":"DBLP 的无编号档案混入了他人记录。保留的记录与本人发表列表一致，另有 3 条无关的正式记录已按逐条 ORCID 或机构证据排除。计入 1 条期刊论文；预印本 2 条单列，不加总。","labDisplayNotes":"本人主页只称在清华交叉信息研究院的 my lab，未写组名；MIT-IBM、SVL、SafeAI 是既往经历，不作为当前团队。图中以「姓名及合作者」单列。"},{"index":99,"name":"Tianfan Xue","nameZh":"薛天帆","affiliation":"The Chinese University of Hong Kong","source":"DBLP Knowledge Graph official SPARQL API","profileUrl":"https://dblp.org/pid/54/8652","identifier":"54/8652","identityEvidence":[{"url":"https://research.cuhk.edu.hk/en/persons/tianfan-xue/","evidence":"University profile identifies CUHK IE assistant professor and ORCID 0000-0001-5031-6618; same ORCID appears on DBLP 2025 paper signatures."},{"url":"https://dblp.org/rec/conf/cvpr/ChenLDGX25","evidence":"DBLP paper author signature connects this profile to Chinese University of Hong Kong (CUHK)."},{"url":"https://dblp.org/rec/conf/cvpr/ChenWCY0ZGX25","evidence":"DBLP paper author signature connects this profile to Shanghai Artificial Intelligence Laboratory."},{"url":"https://dblp.org/rec/journals/tip/YouGCLZDX25","evidence":"DBLP paper author signature connects this profile to Shenzhen Institutes of Advanced Technology (SIAT)."}],"count2025":24,"conference2025":21,"journal2025":3,"preprint2025":30,"status":"verified","notes":"Counts are DBLP indexed coauthored records, not first-author counts, laboratory totals, unique scientific discoveries, or quality assessments. DBLP yearOfPublication=2025; yearOfEvent retained and can differ. Conference workshops are included. Preprints are separate and may overlap formal versions.","papers":[{"key":"conf/cvpr/ChenLDGX25","title":"A Physics-Informed Blur Learning Framework for Imaging Systems.","year":2025,"yearOfEvent":2025,"venue":"CVPR","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/CVPR52734.2025.01019"],"source":"https://dblp.org/rec/conf/cvpr/ChenLDGX25","documentPage":"https://openaccess.thecvf.com/content/CVPR2025/html/Chen_A_Physics-Informed_Blur_Learning_Framework_for_Imaging_Systems_CVPR_2025_paper.html","type":"Inproceedings","doi":"https://doi.org/10.1109/CVPR52734.2025.01019","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/ChenLDGX25","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Chen_A_Physics-Informed_Blur_Learning_Framework_for_Imaging_Systems_CVPR_2025_paper.html"},{"key":"conf/cvpr/ChenWCY0ZGX25","title":"UltraFusion: Ultra High Dynamic Imaging using Exposure Fusion.","year":2025,"yearOfEvent":2025,"venue":"CVPR","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/CVPR52734.2025.01502"],"source":"https://dblp.org/rec/conf/cvpr/ChenWCY0ZGX25","documentPage":"https://openaccess.thecvf.com/content/CVPR2025/html/Chen_UltraFusion_Ultra_High_Dynamic_Imaging_using_Exposure_Fusion_CVPR_2025_paper.html","type":"Inproceedings","doi":"https://doi.org/10.1109/CVPR52734.2025.01502","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/ChenWCY0ZGX25","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Chen_UltraFusion_Ultra_High_Dynamic_Imaging_using_Exposure_Fusion_CVPR_2025_paper.html"},{"key":"conf/cvpr/LiZLX000GXS25","title":"NVComposer: Boosting Generative Novel View Synthesis with Multiple Sparse and Unposed Images.","year":2025,"yearOfEvent":2025,"venue":"CVPR","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/CVPR52734.2025.00081"],"source":"https://dblp.org/rec/conf/cvpr/LiZLX000GXS25","documentPage":"https://openaccess.thecvf.com/content/CVPR2025/html/Li_NVComposer_Boosting_Generative_Novel_View_Synthesis_with_Multiple_Sparse_and_CVPR_2025_paper.html","type":"Inproceedings","doi":"https://doi.org/10.1109/CVPR52734.2025.00081","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/LiZLX000GXS25","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Li_NVComposer_Boosting_Generative_Novel_View_Synthesis_with_Multiple_Sparse_and_CVPR_2025_paper.html"},{"key":"conf/cvpr/YaoWTLXG25","title":"PolarFree: Polarization-based Reflection-Free Imaging.","year":2025,"yearOfEvent":2025,"venue":"CVPR","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/CVPR52734.2025.01017"],"source":"https://dblp.org/rec/conf/cvpr/YaoWTLXG25","documentPage":"https://openaccess.thecvf.com/content/CVPR2025/html/Yao_PolarFree_Polarization-based_Reflection-Free_Imaging_CVPR_2025_paper.html","type":"Inproceedings","doi":"https://doi.org/10.1109/CVPR52734.2025.01017","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/YaoWTLXG25","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Yao_PolarFree_Polarization-based_Reflection-Free_Imaging_CVPR_2025_paper.html"},{"key":"conf/cvpr/YouCGX025","title":"Teaching Large Language Models to Regress Accurate Image Quality Scores Using Score Distribution.","year":2025,"yearOfEvent":2025,"venue":"CVPR","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/CVPR52734.2025.01350"],"source":"https://dblp.org/rec/conf/cvpr/YouCGX025","documentPage":"https://openaccess.thecvf.com/content/CVPR2025/html/You_Teaching_Large_Language_Models_to_Regress_Accurate_Image_Quality_Scores_CVPR_2025_paper.html","type":"Inproceedings","doi":"https://doi.org/10.1109/CVPR52734.2025.01350","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/YouCGX025","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/You_Teaching_Large_Language_Models_to_Regress_Accurate_Image_Quality_Scores_CVPR_2025_paper.html"},{"key":"conf/eccv/ChenGYZGX24","title":"Event-Based Motion Magnification.","year":2025,"yearOfEvent":2024,"venue":"ECCV (58)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1007/978-3-031-73636-0_25"],"source":"https://dblp.org/rec/conf/eccv/ChenGYZGX24","documentPage":"https://doi.org/10.1007/978-3-031-73636-0_25","type":"Inproceedings","doi":"https://doi.org/10.1007/978-3-031-73636-0_25","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/eccv/ChenGYZGX24","documentUrl":"https://doi.org/10.1007/978-3-031-73636-0_25"},{"key":"conf/eccv/JiangZXG24","title":"AutoDIR: Automatic All-in-One Image Restoration with Latent Diffusion.","year":2025,"yearOfEvent":2024,"venue":"ECCV (40)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1007/978-3-031-73661-2_19"],"source":"https://dblp.org/rec/conf/eccv/JiangZXG24","documentPage":"https://doi.org/10.1007/978-3-031-73661-2_19","type":"Inproceedings","doi":"https://doi.org/10.1007/978-3-031-73661-2_19","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/eccv/JiangZXG24","documentUrl":"https://doi.org/10.1007/978-3-031-73661-2_19"},{"key":"conf/eccv/LiWCZGX24","title":"DualDn: Dual-Domain Denoising via Differentiable ISP.","year":2025,"yearOfEvent":2024,"venue":"ECCV (58)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1007/978-3-031-73636-0_10"],"source":"https://dblp.org/rec/conf/eccv/LiWCZGX24","documentPage":"https://doi.org/10.1007/978-3-031-73636-0_10","type":"Inproceedings","doi":"https://doi.org/10.1007/978-3-031-73636-0_10","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/eccv/LiWCZGX24","documentUrl":"https://doi.org/10.1007/978-3-031-73636-0_10"},{"key":"conf/eccv/MaGCXG24","title":"TimeLens-XL: Real-Time Event-Based Video Frame Interpolation with Large Motion.","year":2025,"yearOfEvent":2024,"venue":"ECCV (84)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1007/978-3-031-72907-2_11"],"source":"https://dblp.org/rec/conf/eccv/MaGCXG24","documentPage":"https://doi.org/10.1007/978-3-031-72907-2_11","type":"Inproceedings","doi":"https://doi.org/10.1007/978-3-031-72907-2_11","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/eccv/MaGCXG24","documentUrl":"https://doi.org/10.1007/978-3-031-72907-2_11"},{"key":"conf/eccv/YouLGYXD24","title":"Depicting Beyond Scores: Advancing Image Quality Assessment Through Multi-modal Language Models.","year":2025,"yearOfEvent":2024,"venue":"ECCV (47)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1007/978-3-031-72970-6_15"],"source":"https://dblp.org/rec/conf/eccv/YouLGYXD24","documentPage":"https://doi.org/10.1007/978-3-031-72970-6_15","type":"Inproceedings","doi":"https://doi.org/10.1007/978-3-031-72970-6_15","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/eccv/YouLGYXD24","documentUrl":"https://doi.org/10.1007/978-3-031-72970-6_15"},{"key":"conf/iccv/ChenWLHPX25","title":"Gleam: Learning Generalizable Exploration Policy for Active Mapping in Complex 3D Indoor Scenes.","year":2025,"yearOfEvent":2025,"venue":"ICCV","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/ICCV51701.2025.00527"],"source":"https://dblp.org/rec/conf/iccv/ChenWLHPX25","documentPage":"https://doi.org/10.1109/ICCV51701.2025.00527","type":"Inproceedings","doi":"https://doi.org/10.1109/ICCV51701.2025.00527","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/ChenWLHPX25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.00527"},{"key":"conf/iccv/DongDCLWWWKGHWXX25","title":"From One to More: Contextual Part Latents for 3D Generation.","year":2025,"yearOfEvent":2025,"venue":"ICCV","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/ICCV51701.2025.00771"],"source":"https://dblp.org/rec/conf/iccv/DongDCLWWWKGHWXX25","documentPage":"https://doi.org/10.1109/ICCV51701.2025.00771","type":"Inproceedings","doi":"https://doi.org/10.1109/ICCV51701.2025.00771","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/DongDCLWWWKGHWXX25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.00771"},{"key":"conf/iccv/GaoDHHWX25","title":"From Gallery to Wrist: Realistic 3D Bracelet Insertion in Videos.","year":2025,"yearOfEvent":2025,"venue":"ICCV","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/ICCV51701.2025.02385"],"source":"https://dblp.org/rec/conf/iccv/GaoDHHWX25","documentPage":"https://doi.org/10.1109/ICCV51701.2025.02385","type":"Inproceedings","doi":"https://doi.org/10.1109/ICCV51701.2025.02385","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/GaoDHHWX25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.02385"},{"key":"conf/iccv/JiangGXCMYL25","title":"Token-Efficient VLM: High-Resolution Image Understanding Via Dynamic Region Proposal.","year":2025,"yearOfEvent":2025,"venue":"ICCV","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/ICCV51701.2025.02238"],"source":"https://dblp.org/rec/conf/iccv/JiangGXCMYL25","documentPage":"https://doi.org/10.1109/ICCV51701.2025.02238","type":"Inproceedings","doi":"https://doi.org/10.1109/ICCV51701.2025.02238","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/JiangGXCMYL25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.02238"},{"key":"conf/iccv/WangLZGLXD25","title":"Multi-Identity Human Image Animation with Structural Video Diffusion.","year":2025,"yearOfEvent":2025,"venue":"ICCV","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/ICCV51701.2025.01110"],"source":"https://dblp.org/rec/conf/iccv/WangLZGLXD25","documentPage":"https://doi.org/10.1109/ICCV51701.2025.01110","type":"Inproceedings","doi":"https://doi.org/10.1109/ICCV51701.2025.01110","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/WangLZGLXD25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.01110"},{"key":"conf/iccv/XuZSXW25","title":"AdaptiveAE: An Adaptive Exposure Strategy for HDR Capturing in Dynamic Scenes.","year":2025,"yearOfEvent":2025,"venue":"ICCV","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/ICCV51701.2025.02335"],"source":"https://dblp.org/rec/conf/iccv/XuZSXW25","documentPage":"https://doi.org/10.1109/ICCV51701.2025.02335","type":"Inproceedings","doi":"https://doi.org/10.1109/ICCV51701.2025.02335","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/XuZSXW25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.02335"},{"key":"conf/iccv/ZhangLLWCXG25","title":"EGVD: Event-Guided Video Diffusion Model for Physically Realistic Large-Motion Frame Interpolation.","year":2025,"yearOfEvent":2025,"venue":"ICCVW","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/ICCVW69036.2025.00414"],"source":"https://dblp.org/rec/conf/iccv/ZhangLLWCXG25","documentPage":"https://doi.org/10.1109/ICCVW69036.2025.00414","type":"Inproceedings","doi":"https://doi.org/10.1109/ICCVW69036.2025.00414","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/ZhangLLWCXG25","documentUrl":"https://doi.org/10.1109/ICCVW69036.2025.00414"},{"key":"conf/nips/WangXCXMLYZXYLC25","title":"Unifying Appearance Codes and Bilateral Grids for Driving Scene Gaussian Splatting.","year":2025,"yearOfEvent":2025,"venue":"NeurIPS","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/nips/WangXCXMLYZXYLC25","documentPage":"http://papers.nips.cc/paper_files/paper/2025/hash/2abe51de91c79956bc5ce3892ed02d43-Abstract-Conference.html","type":"Inproceedings","doi":null,"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/nips/WangXCXMLYZXYLC25","documentUrl":"http://papers.nips.cc/paper_files/paper/2025/hash/2abe51de91c79956bc5ce3892ed02d43-Abstract-Conference.html"},{"key":"conf/siggraph/WangLS0LX000G25","title":"CineMaster: A 3D-Aware and Controllable Framework for Cinematic Text-to-Video Generation.","year":2025,"yearOfEvent":2025,"venue":"SIGGRAPH (Conference Paper Track)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1145/3721238.3730755"],"source":"https://dblp.org/rec/conf/siggraph/WangLS0LX000G25","documentPage":"https://doi.org/10.1145/3721238.3730755","type":"Inproceedings","doi":"https://doi.org/10.1145/3721238.3730755","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/siggraph/WangLS0LX000G25","documentUrl":"https://doi.org/10.1145/3721238.3730755"},{"key":"conf/siggrapha/ChenGYDYGX25","title":"4DSloMo: 4D Reconstruction for High Speed Scene with Asynchronous Capture.","year":2025,"yearOfEvent":2025,"venue":"SIGGRAPH Asia","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1145/3757377.3763908"],"source":"https://dblp.org/rec/conf/siggrapha/ChenGYDYGX25","documentPage":"https://doi.org/10.1145/3757377.3763908","type":"Inproceedings","doi":"https://doi.org/10.1145/3757377.3763908","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/siggrapha/ChenGYDYGX25","documentUrl":"https://doi.org/10.1145/3757377.3763908"},{"key":"conf/siggrapha/LuoSBXXW0ZG25","title":"CamCloneMaster: Enabling Reference-based Camera Control for Video Generation.","year":2025,"yearOfEvent":2025,"venue":"SIGGRAPH Asia","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1145/3757377.3763841"],"source":"https://dblp.org/rec/conf/siggrapha/LuoSBXXW0ZG25","documentPage":"https://doi.org/10.1145/3757377.3763841","type":"Inproceedings","doi":"https://doi.org/10.1145/3757377.3763841","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/siggrapha/LuoSBXXW0ZG25","documentUrl":"https://doi.org/10.1145/3757377.3763841"},{"key":"journals/tip/LiYMYXG25","title":"Uni-ISP: Toward Unifying the Learning of ISPs From Multiple Mobile Cameras.","year":2025,"yearOfEvent":null,"venue":"IEEE Trans. Image Process.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1109/TIP.2025.3607617"],"source":"https://dblp.org/rec/journals/tip/LiYMYXG25","documentPage":"https://doi.org/10.1109/TIP.2025.3607617","type":"Article","doi":"https://doi.org/10.1109/TIP.2025.3607617","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/tip/LiYMYXG25","documentUrl":"https://doi.org/10.1109/TIP.2025.3607617"},{"key":"journals/tip/YouGCLZDX25","title":"Enhancing Descriptive Image Quality Assessment With a Large-Scale Multi-Modal Dataset.","year":2025,"yearOfEvent":null,"venue":"IEEE Trans. Image Process.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1109/TIP.2025.3639998"],"source":"https://dblp.org/rec/journals/tip/YouGCLZDX25","documentPage":"https://doi.org/10.1109/TIP.2025.3639998","type":"Article","doi":"https://doi.org/10.1109/TIP.2025.3639998","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/tip/YouGCLZDX25","documentUrl":"https://doi.org/10.1109/TIP.2025.3639998"},{"key":"journals/tmc/DengXC25","title":"FuseGrasp: Radar-Camera Fusion for Robotic Grasping of Transparent Objects.","year":2025,"yearOfEvent":null,"venue":"IEEE Trans. Mob. Comput.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1109/TMC.2025.3547371"],"source":"https://dblp.org/rec/journals/tmc/DengXC25","documentPage":"https://doi.org/10.1109/TMC.2025.3547371","type":"Article","doi":"https://doi.org/10.1109/TMC.2025.3547371","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/tmc/DengXC25","documentUrl":"https://doi.org/10.1109/TMC.2025.3547371"}],"preprints":[{"key":"journals/corr/abs-2501-11515","title":"UltraFusion: Ultra High Dynamic Imaging using Exposure Fusion.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2501.11515"],"source":"https://dblp.org/rec/journals/corr/abs-2501-11515","documentPage":"https://doi.org/10.48550/ARXIV.2501.11515","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2501.11515","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2501-11515","documentUrl":"https://doi.org/10.48550/ARXIV.2501.11515","arxivId":"2501.11515","arxivUrl":"https://arxiv.org/abs/2501.11515"},{"key":"journals/corr/abs-2501-11561","title":"Teaching Large Language Models to Regress Accurate Image Quality Scores using Score Distribution.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2501.11561"],"source":"https://dblp.org/rec/journals/corr/abs-2501-11561","documentPage":"https://doi.org/10.48550/ARXIV.2501.11561","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2501.11561","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2501-11561","documentUrl":"https://doi.org/10.48550/ARXIV.2501.11561","arxivId":"2501.11561","arxivUrl":"https://arxiv.org/abs/2501.11561"},{"key":"journals/corr/abs-2502-04719","title":"Tolerance-Aware Deep Optics.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2502.04719"],"source":"https://dblp.org/rec/journals/corr/abs-2502-04719","documentPage":"https://doi.org/10.48550/ARXIV.2502.04719","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2502.04719","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2502-04719","documentUrl":"https://doi.org/10.48550/ARXIV.2502.04719","arxivId":"2502.04719","arxivUrl":"https://arxiv.org/abs/2502.04719"},{"key":"journals/corr/abs-2502-08639","title":"CineMaster: A 3D-Aware and Controllable Framework for Cinematic Text-to-Video Generation.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2502.08639"],"source":"https://dblp.org/rec/journals/corr/abs-2502-08639","documentPage":"https://doi.org/10.48550/ARXIV.2502.08639","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2502.08639","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2502-08639","documentUrl":"https://doi.org/10.48550/ARXIV.2502.08639","arxivId":"2502.08639","arxivUrl":"https://arxiv.org/abs/2502.08639"},{"key":"journals/corr/abs-2502-11382","title":"A Physics-Informed Blur Learning Framework for Imaging Systems.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2502.11382"],"source":"https://dblp.org/rec/journals/corr/abs-2502-11382","documentPage":"https://doi.org/10.48550/ARXIV.2502.11382","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2502.11382","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2502-11382","documentUrl":"https://doi.org/10.48550/ARXIV.2502.11382","arxivId":"2502.11382","arxivUrl":"https://arxiv.org/abs/2502.11382"},{"key":"journals/corr/abs-2502-12600","title":"Revisiting the Generalization Problem of Low-level Vision Models Through the Lens of Image Deraining.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2502.12600"],"source":"https://dblp.org/rec/journals/corr/abs-2502-12600","documentPage":"https://doi.org/10.48550/ARXIV.2502.12600","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2502.12600","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2502-12600","documentUrl":"https://doi.org/10.48550/ARXIV.2502.12600","arxivId":"2502.12600","arxivUrl":"https://arxiv.org/abs/2502.12600"},{"key":"journals/corr/abs-2502-20037","title":"FuseGrasp: Radar-Camera Fusion for Robotic Grasping of Transparent Objects.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2502.20037"],"source":"https://dblp.org/rec/journals/corr/abs-2502-20037","documentPage":"https://doi.org/10.48550/ARXIV.2502.20037","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2502.20037","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2502-20037","documentUrl":"https://doi.org/10.48550/ARXIV.2502.20037","arxivId":"2502.20037","arxivUrl":"https://arxiv.org/abs/2502.20037"},{"key":"journals/corr/abs-2503-07300","title":"Goal Conditioned Reinforcement Learning for Photo Finishing Tuning.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2503.07300"],"source":"https://dblp.org/rec/journals/corr/abs-2503-07300","documentPage":"https://doi.org/10.48550/ARXIV.2503.07300","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2503.07300","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-07300","documentUrl":"https://doi.org/10.48550/ARXIV.2503.07300","arxivId":"2503.07300","arxivUrl":"https://arxiv.org/abs/2503.07300"},{"key":"journals/corr/abs-2503-18055","title":"PolarFree: Polarization-based Reflection-free Imaging.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2503.18055"],"source":"https://dblp.org/rec/journals/corr/abs-2503-18055","documentPage":"https://doi.org/10.48550/ARXIV.2503.18055","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2503.18055","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-18055","documentUrl":"https://doi.org/10.48550/ARXIV.2503.18055","arxivId":"2503.18055","arxivUrl":"https://arxiv.org/abs/2503.18055"},{"key":"journals/corr/abs-2503-20268","title":"EGVD: Event-Guided Video Diffusion Model for Physically Realistic Large-Motion Frame Interpolation.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2503.20268"],"source":"https://dblp.org/rec/journals/corr/abs-2503-20268","documentPage":"https://doi.org/10.48550/ARXIV.2503.20268","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2503.20268","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-20268","documentUrl":"https://doi.org/10.48550/ARXIV.2503.20268","arxivId":"2503.20268","arxivUrl":"https://arxiv.org/abs/2503.20268"},{"key":"journals/corr/abs-2504-02402","title":"EvMic: Event-based Non-contact sound recovery from effective spatial-temporal modeling.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2504.02402"],"source":"https://dblp.org/rec/journals/corr/abs-2504-02402","documentPage":"https://doi.org/10.48550/ARXIV.2504.02402","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2504.02402","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2504-02402","documentUrl":"https://doi.org/10.48550/ARXIV.2504.02402","arxivId":"2504.02402","arxivUrl":"https://arxiv.org/abs/2504.02402"},{"key":"journals/corr/abs-2504-04126","title":"Multi-identity Human Image Animation with Structural Video Diffusion.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2504.04126"],"source":"https://dblp.org/rec/journals/corr/abs-2504-04126","documentPage":"https://doi.org/10.48550/ARXIV.2504.04126","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2504.04126","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2504-04126","documentUrl":"https://doi.org/10.48550/ARXIV.2504.04126","arxivId":"2504.04126","arxivUrl":"https://arxiv.org/abs/2504.04126"},{"key":"journals/corr/abs-2504-07667","title":"S2R-HDR: A Large-Scale Rendered Dataset for HDR Fusion.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2504.07667"],"source":"https://dblp.org/rec/journals/corr/abs-2504-07667","documentPage":"https://doi.org/10.48550/ARXIV.2504.07667","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2504.07667","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2504-07667","documentUrl":"https://doi.org/10.48550/ARXIV.2504.07667","arxivId":"2504.07667","arxivUrl":"https://arxiv.org/abs/2504.07667"},{"key":"journals/corr/abs-2505-20294","title":"GLEAM: Learning Generalizable Exploration Policy for Active Mapping in Complex 3D Indoor Scenes.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2505.20294"],"source":"https://dblp.org/rec/journals/corr/abs-2505-20294","documentPage":"https://doi.org/10.48550/ARXIV.2505.20294","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2505.20294","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-20294","documentUrl":"https://doi.org/10.48550/ARXIV.2505.20294","arxivId":"2505.20294","arxivUrl":"https://arxiv.org/abs/2505.20294"},{"key":"journals/corr/abs-2506-03140","title":"CamCloneMaster: Enabling Reference-based Camera Control for Video Generation.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2506.03140"],"source":"https://dblp.org/rec/journals/corr/abs-2506-03140","documentPage":"https://doi.org/10.48550/ARXIV.2506.03140","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2506.03140","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-03140","documentUrl":"https://doi.org/10.48550/ARXIV.2506.03140","arxivId":"2506.03140","arxivUrl":"https://arxiv.org/abs/2506.03140"},{"key":"journals/corr/abs-2506-05280","title":"Unifying Appearance Codes and Bilateral Grids for Driving Scene Gaussian Splatting.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2506.05280"],"source":"https://dblp.org/rec/journals/corr/abs-2506-05280","documentPage":"https://doi.org/10.48550/ARXIV.2506.05280","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2506.05280","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-05280","documentUrl":"https://doi.org/10.48550/ARXIV.2506.05280","arxivId":"2506.05280","arxivUrl":"https://arxiv.org/abs/2506.05280"},{"key":"journals/corr/abs-2506-10082","title":"LoRA-Edit: Controllable First-Frame-Guided Video Editing via Mask-Aware LoRA Fine-Tuning.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2506.10082"],"source":"https://dblp.org/rec/journals/corr/abs-2506-10082","documentPage":"https://doi.org/10.48550/ARXIV.2506.10082","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2506.10082","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-10082","documentUrl":"https://doi.org/10.48550/ARXIV.2506.10082","arxivId":"2506.10082","arxivUrl":"https://arxiv.org/abs/2506.10082"},{"key":"journals/corr/abs-2507-05163","title":"4DSloMo: 4D Reconstruction for High Speed Scene with Asynchronous Capture.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2507.05163"],"source":"https://dblp.org/rec/journals/corr/abs-2507-05163","documentPage":"https://doi.org/10.48550/ARXIV.2507.05163","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2507.05163","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2507-05163","documentUrl":"https://doi.org/10.48550/ARXIV.2507.05163","arxivId":"2507.05163","arxivUrl":"https://arxiv.org/abs/2507.05163"},{"key":"journals/corr/abs-2507-08772","title":"From One to More: Contextual Part Latents for 3D Generation.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2507.08772"],"source":"https://dblp.org/rec/journals/corr/abs-2507-08772","documentPage":"https://doi.org/10.48550/ARXIV.2507.08772","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2507.08772","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2507-08772","documentUrl":"https://doi.org/10.48550/ARXIV.2507.08772","arxivId":"2507.08772","arxivUrl":"https://arxiv.org/abs/2507.08772"},{"key":"journals/corr/abs-2507-20331","title":"From Gallery to Wrist: Realistic 3D Bracelet Insertion in Videos.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2507.20331"],"source":"https://dblp.org/rec/journals/corr/abs-2507-20331","documentPage":"https://doi.org/10.48550/ARXIV.2507.20331","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2507.20331","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2507-20331","documentUrl":"https://doi.org/10.48550/ARXIV.2507.20331","arxivId":"2507.20331","arxivUrl":"https://arxiv.org/abs/2507.20331"},{"key":"journals/corr/abs-2508-10881","title":"ToonComposer: Streamlining Cartoon Production with Generative Post-Keyframing.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2508.10881"],"source":"https://dblp.org/rec/journals/corr/abs-2508-10881","documentPage":"https://doi.org/10.48550/ARXIV.2508.10881","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2508.10881","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-10881","documentUrl":"https://doi.org/10.48550/ARXIV.2508.10881","arxivId":"2508.10881","arxivUrl":"https://arxiv.org/abs/2508.10881"},{"key":"journals/corr/abs-2508-13503","title":"AdaptiveAE: An Adaptive Exposure Strategy for HDR Capturing in Dynamic Scenes.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2508.13503"],"source":"https://dblp.org/rec/journals/corr/abs-2508-13503","documentPage":"https://doi.org/10.48550/ARXIV.2508.13503","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2508.13503","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-13503","documentUrl":"https://doi.org/10.48550/ARXIV.2508.13503","arxivId":"2508.13503","arxivUrl":"https://arxiv.org/abs/2508.13503"},{"key":"journals/corr/abs-2508-13628","title":"DiffIER: Optimizing Diffusion Models with Iterative Error Reduction.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2508.13628"],"source":"https://dblp.org/rec/journals/corr/abs-2508-13628","documentPage":"https://doi.org/10.48550/ARXIV.2508.13628","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2508.13628","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-13628","documentUrl":"https://doi.org/10.48550/ARXIV.2508.13628","arxivId":"2508.13628","arxivUrl":"https://arxiv.org/abs/2508.13628"},{"key":"journals/corr/abs-2510-06308","title":"Lumina-DiMOO: An Omni Diffusion Large Language Model for Multi-Modal Generation and Understanding.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2510.06308"],"source":"https://dblp.org/rec/journals/corr/abs-2510-06308","documentPage":"https://doi.org/10.48550/ARXIV.2510.06308","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2510.06308","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-06308","documentUrl":"https://doi.org/10.48550/ARXIV.2510.06308","arxivId":"2510.06308","arxivUrl":"https://arxiv.org/abs/2510.06308"},{"key":"journals/corr/abs-2510-11369","title":"Reasoning as Representation: Rethinking Visual Reinforcement Learning in Image Quality Assessment.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2510.11369"],"source":"https://dblp.org/rec/journals/corr/abs-2510-11369","documentPage":"https://doi.org/10.48550/ARXIV.2510.11369","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2510.11369","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-11369","documentUrl":"https://doi.org/10.48550/ARXIV.2510.11369","arxivId":"2510.11369","arxivUrl":"https://arxiv.org/abs/2510.11369"},{"key":"journals/corr/abs-2510-12747","title":"FlashVSR: Towards Real-Time Diffusion-Based Streaming Video Super-Resolution.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2510.12747"],"source":"https://dblp.org/rec/journals/corr/abs-2510-12747","documentPage":"https://doi.org/10.48550/ARXIV.2510.12747","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2510.12747","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-12747","documentUrl":"https://doi.org/10.48550/ARXIV.2510.12747","arxivId":"2510.12747","arxivUrl":"https://arxiv.org/abs/2510.12747"},{"key":"journals/corr/abs-2510-22213","title":"DynamicTree: Interactive Real Tree Animation via Sparse Voxel Spectrum.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2510.22213"],"source":"https://dblp.org/rec/journals/corr/abs-2510-22213","documentPage":"https://doi.org/10.48550/ARXIV.2510.22213","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2510.22213","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-22213","documentUrl":"https://doi.org/10.48550/ARXIV.2510.22213","arxivId":"2510.22213","arxivUrl":"https://arxiv.org/abs/2510.22213"},{"key":"journals/corr/abs-2510-26140","title":"FullPart: Generating each 3D Part at Full Resolution.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2510.26140"],"source":"https://dblp.org/rec/journals/corr/abs-2510-26140","documentPage":"https://doi.org/10.48550/ARXIV.2510.26140","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2510.26140","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-26140","documentUrl":"https://doi.org/10.48550/ARXIV.2510.26140","arxivId":"2510.26140","arxivUrl":"https://arxiv.org/abs/2510.26140"},{"key":"journals/corr/abs-2512-00993","title":"PhotoFramer: Multi-modal Image Composition Instruction.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2512.00993"],"source":"https://dblp.org/rec/journals/corr/abs-2512-00993","documentPage":"https://doi.org/10.48550/ARXIV.2512.00993","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2512.00993","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-00993","documentUrl":"https://doi.org/10.48550/ARXIV.2512.00993","arxivId":"2512.00993","arxivUrl":"https://arxiv.org/abs/2512.00993"},{"key":"journals/corr/abs-2512-06802","title":"VDOT: Efficient Unified Video Creation via Optimal Transport Distillation.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2512.06802"],"source":"https://dblp.org/rec/journals/corr/abs-2512-06802","documentPage":"https://doi.org/10.48550/ARXIV.2512.06802","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2512.06802","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-06802","documentUrl":"https://doi.org/10.48550/ARXIV.2512.06802","arxivId":"2512.06802","arxivUrl":"https://arxiv.org/abs/2512.06802"}],"excludedFormal":[],"excludedOther":[],"excludedHomonyms":[],"unassignedCandidates":[],"retrievedAt":"2026-10-19","querySource":"https://sparql.dblp.org/","method":"DBLP yearOfPublication=2025; Article + Inproceedings; excludes Informal/CoRR and explicit editorial/correction/erratum/preface; unique DBLP record keys within person.","labName":"Multimedia Laboratory（MMLab）","labUrl":"https://mmlab.ie.cuhk.edu.hk/","labEvidence":"本人主页的现任职务栏明确列出 MMLab（Multimedia Laboratory）；港中文信息工程系官方资料也将其列为该实验室导师。","labSourceUrl":"https://tianfan.info/index.html","affiliationZh":"香港中文大学","sourceWarning":false,"knownPreprintMinimum2025":null,"excludedMisattributed":[],"displayNotes":"身份已经个人或机构主页核对。2025 年正式记录 24 条（会议 21、期刊 3），所有作者位置均计入，不表示主导或贡献份额；预印本 30 条单列，不加总。","labDisplayNotes":"个人主页的现任职务栏列出港中文 MMLab，信息工程系官方资料也列其为导师。与李鸿升、岳翔宇同组；因李鸿升暂无总数，整组不画柱。该组与 HKU-MMLab、MMLab@NTU 分开计数。"},{"index":100,"name":"Min Yang","nameZh":"杨敏","affiliation":"Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences","source":"DBLP Knowledge Graph official SPARQL API","profileUrl":"https://dblp.org/pid/02/1640-7","identifier":"02/1640-7","identityEvidence":[{"url":"https://dblp.org/pid/02/1640-7","evidence":"DBLP curated profile affiliations: Chinese Academy of Sciences, Shenzhen Institutes of Advanced Technology, China; University of Hong Kong, Hong Kong."},{"url":"https://minyang.ai/","evidence":"Personal SIAT faculty page explicitly lists all three titles that use the conflicting ORCID 0000-0003-3814-2728 in DBLP: Generalizing to Unseen Speakers; A Survey on Multimodal and Multilingual Sexism Detection; Few-Shot Relation Extraction With Automatically Generated Prompts. Thus this ORCID conflict alone is not treated as a homonym."}],"count2025":48,"conference2025":39,"journal2025":9,"preprint2025":34,"status":"verified","notes":"Counts are DBLP indexed coauthored records, not first-author counts, laboratory totals, unique scientific discoveries, or quality assessments. DBLP yearOfPublication=2025; yearOfEvent retained and can differ. Conference workshops are included. Preprints are separate and may overlap formal versions.","papers":[{"key":"conf/aaai/NiKL000025","title":"Training on the Benchmark Is Not All You Need.","year":2025,"yearOfEvent":2025,"venue":"AAAI","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1609/AAAI.V39I23.34678"],"source":"https://dblp.org/rec/conf/aaai/NiKL000025","documentPage":"https://doi.org/10.1609/AAAI.V39I23.34678","type":"Inproceedings","doi":"https://doi.org/10.1609/AAAI.V39I23.34678","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/aaai/NiKL000025","documentUrl":"https://doi.org/10.1609/AAAI.V39I23.34678"},{"key":"conf/aaai/WangDLB0WW025","title":"A New Formula for Sticker Retrieval: Reply with Stickers in Multi-Modal and Multi-Session Conversation.","year":2025,"yearOfEvent":2025,"venue":"AAAI","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1609/AAAI.V39I24.34720"],"source":"https://dblp.org/rec/conf/aaai/WangDLB0WW025","documentPage":"https://doi.org/10.1609/AAAI.V39I24.34720","type":"Inproceedings","doi":"https://doi.org/10.1609/AAAI.V39I24.34720","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/aaai/WangDLB0WW025","documentUrl":"https://doi.org/10.1609/AAAI.V39I24.34720"},{"key":"conf/aaai/ZhangLLXYLWCLQY25","title":"Hierarchical Context Pruning: Optimizing Real-World Code Completion with Repository-Level Pretrained Code LLMs.","year":2025,"yearOfEvent":2025,"venue":"AAAI","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1609/AAAI.V39I24.34782"],"source":"https://dblp.org/rec/conf/aaai/ZhangLLXYLWCLQY25","documentPage":"https://doi.org/10.1609/AAAI.V39I24.34782","type":"Inproceedings","doi":"https://doi.org/10.1609/AAAI.V39I24.34782","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/aaai/ZhangLLXYLWCLQY25","documentUrl":"https://doi.org/10.1609/AAAI.V39I24.34782"},{"key":"conf/acl/0004CLT0LLCLAA025","title":"STORYTELLER: An Enhanced Plot-Planning Framework for Coherent and Cohesive Story Generation.","year":2025,"yearOfEvent":2025,"venue":"ACL (Findings)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.18653/V1/2025.FINDINGS-ACL.1071"],"source":"https://dblp.org/rec/conf/acl/0004CLT0LLCLAA025","documentPage":"https://doi.org/10.18653/V1/2025.FINDINGS-ACL.1071","type":"Inproceedings","doi":"https://doi.org/10.18653/V1/2025.FINDINGS-ACL.1071","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/acl/0004CLT0LLCLAA025","documentUrl":"https://doi.org/10.18653/V1/2025.FINDINGS-ACL.1071"},{"key":"conf/acl/0005FBDHDHLWLQZ25","title":"Can MLLMs Understand the Deep Implication Behind Chinese Images?","year":2025,"yearOfEvent":2025,"venue":"ACL (1)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.18653/V1/2025.ACL-LONG.700"],"source":"https://dblp.org/rec/conf/acl/0005FBDHDHLWLQZ25","documentPage":"https://doi.org/10.18653/V1/2025.ACL-LONG.700","type":"Inproceedings","doi":"https://doi.org/10.18653/V1/2025.ACL-LONG.700","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/acl/0005FBDHDHLWLQZ25","documentUrl":"https://doi.org/10.18653/V1/2025.ACL-LONG.700"},{"key":"conf/acl/ChenFGXLLLQAN025","title":"AgentCourt: Simulating Court with Adversarial Evolvable Lawyer Agents.","year":2025,"yearOfEvent":2025,"venue":"ACL (Findings)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.18653/V1/2025.FINDINGS-ACL.304"],"source":"https://dblp.org/rec/conf/acl/ChenFGXLLLQAN025","documentPage":"https://doi.org/10.18653/V1/2025.FINDINGS-ACL.304","type":"Inproceedings","doi":"https://doi.org/10.18653/V1/2025.FINDINGS-ACL.304","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/acl/ChenFGXLLLQAN025","documentUrl":"https://doi.org/10.18653/V1/2025.FINDINGS-ACL.304"},{"key":"conf/acl/ChenSWWLLWAY25","title":"CLaSp: In-Context Layer Skip for Self-Speculative Decoding.","year":2025,"yearOfEvent":2025,"venue":"ACL (1)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.18653/V1/2025.ACL-LONG.1525"],"source":"https://dblp.org/rec/conf/acl/ChenSWWLLWAY25","documentPage":"https://doi.org/10.18653/V1/2025.ACL-LONG.1525","type":"Inproceedings","doi":"https://doi.org/10.18653/V1/2025.ACL-LONG.1525","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/acl/ChenSWWLLWAY25","documentUrl":"https://doi.org/10.18653/V1/2025.ACL-LONG.1525"},{"key":"conf/acl/LeeZALDHW0LA0LW25","title":"Quantification of Large Language Model Distillation.","year":2025,"yearOfEvent":2025,"venue":"ACL (1)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.18653/V1/2025.ACL-LONG.248"],"source":"https://dblp.org/rec/conf/acl/LeeZALDHW0LA0LW25","documentPage":"https://doi.org/10.18653/V1/2025.ACL-LONG.248","type":"Inproceedings","doi":"https://doi.org/10.18653/V1/2025.ACL-LONG.248","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/acl/LeeZALDHW0LA0LW25","documentUrl":"https://doi.org/10.18653/V1/2025.ACL-LONG.248"},{"key":"conf/acl/LuoZCLLWYLWZGSL25","title":"MMEvol: Empowering Multimodal Large Language Models with Evol-Instruct.","year":2025,"yearOfEvent":2025,"venue":"ACL (Findings)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.18653/V1/2025.FINDINGS-ACL.1009"],"source":"https://dblp.org/rec/conf/acl/LuoZCLLWYLWZGSL25","documentPage":"https://doi.org/10.18653/V1/2025.FINDINGS-ACL.1009","type":"Inproceedings","doi":"https://doi.org/10.18653/V1/2025.FINDINGS-ACL.1009","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/acl/LuoZCLLWYLWZGSL25","documentUrl":"https://doi.org/10.18653/V1/2025.FINDINGS-ACL.1009"},{"key":"conf/acl/SunCABH0W0025","title":"Learning First-Order Logic Rules for Argumentation Mining.","year":2025,"yearOfEvent":2025,"venue":"ACL (1)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.18653/V1/2025.ACL-LONG.691"],"source":"https://dblp.org/rec/conf/acl/SunCABH0W0025","documentPage":"https://doi.org/10.18653/V1/2025.ACL-LONG.691","type":"Inproceedings","doi":"https://doi.org/10.18653/V1/2025.ACL-LONG.691","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/acl/SunCABH0W0025","documentUrl":"https://doi.org/10.18653/V1/2025.ACL-LONG.691"},{"key":"conf/acl/ZhangLLWLZQFYGS25","title":"OmniCharacter: Towards Immersive Role-Playing Agents with Seamless Speech-Language Personality Interaction.","year":2025,"yearOfEvent":2025,"venue":"ACL (1)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.18653/V1/2025.ACL-LONG.1276"],"source":"https://dblp.org/rec/conf/acl/ZhangLLWLZQFYGS25","documentPage":"https://doi.org/10.18653/V1/2025.ACL-LONG.1276","type":"Inproceedings","doi":"https://doi.org/10.18653/V1/2025.ACL-LONG.1276","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/acl/ZhangLLWLZQFYGS25","documentUrl":"https://doi.org/10.18653/V1/2025.ACL-LONG.1276"},{"key":"conf/acl/ZhuZJWFLGZGLWQY25","title":"LIME: Less Is More for MLLM Evaluation.","year":2025,"yearOfEvent":2025,"venue":"ACL (Findings)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.18653/V1/2025.FINDINGS-ACL.474"],"source":"https://dblp.org/rec/conf/acl/ZhuZJWFLGZGLWQY25","documentPage":"https://doi.org/10.18653/V1/2025.FINDINGS-ACL.474","type":"Inproceedings","doi":"https://doi.org/10.18653/V1/2025.FINDINGS-ACL.474","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/acl/ZhuZJWFLGZGLWQY25","documentUrl":"https://doi.org/10.18653/V1/2025.FINDINGS-ACL.474"},{"key":"conf/bibm/ZhaoXTZAAY25","title":"RxSafeBench: Identifying Medication Safety Issues of Large Language Models in Simulated Consultation.","year":2025,"yearOfEvent":2025,"venue":"BIBM","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/BIBM66473.2025.11356353"],"source":"https://dblp.org/rec/conf/bibm/ZhaoXTZAAY25","documentPage":"https://doi.org/10.1109/BIBM66473.2025.11356353","type":"Inproceedings","doi":"https://doi.org/10.1109/BIBM66473.2025.11356353","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/bibm/ZhaoXTZAAY25","documentUrl":"https://doi.org/10.1109/BIBM66473.2025.11356353"},{"key":"conf/coling/ZhaoZTYLD0YL0W25","title":"CPsyExam: A Chinese Benchmark for Evaluating Psychology using Examinations.","year":2025,"yearOfEvent":2025,"venue":"COLING","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/coling/ZhaoZTYLD0YL0W25","documentPage":"https://aclanthology.org/2025.coling-main.745/","type":"Inproceedings","doi":null,"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/coling/ZhaoZTYLD0YL0W25","documentUrl":"https://aclanthology.org/2025.coling-main.745/"},{"key":"conf/emnlp/ChenLFLNAAYL25","title":"Expanding before Inferring: Enhancing Factuality in Large Language Models through Premature Layers Interpolation.","year":2025,"yearOfEvent":2025,"venue":"EMNLP","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.18653/V1/2025.EMNLP-MAIN.645"],"source":"https://dblp.org/rec/conf/emnlp/ChenLFLNAAYL25","documentPage":"https://doi.org/10.18653/V1/2025.EMNLP-MAIN.645","type":"Inproceedings","doi":"https://doi.org/10.18653/V1/2025.EMNLP-MAIN.645","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/emnlp/ChenLFLNAAYL25","documentUrl":"https://doi.org/10.18653/V1/2025.EMNLP-MAIN.645"},{"key":"conf/emnlp/LiYHL25","title":"Forget for Get: A Lightweight Two-phase Gradient Method for Knowledge Editing in Large Language Models.","year":2025,"yearOfEvent":2025,"venue":"EMNLP (Findings)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.18653/V1/2025.FINDINGS-EMNLP.402"],"source":"https://dblp.org/rec/conf/emnlp/LiYHL25","documentPage":"https://doi.org/10.18653/V1/2025.FINDINGS-EMNLP.402","type":"Inproceedings","doi":"https://doi.org/10.18653/V1/2025.FINDINGS-EMNLP.402","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/emnlp/LiYHL25","documentUrl":"https://doi.org/10.18653/V1/2025.FINDINGS-EMNLP.402"},{"key":"conf/emnlp/WangLCYYW25","title":"Exploring the Impact of Personality Traits on LLM Bias and Toxicity.","year":2025,"yearOfEvent":2025,"venue":"EMNLP","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.18653/V1/2025.EMNLP-MAIN.206"],"source":"https://dblp.org/rec/conf/emnlp/WangLCYYW25","documentPage":"https://doi.org/10.18653/V1/2025.EMNLP-MAIN.206","type":"Inproceedings","doi":"https://doi.org/10.18653/V1/2025.EMNLP-MAIN.206","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/emnlp/WangLCYYW25","documentUrl":"https://doi.org/10.18653/V1/2025.EMNLP-MAIN.206"},{"key":"conf/emnlp/XiongSYTWLWZGYKW25","title":"UNComp: Can Matrix Entropy Uncover Sparsity? - A Compressor Design from an Uncertainty-Aware Perspective.","year":2025,"yearOfEvent":2025,"venue":"EMNLP","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.18653/V1/2025.EMNLP-MAIN.209"],"source":"https://dblp.org/rec/conf/emnlp/XiongSYTWLWZGYKW25","documentPage":"https://doi.org/10.18653/V1/2025.EMNLP-MAIN.209","type":"Inproceedings","doi":"https://doi.org/10.18653/V1/2025.EMNLP-MAIN.209","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/emnlp/XiongSYTWLWZGYKW25","documentUrl":"https://doi.org/10.18653/V1/2025.EMNLP-MAIN.209"},{"key":"conf/emnlp/ZhangLWKYW25","title":"HiMATE: A Hierarchical Multi-Agent Framework for Machine Translation Evaluation.","year":2025,"yearOfEvent":2025,"venue":"EMNLP (Findings)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.18653/V1/2025.FINDINGS-EMNLP.593"],"source":"https://dblp.org/rec/conf/emnlp/ZhangLWKYW25","documentPage":"https://doi.org/10.18653/V1/2025.FINDINGS-EMNLP.593","type":"Inproceedings","doi":"https://doi.org/10.18653/V1/2025.FINDINGS-EMNLP.593","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/emnlp/ZhangLWKYW25","documentUrl":"https://doi.org/10.18653/V1/2025.FINDINGS-EMNLP.593"},{"key":"conf/icassp/NiC025","title":"Pre-training, Fine-tuning and Re-ranking: A Three-Stage Framework for Legal Question Answering.","year":2025,"yearOfEvent":2025,"venue":"ICASSP","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/ICASSP49660.2025.10890476"],"source":"https://dblp.org/rec/conf/icassp/NiC025","documentPage":"https://doi.org/10.1109/ICASSP49660.2025.10890476","type":"Inproceedings","doi":"https://doi.org/10.1109/ICASSP49660.2025.10890476","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/icassp/NiC025","documentUrl":"https://doi.org/10.1109/ICASSP49660.2025.10890476"},{"key":"conf/icassp/WangT0B0ZY025","title":"Enhancing Emotion Reasoning for Image Multi-Emotion Prediction.","year":2025,"yearOfEvent":2025,"venue":"ICASSP","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/ICASSP49660.2025.10889829"],"source":"https://dblp.org/rec/conf/icassp/WangT0B0ZY025","documentPage":"https://doi.org/10.1109/ICASSP49660.2025.10889829","type":"Inproceedings","doi":"https://doi.org/10.1109/ICASSP49660.2025.10889829","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/icassp/WangT0B0ZY025","documentUrl":"https://doi.org/10.1109/ICASSP49660.2025.10889829"},{"key":"conf/iccv/ZhangLYYLH25","title":"FedPall: Prototype-Based Adversarial and Collaborative Learning for Federated Learning with Feature Drift.","year":2025,"yearOfEvent":2025,"venue":"ICCV","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/ICCV51701.2025.00298"],"source":"https://dblp.org/rec/conf/iccv/ZhangLYYLH25","documentPage":"https://doi.org/10.1109/ICCV51701.2025.00298","type":"Inproceedings","doi":"https://doi.org/10.1109/ICCV51701.2025.00298","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/ZhangLYYLH25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.00298"},{"key":"conf/iclr/LuoLCHLLZSRXLH025","title":"DEEM: Diffusion models serve as the eyes of large language models for image perception.","year":2025,"yearOfEvent":2025,"venue":"ICLR","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/iclr/LuoLCHLLZSRXLH025","documentPage":"https://openreview.net/forum?id=qtWjSboqfe","type":"Inproceedings","doi":null,"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iclr/LuoLCHLLZSRXLH025","documentUrl":"https://openreview.net/forum?id=qtWjSboqfe"},{"key":"conf/icmcs/XiongTZWCLYYX25","title":"Multimodal Emotion Recognition in Conversations via Graph Structure Learning.","year":2025,"yearOfEvent":2025,"venue":"ICME","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/ICME59968.2025.11209584"],"source":"https://dblp.org/rec/conf/icmcs/XiongTZWCLYYX25","documentPage":"https://doi.org/10.1109/ICME59968.2025.11209584","type":"Inproceedings","doi":"https://doi.org/10.1109/ICME59968.2025.11209584","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/icmcs/XiongTZWCLYYX25","documentUrl":"https://doi.org/10.1109/ICME59968.2025.11209584"},{"key":"conf/icml/0201Y00CZCHL25","title":"Synthesizing Software Engineering Data in a Test-Driven Manner.","year":2025,"yearOfEvent":2025,"venue":"ICML","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/icml/0201Y00CZCHL25","documentPage":"https://proceedings.mlr.press/v267/zhang25cn.html","type":"Inproceedings","doi":null,"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/icml/0201Y00CZCHL25","documentUrl":"https://proceedings.mlr.press/v267/zhang25cn.html"},{"key":"conf/icpr/HuZYLLH24","title":"Learning to Generalize Unseen Domains via Multi-source Meta Learning for Text Classification.","year":2025,"yearOfEvent":2024,"venue":"ICPR (19)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1007/978-3-031-78495-8_26"],"source":"https://dblp.org/rec/conf/icpr/HuZYLLH24","documentPage":"https://doi.org/10.1007/978-3-031-78495-8_26","type":"Inproceedings","doi":"https://doi.org/10.1007/978-3-031-78495-8_26","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/icpr/HuZYLLH24","documentUrl":"https://doi.org/10.1007/978-3-031-78495-8_26"},{"key":"conf/mm/Chen0L000H25","title":"MGHFT: Multi-Granularity Hierarchical Fusion Transformer for Cross-Modal Sticker Emotion Recognition.","year":2025,"yearOfEvent":2025,"venue":"ACM Multimedia","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1145/3746027.3755691"],"source":"https://dblp.org/rec/conf/mm/Chen0L000H25","documentPage":"https://doi.org/10.1145/3746027.3755691","type":"Inproceedings","doi":"https://doi.org/10.1145/3746027.3755691","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/mm/Chen0L000H25","documentUrl":"https://doi.org/10.1145/3746027.3755691"},{"key":"conf/naacl/BaiDLJZLFCZZMWYWLHZLFYN25","title":"COIG-CQIA: Quality is All You Need for Chinese Instruction Fine-tuning.","year":2025,"yearOfEvent":2025,"venue":"NAACL (Findings)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.18653/V1/2025.FINDINGS-NAACL.457"],"source":"https://dblp.org/rec/conf/naacl/BaiDLJZLFCZZMWYWLHZLFYN25","documentPage":"https://doi.org/10.18653/V1/2025.FINDINGS-NAACL.457","type":"Inproceedings","doi":"https://doi.org/10.18653/V1/2025.FINDINGS-NAACL.457","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/naacl/BaiDLJZLFCZZMWYWLHZLFYN25","documentUrl":"https://doi.org/10.18653/V1/2025.FINDINGS-NAACL.457"},{"key":"conf/naacl/YuGTCY25","title":"Unsupervised Speech-text word-level alignment with Dynamic Programming.","year":2025,"yearOfEvent":2025,"venue":"NAACL (Findings)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.18653/V1/2025.FINDINGS-NAACL.124"],"source":"https://dblp.org/rec/conf/naacl/YuGTCY25","documentPage":"https://doi.org/10.18653/V1/2025.FINDINGS-NAACL.124","type":"Inproceedings","doi":"https://doi.org/10.18653/V1/2025.FINDINGS-NAACL.124","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/naacl/YuGTCY25","documentUrl":"https://doi.org/10.18653/V1/2025.FINDINGS-NAACL.124"},{"key":"conf/nips/ChenWYLY25","title":"Stochastic Momentum Methods for Non-smooth Non-Convex Finite-Sum Coupled Compositional Optimization.","year":2025,"yearOfEvent":2025,"venue":"NeurIPS","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/nips/ChenWYLY25","documentPage":"http://papers.nips.cc/paper_files/paper/2025/hash/714467868756e0e0614e99de02ac0032-Abstract-Conference.html","type":"Inproceedings","doi":null,"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/nips/ChenWYLY25","documentUrl":"http://papers.nips.cc/paper_files/paper/2025/hash/714467868756e0e0614e99de02ac0032-Abstract-Conference.html"},{"key":"conf/nips/LuoLZWLLCLZXAHY25","title":"OpenOmni: Advancing Open-Source Omnimodal Large Language Models with Progressive Multimodal Alignment and Real-time Emotional Speech Synthesis.","year":2025,"yearOfEvent":2025,"venue":"NeurIPS","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/nips/LuoLZWLLCLZXAHY25","documentPage":"http://papers.nips.cc/paper_files/paper/2025/hash/e92381dba235a8309f08ce46376189a9-Abstract-Conference.html","type":"Inproceedings","doi":null,"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/nips/LuoLZWLLCLZXAHY25","documentUrl":"http://papers.nips.cc/paper_files/paper/2025/hash/e92381dba235a8309f08ce46376189a9-Abstract-Conference.html"},{"key":"conf/nips/LuoSCLWYX25","title":"VCM: Vision Concept Modeling with Adaptive Vision Token Compression via Instruction Fine-Tuning.","year":2025,"yearOfEvent":2025,"venue":"NeurIPS","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/nips/LuoSCLWYX25","documentPage":"http://papers.nips.cc/paper_files/paper/2025/hash/bea94fe9c5573e74294657f692069d89-Abstract-Conference.html","type":"Inproceedings","doi":null,"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/nips/LuoSCLWYX25","documentUrl":"http://papers.nips.cc/paper_files/paper/2025/hash/bea94fe9c5573e74294657f692069d89-Abstract-Conference.html"},{"key":"conf/nips/YaoYZYWWSSQTH25","title":"R1-ShareVL: Incentivizing Reasoning Capabilities of Multimodal Large Language Models via Share-GRPO.","year":2025,"yearOfEvent":2025,"venue":"NeurIPS","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/nips/YaoYZYWWSSQTH25","documentPage":"http://papers.nips.cc/paper_files/paper/2025/hash/73b75e4eafbdb617822bba262cc81c76-Abstract-Conference.html","type":"Inproceedings","doi":null,"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/nips/YaoYZYWWSSQTH25","documentUrl":"http://papers.nips.cc/paper_files/paper/2025/hash/73b75e4eafbdb617822bba262cc81c76-Abstract-Conference.html"},{"key":"conf/nips/ZhanHYCYW25","title":"Are Large Reasoning Models Good Translation Evaluators? Analysis and Performance Boost.","year":2025,"yearOfEvent":2025,"venue":"NeurIPS","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/nips/ZhanHYCYW25","documentPage":"http://papers.nips.cc/paper_files/paper/2025/hash/5dd3a72bc18a1296ff6070fe4e2be3d0-Abstract-Conference.html","type":"Inproceedings","doi":null,"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/nips/ZhanHYCYW25","documentUrl":"http://papers.nips.cc/paper_files/paper/2025/hash/5dd3a72bc18a1296ff6070fe4e2be3d0-Abstract-Conference.html"},{"key":"conf/sigir/WangBWLYZX25","title":"More Than Just A Conversation: A Multi-agent Reasoning Graph Knowledge Distillation for Conversational Stance Detection.","year":2025,"yearOfEvent":2025,"venue":"SIGIR","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1145/3726302.3730232"],"source":"https://dblp.org/rec/conf/sigir/WangBWLYZX25","documentPage":"https://doi.org/10.1145/3726302.3730232","type":"Inproceedings","doi":"https://doi.org/10.1145/3726302.3730232","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/sigir/WangBWLYZX25","documentUrl":"https://doi.org/10.1145/3726302.3730232"},{"key":"conf/socrob/NiY24","title":"Educational-Psychological Dialogue Robot Based on Multi-agent Collaboration.","year":2025,"yearOfEvent":2024,"venue":"ICSR + InnoBiz","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1007/978-981-96-1151-5_12"],"source":"https://dblp.org/rec/conf/socrob/NiY24","documentPage":"https://doi.org/10.1007/978-981-96-1151-5_12","type":"Inproceedings","doi":"https://doi.org/10.1007/978-981-96-1151-5_12","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/socrob/NiY24","documentUrl":"https://doi.org/10.1007/978-981-96-1151-5_12"},{"key":"conf/socrob/ZhuTYLA24","title":"CollectiveSFT: Scaling Large Language Models for Chinese Medical Benchmark with Collective Instructions in Healthcare.","year":2025,"yearOfEvent":2024,"venue":"ICSR + InnoBiz","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1007/978-981-96-1151-5_6"],"source":"https://dblp.org/rec/conf/socrob/ZhuTYLA24","documentPage":"https://doi.org/10.1007/978-981-96-1151-5_6","type":"Inproceedings","doi":"https://doi.org/10.1007/978-981-96-1151-5_6","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/socrob/ZhuTYLA24","documentUrl":"https://doi.org/10.1007/978-981-96-1151-5_6"},{"key":"conf/www/LianGCZDLYLYHSH25","title":"EGRec: Leveraging Generative Rich Intents for Enhanced Recommendation with Large Language Models.","year":2025,"yearOfEvent":2025,"venue":"WWW (Companion Volume)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1145/3701716.3715570"],"source":"https://dblp.org/rec/conf/www/LianGCZDLYLYHSH25","documentPage":"https://doi.org/10.1145/3701716.3715570","type":"Inproceedings","doi":"https://doi.org/10.1145/3701716.3715570","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/www/LianGCZDLYLYHSH25","documentUrl":"https://doi.org/10.1145/3701716.3715570"},{"key":"conf/www/YangZWTL025","title":"CascadeRCG: Retrieval-Augmented Generation for Enhancing Professionalism and Knowledgeability in Online Mental Health Support.","year":2025,"yearOfEvent":2025,"venue":"WWW (Companion Volume)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1145/3701716.3715466"],"source":"https://dblp.org/rec/conf/www/YangZWTL025","documentPage":"https://doi.org/10.1145/3701716.3715466","type":"Inproceedings","doi":"https://doi.org/10.1145/3701716.3715466","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/www/YangZWTL025","documentUrl":"https://doi.org/10.1145/3701716.3715466"},{"key":"journals/aiethics/WangCDNYZ25","title":"History, development, and principles of large language models: an introductory survey.","year":2025,"yearOfEvent":null,"venue":"AI Ethics","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1007/S43681-024-00583-7"],"source":"https://dblp.org/rec/journals/aiethics/WangCDNYZ25","documentPage":"https://doi.org/10.1007/S43681-024-00583-7","type":"Article","doi":"https://doi.org/10.1007/S43681-024-00583-7","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/aiethics/WangCDNYZ25","documentUrl":"https://doi.org/10.1007/S43681-024-00583-7"},{"key":"journals/cogcom/SunBTLYX25","title":"Multi-view Hierarchical Graph Neural Network for Argumentation Mining.","year":2025,"yearOfEvent":null,"venue":"Cogn. Comput.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1007/S12559-024-10391-0"],"source":"https://dblp.org/rec/journals/cogcom/SunBTLYX25","documentPage":"https://doi.org/10.1007/S12559-024-10391-0","type":"Article","doi":"https://doi.org/10.1007/S12559-024-10391-0","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/cogcom/SunBTLYX25","documentUrl":"https://doi.org/10.1007/S12559-024-10391-0"},{"key":"journals/ijon/WangLBYGX25","title":"GazeGCN: Gaze-aware Graph Convolutional Network for Text Classification.","year":2025,"yearOfEvent":null,"venue":"Neurocomputing","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1016/J.NEUCOM.2024.128680"],"source":"https://dblp.org/rec/journals/ijon/WangLBYGX25","documentPage":"https://doi.org/10.1016/J.NEUCOM.2024.128680","type":"Article","doi":"https://doi.org/10.1016/J.NEUCOM.2024.128680","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/ijon/WangLBYGX25","documentUrl":"https://doi.org/10.1016/J.NEUCOM.2024.128680"},{"key":"journals/ipm/WenWWGLCLYX25","title":"FGVIrony: A Chinese Dataset of Fine-grained Verbal Irony.","year":2025,"yearOfEvent":null,"venue":"Inf. Process. Manag.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1016/J.IPM.2025.104169"],"source":"https://dblp.org/rec/journals/ipm/WenWWGLCLYX25","documentPage":"https://doi.org/10.1016/J.IPM.2025.104169","type":"Article","doi":"https://doi.org/10.1016/J.IPM.2025.104169","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/ipm/WenWWGLCLYX25","documentUrl":"https://doi.org/10.1016/J.IPM.2025.104169"},{"key":"journals/tacl/ChenWYZWLWYCW25","title":"RepreGuard: Detecting LLM-Generated Text by Revealing Hidden Representation Patterns.","year":2025,"yearOfEvent":null,"venue":"Trans. Assoc. Comput. Linguistics","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1162/TACL.A.61"],"source":"https://dblp.org/rec/journals/tacl/ChenWYZWLWYCW25","documentPage":"https://doi.org/10.1162/TACL.A.61","type":"Article","doi":"https://doi.org/10.1162/TACL.A.61","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/tacl/ChenWYZWLWYCW25","documentUrl":"https://doi.org/10.1162/TACL.A.61"},{"key":"journals/tacl/YuLWYHL25","title":"Diverse AI Feedback For Large Language Model Alignment.","year":2025,"yearOfEvent":null,"venue":"Trans. Assoc. Comput. Linguistics","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1162/TACL_A_00746"],"source":"https://dblp.org/rec/journals/tacl/YuLWYHL25","documentPage":"https://doi.org/10.1162/TACL_A_00746","type":"Article","doi":"https://doi.org/10.1162/TACL_A_00746","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/tacl/YuLWYHL25","documentUrl":"https://doi.org/10.1162/TACL_A_00746"},{"key":"journals/taffco/TuJLYYQX25","title":"Generalizing to Unseen Speakers: Multimodal Emotion Recognition in Conversations With Speaker Generalization.","year":2025,"yearOfEvent":null,"venue":"IEEE Trans. Affect. Comput.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1109/TAFFC.2025.3566059"],"source":"https://dblp.org/rec/journals/taffco/TuJLYYQX25","documentPage":"https://doi.org/10.1109/TAFFC.2025.3566059","type":"Article","doi":"https://doi.org/10.1109/TAFFC.2025.3566059","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/taffco/TuJLYYQX25","documentUrl":"https://doi.org/10.1109/TAFFC.2025.3566059"},{"key":"journals/tcss/LuoLWLCZHYX25","title":"A Literature Survey on Multimodal and Multilingual Sexism Detection.","year":2025,"yearOfEvent":null,"venue":"IEEE Trans. Comput. Soc. Syst.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1109/TCSS.2025.3561921"],"source":"https://dblp.org/rec/journals/tcss/LuoLWLCZHYX25","documentPage":"https://doi.org/10.1109/TCSS.2025.3561921","type":"Article","doi":"https://doi.org/10.1109/TCSS.2025.3561921","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/tcss/LuoLWLCZHYX25","documentUrl":"https://doi.org/10.1109/TCSS.2025.3561921"},{"key":"journals/tnn/ZhaoYQX25","title":"Few-Shot Relation Extraction With Automatically Generated Prompts.","year":2025,"yearOfEvent":null,"venue":"IEEE Trans. Neural Networks Learn. Syst.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1109/TNNLS.2024.3365858"],"source":"https://dblp.org/rec/journals/tnn/ZhaoYQX25","documentPage":"https://doi.org/10.1109/TNNLS.2024.3365858","type":"Article","doi":"https://doi.org/10.1109/TNNLS.2024.3365858","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/tnn/ZhaoYQX25","documentUrl":"https://doi.org/10.1109/TNNLS.2024.3365858"}],"preprints":[{"key":"journals/corr/abs-2501-04561","title":"OpenOmni: Large Language Models Pivot Zero-shot Omnimodal Alignment across Language with Real-time Self-Aware Emotional Speech Synthesis.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2501.04561"],"source":"https://dblp.org/rec/journals/corr/abs-2501-04561","documentPage":"https://doi.org/10.48550/ARXIV.2501.04561","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2501.04561","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2501-04561","documentUrl":"https://doi.org/10.48550/ARXIV.2501.04561","arxivId":"2501.04561","arxivUrl":"https://arxiv.org/abs/2501.04561"},{"key":"journals/corr/abs-2501-09426","title":"AutoCBT: An Autonomous Multi-agent Framework for Cognitive Behavioral Therapy in Psychological Counseling.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2501.09426"],"source":"https://dblp.org/rec/journals/corr/abs-2501-09426","documentPage":"https://doi.org/10.48550/ARXIV.2501.09426","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2501.09426","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2501-09426","documentUrl":"https://doi.org/10.48550/ARXIV.2501.09426","arxivId":"2501.09426","arxivUrl":"https://arxiv.org/abs/2501.09426"},{"key":"journals/corr/abs-2501-12619","title":"Distillation Quantification for Large Language Models.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2501.12619"],"source":"https://dblp.org/rec/journals/corr/abs-2501-12619","documentPage":"https://doi.org/10.48550/ARXIV.2501.12619","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2501.12619","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2501-12619","documentUrl":"https://doi.org/10.48550/ARXIV.2501.12619","arxivId":"2501.12619","arxivUrl":"https://arxiv.org/abs/2501.12619"},{"key":"journals/corr/abs-2501-16727","title":"xJailbreak: Representation Space Guided Reinforcement Learning for Interpretable LLM Jailbreaking.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2501.16727"],"source":"https://dblp.org/rec/journals/corr/abs-2501-16727","documentPage":"https://doi.org/10.48550/ARXIV.2501.16727","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2501.16727","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2501-16727","documentUrl":"https://doi.org/10.48550/ARXIV.2501.16727","arxivId":"2501.16727","arxivUrl":"https://arxiv.org/abs/2501.16727"},{"key":"journals/corr/abs-2502-12566","title":"Exploring the Impact of Personality Traits on LLM Bias and Toxicity.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2502.12566"],"source":"https://dblp.org/rec/journals/corr/abs-2502-12566","documentPage":"https://doi.org/10.48550/ARXIV.2502.12566","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2502.12566","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2502-12566","documentUrl":"https://doi.org/10.48550/ARXIV.2502.12566","arxivId":"2502.12566","arxivUrl":"https://arxiv.org/abs/2502.12566"},{"key":"journals/corr/abs-2504-15524","title":"IPBench: Benchmarking the Knowledge of Large Language Models in Intellectual Property.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2504.15524"],"source":"https://dblp.org/rec/journals/corr/abs-2504-15524","documentPage":"https://doi.org/10.48550/ARXIV.2504.15524","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2504.15524","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2504-15524","documentUrl":"https://doi.org/10.48550/ARXIV.2504.15524","arxivId":"2504.15524","arxivUrl":"https://arxiv.org/abs/2504.15524"},{"key":"journals/corr/abs-2504-19627","title":"VCM: Vision Concept Modeling Based on Implicit Contrastive Learning with Vision-Language Instruction Fine-Tuning.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2504.19627"],"source":"https://dblp.org/rec/journals/corr/abs-2504-19627","documentPage":"https://doi.org/10.48550/ARXIV.2504.19627","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2504.19627","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2504-19627","documentUrl":"https://doi.org/10.48550/ARXIV.2504.19627","arxivId":"2504.19627","arxivUrl":"https://arxiv.org/abs/2504.19627"},{"key":"journals/corr/abs-2505-01696","title":"Interpretable graph-based models on multimodal biomedical data integration: A technical review and benchmarking.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2505.01696"],"source":"https://dblp.org/rec/journals/corr/abs-2505-01696","documentPage":"https://doi.org/10.48550/ARXIV.2505.01696","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2505.01696","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-01696","documentUrl":"https://doi.org/10.48550/ARXIV.2505.01696","arxivId":"2505.01696","arxivUrl":"https://arxiv.org/abs/2505.01696"},{"key":"journals/corr/abs-2505-16281","title":"HiMATE: A Hierarchical Multi-Agent Framework for Machine Translation Evaluation.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2505.16281"],"source":"https://dblp.org/rec/journals/corr/abs-2505-16281","documentPage":"https://doi.org/10.48550/ARXIV.2505.16281","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2505.16281","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-16281","documentUrl":"https://doi.org/10.48550/ARXIV.2505.16281","arxivId":"2505.16281","arxivUrl":"https://arxiv.org/abs/2505.16281"},{"key":"journals/corr/abs-2505-16673","title":"R1-ShareVL: Incentivizing Reasoning Capability of Multimodal Large Language Models via Share-GRPO.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2505.16673"],"source":"https://dblp.org/rec/journals/corr/abs-2505-16673","documentPage":"https://doi.org/10.48550/ARXIV.2505.16673","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2505.16673","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-16673","documentUrl":"https://doi.org/10.48550/ARXIV.2505.16673","arxivId":"2505.16673","arxivUrl":"https://arxiv.org/abs/2505.16673"},{"key":"journals/corr/abs-2505-17654","title":"EVADE: Multimodal Benchmark for Evasive Content Detection in E-Commerce Applications.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2505.17654"],"source":"https://dblp.org/rec/journals/corr/abs-2505-17654","documentPage":"https://doi.org/10.48550/ARXIV.2505.17654","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2505.17654","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-17654","documentUrl":"https://doi.org/10.48550/ARXIV.2505.17654","arxivId":"2505.17654","arxivUrl":"https://arxiv.org/abs/2505.17654"},{"key":"journals/corr/abs-2505-20277","title":"OmniCharacter: Towards Immersive Role-Playing Agents with Seamless Speech-Language Personality Interaction.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2505.20277"],"source":"https://dblp.org/rec/journals/corr/abs-2505-20277","documentPage":"https://doi.org/10.48550/ARXIV.2505.20277","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2505.20277","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-20277","documentUrl":"https://doi.org/10.48550/ARXIV.2505.20277","arxivId":"2505.20277","arxivUrl":"https://arxiv.org/abs/2505.20277"},{"key":"journals/corr/abs-2505-23923","title":"ChARM: Character-based Act-adaptive Reward Modeling for Advanced Role-Playing Language Agents.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2505.23923"],"source":"https://dblp.org/rec/journals/corr/abs-2505-23923","documentPage":"https://doi.org/10.48550/ARXIV.2505.23923","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2505.23923","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-23923","documentUrl":"https://doi.org/10.48550/ARXIV.2505.23923","arxivId":"2505.23923","arxivUrl":"https://arxiv.org/abs/2505.23923"},{"key":"journals/corr/abs-2505-24196","title":"CLaSp: In-Context Layer Skip for Self-Speculative Decoding.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2505.24196"],"source":"https://dblp.org/rec/journals/corr/abs-2505-24196","documentPage":"https://doi.org/10.48550/ARXIV.2505.24196","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2505.24196","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-24196","documentUrl":"https://doi.org/10.48550/ARXIV.2505.24196","arxivId":"2505.24196","arxivUrl":"https://arxiv.org/abs/2505.24196"},{"key":"journals/corr/abs-2506-02347","title":"STORYTELLER: An Enhanced Plot-Planning Framework for Coherent and Cohesive Story Generation.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2506.02347"],"source":"https://dblp.org/rec/journals/corr/abs-2506-02347","documentPage":"https://doi.org/10.48550/ARXIV.2506.02347","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2506.02347","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-02347","documentUrl":"https://doi.org/10.48550/ARXIV.2506.02347","arxivId":"2506.02347","arxivUrl":"https://arxiv.org/abs/2506.02347"},{"key":"journals/corr/abs-2506-02504","title":"Stochastic Momentum Methods for Non-smooth Non-Convex Finite-Sum Coupled Compositional Optimization.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2506.02504"],"source":"https://dblp.org/rec/journals/corr/abs-2506-02504","documentPage":"https://doi.org/10.48550/ARXIV.2506.02504","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2506.02504","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-02504","documentUrl":"https://doi.org/10.48550/ARXIV.2506.02504","arxivId":"2506.02504","arxivUrl":"https://arxiv.org/abs/2506.02504"},{"key":"journals/corr/abs-2506-02973","title":"Expanding before Inferring: Enhancing Factuality in Large Language Models through Premature Layers Interpolation.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2506.02973"],"source":"https://dblp.org/rec/journals/corr/abs-2506-02973","documentPage":"https://doi.org/10.48550/ARXIV.2506.02973","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2506.02973","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-02973","documentUrl":"https://doi.org/10.48550/ARXIV.2506.02973","arxivId":"2506.02973","arxivUrl":"https://arxiv.org/abs/2506.02973"},{"key":"journals/corr/abs-2506-07691","title":"Training Superior Sparse Autoencoders for Instruct Models.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2506.07691"],"source":"https://dblp.org/rec/journals/corr/abs-2506-07691","documentPage":"https://doi.org/10.48550/ARXIV.2506.07691","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2506.07691","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-07691","documentUrl":"https://doi.org/10.48550/ARXIV.2506.07691","arxivId":"2506.07691","arxivUrl":"https://arxiv.org/abs/2506.07691"},{"key":"journals/corr/abs-2506-09003","title":"SWE-Flow: Synthesizing Software Engineering Data in a Test-Driven Manner.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2506.09003"],"source":"https://dblp.org/rec/journals/corr/abs-2506-09003","documentPage":"https://doi.org/10.48550/ARXIV.2506.09003","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2506.09003","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-09003","documentUrl":"https://doi.org/10.48550/ARXIV.2506.09003","arxivId":"2506.09003","arxivUrl":"https://arxiv.org/abs/2506.09003"},{"key":"journals/corr/abs-2507-04781","title":"FedPall: Prototype-based Adversarial and Collaborative Learning for Federated Learning with Feature Drift.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2507.04781"],"source":"https://dblp.org/rec/journals/corr/abs-2507-04781","documentPage":"https://doi.org/10.48550/ARXIV.2507.04781","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2507.04781","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2507-04781","documentUrl":"https://doi.org/10.48550/ARXIV.2507.04781","arxivId":"2507.04781","arxivUrl":"https://arxiv.org/abs/2507.04781"},{"key":"journals/corr/abs-2507-18929","title":"MGHFT: Multi-Granularity Hierarchical Fusion Transformer for Cross-Modal Sticker Emotion Recognition.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2507.18929"],"source":"https://dblp.org/rec/journals/corr/abs-2507-18929","documentPage":"https://doi.org/10.48550/ARXIV.2507.18929","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2507.18929","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2507-18929","documentUrl":"https://doi.org/10.48550/ARXIV.2507.18929","arxivId":"2507.18929","arxivUrl":"https://arxiv.org/abs/2507.18929"},{"key":"journals/corr/abs-2508-13152","title":"RepreGuard: Detecting LLM-Generated Text by Revealing Hidden Representation Patterns.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2508.13152"],"source":"https://dblp.org/rec/journals/corr/abs-2508-13152","documentPage":"https://doi.org/10.48550/ARXIV.2508.13152","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2508.13152","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-13152","documentUrl":"https://doi.org/10.48550/ARXIV.2508.13152","arxivId":"2508.13152","arxivUrl":"https://arxiv.org/abs/2508.13152"},{"key":"journals/corr/abs-2508-15361","title":"A Survey on Large Language Model Benchmarks.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2508.15361"],"source":"https://dblp.org/rec/journals/corr/abs-2508-15361","documentPage":"https://doi.org/10.48550/ARXIV.2508.15361","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2508.15361","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-15361","documentUrl":"https://doi.org/10.48550/ARXIV.2508.15361","arxivId":"2508.15361","arxivUrl":"https://arxiv.org/abs/2508.15361"},{"key":"journals/corr/abs-2509-02522","title":"Implicit Actor Critic Coupling via a Supervised Learning Framework for RLVR.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2509.02522"],"source":"https://dblp.org/rec/journals/corr/abs-2509-02522","documentPage":"https://doi.org/10.48550/ARXIV.2509.02522","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2509.02522","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-02522","documentUrl":"https://doi.org/10.48550/ARXIV.2509.02522","arxivId":"2509.02522","arxivUrl":"https://arxiv.org/abs/2509.02522"},{"key":"journals/corr/abs-2510-05134","title":"Structuring Reasoning for Complex Rules Beyond Flat Representations.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2510.05134"],"source":"https://dblp.org/rec/journals/corr/abs-2510-05134","documentPage":"https://doi.org/10.48550/ARXIV.2510.05134","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2510.05134","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-05134","documentUrl":"https://doi.org/10.48550/ARXIV.2510.05134","arxivId":"2510.05134","arxivUrl":"https://arxiv.org/abs/2510.05134"},{"key":"journals/corr/abs-2510-05969","title":"Probing the Difficulty Perception Mechanism of Large Language Models.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2510.05969"],"source":"https://dblp.org/rec/journals/corr/abs-2510-05969","documentPage":"https://doi.org/10.48550/ARXIV.2510.05969","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2510.05969","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-05969","documentUrl":"https://doi.org/10.48550/ARXIV.2510.05969","arxivId":"2510.05969","arxivUrl":"https://arxiv.org/abs/2510.05969"},{"key":"journals/corr/abs-2510-13721","title":"NExT-OMNI: Towards Any-to-Any Omnimodal Foundation Models with Discrete Flow Matching.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2510.13721"],"source":"https://dblp.org/rec/journals/corr/abs-2510-13721","documentPage":"https://doi.org/10.48550/ARXIV.2510.13721","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2510.13721","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-13721","documentUrl":"https://doi.org/10.48550/ARXIV.2510.13721","arxivId":"2510.13721","arxivUrl":"https://arxiv.org/abs/2510.13721"},{"key":"journals/corr/abs-2510-14000","title":"A Diffusion-Refined Planner with Reinforcement Learning Priors for Confined-Space Parking.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2510.14000"],"source":"https://dblp.org/rec/journals/corr/abs-2510-14000","documentPage":"https://doi.org/10.48550/ARXIV.2510.14000","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2510.14000","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-14000","documentUrl":"https://doi.org/10.48550/ARXIV.2510.14000","arxivId":"2510.14000","arxivUrl":"https://arxiv.org/abs/2510.14000"},{"key":"journals/corr/abs-2510-20780","title":"Are Large Reasoning Models Good Translation Evaluators? Analysis and Performance Boost.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2510.20780"],"source":"https://dblp.org/rec/journals/corr/abs-2510-20780","documentPage":"https://doi.org/10.48550/ARXIV.2510.20780","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2510.20780","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-20780","documentUrl":"https://doi.org/10.48550/ARXIV.2510.20780","arxivId":"2510.20780","arxivUrl":"https://arxiv.org/abs/2510.20780"},{"key":"journals/corr/abs-2510-26167","title":"One Model to Critique Them All: Rewarding Agentic Tool-Use via Efficient Reasoning.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2510.26167"],"source":"https://dblp.org/rec/journals/corr/abs-2510-26167","documentPage":"https://doi.org/10.48550/ARXIV.2510.26167","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2510.26167","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-26167","documentUrl":"https://doi.org/10.48550/ARXIV.2510.26167","arxivId":"2510.26167","arxivUrl":"https://arxiv.org/abs/2510.26167"},{"key":"journals/corr/abs-2511-04328","title":"RxSafeBench: Identifying Medication Safety Issues of Large Language Models in Simulated Consultation.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2511.04328"],"source":"https://dblp.org/rec/journals/corr/abs-2511-04328","documentPage":"https://doi.org/10.48550/ARXIV.2511.04328","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2511.04328","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2511-04328","documentUrl":"https://doi.org/10.48550/ARXIV.2511.04328","arxivId":"2511.04328","arxivUrl":"https://arxiv.org/abs/2511.04328"},{"key":"journals/corr/abs-2511-08317","title":"Automatic Paper Reviewing with Heterogeneous Graph Reasoning over LLM-Simulated Reviewer-Author Debates.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2511.08317"],"source":"https://dblp.org/rec/journals/corr/abs-2511-08317","documentPage":"https://doi.org/10.48550/ARXIV.2511.08317","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2511.08317","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2511-08317","documentUrl":"https://doi.org/10.48550/ARXIV.2511.08317","arxivId":"2511.08317","arxivUrl":"https://arxiv.org/abs/2511.08317"},{"key":"journals/corr/abs-2511-09146","title":"DoPE: Denoising Rotary Position Embedding.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2511.09146"],"source":"https://dblp.org/rec/journals/corr/abs-2511-09146","documentPage":"https://doi.org/10.48550/ARXIV.2511.09146","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2511.09146","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2511-09146","documentUrl":"https://doi.org/10.48550/ARXIV.2511.09146","arxivId":"2511.09146","arxivUrl":"https://arxiv.org/abs/2511.09146"},{"key":"journals/corr/abs-2511-22619","title":"AI Deception: Risks, Dynamics, and Controls.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2511.22619"],"source":"https://dblp.org/rec/journals/corr/abs-2511-22619","documentPage":"https://doi.org/10.48550/ARXIV.2511.22619","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2511.22619","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2511-22619","documentUrl":"https://doi.org/10.48550/ARXIV.2511.22619","arxivId":"2511.22619","arxivUrl":"https://arxiv.org/abs/2511.22619"}],"excludedFormal":[],"excludedOther":[],"excludedHomonyms":[],"unassignedCandidates":[],"retrievedAt":"2026-10-19","querySource":"https://sparql.dblp.org/","method":"DBLP yearOfPublication=2025; Article + Inproceedings; excludes Informal/CoRR and explicit editorial/correction/erratum/preface; unique DBLP record keys within person.","sourceWarning":true,"labName":"Shenzhen Key Laboratory for High-Performance Data Mining","labUrl":null,"labEvidence":"此前读取的本人主页明确称其任该深圳市重点实验室主任；没有据此编造独立实验室网址。","labSourceUrl":"https://minyang.ai/","affiliationZh":"中科院深圳先进技术研究院","knownPreprintMinimum2025":null,"excludedMisattributed":[],"displayNotes":"身份已经本人主页核对。DBLP 档案及逐篇署名中出现两个 ORCID（0000-0001-7345-5071 与 0000-0003-3814-2728），因此标有来源警告。涉及第二个 ORCID 的 3 篇 2025 年正式记录（TAFFC、TCSS、TNNLS 各一篇）都已在本人论文列表中逐篇找到，予以保留；其中 TNNLS 一篇本人列为 2024 年，本页统一采用 DBLP 的出版年份。警告提示的是元数据冲突，不表示混入了同名作者的论文；冲突的成因未知，不作推断。计入 48 条（会议 39、期刊 9）；预印本 34 条单列，不加总。","labDisplayNotes":"此前读取的本人主页称其任深圳市高性能数据挖掘重点实验室主任。这是市级重点实验室，未附独立网址；分组只含本人的记录。"},{"index":101,"name":"Yao Yao","nameZh":"姚遥","affiliation":"Nanjing University","source":"DBLP Knowledge Graph official SPARQL API","profileUrl":"https://dblp.org/pid/07/4410-8","identifier":"07/4410-8","identityEvidence":[{"url":"https://dblp.org/pid/07/4410-8","evidence":"DBLP curated profile affiliations: Hong Kong University of Science and Technology, Hong Kong."},{"url":"https://is.nju.edu.cn/yy_en/main.htm","evidence":"School profile identifies 姚遥, Nanjing, previously Apple / Altizure and HKUST PhD under Long Quan; MVSNet / BlendedMVS / NeILF research matches DBLP Yao Yao 0008, HKUST."},{"url":"https://yoyo000.github.io/publications.html","evidence":"Personal publication list confirms retained titles. Three title variants were manually reconciled: 4D Diffusion (Reference Guided Motion Alignment), Relightable 3D Gaussian (Real-time), and Head360 (360-degree notation)."},{"url":"https://github.com/Zoeyyao27","evidence":"Different Yao Yao is an SJTU NLP doctoral student and maintains the Igniting Language Intelligence survey repository."},{"url":"https://aclanthology.org/2025.acl-long.1087.pdf","evidence":"Caution for the Environment assigns Yao Yao to SJTU and email yaoyao27@sjtu.edu.cn, not NJU faculty 姚遥."},{"url":"https://aclanthology.org/2025.acl-long.1095.pdf","evidence":"LESA assigns Yao Yao to SJTU; excluded as the NLP homonym."},{"url":"https://aclanthology.org/2025.emnlp-main.494.pdf","evidence":"XQuant assigns Yao Yao to SJTU and email yaoyao27@sjtu.edu.cn; excluded as the NLP homonym."}],"count2025":14,"conference2025":14,"journal2025":0,"preprint2025":null,"status":"verified_manual","notes":"Counts are DBLP indexed coauthored records, not first-author counts, laboratory totals, unique scientific discoveries, or quality assessments. DBLP yearOfPublication=2025; yearOfEvent retained and can differ. Conference workshops are included. Preprints are separate and may overlap formal versions. Formal 2025 records were reviewed individually after detected DBLP homonyms were excluded. The preprint pool is still incomplete and its total is withheld independently.","papers":[{"key":"conf/cvpr/Gao0ZZ0Z0SQ25","title":"Mani-GS: Gaussian Splatting Manipulation with Triangular Mesh.","year":2025,"yearOfEvent":2025,"venue":"CVPR","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/CVPR52734.2025.01993"],"source":"https://dblp.org/rec/conf/cvpr/Gao0ZZ0Z0SQ25","documentPage":"https://openaccess.thecvf.com/content/CVPR2025/html/Gao_Mani-GS_Gaussian_Splatting_Manipulation_with_Triangular_Mesh_CVPR_2025_paper.html","type":"Inproceedings","doi":"https://doi.org/10.1109/CVPR52734.2025.01993","authorSignatures":[{"inst":"https://dblp.org/inst/9/165","instLabel":"Nanjing University (NJU)"}],"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/Gao0ZZ0Z0SQ25","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Gao_Mani-GS_Gaussian_Splatting_Manipulation_with_Triangular_Mesh_CVPR_2025_paper.html"},{"key":"conf/cvpr/LuZFNTQC0025","title":"Matrix3D: Large Photogrammetry Model All-in-One.","year":2025,"yearOfEvent":2025,"venue":"CVPR","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/CVPR52734.2025.01051"],"source":"https://dblp.org/rec/conf/cvpr/LuZFNTQC0025","documentPage":"https://openaccess.thecvf.com/content/CVPR2025/html/Lu_Matrix3D_Large_Photogrammetry_Model_All-in-One_CVPR_2025_paper.html","type":"Inproceedings","doi":"https://doi.org/10.1109/CVPR52734.2025.01051","authorSignatures":[{"inst":"https://dblp.org/inst/9/165","instLabel":"Nanjing University (NJU)"}],"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/LuZFNTQC0025","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Lu_Matrix3D_Large_Photogrammetry_Model_All-in-One_CVPR_2025_paper.html"},{"key":"conf/cvpr/ZhangW0GH0C025","title":"FATE: Full-head Gaussian Avatar with Textural Editing from Monocular Video.","year":2025,"yearOfEvent":2025,"venue":"CVPR","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/CVPR52734.2025.00520"],"source":"https://dblp.org/rec/conf/cvpr/ZhangW0GH0C025","documentPage":"https://openaccess.thecvf.com/content/CVPR2025/html/Zhang_FATE_Full-head_Gaussian_Avatar_with_Textural_Editing_from_Monocular_Video_CVPR_2025_paper.html","type":"Inproceedings","doi":"https://doi.org/10.1109/CVPR52734.2025.00520","authorSignatures":[{"inst":"https://dblp.org/inst/9/165","instLabel":"Nanjing University (NJU)"}],"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/ZhangW0GH0C025","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Zhang_FATE_Full-head_Gaussian_Avatar_with_Textural_Editing_from_Monocular_Video_CVPR_2025_paper.html"},{"key":"conf/eccv/HeJGLDHYZMXWZCZ24","title":"EmoTalk3D: High-Fidelity Free-View Synthesis of Emotional 3D Talking Head.","year":2025,"yearOfEvent":2024,"venue":"ECCV (57)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1007/978-3-031-72998-0_4"],"source":"https://dblp.org/rec/conf/eccv/HeJGLDHYZMXWZCZ24","documentPage":"https://doi.org/10.1007/978-3-031-72998-0_4","type":"Inproceedings","doi":"https://doi.org/10.1007/978-3-031-72998-0_4","authorSignatures":[{"inst":"https://dblp.org/inst/9/165","instLabel":"Nanjing University (NJU)"}],"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/eccv/HeJGLDHYZMXWZCZ24","documentUrl":"https://doi.org/10.1007/978-3-031-72998-0_4"},{"key":"conf/eccv/ZengJZLLZHCY24","title":"STAG4D: Spatial-Temporal Anchored Generative 4D Gaussians.","year":2025,"yearOfEvent":2024,"venue":"ECCV (36)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1007/978-3-031-72764-1_10"],"source":"https://dblp.org/rec/conf/eccv/ZengJZLLZHCY24","documentPage":"https://doi.org/10.1007/978-3-031-72764-1_10","type":"Inproceedings","doi":"https://doi.org/10.1007/978-3-031-72764-1_10","authorSignatures":[{"inst":"https://dblp.org/inst/9/165","instLabel":"Nanjing University (NJU)"}],"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/eccv/ZengJZLLZHCY24","documentUrl":"https://doi.org/10.1007/978-3-031-72764-1_10"},{"key":"conf/eccv/ZhuCDDXCYZZ24","title":"Champ: Controllable and Consistent Human Image Animation with 3D Parametric Guidance.","year":2025,"yearOfEvent":2024,"venue":"ECCV (55)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1007/978-3-031-73001-6_9"],"source":"https://dblp.org/rec/conf/eccv/ZhuCDDXCYZZ24","documentPage":"https://doi.org/10.1007/978-3-031-73001-6_9","type":"Inproceedings","doi":"https://doi.org/10.1007/978-3-031-73001-6_9","authorSignatures":[{"inst":"https://dblp.org/inst/9/165","instLabel":"Nanjing University (NJU)"}],"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/eccv/ZhuCDDXCYZZ24","documentUrl":"https://doi.org/10.1007/978-3-031-73001-6_9"},{"key":"conf/iclr/0003LYZSCZZ025","title":"Hallo2: Long-Duration and High-Resolution Audio-Driven Portrait Image Animation.","year":2025,"yearOfEvent":2025,"venue":"ICLR","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/iclr/0003LYZSCZZ025","documentPage":"https://openreview.net/forum?id=rkzabmWl5k","type":"Inproceedings","doi":null,"authorSignatures":[{}],"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iclr/0003LYZSCZZ025","documentUrl":"https://openreview.net/forum?id=rkzabmWl5k"},{"key":"conf/iclr/ChenLL00C025","title":"Flow Distillation Sampling: Regularizing 3D Gaussians with Pre-trained Matching Priors.","year":2025,"yearOfEvent":2025,"venue":"ICLR","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/iclr/ChenLL00C025","documentPage":"https://openreview.net/forum?id=BzsjHiBfLk","type":"Inproceedings","doi":null,"authorSignatures":[{}],"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iclr/ChenLL00C025","documentUrl":"https://openreview.net/forum?id=BzsjHiBfLk"},{"key":"conf/nips/WuLZZYBQZCTY25","title":"Direct3D-S2: Gigascale 3D Generation Made Easy with Spatial Sparse Attention.","year":2025,"yearOfEvent":2025,"venue":"NeurIPS","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/nips/WuLZZYBQZCTY25","documentPage":"http://papers.nips.cc/paper_files/paper/2025/hash/f9666a092153f281b5116cd1f64b5c91-Abstract-Conference.html","type":"Inproceedings","doi":null,"authorSignatures":[{}],"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/nips/WuLZZYBQZCTY25","documentUrl":"http://papers.nips.cc/paper_files/paper/2025/hash/f9666a092153f281b5116cd1f64b5c91-Abstract-Conference.html"},{"key":"conf/eccv/GaoGLLZCZY24","title":"Relightable 3D Gaussians: Realistic Point Cloud Relighting with BRDF Decomposition and Ray Tracing.","year":2025,"yearOfEvent":2024,"venue":"ECCV (45)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1007/978-3-031-72995-9_5"],"source":"https://dblp.org/rec/conf/eccv/GaoGLLZCZY24","documentPage":"https://doi.org/10.1007/978-3-031-72995-9_5","type":"Inproceedings","doi":"https://doi.org/10.1007/978-3-031-72995-9_5","authorSignatures":[{"inst":"https://dblp.org/inst/9/165","instLabel":"Nanjing University (NJU)"}],"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/eccv/GaoGLLZCZY24","documentUrl":"https://doi.org/10.1007/978-3-031-72995-9_5"},{"key":"conf/eccv/HeZWYZLZCZ24","title":"Head360: Learning a Parametric 3D Full-Head for Free-View Synthesis in 360$^\\circ $.","year":2025,"yearOfEvent":2024,"venue":"ECCV (56)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1007/978-3-031-72992-8_15"],"source":"https://dblp.org/rec/conf/eccv/HeZWYZLZCZ24","documentPage":"https://doi.org/10.1007/978-3-031-72992-8_15","type":"Inproceedings","doi":"https://doi.org/10.1007/978-3-031-72992-8_15","authorSignatures":[{"inst":"https://dblp.org/inst/9/165","instLabel":"Nanjing University (NJU)"}],"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/eccv/HeZWYZLZCZ24","documentUrl":"https://doi.org/10.1007/978-3-031-72992-8_15"},{"key":"conf/siggrapha/0003CXSCSD00Z25","title":"High-Fidelity Dynamic Portrait Animation via Direct Preference Optimization and Temporal Motion Modulation.","year":2025,"yearOfEvent":2025,"venue":"SIGGRAPH Asia","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1145/3757377.3763914"],"source":"https://dblp.org/rec/conf/siggrapha/0003CXSCSD00Z25","documentPage":"https://doi.org/10.1145/3757377.3763914","type":"Inproceedings","doi":"https://doi.org/10.1145/3757377.3763914","authorSignatures":[{"orcid":"https://orcid.org/0000-0001-9866-4291","inst":"https://dblp.org/inst/9/165","instLabel":"Nanjing University (NJU)"}],"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/siggrapha/0003CXSCSD00Z25","documentUrl":"https://doi.org/10.1145/3757377.3763914"},{"key":"conf/sips/ZhangGZYZT25","title":"Low-Complexity and High-Performance Accelerator for 3D Gaussian Splatting Preprocessing.","year":2025,"yearOfEvent":2025,"venue":"SiPS","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/SIPS66314.2025.11261308"],"source":"https://dblp.org/rec/conf/sips/ZhangGZYZT25","documentPage":"https://doi.org/10.1109/SIPS66314.2025.11261308","type":"Inproceedings","doi":"https://doi.org/10.1109/SIPS66314.2025.11261308","authorSignatures":[{"inst":"https://dblp.org/inst/12/001","instLabel":"Nanjing University of Science and Technology (NUST)"},{"inst":"https://dblp.org/inst/9/165","instLabel":"Nanjing University (NJU)"},{"inst":"https://dblp.org/inst/9/525","instLabel":"Suzhou University of Science and Technology"}],"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/sips/ZhangGZYZT25","documentUrl":"https://doi.org/10.1109/SIPS66314.2025.11261308"},{"key":"conf/aaai/ChengLSWZT00Q25","title":"4D Diffusion for Dynamic Protein Structure Prediction with Reference and Motion Guidance.","year":2025,"yearOfEvent":2025,"venue":"AAAI","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1609/AAAI.V39I1.31984"],"source":"https://dblp.org/rec/conf/aaai/ChengLSWZT00Q25","documentPage":"https://doi.org/10.1609/AAAI.V39I1.31984","type":"Inproceedings","doi":"https://doi.org/10.1609/AAAI.V39I1.31984","authorSignatures":[{}],"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/aaai/ChengLSWZT00Q25","documentUrl":"https://doi.org/10.1609/AAAI.V39I1.31984"}],"preprints":[{"key":"journals/corr/abs-2502-07615","title":"Flow Distillation Sampling: Regularizing 3D Gaussians with Pre-trained Matching Priors.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2502.07615"],"source":"https://dblp.org/rec/journals/corr/abs-2502-07615","documentPage":"https://doi.org/10.48550/ARXIV.2502.07615","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2502.07615","authorSignatures":[{}],"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2502-07615","documentUrl":"https://doi.org/10.48550/ARXIV.2502.07615","arxivId":"2502.07615","arxivUrl":"https://arxiv.org/abs/2502.07615"},{"key":"journals/corr/abs-2502-07685","title":"Matrix3D: Large Photogrammetry Model All-in-One.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2502.07685"],"source":"https://dblp.org/rec/journals/corr/abs-2502-07685","documentPage":"https://doi.org/10.48550/ARXIV.2502.07685","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2502.07685","authorSignatures":[{}],"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2502-07685","documentUrl":"https://doi.org/10.48550/ARXIV.2502.07685","arxivId":"2502.07685","arxivUrl":"https://arxiv.org/abs/2502.07685"},{"key":"journals/corr/abs-2505-17412","title":"Direct3D-S2: Gigascale 3D Generation Made Easy with Spatial Sparse Attention.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2505.17412"],"source":"https://dblp.org/rec/journals/corr/abs-2505-17412","documentPage":"https://doi.org/10.48550/ARXIV.2505.17412","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2505.17412","authorSignatures":[{}],"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-17412","documentUrl":"https://doi.org/10.48550/ARXIV.2505.17412","arxivId":"2505.17412","arxivUrl":"https://arxiv.org/abs/2505.17412"},{"key":"journals/corr/abs-2509-09676","title":"SpatialVID: A Large-Scale Video Dataset with Spatial Annotations.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2509.09676"],"source":"https://dblp.org/rec/journals/corr/abs-2509-09676","documentPage":"https://doi.org/10.48550/ARXIV.2509.09676","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2509.09676","authorSignatures":[{}],"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-09676","documentUrl":"https://doi.org/10.48550/ARXIV.2509.09676","arxivId":"2509.09676","arxivUrl":"https://arxiv.org/abs/2509.09676"},{"key":"journals/corr/abs-2510-07729","title":"ComGS: Efficient 3D Object-Scene Composition via Surface Octahedral Probes.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2510.07729"],"source":"https://dblp.org/rec/journals/corr/abs-2510-07729","documentPage":"https://doi.org/10.48550/ARXIV.2510.07729","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2510.07729","authorSignatures":[{}],"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-07729","documentUrl":"https://doi.org/10.48550/ARXIV.2510.07729","arxivId":"2510.07729","arxivUrl":"https://arxiv.org/abs/2510.07729"},{"key":"journals/corr/abs-2512-02993","title":"TEXTRIX: Latent Attribute Grid for Native Texture Generation and Beyond.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2512.02993"],"source":"https://dblp.org/rec/journals/corr/abs-2512-02993","documentPage":"https://doi.org/10.48550/ARXIV.2512.02993","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2512.02993","authorSignatures":[{}],"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-02993","documentUrl":"https://doi.org/10.48550/ARXIV.2512.02993","arxivId":"2512.02993","arxivUrl":"https://arxiv.org/abs/2512.02993"},{"key":"journals/corr/abs-2512-04939","title":"LiteVGGT: Boosting Vanilla VGGT via Geometry-aware Cached Token Merging.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2512.04939"],"source":"https://dblp.org/rec/journals/corr/abs-2512-04939","documentPage":"https://doi.org/10.48550/ARXIV.2512.04939","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2512.04939","authorSignatures":[{}],"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-04939","documentUrl":"https://doi.org/10.48550/ARXIV.2512.04939","arxivId":"2512.04939","arxivUrl":"https://arxiv.org/abs/2512.04939"}],"excludedFormal":[],"excludedOther":[],"excludedHomonyms":[{"key":"conf/acl/MaWYYZ0025","title":"Caution for the Environment: Multimodal LLM Agents are Susceptible to Environmental Distractions.","year":2025,"yearOfEvent":2025,"venue":"ACL (1)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.18653/V1/2025.ACL-LONG.1087"],"source":"https://dblp.org/rec/conf/acl/MaWYYZ0025","documentPage":"https://doi.org/10.18653/V1/2025.ACL-LONG.1087","type":"Inproceedings","doi":"https://doi.org/10.18653/V1/2025.ACL-LONG.1087","authorSignatures":[{}],"exclusionReason":"Original paper assigns Yao Yao to SJTU and yaoyao27@sjtu.edu.cn, not NJU faculty 姚遥.","exclusionSource":"https://aclanthology.org/2025.acl-long.1087.pdf","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/acl/MaWYYZ0025","documentUrl":"https://doi.org/10.18653/V1/2025.ACL-LONG.1087"},{"key":"conf/acl/YangCMYC0Z25","title":"LESA: Learnable LLM Layer Scaling-Up.","year":2025,"yearOfEvent":2025,"venue":"ACL (1)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.18653/V1/2025.ACL-LONG.1095"],"source":"https://dblp.org/rec/conf/acl/YangCMYC0Z25","documentPage":"https://doi.org/10.18653/V1/2025.ACL-LONG.1095","type":"Inproceedings","doi":"https://doi.org/10.18653/V1/2025.ACL-LONG.1095","authorSignatures":[{}],"exclusionReason":"Original paper assigns Yao Yao to SJTU, matching the NLP homonym.","exclusionSource":"https://aclanthology.org/2025.acl-long.1095.pdf","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/acl/YangCMYC0Z25","documentUrl":"https://doi.org/10.18653/V1/2025.ACL-LONG.1095"},{"key":"conf/emnlp/YangYLQGZ25","title":"XQuant: Achieving Ultra-Low Bit KV Cache Quantization with Cross-Layer Compression.","year":2025,"yearOfEvent":2025,"venue":"EMNLP","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.18653/V1/2025.EMNLP-MAIN.494"],"source":"https://dblp.org/rec/conf/emnlp/YangYLQGZ25","documentPage":"https://doi.org/10.18653/V1/2025.EMNLP-MAIN.494","type":"Inproceedings","doi":"https://doi.org/10.18653/V1/2025.EMNLP-MAIN.494","authorSignatures":[{}],"exclusionReason":"Original paper assigns Yao Yao to SJTU and yaoyao27@sjtu.edu.cn.","exclusionSource":"https://aclanthology.org/2025.emnlp-main.494.pdf","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/emnlp/YangYLQGZ25","documentUrl":"https://doi.org/10.18653/V1/2025.EMNLP-MAIN.494"},{"key":"journals/corr/abs-2502-13794","title":"LESA: Learnable LLM Layer Scaling-Up.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2502.13794"],"source":"https://dblp.org/rec/journals/corr/abs-2502-13794","documentPage":"https://doi.org/10.48550/ARXIV.2502.13794","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2502.13794","authorSignatures":[{}],"exclusionReason":"Original paper assigns Yao Yao to SJTU, matching the NLP homonym.","exclusionSource":"https://aclanthology.org/2025.acl-long.1095.pdf","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2502-13794","documentUrl":"https://doi.org/10.48550/ARXIV.2502.13794"},{"key":"journals/corr/abs-2510-11236","title":"XQuant: Achieving Ultra-Low Bit KV Cache Quantization with Cross-Layer Compression.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2510.11236"],"source":"https://dblp.org/rec/journals/corr/abs-2510-11236","documentPage":"https://doi.org/10.48550/ARXIV.2510.11236","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2510.11236","authorSignatures":[{}],"exclusionReason":"Original paper assigns Yao Yao to SJTU and yaoyao27@sjtu.edu.cn.","exclusionSource":"https://aclanthology.org/2025.emnlp-main.494.pdf","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-11236","documentUrl":"https://doi.org/10.48550/ARXIV.2510.11236"},{"key":"journals/csur/ZhangYZTMHWGWLZ25","title":"Igniting Language Intelligence: The Hitchhiker's Guide from Chain-of-Thought Reasoning to Language Agents.","year":2025,"yearOfEvent":null,"venue":"ACM Comput. Surv.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1145/3719341"],"source":"https://dblp.org/rec/journals/csur/ZhangYZTMHWGWLZ25","documentPage":"https://doi.org/10.1145/3719341","type":"Article","doi":"https://doi.org/10.1145/3719341","authorSignatures":[{"orcid":"https://orcid.org/0009-0006-6055-2546","inst":"https://dblp.org/inst/9/595","instLabel":"Shanghai Jiao Tong University (SJTU)"}],"exclusionReason":"Different SJTU NLP student Yao Yao, ORCID 0009-0006-6055-2546, author of the linked CoT survey repository.","exclusionSource":"https://github.com/Zoeyyao27","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/csur/ZhangYZTMHWGWLZ25","documentUrl":"https://doi.org/10.1145/3719341"}],"unassignedCandidates":[{"key":"journals/corr/abs-2503-00330","title":"How Deep is Love in LLMs' Hearts? Exploring Semantic Size in Human-like Cognition.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2503.00330"],"source":"https://dblp.org/rec/journals/corr/abs-2503-00330","documentPage":"https://doi.org/10.48550/ARXIV.2503.00330","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2503.00330","authorSignatures":[{}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-00330","documentUrl":"https://doi.org/10.48550/ARXIV.2503.00330"},{"key":"journals/corr/abs-2505-23525","title":"Hallo4: High-Fidelity Dynamic Portrait Animation via Direct Preference Optimization and Temporal Motion Modulation.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2505.23525"],"source":"https://dblp.org/rec/journals/corr/abs-2505-23525","documentPage":"https://doi.org/10.48550/ARXIV.2505.23525","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2505.23525","authorSignatures":[{}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-23525","documentUrl":"https://doi.org/10.48550/ARXIV.2505.23525"},{"key":"journals/corr/abs-2507-00917","title":"A Survey: Learning Embodied Intelligence from Physical Simulators and World Models.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2507.00917"],"source":"https://dblp.org/rec/journals/corr/abs-2507-00917","documentPage":"https://doi.org/10.48550/ARXIV.2507.00917","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2507.00917","authorSignatures":[{}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2507-00917","documentUrl":"https://doi.org/10.48550/ARXIV.2507.00917"},{"key":"journals/corr/abs-2511-05038","title":"Pressure2Motion: Hierarchical Motion Synthesis from Ground Pressure with Text Guidance.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2511.05038"],"source":"https://dblp.org/rec/journals/corr/abs-2511-05038","documentPage":"https://doi.org/10.48550/ARXIV.2511.05038","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2511.05038","authorSignatures":[{}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2511-05038","documentUrl":"https://doi.org/10.48550/ARXIV.2511.05038"},{"key":"journals/corr/abs-2511-21887","title":"UniArt: Unified 3D Representation for Generating 3D Articulated Objects with Open-Set Articulation.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2511.21887"],"source":"https://dblp.org/rec/journals/corr/abs-2511-21887","documentPage":"https://doi.org/10.48550/ARXIV.2511.21887","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2511.21887","authorSignatures":[{}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2511-21887","documentUrl":"https://doi.org/10.48550/ARXIV.2511.21887"}],"retrievedAt":"2026-10-19","querySource":"https://sparql.dblp.org/","method":"DBLP yearOfPublication=2025; Article + Inproceedings; excludes Informal/CoRR and explicit editorial/correction/erratum/preface; unique DBLP record keys within person.","preprintStatus":"partial_identity_review","preprintLowerBound2025":7,"sourceWarning":true,"labName":"Physical Intelligence Lab（NJU-PIL）","labUrl":"https://yoyo000.github.io/group.html","labEvidence":"本人主页明确称自己是 Physical Intelligence Lab（NJU-PIL）成员，并说明该组原名 NJU-3DV；导航给出 Group 页面。名称为本次读取时的现称，不声称是2025全年的固定组织边界。","labSourceUrl":"https://yoyo000.github.io/","affiliationZh":"南京大学","knownPreprintMinimum2025":7,"excludedMisattributed":[{"key":"conf/acl/MaWYYZ0025","title":"Caution for the Environment: Multimodal LLM Agents are Susceptible to Environmental Distractions.","year":2025,"yearOfEvent":2025,"venue":"ACL (1)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.18653/V1/2025.ACL-LONG.1087"],"source":"https://dblp.org/rec/conf/acl/MaWYYZ0025","documentPage":"https://doi.org/10.18653/V1/2025.ACL-LONG.1087","type":"Inproceedings","doi":"https://doi.org/10.18653/V1/2025.ACL-LONG.1087","authorSignatures":[{}],"exclusionReason":"Original paper assigns Yao Yao to SJTU and yaoyao27@sjtu.edu.cn, not NJU faculty 姚遥.","exclusionSource":"https://aclanthology.org/2025.acl-long.1087.pdf","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/acl/MaWYYZ0025","documentUrl":"https://doi.org/10.18653/V1/2025.ACL-LONG.1087"},{"key":"conf/acl/YangCMYC0Z25","title":"LESA: Learnable LLM Layer Scaling-Up.","year":2025,"yearOfEvent":2025,"venue":"ACL (1)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.18653/V1/2025.ACL-LONG.1095"],"source":"https://dblp.org/rec/conf/acl/YangCMYC0Z25","documentPage":"https://doi.org/10.18653/V1/2025.ACL-LONG.1095","type":"Inproceedings","doi":"https://doi.org/10.18653/V1/2025.ACL-LONG.1095","authorSignatures":[{}],"exclusionReason":"Original paper assigns Yao Yao to SJTU, matching the NLP homonym.","exclusionSource":"https://aclanthology.org/2025.acl-long.1095.pdf","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/acl/YangCMYC0Z25","documentUrl":"https://doi.org/10.18653/V1/2025.ACL-LONG.1095"},{"key":"conf/emnlp/YangYLQGZ25","title":"XQuant: Achieving Ultra-Low Bit KV Cache Quantization with Cross-Layer Compression.","year":2025,"yearOfEvent":2025,"venue":"EMNLP","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.18653/V1/2025.EMNLP-MAIN.494"],"source":"https://dblp.org/rec/conf/emnlp/YangYLQGZ25","documentPage":"https://doi.org/10.18653/V1/2025.EMNLP-MAIN.494","type":"Inproceedings","doi":"https://doi.org/10.18653/V1/2025.EMNLP-MAIN.494","authorSignatures":[{}],"exclusionReason":"Original paper assigns Yao Yao to SJTU and yaoyao27@sjtu.edu.cn.","exclusionSource":"https://aclanthology.org/2025.emnlp-main.494.pdf","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/emnlp/YangYLQGZ25","documentUrl":"https://doi.org/10.18653/V1/2025.EMNLP-MAIN.494"},{"key":"journals/corr/abs-2502-13794","title":"LESA: Learnable LLM Layer Scaling-Up.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2502.13794"],"source":"https://dblp.org/rec/journals/corr/abs-2502-13794","documentPage":"https://doi.org/10.48550/ARXIV.2502.13794","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2502.13794","authorSignatures":[{}],"exclusionReason":"Original paper assigns Yao Yao to SJTU, matching the NLP homonym.","exclusionSource":"https://aclanthology.org/2025.acl-long.1095.pdf","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2502-13794","documentUrl":"https://doi.org/10.48550/ARXIV.2502.13794"},{"key":"journals/corr/abs-2510-11236","title":"XQuant: Achieving Ultra-Low Bit KV Cache Quantization with Cross-Layer Compression.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2510.11236"],"source":"https://dblp.org/rec/journals/corr/abs-2510-11236","documentPage":"https://doi.org/10.48550/ARXIV.2510.11236","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2510.11236","authorSignatures":[{}],"exclusionReason":"Original paper assigns Yao Yao to SJTU and yaoyao27@sjtu.edu.cn.","exclusionSource":"https://aclanthology.org/2025.emnlp-main.494.pdf","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-11236","documentUrl":"https://doi.org/10.48550/ARXIV.2510.11236"},{"key":"journals/csur/ZhangYZTMHWGWLZ25","title":"Igniting Language Intelligence: The Hitchhiker's Guide from Chain-of-Thought Reasoning to Language Agents.","year":2025,"yearOfEvent":null,"venue":"ACM Comput. Surv.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1145/3719341"],"source":"https://dblp.org/rec/journals/csur/ZhangYZTMHWGWLZ25","documentPage":"https://doi.org/10.1145/3719341","type":"Article","doi":"https://doi.org/10.1145/3719341","authorSignatures":[{"orcid":"https://orcid.org/0009-0006-6055-2546","inst":"https://dblp.org/inst/9/595","instLabel":"Shanghai Jiao Tong University (SJTU)"}],"exclusionReason":"Different SJTU NLP student Yao Yao, ORCID 0009-0006-6055-2546, author of the linked CoT survey repository.","exclusionSource":"https://github.com/Zoeyyao27","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/csur/ZhangYZTMHWGWLZ25","documentUrl":"https://doi.org/10.1145/3719341"}],"displayNotes":"检出的 DBLP 同名记录已排除，2025 年的正式记录已逐条复核。计入 14 条，均为会议论文，所有作者位置均计入。预印本候选池尚不完整，暂不给出总数，这不是零。","labDisplayNotes":"个人主页写明本人是 Physical Intelligence Lab（NJU-PIL，原名 NJU-3DV）的成员，据此归组；名称为检索时的现称，不代表 2025 全年的组织边界。"},{"index":102,"name":"Mang Ye","nameZh":"叶茫","affiliation":"Wuhan University","source":"DBLP Knowledge Graph official SPARQL API","profileUrl":"https://dblp.org/pid/156/0610","identifier":"156/0610","identityEvidence":[{"url":"https://marswhu.github.io/index.html","evidence":"Personal faculty site identifies Wuhan professor Mang Ye and directly links to DBLP 156/0610."},{"url":"https://orcid.org/0000-0003-3989-7655","evidence":"ORCID linked to DBLP records identifies Wuhan University professor and verified whu.edu.cn email domain."},{"url":"https://dblp.org/rec/conf/cvpr/FangHWSY25","evidence":"DBLP paper author signature connects this profile to Wuhan University (WHU)."},{"url":"https://dblp.org/rec/journals/npjdm/LeiWLYSYLXGZYYDW25","evidence":"DBLP paper author signature connects this profile to Hubei University and https://orcid.org/0000-0003-3989-7655."},{"url":"https://dblp.org/rec/journals/visintelligence/XuWGCYL25","evidence":"DBLP paper author signature connects this profile to Wuhan University (WHU) and https://orcid.org/0000-0003-3989-7655."}],"count2025":76,"conference2025":47,"journal2025":29,"preprint2025":26,"status":"verified","notes":"Counts are DBLP indexed coauthored records, not first-author counts, laboratory totals, unique scientific discoveries, or quality assessments. DBLP yearOfPublication=2025; yearOfEvent retained and can differ. Conference workshops are included. Preprints are separate and may overlap formal versions.","papers":[{"key":"conf/aaai/0006HWY25","title":"Label-Free Backdoor Attacks in Vertical Federated Learning.","year":2025,"yearOfEvent":2025,"venue":"AAAI","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1609/AAAI.V39I19.34246"],"source":"https://dblp.org/rec/conf/aaai/0006HWY25","documentPage":"https://doi.org/10.1609/AAAI.V39I19.34246","type":"Inproceedings","doi":"https://doi.org/10.1609/AAAI.V39I19.34246","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/aaai/0006HWY25","documentUrl":"https://doi.org/10.1609/AAAI.V39I19.34246"},{"key":"conf/aaai/WangLYYWX25","title":"TokenMatcher: Diverse Tokens Matching for Unsupervised Visible-Infrared Person Re-Identification.","year":2025,"yearOfEvent":2025,"venue":"AAAI","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1609/AAAI.V39I8.32855"],"source":"https://dblp.org/rec/conf/aaai/WangLYYWX25","documentPage":"https://doi.org/10.1609/AAAI.V39I8.32855","type":"Inproceedings","doi":"https://doi.org/10.1609/AAAI.V39I8.32855","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/aaai/WangLYYWX25","documentUrl":"https://doi.org/10.1609/AAAI.V39I8.32855"},{"key":"conf/aaai/WangZHZLY25","title":"MDFG: Multi-Dimensional Fine-Grained Modeling for Fatigue Detection.","year":2025,"yearOfEvent":2025,"venue":"AAAI","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1609/AAAI.V39I12.33388"],"source":"https://dblp.org/rec/conf/aaai/WangZHZLY25","documentPage":"https://doi.org/10.1609/AAAI.V39I12.33388","type":"Inproceedings","doi":"https://doi.org/10.1609/AAAI.V39I12.33388","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/aaai/WangZHZLY25","documentUrl":"https://doi.org/10.1609/AAAI.V39I12.33388"},{"key":"conf/aaai/ZhaoRLY25","title":"NightReID: A Large-Scale Nighttime Person Re-Identification Benchmark.","year":2025,"yearOfEvent":2025,"venue":"AAAI","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1609/AAAI.V39I10.33142"],"source":"https://dblp.org/rec/conf/aaai/ZhaoRLY25","documentPage":"https://doi.org/10.1609/AAAI.V39I10.33142","type":"Inproceedings","doi":"https://doi.org/10.1609/AAAI.V39I10.33142","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/aaai/ZhaoRLY25","documentUrl":"https://doi.org/10.1609/AAAI.V39I10.33142"},{"key":"conf/cvpr/0001HWYY25","title":"LoRASculpt: Sculpting LoRA for Harmonizing General and Specialized Knowledge in Multimodal Large Language Models.","year":2025,"yearOfEvent":2025,"venue":"CVPR","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/CVPR52734.2025.02437"],"source":"https://dblp.org/rec/conf/cvpr/0001HWYY25","documentPage":"https://openaccess.thecvf.com/content/CVPR2025/html/Liang_LoRASculpt_Sculpting_LoRA_for_Harmonizing_General_and_Specialized_Knowledge_in_CVPR_2025_paper.html","type":"Inproceedings","doi":"https://doi.org/10.1109/CVPR52734.2025.02437","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/0001HWYY25","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Liang_LoRASculpt_Sculpting_LoRA_for_Harmonizing_General_and_Specialized_Knowledge_in_CVPR_2025_paper.html"},{"key":"conf/cvpr/BaiJCWY25","title":"Chat-based Person Retrieval via Dialogue-Refined Cross-Modal Alignment.","year":2025,"yearOfEvent":2025,"venue":"CVPR","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/CVPR52734.2025.00374"],"source":"https://dblp.org/rec/conf/cvpr/BaiJCWY25","documentPage":"https://openaccess.thecvf.com/content/CVPR2025/html/Bai_Chat-based_Person_Retrieval_via_Dialogue-Refined_Cross-Modal_Alignment_CVPR_2025_paper.html","type":"Inproceedings","doi":"https://doi.org/10.1109/CVPR52734.2025.00374","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/BaiJCWY25","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Bai_Chat-based_Person_Retrieval_via_Dialogue-Refined_Cross-Modal_Alignment_CVPR_2025_paper.html"},{"key":"conf/cvpr/FangHWSY25","title":"EMOE: Modality-Specific Enhanced Dynamic Emotion Experts.","year":2025,"yearOfEvent":2025,"venue":"CVPR","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/CVPR52734.2025.01335"],"source":"https://dblp.org/rec/conf/cvpr/FangHWSY25","documentPage":"https://openaccess.thecvf.com/content/CVPR2025/html/Fang_EMOE_Modality-Specific_Enhanced_Dynamic_Emotion_Experts_CVPR_2025_paper.html","type":"Inproceedings","doi":"https://doi.org/10.1109/CVPR52734.2025.01335","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/FangHWSY25","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Fang_EMOE_Modality-Specific_Enhanced_Dynamic_Emotion_Experts_CVPR_2025_paper.html"},{"key":"conf/cvpr/TanWHLZ0Y25","title":"FedSPA: Generalizable Federated Graph Learning under Homophily Heterogeneity.","year":2025,"yearOfEvent":2025,"venue":"CVPR","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/CVPR52734.2025.01441"],"source":"https://dblp.org/rec/conf/cvpr/TanWHLZ0Y25","documentPage":"https://openaccess.thecvf.com/content/CVPR2025/html/Tan_FedSPA_Generalizable_Federated_Graph_Learning_under_Homophily_Heterogeneity_CVPR_2025_paper.html","type":"Inproceedings","doi":"https://doi.org/10.1109/CVPR52734.2025.01441","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/TanWHLZ0Y25","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Tan_FedSPA_Generalizable_Federated_Graph_Learning_under_Homophily_Heterogeneity_CVPR_2025_paper.html"},{"key":"conf/cvpr/WuSWY25","title":"Synthetic Data is an Elegant GIFT for Continual Vision-Language Models.","year":2025,"yearOfEvent":2025,"venue":"CVPR","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/CVPR52734.2025.00268"],"source":"https://dblp.org/rec/conf/cvpr/WuSWY25","documentPage":"https://openaccess.thecvf.com/content/CVPR2025/html/Wu_Synthetic_Data_is_an_Elegant_GIFT_for_Continual_Vision-Language_Models_CVPR_2025_paper.html","type":"Inproceedings","doi":"https://doi.org/10.1109/CVPR52734.2025.00268","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/WuSWY25","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Wu_Synthetic_Data_is_an_Elegant_GIFT_for_Continual_Vision-Language_Models_CVPR_2025_paper.html"},{"key":"conf/cvpr/YangL0Y25","title":"Cheb-GR: Rethinking K-nearest Neighbor Search in Re-ranking for Person Re-identification.","year":2025,"yearOfEvent":2025,"venue":"CVPR","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/CVPR52734.2025.01794"],"source":"https://dblp.org/rec/conf/cvpr/YangL0Y25","documentPage":"https://openaccess.thecvf.com/content/CVPR2025/html/Yang_Cheb-GR_Rethinking_K-nearest_Neighbor_Search_in_Re-ranking_for_Person_Re-identification_CVPR_2025_paper.html","type":"Inproceedings","doi":"https://doi.org/10.1109/CVPR52734.2025.01794","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/YangL0Y25","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Yang_Cheb-GR_Rethinking_K-nearest_Neighbor_Search_in_Re-ranking_for_Person_Re-identification_CVPR_2025_paper.html"},{"key":"conf/cvpr/YangSWY25","title":"Uncertain Multimodal Intention and Emotion Understanding in the Wild.","year":2025,"yearOfEvent":2025,"venue":"CVPR","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/CVPR52734.2025.02300"],"source":"https://dblp.org/rec/conf/cvpr/YangSWY25","documentPage":"https://openaccess.thecvf.com/content/CVPR2025/html/Yang_Uncertain_Multimodal_Intention_and_Emotion_Understanding_in_the_Wild_CVPR_2025_paper.html","type":"Inproceedings","doi":"https://doi.org/10.1109/CVPR52734.2025.02300","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/YangSWY25","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Yang_Uncertain_Multimodal_Intention_and_Emotion_Understanding_in_the_Wild_CVPR_2025_paper.html"},{"key":"conf/eccv/HuangYSDT24","title":"Fisher Calibration for Backdoor-Robust Heterogeneous Federated Learning.","year":2025,"yearOfEvent":2024,"venue":"ECCV (15)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1007/978-3-031-72633-0_14"],"source":"https://dblp.org/rec/conf/eccv/HuangYSDT24","documentPage":"https://doi.org/10.1007/978-3-031-72633-0_14","type":"Inproceedings","doi":"https://doi.org/10.1007/978-3-031-72633-0_14","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/eccv/HuangYSDT24","documentUrl":"https://doi.org/10.1007/978-3-031-72633-0_14"},{"key":"conf/eccv/LiCY24","title":"Adaptive High-Frequency Transformer for Diverse Wildlife Re-identification.","year":2025,"yearOfEvent":2024,"venue":"ECCV (44)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1007/978-3-031-72784-9_17"],"source":"https://dblp.org/rec/conf/eccv/LiCY24","documentPage":"https://doi.org/10.1007/978-3-031-72784-9_17","type":"Inproceedings","doi":"https://doi.org/10.1007/978-3-031-72784-9_17","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/eccv/LiCY24","documentUrl":"https://doi.org/10.1007/978-3-031-72784-9_17"},{"key":"conf/eccv/YangYT24","title":"Synergy of Sight and Semantics: Visual Intention Understanding with CLIP.","year":2025,"yearOfEvent":2024,"venue":"ECCV (11)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1007/978-3-031-73247-8_9"],"source":"https://dblp.org/rec/conf/eccv/YangYT24","documentPage":"https://doi.org/10.1007/978-3-031-73247-8_9","type":"Inproceedings","doi":"https://doi.org/10.1007/978-3-031-73247-8_9","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/eccv/YangYT24","documentUrl":"https://doi.org/10.1007/978-3-031-73247-8_9"},{"key":"conf/icassp/ZhengYFYY25","title":"Image-assisted Label Connective Completion for Vessel Segmentation with Insufficient Annotations.","year":2025,"yearOfEvent":2025,"venue":"ICASSP","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/ICASSP49660.2025.10888997"],"source":"https://dblp.org/rec/conf/icassp/ZhengYFYY25","documentPage":"https://doi.org/10.1109/ICASSP49660.2025.10888997","type":"Inproceedings","doi":"https://doi.org/10.1109/ICASSP49660.2025.10888997","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/icassp/ZhengYFYY25","documentUrl":"https://doi.org/10.1109/ICASSP49660.2025.10888997"},{"key":"conf/iccv/DongY25","title":"Pose-Star: Anatomy-Aware Editing for Open-World Fashion Images.","year":2025,"yearOfEvent":2025,"venue":"ICCV","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/ICCV51701.2025.01468"],"source":"https://dblp.org/rec/conf/iccv/DongY25","documentPage":"https://doi.org/10.1109/ICCV51701.2025.01468","type":"Inproceedings","doi":"https://doi.org/10.1109/ICCV51701.2025.01468","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/DongY25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.01468"},{"key":"conf/iccv/YaoYHDY25","title":"Unsupervised Visible-Infrared Person Re-Identification Under Unpaired Settings.","year":2025,"yearOfEvent":2025,"venue":"ICCV","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/ICCV51701.2025.01108"],"source":"https://dblp.org/rec/conf/iccv/YaoYHDY25","documentPage":"https://doi.org/10.1109/ICCV51701.2025.01108","type":"Inproceedings","doi":"https://doi.org/10.1109/ICCV51701.2025.01108","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/YaoYHDY25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.01108"},{"key":"conf/iclr/WanSHZTY25","title":"Energy-based Backdoor Defense Against Federated Graph Learning.","year":2025,"yearOfEvent":2025,"venue":"ICLR","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/iclr/WanSHZTY25","documentPage":"https://openreview.net/forum?id=5Jc7r5aqHJ","type":"Inproceedings","doi":null,"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iclr/WanSHZTY25","documentUrl":"https://openreview.net/forum?id=5Jc7r5aqHJ"},{"key":"conf/icmcs/WuCZCDY25","title":"Interactive Sketch-Based Person Re-Identification with Text Feedback.","year":2025,"yearOfEvent":2025,"venue":"ICME","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/ICME59968.2025.11210050"],"source":"https://dblp.org/rec/conf/icmcs/WuCZCDY25","documentPage":"https://doi.org/10.1109/ICME59968.2025.11210050","type":"Inproceedings","doi":"https://doi.org/10.1109/ICME59968.2025.11210050","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/icmcs/WuCZCDY25","documentUrl":"https://doi.org/10.1109/ICME59968.2025.11210050"},{"key":"conf/icml/00030SZW00TY25","title":"Learn from Downstream and Be Yourself in Multimodal Large Language Models Fine-Tuning.","year":2025,"yearOfEvent":2025,"venue":"ICML","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/icml/00030SZW00TY25","documentPage":"https://proceedings.mlr.press/v267/huang25q.html","type":"Inproceedings","doi":null,"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/icml/00030SZW00TY25","documentUrl":"https://proceedings.mlr.press/v267/huang25q.html"},{"key":"conf/icml/00030WZ0SY0T25","title":"Be Confident: Uncovering Overfitting in MLLM Multi-Task Tuning.","year":2025,"yearOfEvent":2025,"venue":"ICML","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/icml/00030WZ0SY0T25","documentPage":"https://proceedings.mlr.press/v267/huang25r.html","type":"Inproceedings","doi":null,"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/icml/00030WZ0SY0T25","documentUrl":"https://proceedings.mlr.press/v267/huang25r.html"},{"key":"conf/icml/Fang000SY25","title":"Catch Your Emotion: Sharpening Emotion Perception in Multimodal Large Language Models.","year":2025,"yearOfEvent":2025,"venue":"ICML","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/icml/Fang000SY25","documentPage":"https://proceedings.mlr.press/v267/fang25h.html","type":"Inproceedings","doi":null,"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/icml/Fang000SY25","documentUrl":"https://proceedings.mlr.press/v267/fang25h.html"},{"key":"conf/icml/Fang0WYY25","title":"FedPHA: Federated Prompt Learning for Heterogeneous Client Adaptation.","year":2025,"yearOfEvent":2025,"venue":"ICML","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/icml/Fang0WYY25","documentPage":"https://proceedings.mlr.press/v267/fang25e.html","type":"Inproceedings","doi":null,"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/icml/Fang0WYY25","documentUrl":"https://proceedings.mlr.press/v267/fang25e.html"},{"key":"conf/icml/He00LY25","title":"SPMC: Self-Purifying Federated Backdoor Defense via Margin Contribution.","year":2025,"yearOfEvent":2025,"venue":"ICML","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/icml/He00LY25","documentPage":"https://proceedings.mlr.press/v267/he25f.html","type":"Inproceedings","doi":null,"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/icml/He00LY25","documentUrl":"https://proceedings.mlr.press/v267/he25f.html"},{"key":"conf/icml/Liao0W00Y25","title":"Splitting with Importance-aware Updating for Heterogeneous Federated Learning with Large Language Models.","year":2025,"yearOfEvent":2025,"venue":"ICML","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/icml/Liao0W00Y25","documentPage":"https://proceedings.mlr.press/v267/liao25c.html","type":"Inproceedings","doi":null,"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/icml/Liao0W00Y25","documentUrl":"https://proceedings.mlr.press/v267/liao25c.html"},{"key":"conf/icml/QianW0ZW0Y25","title":"GHOST: Generalizable One-Shot Federated Graph Learning with Proxy-Based Topology Knowledge Retention.","year":2025,"yearOfEvent":2025,"venue":"ICML","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/icml/QianW0ZW0Y25","documentPage":"https://proceedings.mlr.press/v267/qian25a.html","type":"Inproceedings","doi":null,"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/icml/QianW0ZW0Y25","documentUrl":"https://proceedings.mlr.press/v267/qian25a.html"},{"key":"conf/icml/Rong0HY25","title":"CAN: Leveraging Clients As Navigators for Generative Replay in Federated Continual Learning.","year":2025,"yearOfEvent":2025,"venue":"ICML","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/icml/Rong0HY25","documentPage":"https://proceedings.mlr.press/v267/rong25a.html","type":"Inproceedings","doi":null,"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/icml/Rong0HY25","documentUrl":"https://proceedings.mlr.press/v267/rong25a.html"},{"key":"conf/icml/ShiW0Z00Y25","title":"EAGLES: Towards Effective, Efficient, and Economical Federated Graph Learning via Unified Sparsification.","year":2025,"yearOfEvent":2025,"venue":"ICML","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/icml/ShiW0Z00Y25","documentPage":"https://proceedings.mlr.press/v267/shi25j.html","type":"Inproceedings","doi":null,"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/icml/ShiW0Z00Y25","documentUrl":"https://proceedings.mlr.press/v267/shi25j.html"},{"key":"conf/icml/Tan0W00Y25","title":"S2FGL: Spatial Spectral Federated Graph Learning.","year":2025,"yearOfEvent":2025,"venue":"ICML","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/icml/Tan0W00Y25","documentPage":"https://proceedings.mlr.press/v267/tan25d.html","type":"Inproceedings","doi":null,"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/icml/Tan0W00Y25","documentUrl":"https://proceedings.mlr.press/v267/tan25d.html"},{"key":"conf/icml/YangHW0Y25","title":"Federated Disentangled Tuning with Textual Prior Decoupling and Visual Dynamic Adaptation.","year":2025,"yearOfEvent":2025,"venue":"ICML","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/icml/YangHW0Y25","documentPage":"https://proceedings.mlr.press/v267/yang25k.html","type":"Inproceedings","doi":null,"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/icml/YangHW0Y25","documentUrl":"https://proceedings.mlr.press/v267/yang25k.html"},{"key":"conf/ijcai/ChenHWSLDYDX25","title":"Pixel-wise Divide and Conquer for Federated Vessel Segmentation.","year":2025,"yearOfEvent":2025,"venue":"IJCAI","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.24963/IJCAI.2025/540"],"source":"https://dblp.org/rec/conf/ijcai/ChenHWSLDYDX25","documentPage":"https://doi.org/10.24963/IJCAI.2025/540","type":"Inproceedings","doi":"https://doi.org/10.24963/IJCAI.2025/540","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/ijcai/ChenHWSLDYDX25","documentUrl":"https://doi.org/10.24963/IJCAI.2025/540"},{"key":"conf/ijcai/LiLLLYG0YY25","title":"Towards Anytime Retrieval: A Benchmark for Anytime Person Re-Identification.","year":2025,"yearOfEvent":2025,"venue":"IJCAI","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.24963/IJCAI.2025/164"],"source":"https://dblp.org/rec/conf/ijcai/LiLLLYG0YY25","documentPage":"https://doi.org/10.24963/IJCAI.2025/164","type":"Inproceedings","doi":"https://doi.org/10.24963/IJCAI.2025/164","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/ijcai/LiLLLYG0YY25","documentUrl":"https://doi.org/10.24963/IJCAI.2025/164"},{"key":"conf/ijcai/LuSLY25","title":"Prototype-guided Knowledge Propagation with Adaptive Learning for Lifelong Person Re-identification.","year":2025,"yearOfEvent":2025,"venue":"IJCAI","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.24963/IJCAI.2025/651"],"source":"https://dblp.org/rec/conf/ijcai/LuSLY25","documentPage":"https://doi.org/10.24963/IJCAI.2025/651","type":"Inproceedings","doi":"https://doi.org/10.24963/IJCAI.2025/651","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/ijcai/LuSLY25","documentUrl":"https://doi.org/10.24963/IJCAI.2025/651"},{"key":"conf/ijcai/WangHCSWQYWLY25","title":"An Empirical Study of Federated Prompt Learning for Vision Language Model.","year":2025,"yearOfEvent":2025,"venue":"IJCAI","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.24963/IJCAI.2025/1188"],"source":"https://dblp.org/rec/conf/ijcai/WangHCSWQYWLY25","documentPage":"https://doi.org/10.24963/IJCAI.2025/1188","type":"Inproceedings","doi":"https://doi.org/10.24963/IJCAI.2025/1188","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/ijcai/WangHCSWQYWLY25","documentUrl":"https://doi.org/10.24963/IJCAI.2025/1188"},{"key":"conf/mm/Duan0Y25","title":"MLLMs Meet Person Re-identification.","year":2025,"yearOfEvent":2025,"venue":"ACM Multimedia","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1145/3746027.3758150"],"source":"https://dblp.org/rec/conf/mm/Duan0Y25","documentPage":"https://doi.org/10.1145/3746027.3758150","type":"Inproceedings","doi":"https://doi.org/10.1145/3746027.3758150","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/mm/Duan0Y25","documentUrl":"https://doi.org/10.1145/3746027.3758150"},{"key":"conf/nips/FangY25","title":"Towards Robust Parameter-Efficient Fine-Tuning for Federated Learning.","year":2025,"yearOfEvent":2025,"venue":"NeurIPS","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/nips/FangY25","documentPage":"http://papers.nips.cc/paper_files/paper/2025/hash/cfcb1905d4acb46df42bfb5bf204bd6a-Abstract-Conference.html","type":"Inproceedings","doi":null,"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/nips/FangY25","documentUrl":"http://papers.nips.cc/paper_files/paper/2025/hash/cfcb1905d4acb46df42bfb5bf204bd6a-Abstract-Conference.html"},{"key":"conf/nips/GuanHGYYY25","title":"Rethinking Fair Federated Learning from Parameter and Client View.","year":2025,"yearOfEvent":2025,"venue":"NeurIPS","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/nips/GuanHGYYY25","documentPage":"http://papers.nips.cc/paper_files/paper/2025/hash/1b1205172b8a57ad504002a081b37859-Abstract-Conference.html","type":"Inproceedings","doi":null,"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/nips/GuanHGYYY25","documentUrl":"http://papers.nips.cc/paper_files/paper/2025/hash/1b1205172b8a57ad504002a081b37859-Abstract-Conference.html"},{"key":"conf/nips/RongHLBXLDY25","title":"Backdoor Cleaning without External Guidance in MLLM Fine-tuning.","year":2025,"yearOfEvent":2025,"venue":"NeurIPS","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/nips/RongHLBXLDY25","documentPage":"http://papers.nips.cc/paper_files/paper/2025/hash/23e6f78bdec844a9f7b6c957de2aae91-Abstract-Conference.html","type":"Inproceedings","doi":null,"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/nips/RongHLBXLDY25","documentUrl":"http://papers.nips.cc/paper_files/paper/2025/hash/23e6f78bdec844a9f7b6c957de2aae91-Abstract-Conference.html"},{"key":"conf/nips/ShenLCHY25","title":"MARS-VFL: A Unified Benchmark for Vertical Federated Learning with Realistic Evaluation.","year":2025,"yearOfEvent":2025,"venue":"NeurIPS","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/nips/ShenLCHY25","documentPage":"http://papers.nips.cc/paper_files/paper/2025/hash/ba4b5a1a98545548ff45143ade817e8e-Abstract-Datasets_and_Benchmarks_Track.html","type":"Inproceedings","doi":null,"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/nips/ShenLCHY25","documentUrl":"http://papers.nips.cc/paper_files/paper/2025/hash/ba4b5a1a98545548ff45143ade817e8e-Abstract-Datasets_and_Benchmarks_Track.html"},{"key":"conf/nips/WanCLHSJZDY25","title":"Multi-order Orchestrated Curriculum Distillation for Model-Heterogeneous Federated Graph Learning.","year":2025,"yearOfEvent":2025,"venue":"NeurIPS","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/nips/WanCLHSJZDY25","documentPage":"http://papers.nips.cc/paper_files/paper/2025/hash/66808849a9f5d8e2d00dbdc844de6333-Abstract-Conference.html","type":"Inproceedings","doi":null,"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/nips/WanCLHSJZDY25","documentUrl":"http://papers.nips.cc/paper_files/paper/2025/hash/66808849a9f5d8e2d00dbdc844de6333-Abstract-Conference.html"},{"key":"conf/nips/WanQHXGLZDY25","title":"OASIS: One-Shot Federated Graph Learning via Wasserstein Assisted Knowledge Integration.","year":2025,"yearOfEvent":2025,"venue":"NeurIPS","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/nips/WanQHXGLZDY25","documentPage":"http://papers.nips.cc/paper_files/paper/2025/hash/7300dd4d625cb42a438c1b822c77569f-Abstract-Conference.html","type":"Inproceedings","doi":null,"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/nips/WanQHXGLZDY25","documentUrl":"http://papers.nips.cc/paper_files/paper/2025/hash/7300dd4d625cb42a438c1b822c77569f-Abstract-Conference.html"},{"key":"conf/nips/WanRZHRZWDY25","title":"MOTION: Multi-Sculpt Evolutionary Coarsening for Federated Continual Graph Learning.","year":2025,"yearOfEvent":2025,"venue":"NeurIPS","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/nips/WanRZHRZWDY25","documentPage":"http://papers.nips.cc/paper_files/paper/2025/hash/659afd140447b7d50fadf8bde6a2240d-Abstract-Conference.html","type":"Inproceedings","doi":null,"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/nips/WanRZHRZWDY25","documentUrl":"http://papers.nips.cc/paper_files/paper/2025/hash/659afd140447b7d50fadf8bde6a2240d-Abstract-Conference.html"},{"key":"conf/nips/XiaoLLHXZYP25","title":"MoodAngels: A Retrieval-augmented Multi-agent Framework for Psychiatry Diagnosis.","year":2025,"yearOfEvent":2025,"venue":"NeurIPS","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/nips/XiaoLLHXZYP25","documentPage":"http://papers.nips.cc/paper_files/paper/2025/hash/27bb4753c44e0990865583fa49296465-Abstract-Conference.html","type":"Inproceedings","doi":null,"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/nips/XiaoLLHXZYP25","documentUrl":"http://papers.nips.cc/paper_files/paper/2025/hash/27bb4753c44e0990865583fa49296465-Abstract-Conference.html"},{"key":"conf/nips/YangLLY25","title":"Adaptive Re-calibration Learning for Balanced Multimodal Intention Recognition.","year":2025,"yearOfEvent":2025,"venue":"NeurIPS","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/nips/YangLLY25","documentPage":"http://papers.nips.cc/paper_files/paper/2025/hash/cbed27fa7f3b112caebf3ba6e8b3cd8c-Abstract-Conference.html","type":"Inproceedings","doi":null,"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/nips/YangLLY25","documentUrl":"http://papers.nips.cc/paper_files/paper/2025/hash/cbed27fa7f3b112caebf3ba6e8b3cd8c-Abstract-Conference.html"},{"key":"conf/nips/YuanHWGLY25","title":"DKDR: Dynamic Knowledge Distillation for Reliability in Federated Learning.","year":2025,"yearOfEvent":2025,"venue":"NeurIPS","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/nips/YuanHWGLY25","documentPage":"http://papers.nips.cc/paper_files/paper/2025/hash/3181db351fd3ced43cd589b0b572675d-Abstract-Conference.html","type":"Inproceedings","doi":null,"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/nips/YuanHWGLY25","documentUrl":"http://papers.nips.cc/paper_files/paper/2025/hash/3181db351fd3ced43cd589b0b572675d-Abstract-Conference.html"},{"key":"conf/nips/ZhouSXDWY25","title":"PC-Net: Weakly Supervised Compositional Moment Retrieval via Proposal-Centric Network.","year":2025,"yearOfEvent":2025,"venue":"NeurIPS","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/nips/ZhouSXDWY25","documentPage":"http://papers.nips.cc/paper_files/paper/2025/hash/bfc02f1f412e8a6e710b1e00ea9ca670-Abstract-Conference.html","type":"Inproceedings","doi":null,"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/nips/ZhouSXDWY25","documentUrl":"http://papers.nips.cc/paper_files/paper/2025/hash/bfc02f1f412e8a6e710b1e00ea9ca670-Abstract-Conference.html"},{"key":"conf/nips/ZhouYHCY25","title":"Unbiased Prototype Consistency Learning for Multi-Modal and Multi-Task Object Re-Identification.","year":2025,"yearOfEvent":2025,"venue":"NeurIPS","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/nips/ZhouYHCY25","documentPage":"http://papers.nips.cc/paper_files/paper/2025/hash/82a0696bea2c4ebf726fc796eaca7a55-Abstract-Conference.html","type":"Inproceedings","doi":null,"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/nips/ZhouYHCY25","documentUrl":"http://papers.nips.cc/paper_files/paper/2025/hash/82a0696bea2c4ebf726fc796eaca7a55-Abstract-Conference.html"},{"key":"journals/caaitrit/YeHSYD25","title":"BiaMix Contrastive Learning and Memory Similarity Distillation in Class-Incremental Learning.","year":2025,"yearOfEvent":null,"venue":"CAAI Trans. Intell. Technol.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1049/CIT2.70064"],"source":"https://dblp.org/rec/journals/caaitrit/YeHSYD25","documentPage":"https://doi.org/10.1049/CIT2.70064","type":"Article","doi":"https://doi.org/10.1049/CIT2.70064","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/caaitrit/YeHSYD25","documentUrl":"https://doi.org/10.1049/CIT2.70064"},{"key":"journals/chinaf/HuangYSLD25","title":"Self-knowledge distillation with dimensional history knowledge.","year":2025,"yearOfEvent":null,"venue":"Sci. China Inf. Sci.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1007/S11432-023-4283-3"],"source":"https://dblp.org/rec/journals/chinaf/HuangYSLD25","documentPage":"https://doi.org/10.1007/S11432-023-4283-3","type":"Article","doi":"https://doi.org/10.1007/S11432-023-4283-3","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/chinaf/HuangYSLD25","documentUrl":"https://doi.org/10.1007/S11432-023-4283-3"},{"key":"journals/chinaf/YeHSLD25","title":"Revisiting federated learning with label skew: an over-confidence perspective.","year":2025,"yearOfEvent":null,"venue":"Sci. China Inf. Sci.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1007/S11432-023-4202-1"],"source":"https://dblp.org/rec/journals/chinaf/YeHSLD25","documentPage":"https://doi.org/10.1007/S11432-023-4202-1","type":"Article","doi":"https://doi.org/10.1007/S11432-023-4202-1","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/chinaf/YeHSLD25","documentUrl":"https://doi.org/10.1007/S11432-023-4202-1"},{"key":"journals/csur/YeSDSKY25","title":"Vertical Federated Learning for Effectiveness, Security, Applicability: A Survey.","year":2025,"yearOfEvent":null,"venue":"ACM Comput. Surv.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1145/3720539"],"source":"https://dblp.org/rec/journals/csur/YeSDSKY25","documentPage":"https://doi.org/10.1145/3720539","type":"Article","doi":"https://doi.org/10.1145/3720539","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/csur/YeSDSKY25","documentUrl":"https://doi.org/10.1145/3720539"},{"key":"journals/ijcv/YeCLZCD25","title":"Transformer for Object Re-identification: A Survey.","year":2025,"yearOfEvent":null,"venue":"Int. J. Comput. Vis.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1007/S11263-024-02284-4"],"source":"https://dblp.org/rec/journals/ijcv/YeCLZCD25","documentPage":"https://doi.org/10.1007/S11263-024-02284-4","type":"Article","doi":"https://doi.org/10.1007/S11263-024-02284-4","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/ijcv/YeCLZCD25","documentUrl":"https://doi.org/10.1007/S11263-024-02284-4"},{"key":"journals/ijcv/ZhangZYYS25","title":"Modality Confusion Learning: A Versatile Framework for Visible-Infrared Re-identification.","year":2025,"yearOfEvent":null,"venue":"Int. J. Comput. Vis.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1007/S11263-025-02563-8"],"source":"https://dblp.org/rec/journals/ijcv/ZhangZYYS25","documentPage":"https://doi.org/10.1007/S11263-025-02563-8","type":"Article","doi":"https://doi.org/10.1007/S11263-025-02563-8","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/ijcv/ZhangZYYS25","documentUrl":"https://doi.org/10.1007/S11263-025-02563-8"},{"key":"journals/nn/MeiYYLYYMC25","title":"Multi-feature balanced network for clothes-changing person re-identification.","year":2025,"yearOfEvent":null,"venue":"Neural Networks","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1016/J.NEUNET.2025.107617"],"source":"https://dblp.org/rec/journals/nn/MeiYYLYYMC25","documentPage":"https://doi.org/10.1016/J.NEUNET.2025.107617","type":"Article","doi":"https://doi.org/10.1016/J.NEUNET.2025.107617","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/nn/MeiYYLYYMC25","documentUrl":"https://doi.org/10.1016/J.NEUNET.2025.107617"},{"key":"journals/npjdm/LeiWLYSYLXGZYYDW25","title":"An interpretable deep learning model for first-trimester fetal cardiac screening.","year":2025,"yearOfEvent":null,"venue":"npj Digit. Medicine","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1038/S41746-025-02217-6"],"source":"https://dblp.org/rec/journals/npjdm/LeiWLYSYLXGZYYDW25","documentPage":"https://doi.org/10.1038/S41746-025-02217-6","type":"Article","doi":"https://doi.org/10.1038/S41746-025-02217-6","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/npjdm/LeiWLYSYLXGZYYDW25","documentUrl":"https://doi.org/10.1038/S41746-025-02217-6"},{"key":"journals/pami/FangYD25","title":"Robust Asymmetric Heterogeneous Federated Learning With Corrupted Clients.","year":2025,"yearOfEvent":null,"venue":"IEEE Trans. Pattern Anal. Mach. Intell.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1109/TPAMI.2025.3527137"],"source":"https://dblp.org/rec/journals/pami/FangYD25","documentPage":"https://doi.org/10.1109/TPAMI.2025.3527137","type":"Article","doi":"https://doi.org/10.1109/TPAMI.2025.3527137","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/pami/FangYD25","documentUrl":"https://doi.org/10.1109/TPAMI.2025.3527137"},{"key":"journals/pami/OuyangDYDSS25","title":"Semantic-Aware Pseudo-Labeling for Unsupervised Meta-Learning.","year":2025,"yearOfEvent":null,"venue":"IEEE Trans. Pattern Anal. Mach. Intell.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1109/TPAMI.2025.3556378"],"source":"https://dblp.org/rec/journals/pami/OuyangDYDSS25","documentPage":"https://doi.org/10.1109/TPAMI.2025.3556378","type":"Article","doi":"https://doi.org/10.1109/TPAMI.2025.3556378","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/pami/OuyangDYDSS25","documentUrl":"https://doi.org/10.1109/TPAMI.2025.3556378"},{"key":"journals/pami/YeWD25","title":"Dual-Level Matching With Outlier Filtering for Unsupervised Visible-Infrared Person Re-Identification.","year":2025,"yearOfEvent":null,"venue":"IEEE Trans. Pattern Anal. Mach. Intell.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1109/TPAMI.2025.3541053"],"source":"https://dblp.org/rec/journals/pami/YeWD25","documentPage":"https://doi.org/10.1109/TPAMI.2025.3541053","type":"Article","doi":"https://doi.org/10.1109/TPAMI.2025.3541053","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/pami/YeWD25","documentUrl":"https://doi.org/10.1109/TPAMI.2025.3541053"},{"key":"journals/pr/LiuJZJYY25","title":"Dynamic and static mutual fitting for action recognition.","year":2025,"yearOfEvent":null,"venue":"Pattern Recognit.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1016/J.PATCOG.2024.110948"],"source":"https://dblp.org/rec/journals/pr/LiuJZJYY25","documentPage":"https://doi.org/10.1016/J.PATCOG.2024.110948","type":"Article","doi":"https://doi.org/10.1016/J.PATCOG.2024.110948","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/pr/LiuJZJYY25","documentUrl":"https://doi.org/10.1016/J.PATCOG.2024.110948"},{"key":"journals/taffco/RaoCY25","title":"Contextual Graph Reconstruction and Emotional Variation Learning for Conversational Emotion Recognition.","year":2025,"yearOfEvent":null,"venue":"IEEE Trans. Affect. Comput.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1109/TAFFC.2025.3568519"],"source":"https://dblp.org/rec/journals/taffco/RaoCY25","documentPage":"https://doi.org/10.1109/TAFFC.2025.3568519","type":"Article","doi":"https://doi.org/10.1109/TAFFC.2025.3568519","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/taffco/RaoCY25","documentUrl":"https://doi.org/10.1109/TAFFC.2025.3568519"},{"key":"journals/tbbis/LiYSD25","title":"WePerson: Generalizable Re-Identification From Synthetic Data With Single Query Adaptation.","year":2025,"yearOfEvent":null,"venue":"IEEE Trans. Biom. Behav. Identity Sci.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1109/TBIOM.2025.3540919"],"source":"https://dblp.org/rec/journals/tbbis/LiYSD25","documentPage":"https://doi.org/10.1109/TBIOM.2025.3540919","type":"Article","doi":"https://doi.org/10.1109/TBIOM.2025.3540919","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/tbbis/LiYSD25","documentUrl":"https://doi.org/10.1109/TBIOM.2025.3540919"},{"key":"journals/tcsv/SunWFYJLZHM25","title":"Multiple Pedestrian Tracking Under Occlusion: A Survey and Outlook.","year":2025,"yearOfEvent":null,"venue":"IEEE Trans. Circuits Syst. Video Technol.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1109/TCSVT.2024.3481425"],"source":"https://dblp.org/rec/journals/tcsv/SunWFYJLZHM25","documentPage":"https://doi.org/10.1109/TCSVT.2024.3481425","type":"Article","doi":"https://doi.org/10.1109/TCSVT.2024.3481425","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/tcsv/SunWFYJLZHM25","documentUrl":"https://doi.org/10.1109/TCSVT.2024.3481425"},{"key":"journals/tifs/ChenYHD25","title":"Towards Effective Rotation Generalization in UAV Object Re-Identification.","year":2025,"yearOfEvent":null,"venue":"IEEE Trans. Inf. Forensics Secur.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1109/TIFS.2025.3544088"],"source":"https://dblp.org/rec/journals/tifs/ChenYHD25","documentPage":"https://doi.org/10.1109/TIFS.2025.3544088","type":"Article","doi":"https://doi.org/10.1109/TIFS.2025.3544088","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/tifs/ChenYHD25","documentUrl":"https://doi.org/10.1109/TIFS.2025.3544088"},{"key":"journals/tifs/FangCSLZHYX25","title":"A Blockchain-Based Secure and Fair Online Incentive Mechanism for Crowdsensed Data Trading.","year":2025,"yearOfEvent":null,"venue":"IEEE Trans. Inf. Forensics Secur.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1109/TIFS.2025.3607256"],"source":"https://dblp.org/rec/journals/tifs/FangCSLZHYX25","documentPage":"https://doi.org/10.1109/TIFS.2025.3607256","type":"Article","doi":"https://doi.org/10.1109/TIFS.2025.3607256","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/tifs/FangCSLZHYX25","documentUrl":"https://doi.org/10.1109/TIFS.2025.3607256"},{"key":"journals/tifs/HuangYSLD25","title":"Kindle Federated Generalization With Domain Specialized and Invariant Knowledge.","year":2025,"yearOfEvent":null,"venue":"IEEE Trans. Inf. Forensics Secur.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1109/TIFS.2025.3550071"],"source":"https://dblp.org/rec/journals/tifs/HuangYSLD25","documentPage":"https://doi.org/10.1109/TIFS.2025.3550071","type":"Article","doi":"https://doi.org/10.1109/TIFS.2025.3550071","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/tifs/HuangYSLD25","documentUrl":"https://doi.org/10.1109/TIFS.2025.3550071"},{"key":"journals/tifs/YouCFLJY25","title":"Diverse Co-Saliency Feature Learning for Text-Based Person Retrieval.","year":2025,"yearOfEvent":null,"venue":"IEEE Trans. Inf. Forensics Secur.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1109/TIFS.2025.3573185"],"source":"https://dblp.org/rec/journals/tifs/YouCFLJY25","documentPage":"https://doi.org/10.1109/TIFS.2025.3573185","type":"Article","doi":"https://doi.org/10.1109/TIFS.2025.3573185","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/tifs/YouCFLJY25","documentUrl":"https://doi.org/10.1109/TIFS.2025.3573185"},{"key":"journals/tifs/ZhuZHWLY25","title":"Detecting Deceptive Behavior via Learning Relation-Aware Visual Representations.","year":2025,"yearOfEvent":null,"venue":"IEEE Trans. Inf. Forensics Secur.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1109/TIFS.2025.3586468"],"source":"https://dblp.org/rec/journals/tifs/ZhuZHWLY25","documentPage":"https://doi.org/10.1109/TIFS.2025.3586468","type":"Article","doi":"https://doi.org/10.1109/TIFS.2025.3586468","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/tifs/ZhuZHWLY25","documentUrl":"https://doi.org/10.1109/TIFS.2025.3586468"},{"key":"journals/tip/ChenYDD25","title":"Perception Assisted Transformer for Unsupervised Object Re-Identification.","year":2025,"yearOfEvent":null,"venue":"IEEE Trans. Image Process.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1109/TIP.2025.3553777"],"source":"https://dblp.org/rec/journals/tip/ChenYDD25","documentPage":"https://doi.org/10.1109/TIP.2025.3553777","type":"Article","doi":"https://doi.org/10.1109/TIP.2025.3553777","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/tip/ChenYDD25","documentUrl":"https://doi.org/10.1109/TIP.2025.3553777"},{"key":"journals/tip/GaoBCDYZ25","title":"Semi-Supervised Text-Based Person Search.","year":2025,"yearOfEvent":null,"venue":"IEEE Trans. Image Process.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1109/TIP.2025.3607637"],"source":"https://dblp.org/rec/journals/tip/GaoBCDYZ25","documentPage":"https://doi.org/10.1109/TIP.2025.3607637","type":"Article","doi":"https://doi.org/10.1109/TIP.2025.3607637","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/tip/GaoBCDYZ25","documentUrl":"https://doi.org/10.1109/TIP.2025.3607637"},{"key":"journals/tip/ShiYHDZ25","title":"Gradient and Structure Consistency in Multimodal Emotion Recognition.","year":2025,"yearOfEvent":null,"venue":"IEEE Trans. Image Process.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1109/TIP.2025.3608664"],"source":"https://dblp.org/rec/journals/tip/ShiYHDZ25","documentPage":"https://doi.org/10.1109/TIP.2025.3608664","type":"Article","doi":"https://doi.org/10.1109/TIP.2025.3608664","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/tip/ShiYHDZ25","documentUrl":"https://doi.org/10.1109/TIP.2025.3608664"},{"key":"journals/titb/HuYWSKY25","title":"MLDA-Net: Multi-Level Deep Aggregation Network for 3D Nuclei Instance Segmentation.","year":2025,"yearOfEvent":null,"venue":"IEEE J. Biomed. Health Informatics","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1109/JBHI.2025.3529464"],"source":"https://dblp.org/rec/journals/titb/HuYWSKY25","documentPage":"https://doi.org/10.1109/JBHI.2025.3529464","type":"Article","doi":"https://doi.org/10.1109/JBHI.2025.3529464","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/titb/HuYWSKY25","documentUrl":"https://doi.org/10.1109/JBHI.2025.3529464"},{"key":"journals/tmc/FangY25","title":"Noise-Robust Federated Learning With Model Heterogeneous Clients.","year":2025,"yearOfEvent":null,"venue":"IEEE Trans. Mob. Comput.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1109/TMC.2024.3522573"],"source":"https://dblp.org/rec/journals/tmc/FangY25","documentPage":"https://doi.org/10.1109/TMC.2024.3522573","type":"Article","doi":"https://doi.org/10.1109/TMC.2024.3522573","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/tmc/FangY25","documentUrl":"https://doi.org/10.1109/TMC.2024.3522573"},{"key":"journals/tmc/ShenYYY25","title":"Build Yourself Before Collaboration: Vertical Federated Learning With Limited Aligned Samples.","year":2025,"yearOfEvent":null,"venue":"IEEE Trans. Mob. Comput.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1109/TMC.2025.3543923"],"source":"https://dblp.org/rec/journals/tmc/ShenYYY25","documentPage":"https://doi.org/10.1109/TMC.2025.3543923","type":"Article","doi":"https://doi.org/10.1109/TMC.2025.3543923","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/tmc/ShenYYY25","documentUrl":"https://doi.org/10.1109/TMC.2025.3543923"},{"key":"journals/tmi/WenYLCX25","title":"Concept-Based Lesion Aware Transformer for Interpretable Retinal Disease Diagnosis.","year":2025,"yearOfEvent":null,"venue":"IEEE Trans. Medical Imaging","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1109/TMI.2024.3429148"],"source":"https://dblp.org/rec/journals/tmi/WenYLCX25","documentPage":"https://doi.org/10.1109/TMI.2024.3429148","type":"Article","doi":"https://doi.org/10.1109/TMI.2024.3429148","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/tmi/WenYLCX25","documentUrl":"https://doi.org/10.1109/TMI.2024.3429148"},{"key":"journals/tnn/PangWYCZHW25","title":"Heterogeneous Prototype Learning From Contaminated Faces Across Domains via Disentangling Latent Factors.","year":2025,"yearOfEvent":null,"venue":"IEEE Trans. Neural Networks Learn. Syst.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1109/TNNLS.2024.3393072"],"source":"https://dblp.org/rec/journals/tnn/PangWYCZHW25","documentPage":"https://doi.org/10.1109/TNNLS.2024.3393072","type":"Article","doi":"https://doi.org/10.1109/TNNLS.2024.3393072","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/tnn/PangWYCZHW25","documentUrl":"https://doi.org/10.1109/TNNLS.2024.3393072"},{"key":"journals/visintelligence/XuWGCYL25","title":"Efficient text-to-video retrieval via multi-modal multi-tagger derived pre-screening.","year":2025,"yearOfEvent":null,"venue":"Vis. Intell.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1007/S44267-025-00073-2"],"source":"https://dblp.org/rec/journals/visintelligence/XuWGCYL25","documentPage":"https://doi.org/10.1007/S44267-025-00073-2","type":"Article","doi":"https://doi.org/10.1007/S44267-025-00073-2","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/visintelligence/XuWGCYL25","documentUrl":"https://doi.org/10.1007/S44267-025-00073-2"}],"preprints":[{"key":"journals/corr/abs-2502-14881","title":"A Survey of Safety on Large Vision-Language Models: Attacks, Defenses and Evaluations.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2502.14881"],"source":"https://dblp.org/rec/journals/corr/abs-2502-14881","documentPage":"https://doi.org/10.48550/ARXIV.2502.14881","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2502.14881","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2502-14881","documentUrl":"https://doi.org/10.48550/ARXIV.2502.14881","arxivId":"2502.14881","arxivUrl":"https://arxiv.org/abs/2502.14881"},{"key":"journals/corr/abs-2503-04229","title":"Synthetic Data is an Elegant GIFT for Continual Vision-Language Models.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2503.04229"],"source":"https://dblp.org/rec/journals/corr/abs-2503-04229","documentPage":"https://doi.org/10.48550/ARXIV.2503.04229","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2503.04229","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-04229","documentUrl":"https://doi.org/10.48550/ARXIV.2503.04229","arxivId":"2503.04229","arxivUrl":"https://arxiv.org/abs/2503.04229"},{"key":"journals/corr/abs-2503-04543","title":"Keeping Yourself is Important in Downstream Tuning Multimodal Large Language Model.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2503.04543"],"source":"https://dblp.org/rec/journals/corr/abs-2503-04543","documentPage":"https://doi.org/10.48550/ARXIV.2503.04543","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2503.04543","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-04543","documentUrl":"https://doi.org/10.48550/ARXIV.2503.04543","arxivId":"2503.04543","arxivUrl":"https://arxiv.org/abs/2503.04543"},{"key":"journals/corr/abs-2503-08175","title":"Privacy-Enhancing Paradigms within Federated Multi-Agent Systems.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2503.08175"],"source":"https://dblp.org/rec/journals/corr/abs-2503-08175","documentPage":"https://doi.org/10.48550/ARXIV.2503.08175","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2503.08175","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-08175","documentUrl":"https://doi.org/10.48550/ARXIV.2503.08175","arxivId":"2503.08175","arxivUrl":"https://arxiv.org/abs/2503.08175"},{"key":"journals/corr/abs-2503-09206","title":"Robust Asymmetric Heterogeneous Federated Learning with Corrupted Clients.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2503.09206"],"source":"https://dblp.org/rec/journals/corr/abs-2503-09206","documentPage":"https://doi.org/10.48550/ARXIV.2503.09206","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2503.09206","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-09206","documentUrl":"https://doi.org/10.48550/ARXIV.2503.09206","arxivId":"2503.09206","arxivUrl":"https://arxiv.org/abs/2503.09206"},{"key":"journals/corr/abs-2503-16843","title":"LoRASculpt: Sculpting LoRA for Harmonizing General and Specialized Knowledge in Multimodal Large Language Models.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2503.16843"],"source":"https://dblp.org/rec/journals/corr/abs-2503-16843","documentPage":"https://doi.org/10.48550/ARXIV.2503.16843","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2503.16843","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-16843","documentUrl":"https://doi.org/10.48550/ARXIV.2503.16843","arxivId":"2503.16843","arxivUrl":"https://arxiv.org/abs/2503.16843"},{"key":"journals/corr/abs-2503-22171","title":"An Empirical Study of Validating Synthetic Data for Text-Based Person Retrieval.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2503.22171"],"source":"https://dblp.org/rec/journals/corr/abs-2503-22171","documentPage":"https://doi.org/10.48550/ARXIV.2503.22171","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2503.22171","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-22171","documentUrl":"https://doi.org/10.48550/ARXIV.2503.22171","arxivId":"2503.22171","arxivUrl":"https://arxiv.org/abs/2503.22171"},{"key":"journals/corr/abs-2504-00540","title":"Adversarial Curriculum Graph-Free Knowledge Distillation for Graph Neural Networks.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2504.00540"],"source":"https://dblp.org/rec/journals/corr/abs-2504-00540","documentPage":"https://doi.org/10.48550/ARXIV.2504.00540","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2504.00540","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2504-00540","documentUrl":"https://doi.org/10.48550/ARXIV.2504.00540","arxivId":"2504.00540","arxivUrl":"https://arxiv.org/abs/2504.00540"},{"key":"journals/corr/abs-2505-13408","title":"CoT-Kinetics: A Theoretical Modeling Assessing LRM Reasoning Process.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2505.13408"],"source":"https://dblp.org/rec/journals/corr/abs-2505-13408","documentPage":"https://doi.org/10.48550/ARXIV.2505.13408","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2505.13408","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-13408","documentUrl":"https://doi.org/10.48550/ARXIV.2505.13408","arxivId":"2505.13408","arxivUrl":"https://arxiv.org/abs/2505.13408"},{"key":"journals/corr/abs-2505-16916","title":"Backdoor Cleaning without External Guidance in MLLM Fine-tuning.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2505.16916"],"source":"https://dblp.org/rec/journals/corr/abs-2505-16916","documentPage":"https://doi.org/10.48550/ARXIV.2505.16916","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2505.16916","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-16916","documentUrl":"https://doi.org/10.48550/ARXIV.2505.16916","arxivId":"2505.16916","arxivUrl":"https://arxiv.org/abs/2505.16916"},{"key":"journals/corr/abs-2505-18640","title":"ThanoRA: Task Heterogeneity-Aware Multi-Task Low-Rank Adaptation.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2505.18640"],"source":"https://dblp.org/rec/journals/corr/abs-2505-18640","documentPage":"https://doi.org/10.48550/ARXIV.2505.18640","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2505.18640","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-18640","documentUrl":"https://doi.org/10.48550/ARXIV.2505.18640","arxivId":"2505.18640","arxivUrl":"https://arxiv.org/abs/2505.18640"},{"key":"journals/corr/abs-2505-23024","title":"An Empirical Study of Federated Prompt Learning for Vision Language Model.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2505.23024"],"source":"https://dblp.org/rec/journals/corr/abs-2505-23024","documentPage":"https://doi.org/10.48550/ARXIV.2505.23024","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2505.23024","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-23024","documentUrl":"https://doi.org/10.48550/ARXIV.2505.23024","arxivId":"2505.23024","arxivUrl":"https://arxiv.org/abs/2505.23024"},{"key":"journals/corr/abs-2506-03750","title":"A Retrieval-Augmented Multi-Agent Framework for Psychiatry Diagnosis.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2506.03750"],"source":"https://dblp.org/rec/journals/corr/abs-2506-03750","documentPage":"https://doi.org/10.48550/ARXIV.2506.03750","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2506.03750","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-03750","documentUrl":"https://doi.org/10.48550/ARXIV.2506.03750","arxivId":"2506.03750","arxivUrl":"https://arxiv.org/abs/2506.03750"},{"key":"journals/corr/abs-2507-02409","title":"S2FGL: Spatial Spectral Federated Graph Learning.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2507.02409"],"source":"https://dblp.org/rec/journals/corr/abs-2507-02409","documentPage":"https://doi.org/10.48550/ARXIV.2507.02409","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2507.02409","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2507-02409","documentUrl":"https://doi.org/10.48550/ARXIV.2507.02409","arxivId":"2507.02409","arxivUrl":"https://arxiv.org/abs/2507.02409"},{"key":"journals/corr/abs-2507-03402","title":"Pose-Star: Anatomy-Aware Editing for Open-World Fashion Images.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2507.03402"],"source":"https://dblp.org/rec/journals/corr/abs-2507-03402","documentPage":"https://doi.org/10.48550/ARXIV.2507.03402","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2507.03402","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2507-03402","documentUrl":"https://doi.org/10.48550/ARXIV.2507.03402","arxivId":"2507.03402","arxivUrl":"https://arxiv.org/abs/2507.03402"},{"key":"journals/corr/abs-2508-08789","title":"Never Compromise to Vulnerabilities: A Comprehensive Survey on AI Governance.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2508.08789"],"source":"https://dblp.org/rec/journals/corr/abs-2508-08789","documentPage":"https://doi.org/10.48550/ARXIV.2508.08789","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2508.08789","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-08789","documentUrl":"https://doi.org/10.48550/ARXIV.2508.08789","arxivId":"2508.08789","arxivUrl":"https://arxiv.org/abs/2508.08789"},{"key":"journals/corr/abs-2509-00540","title":"FedThief: Harming Others to Benefit Oneself in Self-Centered Federated Learning.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2509.00540"],"source":"https://dblp.org/rec/journals/corr/abs-2509-00540","documentPage":"https://doi.org/10.48550/ARXIV.2509.00540","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2509.00540","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-00540","documentUrl":"https://doi.org/10.48550/ARXIV.2509.00540","arxivId":"2509.00540","arxivUrl":"https://arxiv.org/abs/2509.00540"},{"key":"journals/corr/abs-2509-16635","title":"Towards Anytime Retrieval: A Benchmark for Anytime Person Re-Identification.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2509.16635"],"source":"https://dblp.org/rec/journals/corr/abs-2509-16635","documentPage":"https://doi.org/10.48550/ARXIV.2509.16635","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2509.16635","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-16635","documentUrl":"https://doi.org/10.48550/ARXIV.2509.16635","arxivId":"2509.16635","arxivUrl":"https://arxiv.org/abs/2509.16635"},{"key":"journals/corr/abs-2509-18849","title":"MAPO: Mixed Advantage Policy Optimization.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2509.18849"],"source":"https://dblp.org/rec/journals/corr/abs-2509-18849","documentPage":"https://doi.org/10.48550/ARXIV.2509.18849","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2509.18849","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-18849","documentUrl":"https://doi.org/10.48550/ARXIV.2509.18849","arxivId":"2509.18849","arxivUrl":"https://arxiv.org/abs/2509.18849"},{"key":"journals/corr/abs-2510-17685","title":"Multilingual Text-to-Image Person Retrieval via Bidirectional Relation Reasoning and Aligning.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2510.17685"],"source":"https://dblp.org/rec/journals/corr/abs-2510-17685","documentPage":"https://doi.org/10.48550/ARXIV.2510.17685","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2510.17685","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-17685","documentUrl":"https://doi.org/10.48550/ARXIV.2510.17685","arxivId":"2510.17685","arxivUrl":"https://arxiv.org/abs/2510.17685"},{"key":"journals/corr/abs-2511-08369","title":"Text-based Aerial-Ground Person Retrieval.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2511.08369"],"source":"https://dblp.org/rec/journals/corr/abs-2511-08369","documentPage":"https://doi.org/10.48550/ARXIV.2511.08369","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2511.08369","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2511-08369","documentUrl":"https://doi.org/10.48550/ARXIV.2511.08369","arxivId":"2511.08369","arxivUrl":"https://arxiv.org/abs/2511.08369"},{"key":"journals/corr/abs-2511-09141","title":"RGMP: Recurrent Geometric-prior Multimodal Policy for Generalizable Humanoid Robot Manipulation.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2511.09141"],"source":"https://dblp.org/rec/journals/corr/abs-2511-09141","documentPage":"https://doi.org/10.48550/ARXIV.2511.09141","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2511.09141","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2511-09141","documentUrl":"https://doi.org/10.48550/ARXIV.2511.09141","arxivId":"2511.09141","arxivUrl":"https://arxiv.org/abs/2511.09141"},{"key":"journals/corr/abs-2511-10945","title":"Divide, Conquer and Unite: Hierarchical Style-Recalibrated Prototype Alignment for Federated Medical Image Segmentation.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2511.10945"],"source":"https://dblp.org/rec/journals/corr/abs-2511-10945","documentPage":"https://doi.org/10.48550/ARXIV.2511.10945","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2511.10945","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2511-10945","documentUrl":"https://doi.org/10.48550/ARXIV.2511.10945","arxivId":"2511.10945","arxivUrl":"https://arxiv.org/abs/2511.10945"},{"key":"journals/corr/abs-2511-12982","title":"SafeGRPO: Self-Rewarded Multimodal Safety Alignment via Rule-Governed Policy Optimization.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2511.12982"],"source":"https://dblp.org/rec/journals/corr/abs-2511-12982","documentPage":"https://doi.org/10.48550/ARXIV.2511.12982","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2511.12982","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2511-12982","documentUrl":"https://doi.org/10.48550/ARXIV.2511.12982","arxivId":"2511.12982","arxivUrl":"https://arxiv.org/abs/2511.12982"},{"key":"journals/corr/abs-2512-03745","title":"Dual-level Modality Debiasing Learning for Unsupervised Visible-Infrared Person Re-Identification.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2512.03745"],"source":"https://dblp.org/rec/journals/corr/abs-2512-03745","documentPage":"https://doi.org/10.48550/ARXIV.2512.03745","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2512.03745","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-03745","documentUrl":"https://doi.org/10.48550/ARXIV.2512.03745","arxivId":"2512.03745","arxivUrl":"https://arxiv.org/abs/2512.03745"},{"key":"journals/corr/abs-2512-07216","title":"MUSE: A Simple Yet Effective Multimodal Search-Based Framework for Lifelong User Interest Modeling.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2512.07216"],"source":"https://dblp.org/rec/journals/corr/abs-2512-07216","documentPage":"https://doi.org/10.48550/ARXIV.2512.07216","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2512.07216","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-07216","documentUrl":"https://doi.org/10.48550/ARXIV.2512.07216","arxivId":"2512.07216","arxivUrl":"https://arxiv.org/abs/2512.07216"}],"excludedFormal":[],"excludedOther":[],"excludedHomonyms":[],"unassignedCandidates":[],"retrievedAt":"2026-10-19","querySource":"https://sparql.dblp.org/","method":"DBLP yearOfPublication=2025; Article + Inproceedings; excludes Informal/CoRR and explicit editorial/correction/erratum/preface; unique DBLP record keys within person.","labName":"Multimedia Analysis and ReaSoning（MARS）Group","labUrl":"https://marswhu.github.io/","labEvidence":"本人暨课题组主页明确写明 MARS Group 由 Prof. Mang Ye 领导；页脚也称 MARS Lab。","labSourceUrl":"https://marswhu.github.io/index.html","affiliationZh":"武汉大学","sourceWarning":false,"knownPreprintMinimum2025":null,"excludedMisattributed":[],"displayNotes":"身份已经个人或机构主页核对。2025 年正式记录 76 条（会议 47、期刊 29），所有作者位置均计入，不表示主导或贡献份额；预印本 26 条单列，不加总。","labDisplayNotes":"课题组主页写明 MARS Group 由其领导，页脚也称 MARS Lab，据此归组；它与上科大许岚、清华赵行的 MARS 是不同团队。分组只含本人参与的记录。"},{"index":103,"name":"Li Yi","nameZh":"弋力","affiliation":"Tsinghua University","source":"DBLP Knowledge Graph official SPARQL API","profileUrl":"https://dblp.org/pid/26/4239-1","identifier":"26/4239-1","identityEvidence":[{"url":"https://dblp.org/pid/26/4239-1","evidence":"DBLP curated profile affiliations: Stanford University, CA, USA; Tsinghua University, China."},{"url":"https://dblp.org/pid/26/4239-1","evidence":"DBLP curated profile homepages: https://ericyi.github.io/; https://openreview.net/profile?id=~Li_Yi2."}],"count2025":16,"conference2025":15,"journal2025":1,"preprint2025":14,"status":"verified","notes":"Counts are DBLP indexed coauthored records, not first-author counts, laboratory totals, unique scientific discoveries, or quality assessments. DBLP yearOfPublication=2025; yearOfEvent retained and can differ. Conference workshops are included. Preprints are separate and may overlap formal versions.","papers":[{"key":"conf/3dim/LiuLLZLYT25","title":"Gaussianavatar-Editor: Photorealistic Animatable Gaussian Head Avatar Editor.","year":2025,"yearOfEvent":2025,"venue":"3DV","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/3DV66043.2025.00108"],"source":"https://dblp.org/rec/conf/3dim/LiuLLZLYT25","documentPage":"https://doi.org/10.1109/3DV66043.2025.00108","type":"Inproceedings","doi":"https://doi.org/10.1109/3DV66043.2025.00108","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/3dim/LiuLLZLYT25","documentUrl":"https://doi.org/10.1109/3DV66043.2025.00108"},{"key":"conf/3dim/YiCY25","title":"Interactive Humanoid: Online Full Body Human Motion Reaction Synthesis with Social Affordance Forecasting and Canonicalization.","year":2025,"yearOfEvent":2025,"venue":"3DV","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/3DV66043.2025.00136"],"source":"https://dblp.org/rec/conf/3dim/YiCY25","documentPage":"https://doi.org/10.1109/3DV66043.2025.00136","type":"Inproceedings","doi":"https://doi.org/10.1109/3DV66043.2025.00136","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/3dim/YiCY25","documentUrl":"https://doi.org/10.1109/3DV66043.2025.00136"},{"key":"conf/cvpr/GaoPGZLDT0025","title":"PartRM: Modeling Part-Level Dynamics with Large Cross-State Reconstruction Model.","year":2025,"yearOfEvent":2025,"venue":"CVPR","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/CVPR52734.2025.00657"],"source":"https://dblp.org/rec/conf/cvpr/GaoPGZLDT0025","documentPage":"https://openaccess.thecvf.com/content/CVPR2025/html/Gao_PartRM_Modeling_Part-Level_Dynamics_with_Large_Cross-State_Reconstruction_Model_CVPR_2025_paper.html","type":"Inproceedings","doi":"https://doi.org/10.1109/CVPR52734.2025.00657","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/GaoPGZLDT0025","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Gao_PartRM_Modeling_Part-Level_Dynamics_with_Large_Cross-State_Reconstruction_Model_CVPR_2025_paper.html"},{"key":"conf/cvpr/LiLLDCY25","title":"Learning Physics-Based Full-Body Human Reaching and Grasping from Brief Walking References.","year":2025,"yearOfEvent":2025,"venue":"CVPR","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/CVPR52734.2025.02577"],"source":"https://dblp.org/rec/conf/cvpr/LiLLDCY25","documentPage":"https://openaccess.thecvf.com/content/CVPR2025/html/Li_Learning_Physics-Based_Full-Body_Human_Reaching_and_Grasping_from_Brief_Walking_CVPR_2025_paper.html","type":"Inproceedings","doi":"https://doi.org/10.1109/CVPR52734.2025.02577","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/LiLLDCY25","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Li_Learning_Physics-Based_Full-Body_Human_Reaching_and_Grasping_from_Brief_Walking_CVPR_2025_paper.html"},{"key":"conf/cvpr/Liu025","title":"MAP: Unleashing Hybrid Mamba-Transformer Vision Backbone's Potential with Masked Autoregressive Pretraining.","year":2025,"yearOfEvent":2025,"venue":"CVPR","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/CVPR52734.2025.00904"],"source":"https://dblp.org/rec/conf/cvpr/Liu025","documentPage":"https://openaccess.thecvf.com/content/CVPR2025/html/Liu_MAP_Unleashing_Hybrid_Mamba-Transformer_Vision_Backbones_Potential_with_Masked_Autoregressive_CVPR_2025_paper.html","type":"Inproceedings","doi":"https://doi.org/10.1109/CVPR52734.2025.00904","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/Liu025","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Liu_MAP_Unleashing_Hybrid_Mamba-Transformer_Vision_Backbones_Potential_with_Masked_Autoregressive_CVPR_2025_paper.html"},{"key":"conf/cvpr/LiuZXTYY25","title":"CORE4D: A 4D Human-Object-Human Interaction Dataset for Collaborative Object REarrangement.","year":2025,"yearOfEvent":2025,"venue":"CVPR","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/CVPR52734.2025.00172"],"source":"https://dblp.org/rec/conf/cvpr/LiuZXTYY25","documentPage":"https://openaccess.thecvf.com/content/CVPR2025/html/Liu_CORE4D_A_4D_Human-Object-Human_Interaction_Dataset_for_Collaborative_Object_REarrangement_CVPR_2025_paper.html","type":"Inproceedings","doi":"https://doi.org/10.1109/CVPR52734.2025.00172","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/LiuZXTYY25","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Liu_CORE4D_A_4D_Human-Object-Human_Interaction_Dataset_for_Collaborative_Object_REarrangement_CVPR_2025_paper.html"},{"key":"conf/cvpr/WangCC0YLLW025","title":"MobileH2R: Learning Generalizable Human to Mobile Robot Handover Exclusively from Scalable and Diverse Synthetic Data.","year":2025,"yearOfEvent":2025,"venue":"CVPR","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/CVPR52734.2025.01614"],"source":"https://dblp.org/rec/conf/cvpr/WangCC0YLLW025","documentPage":"https://openaccess.thecvf.com/content/CVPR2025/html/Wang_MobileH2R_Learning_Generalizable_Human_to_Mobile_Robot_Handover_Exclusively_from_CVPR_2025_paper.html","type":"Inproceedings","doi":"https://doi.org/10.1109/CVPR52734.2025.01614","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/WangCC0YLLW025","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Wang_MobileH2R_Learning_Generalizable_Human_to_Mobile_Robot_Handover_Exclusively_from_CVPR_2025_paper.html"},{"key":"conf/eccv/LiuLZDY24","title":"Parameterized Quasi-Physical Simulators for Dexterous Manipulations Transfer.","year":2025,"yearOfEvent":2024,"venue":"ECCV (78)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1007/978-3-031-73229-4_10"],"source":"https://dblp.org/rec/conf/eccv/LiuLZDY24","documentPage":"https://doi.org/10.1007/978-3-031-73229-4_10","type":"Inproceedings","doi":"https://doi.org/10.1007/978-3-031-73229-4_10","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/eccv/LiuLZDY24","documentUrl":"https://doi.org/10.1007/978-3-031-73229-4_10"},{"key":"conf/eccv/QiDZGHGYM24","title":"ShapeLLM: Universal 3D Object Understanding for Embodied Interaction.","year":2025,"yearOfEvent":2024,"venue":"ECCV (43)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1007/978-3-031-72775-7_13"],"source":"https://dblp.org/rec/conf/eccv/QiDZGHGYM24","documentPage":"https://doi.org/10.1007/978-3-031-72775-7_13","type":"Inproceedings","doi":"https://doi.org/10.1007/978-3-031-72775-7_13","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/eccv/QiDZGHGYM24","documentUrl":"https://doi.org/10.1007/978-3-031-72775-7_13"},{"key":"conf/eccv/ZhangLHLY24","title":"FreeMotion: MoCap-Free Human Motion Synthesis with Multimodal Large Language Models.","year":2025,"yearOfEvent":2024,"venue":"ECCV (23)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1007/978-3-031-73337-6_23"],"source":"https://dblp.org/rec/conf/eccv/ZhangLHLY24","documentPage":"https://doi.org/10.1007/978-3-031-73337-6_23","type":"Inproceedings","doi":"https://doi.org/10.1007/978-3-031-73337-6_23","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/eccv/ZhangLHLY24","documentUrl":"https://doi.org/10.1007/978-3-031-73337-6_23"},{"key":"conf/iccv/HeLYQZCZZYW25","title":"DexVLG: Dexterous Vision-Language-Grasp Model at Scale.","year":2025,"yearOfEvent":2025,"venue":"ICCV","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/ICCV51701.2025.01322"],"source":"https://dblp.org/rec/conf/iccv/HeLYQZCZZYW25","documentPage":"https://doi.org/10.1109/ICCV51701.2025.01322","type":"Inproceedings","doi":"https://doi.org/10.1109/ICCV51701.2025.01322","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/HeLYQZCZZYW25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.01322"},{"key":"conf/iclr/LiuAHQ025","title":"DexTrack: Towards Generalizable Neural Tracking Control for Dexterous Manipulation from Human References.","year":2025,"yearOfEvent":2025,"venue":"ICLR","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/iclr/LiuAHQ025","documentPage":"https://openreview.net/forum?id=ajSmXqgS24","type":"Inproceedings","doi":null,"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iclr/LiuAHQ025","documentUrl":"https://openreview.net/forum?id=ajSmXqgS24"},{"key":"conf/iclr/WuZCTLFZXYY0025","title":"VILA-U: a Unified Foundation Model Integrating Visual Understanding and Generation.","year":2025,"yearOfEvent":2025,"venue":"ICLR","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/iclr/WuZCTLFZXYY0025","documentPage":"https://openreview.net/forum?id=02haSpO453","type":"Inproceedings","doi":null,"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iclr/WuZCTLFZXYY0025","documentUrl":"https://openreview.net/forum?id=02haSpO453"},{"key":"conf/nips/QiZDDYLXLHFZHGJ25","title":"SoFar: Language-Grounded Orientation Bridges Spatial Reasoning and Object Manipulation.","year":2025,"yearOfEvent":2025,"venue":"NeurIPS","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/nips/QiZDDYLXLHFZHGJ25","documentPage":"http://papers.nips.cc/paper_files/paper/2025/hash/6ea83df350753236215cbf2fe9716eca-Abstract-Conference.html","type":"Inproceedings","doi":null,"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/nips/QiZDDYLXLHFZHGJ25","documentUrl":"http://papers.nips.cc/paper_files/paper/2025/hash/6ea83df350753236215cbf2fe9716eca-Abstract-Conference.html"},{"key":"conf/nips/ZhangLQWYZDHWZY25","title":"DreamVLA: A Vision-Language-Action Model Dreamed with Comprehensive World Knowledge.","year":2025,"yearOfEvent":2025,"venue":"NeurIPS","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/nips/ZhangLQWYZDHWZY25","documentPage":"http://papers.nips.cc/paper_files/paper/2025/hash/22d4f952efa13970f0b1ffb22170d416-Abstract-Conference.html","type":"Inproceedings","doi":null,"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/nips/ZhangLQWYZDHWZY25","documentUrl":"http://papers.nips.cc/paper_files/paper/2025/hash/22d4f952efa13970f0b1ffb22170d416-Abstract-Conference.html"},{"key":"journals/tvcg/ShiTYLYZ25","title":"Articulated Motion-Aware NeRF for 3D Dynamic Appearance and Geometry Reconstruction by Implicit Motion States.","year":2025,"yearOfEvent":null,"venue":"IEEE Trans. Vis. Comput. Graph.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1109/TVCG.2024.3400830"],"source":"https://dblp.org/rec/journals/tvcg/ShiTYLYZ25","documentPage":"https://doi.org/10.1109/TVCG.2024.3400830","type":"Article","doi":"https://doi.org/10.1109/TVCG.2024.3400830","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/tvcg/ShiTYLYZ25","documentUrl":"https://doi.org/10.1109/TVCG.2024.3400830"}],"preprints":[{"key":"journals/corr/abs-2501-04595","title":"MobileH2R: Learning Generalizable Human to Mobile Robot Handover Exclusively from Scalable and Diverse Synthetic Data.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2501.04595"],"source":"https://dblp.org/rec/journals/corr/abs-2501-04595","documentPage":"https://doi.org/10.48550/ARXIV.2501.04595","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2501.04595","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2501-04595","documentUrl":"https://doi.org/10.48550/ARXIV.2501.04595","arxivId":"2501.04595","arxivUrl":"https://arxiv.org/abs/2501.04595"},{"key":"journals/corr/abs-2501-09978","title":"GaussianAvatar-Editor: Photorealistic Animatable Gaussian Head Avatar Editor.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2501.09978"],"source":"https://dblp.org/rec/journals/corr/abs-2501-09978","documentPage":"https://doi.org/10.48550/ARXIV.2501.09978","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2501.09978","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2501-09978","documentUrl":"https://doi.org/10.48550/ARXIV.2501.09978","arxivId":"2501.09978","arxivUrl":"https://arxiv.org/abs/2501.09978"},{"key":"journals/corr/abs-2502-09614","title":"DexTrack: Towards Generalizable Neural Tracking Control for Dexterous Manipulation from Human References.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2502.09614"],"source":"https://dblp.org/rec/journals/corr/abs-2502-09614","documentPage":"https://doi.org/10.48550/ARXIV.2502.09614","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2502.09614","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2502-09614","documentUrl":"https://doi.org/10.48550/ARXIV.2502.09614","arxivId":"2502.09614","arxivUrl":"https://arxiv.org/abs/2502.09614"},{"key":"journals/corr/abs-2502-13143","title":"SoFar: Language-Grounded Orientation Bridges Spatial Reasoning and Object Manipulation.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2502.13143"],"source":"https://dblp.org/rec/journals/corr/abs-2502-13143","documentPage":"https://doi.org/10.48550/ARXIV.2502.13143","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2502.13143","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2502-13143","documentUrl":"https://doi.org/10.48550/ARXIV.2502.13143","arxivId":"2502.13143","arxivUrl":"https://arxiv.org/abs/2502.13143"},{"key":"journals/corr/abs-2503-07481","title":"Learning Physics-Based Full-Body Human Reaching and Grasping from Brief Walking References.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2503.07481"],"source":"https://dblp.org/rec/journals/corr/abs-2503-07481","documentPage":"https://doi.org/10.48550/ARXIV.2503.07481","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2503.07481","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-07481","documentUrl":"https://doi.org/10.48550/ARXIV.2503.07481","arxivId":"2503.07481","arxivUrl":"https://arxiv.org/abs/2503.07481"},{"key":"journals/corr/abs-2503-12332","title":"VideoMAP: Toward Scalable Mamba-based Video Autoregressive Pretraining.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2503.12332"],"source":"https://dblp.org/rec/journals/corr/abs-2503-12332","documentPage":"https://doi.org/10.48550/ARXIV.2503.12332","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2503.12332","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-12332","documentUrl":"https://doi.org/10.48550/ARXIV.2503.12332","arxivId":"2503.12332","arxivUrl":"https://arxiv.org/abs/2503.12332"},{"key":"journals/corr/abs-2503-19913","title":"PartRM: Modeling Part-Level Dynamics with Large Cross-State Reconstruction Model.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2503.19913"],"source":"https://dblp.org/rec/journals/corr/abs-2503-19913","documentPage":"https://doi.org/10.48550/ARXIV.2503.19913","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2503.19913","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-19913","documentUrl":"https://doi.org/10.48550/ARXIV.2503.19913","arxivId":"2503.19913","arxivUrl":"https://arxiv.org/abs/2503.19913"},{"key":"journals/corr/abs-2503-20784","title":"FB-4D: Spatial-Temporal Coherent Dynamic 3D Content Generation with Feature Banks.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2503.20784"],"source":"https://dblp.org/rec/journals/corr/abs-2503-20784","documentPage":"https://doi.org/10.48550/ARXIV.2503.20784","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2503.20784","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-20784","documentUrl":"https://doi.org/10.48550/ARXIV.2503.20784","arxivId":"2503.20784","arxivUrl":"https://arxiv.org/abs/2503.20784"},{"key":"journals/corr/abs-2505-10918","title":"Unleashing Humanoid Reaching Potential via Real-world-Ready Skill Space.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2505.10918"],"source":"https://dblp.org/rec/journals/corr/abs-2505-10918","documentPage":"https://doi.org/10.48550/ARXIV.2505.10918","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2505.10918","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-10918","documentUrl":"https://doi.org/10.48550/ARXIV.2505.10918","arxivId":"2505.10918","arxivUrl":"https://arxiv.org/abs/2505.10918"},{"key":"journals/corr/abs-2506-03135","title":"OmniSpatial: Towards Comprehensive Spatial Reasoning Benchmark for Vision Language Models.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2506.03135"],"source":"https://dblp.org/rec/journals/corr/abs-2506-03135","documentPage":"https://doi.org/10.48550/ARXIV.2506.03135","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2506.03135","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-03135","documentUrl":"https://doi.org/10.48550/ARXIV.2506.03135","arxivId":"2506.03135","arxivUrl":"https://arxiv.org/abs/2506.03135"},{"key":"journals/corr/abs-2507-02747","title":"DexVLG: Dexterous Vision-Language-Grasp Model at Scale.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2507.02747"],"source":"https://dblp.org/rec/journals/corr/abs-2507-02747","documentPage":"https://doi.org/10.48550/ARXIV.2507.02747","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2507.02747","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2507-02747","documentUrl":"https://doi.org/10.48550/ARXIV.2507.02747","arxivId":"2507.02747","arxivUrl":"https://arxiv.org/abs/2507.02747"},{"key":"journals/corr/abs-2507-04447","title":"DreamVLA: A Vision-Language-Action Model Dreamed with Comprehensive World Knowledge.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2507.04447"],"source":"https://dblp.org/rec/journals/corr/abs-2507-04447","documentPage":"https://doi.org/10.48550/ARXIV.2507.04447","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2507.04447","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2507-04447","documentUrl":"https://doi.org/10.48550/ARXIV.2507.04447","arxivId":"2507.04447","arxivUrl":"https://arxiv.org/abs/2507.04447"},{"key":"journals/corr/abs-2509-13833","title":"Track Any Motions under Any Disturbances.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2509.13833"],"source":"https://dblp.org/rec/journals/corr/abs-2509-13833","documentPage":"https://doi.org/10.48550/ARXIV.2509.13833","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2509.13833","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-13833","documentUrl":"https://doi.org/10.48550/ARXIV.2509.13833","arxivId":"2509.13833","arxivUrl":"https://arxiv.org/abs/2509.13833"},{"key":"journals/corr/abs-2509-17759","title":"MotionTrans: Human VR Data Enable Motion-Level Learning for Robotic Manipulation Policies.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2509.17759"],"source":"https://dblp.org/rec/journals/corr/abs-2509-17759","documentPage":"https://doi.org/10.48550/ARXIV.2509.17759","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2509.17759","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-17759","documentUrl":"https://doi.org/10.48550/ARXIV.2509.17759","arxivId":"2509.17759","arxivUrl":"https://arxiv.org/abs/2509.17759"}],"excludedFormal":[],"excludedOther":[],"excludedHomonyms":[],"unassignedCandidates":[],"retrievedAt":"2026-10-19","querySource":"https://sparql.dblp.org/","method":"DBLP yearOfPublication=2025; Article + Inproceedings; excludes Informal/CoRR and explicit editorial/correction/erratum/preface; unique DBLP record keys within person.","labName":null,"labUrl":null,"labEvidence":"本人主页未出现明确命名Lab；学生主页检索有3DVICI线索，但本轮未取得本人或机构页面明确关联，按本任务标准留空。","labSourceUrl":"https://ericyi.github.io/","affiliationZh":"清华大学","sourceWarning":false,"knownPreprintMinimum2025":null,"excludedMisattributed":[],"displayNotes":"身份已经个人或机构主页核对。2025 年正式记录 16 条（会议 15、期刊 1），所有作者位置均计入，不表示主导或贡献份额；预印本 14 条单列，不加总。","labDisplayNotes":"本人主页未见当前实验室专名；学生主页出现 3DVICI 的线索，但没有本人或机构页面的明确表述，暂不采用。图中以「姓名及合作者」单列。"},{"index":104,"name":"Yang Yu","nameZh":"俞扬","affiliation":"Nanjing University","source":"DBLP Knowledge Graph official SPARQL API","profileUrl":"https://dblp.org/pid/46/2181-1","identifier":"46/2181-1","identityEvidence":[{"url":"https://dblp.org/pid/46/2181-1","evidence":"DBLP curated profile affiliations: Nanjing University, State Key Laboratory for Novel Software Technology, China; Pazhou Lab, Guangzhou, China."},{"url":"https://dblp.org/pid/46/2181-1","evidence":"DBLP curated profile homepages: http://www.lamda.nju.edu.cn/yuy/default.aspx; https://openreview.net/profile?id=~Yang_Yu5; https://www.wolai.com/eyounx/dtR1MTyRXS5tP5Cex4KtdK."}],"count2025":29,"conference2025":16,"journal2025":13,"preprint2025":10,"status":"verified","notes":"Counts are DBLP indexed coauthored records, not first-author counts, laboratory totals, unique scientific discoveries, or quality assessments. DBLP yearOfPublication=2025; yearOfEvent retained and can differ. Conference workshops are included. Preprints are separate and may overlap formal versions.","papers":[{"key":"conf/iclr/0001BLZG025","title":"Efficient Multi-agent Offline Coordination via Diffusion-based Trajectory Stitching.","year":2025,"yearOfEvent":2025,"venue":"ICLR","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/iclr/0001BLZG025","documentPage":"https://openreview.net/forum?id=EpnZEzYDUT","type":"Inproceedings","doi":null,"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iclr/0001BLZG025","documentUrl":"https://openreview.net/forum?id=EpnZEzYDUT"},{"key":"conf/iclr/0001Z00JZ0A25","title":"Q-Adapter: Customizing Pre-trained LLMs to New Preferences with Forgetting Mitigation.","year":2025,"yearOfEvent":2025,"venue":"ICLR","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/iclr/0001Z00JZ0A25","documentPage":"https://openreview.net/forum?id=WLSrq1254E","type":"Inproceedings","doi":null,"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iclr/0001Z00JZ0A25","documentUrl":"https://openreview.net/forum?id=WLSrq1254E"},{"key":"conf/iclr/LinXSZ0JYZ025","title":"Any-step Dynamics Model Improves Future Predictions for Online and Offline Reinforcement Learning.","year":2025,"yearOfEvent":2025,"venue":"ICLR","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/iclr/LinXSZ0JYZ025","documentPage":"https://openreview.net/forum?id=JZCxlrwjZ8","type":"Inproceedings","doi":null,"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iclr/LinXSZ0JYZ025","documentUrl":"https://openreview.net/forum?id=JZCxlrwjZ8"},{"key":"conf/iclr/Liu00025","title":"On the Optimization Landscape of Low Rank Adaptation Methods for Large Language Models.","year":2025,"yearOfEvent":2025,"venue":"ICLR","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/iclr/Liu00025","documentPage":"https://openreview.net/forum?id=pxclAomHat","type":"Inproceedings","doi":null,"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iclr/Liu00025","documentUrl":"https://openreview.net/forum?id=pxclAomHat"},{"key":"conf/iclr/LiuL0JWZ025","title":"Semantic Temporal Abstraction via Vision-Language Model Guidance for Efficient Reinforcement Learning.","year":2025,"yearOfEvent":2025,"venue":"ICLR","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/iclr/LiuL0JWZ025","documentPage":"https://openreview.net/forum?id=zY37C8d6bS","type":"Inproceedings","doi":null,"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iclr/LiuL0JWZ025","documentUrl":"https://openreview.net/forum?id=zY37C8d6bS"},{"key":"conf/iclr/PangTLTCZ0S025","title":"Learning View-invariant World Models for Visual Robotic Manipulation.","year":2025,"yearOfEvent":2025,"venue":"ICLR","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/iclr/PangTLTCZ0S025","documentPage":"https://openreview.net/forum?id=vJwjWyt4Ed","type":"Inproceedings","doi":null,"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iclr/PangTLTCZ0S025","documentUrl":"https://openreview.net/forum?id=vJwjWyt4Ed"},{"key":"conf/iclr/QianZSLWALZ0Y25","title":"SOO-Bench: Benchmarks for Evaluating the Stability of Offline Black-Box Optimization.","year":2025,"yearOfEvent":2025,"venue":"ICLR","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/iclr/QianZSLWALZ0Y25","documentPage":"https://openreview.net/forum?id=bqf0aCF3Dd","type":"Inproceedings","doi":null,"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iclr/QianZSLWALZ0Y25","documentUrl":"https://openreview.net/forum?id=bqf0aCF3Dd"},{"key":"conf/icml/Gao0CX0Z25","title":"Behavior-Regularized Diffusion Policy Optimization for Offline Reinforcement Learning.","year":2025,"yearOfEvent":2025,"venue":"ICML","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/icml/Gao0CX0Z25","documentPage":"https://proceedings.mlr.press/v267/gao25q.html","type":"Inproceedings","doi":null,"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/icml/Gao0CX0Z25","documentUrl":"https://proceedings.mlr.press/v267/gao25q.html"},{"key":"conf/icml/JiaLW0HD025","title":"Controlling Large Language Model with Latent Action.","year":2025,"yearOfEvent":2025,"venue":"ICML","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/icml/JiaLW0HD025","documentPage":"https://proceedings.mlr.press/v267/jia25e.html","type":"Inproceedings","doi":null,"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/icml/JiaLW0HD025","documentUrl":"https://proceedings.mlr.press/v267/jia25e.html"},{"key":"conf/icml/Li0LJ025","title":"LLM-Assisted Semantically Diverse Teammate Generation for Efficient Multi-agent Coordination.","year":2025,"yearOfEvent":2025,"venue":"ICML","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/icml/Li0LJ025","documentPage":"https://proceedings.mlr.press/v267/li25dq.html","type":"Inproceedings","doi":null,"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/icml/Li0LJ025","documentUrl":"https://proceedings.mlr.press/v267/li25dq.html"},{"key":"conf/icml/Zhang0DCS025","title":"Improving Reward Model Generalization from Adversarial Process Enhanced Preferences.","year":2025,"yearOfEvent":2025,"venue":"ICML","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/icml/Zhang0DCS025","documentPage":"https://proceedings.mlr.press/v267/zhang25ci.html","type":"Inproceedings","doi":null,"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/icml/Zhang0DCS025","documentUrl":"https://proceedings.mlr.press/v267/zhang25ci.html"},{"key":"conf/icml/ZhangYLBX000025","title":"Learning to Reuse Policies in State Evolvable Environments.","year":2025,"yearOfEvent":2025,"venue":"ICML","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/icml/ZhangYLBX000025","documentPage":"https://proceedings.mlr.press/v267/zhang25ck.html","type":"Inproceedings","doi":null,"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/icml/ZhangYLBX000025","documentUrl":"https://proceedings.mlr.press/v267/zhang25ck.html"},{"key":"conf/nips/LiLJZWYZY25","title":"Multi-Agent Imitation by Learning and Sampling from Factorized Soft Q-Function.","year":2025,"yearOfEvent":2025,"venue":"NeurIPS","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/nips/LiLJZWYZY25","documentPage":"http://papers.nips.cc/paper_files/paper/2025/hash/13a6f537e943a598b8719b03181a8e2a-Abstract-Conference.html","type":"Inproceedings","doi":null,"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/nips/LiLJZWYZY25","documentUrl":"http://papers.nips.cc/paper_files/paper/2025/hash/13a6f537e943a598b8719b03181a8e2a-Abstract-Conference.html"},{"key":"conf/nips/LuoYY25","title":"Uncertainty-Sensitive Privileged Learning.","year":2025,"yearOfEvent":2025,"venue":"NeurIPS","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/nips/LuoYY25","documentPage":"http://papers.nips.cc/paper_files/paper/2025/hash/724711fccb09d4519cbbb6d245d3675d-Abstract-Conference.html","type":"Inproceedings","doi":null,"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/nips/LuoYY25","documentUrl":"http://papers.nips.cc/paper_files/paper/2025/hash/724711fccb09d4519cbbb6d245d3675d-Abstract-Conference.html"},{"key":"conf/nips/WangCXZY25","title":"Focus-Then-Reuse: Fast Adaptation in Visual Perturbation Environments.","year":2025,"yearOfEvent":2025,"venue":"NeurIPS","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/nips/WangCXZY25","documentPage":"http://papers.nips.cc/paper_files/paper/2025/hash/283defcb522d94ff20703f889c1f94ec-Abstract-Conference.html","type":"Inproceedings","doi":null,"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/nips/WangCXZY25","documentUrl":"http://papers.nips.cc/paper_files/paper/2025/hash/283defcb522d94ff20703f889c1f94ec-Abstract-Conference.html"},{"key":"conf/nips/XueZLGYY25","title":"Adaptable Safe Policy Learning from Multi-task Data with Constraint Prioritized Decision Transformer.","year":2025,"yearOfEvent":2025,"venue":"NeurIPS","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/nips/XueZLGYY25","documentPage":"http://papers.nips.cc/paper_files/paper/2025/hash/5dbe62f1fec0306cb9f9d0c4a458f93b-Abstract-Conference.html","type":"Inproceedings","doi":null,"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/nips/XueZLGYY25","documentUrl":"http://papers.nips.cc/paper_files/paper/2025/hash/5dbe62f1fec0306cb9f9d0c4a458f93b-Abstract-Conference.html"},{"key":"journals/fcsc/GuanXFCZYQY25","title":"Open and real-world human-AI coordination by heterogeneous training with communication.","year":2025,"yearOfEvent":null,"venue":"Frontiers Comput. Sci.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1007/S11704-024-3797-6"],"source":"https://dblp.org/rec/journals/fcsc/GuanXFCZYQY25","documentPage":"https://doi.org/10.1007/S11704-024-3797-6","type":"Article","doi":"https://doi.org/10.1007/S11704-024-3797-6","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/fcsc/GuanXFCZYQY25","documentUrl":"https://doi.org/10.1007/S11704-024-3797-6"},{"key":"journals/fcsc/ZhuTCZY25","title":"Offline model-based reinforcement learning with causal structured world models.","year":2025,"yearOfEvent":null,"venue":"Frontiers Comput. Sci.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1007/S11704-024-3946-Y"],"source":"https://dblp.org/rec/journals/fcsc/ZhuTCZY25","documentPage":"https://doi.org/10.1007/S11704-024-3946-Y","type":"Article","doi":"https://doi.org/10.1007/S11704-024-3946-Y","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/fcsc/ZhuTCZY25","documentUrl":"https://doi.org/10.1007/S11704-024-3946-Y"},{"key":"journals/nn/GuanJLZYY25","title":"Constraining an Unconstrained Multi-agent Policy with offline data.","year":2025,"yearOfEvent":null,"venue":"Neural Networks","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1016/J.NEUNET.2025.107253"],"source":"https://dblp.org/rec/journals/nn/GuanJLZYY25","documentPage":"https://doi.org/10.1016/J.NEUNET.2025.107253","type":"Article","doi":"https://doi.org/10.1016/J.NEUNET.2025.107253","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/nn/GuanJLZYY25","documentUrl":"https://doi.org/10.1016/J.NEUNET.2025.107253"},{"key":"journals/pami/LiCZZYY25","title":"Generalizable Multi-Modal Adversarial Imitation Learning for Non-Stationary Dynamics.","year":2025,"yearOfEvent":null,"venue":"IEEE Trans. Pattern Anal. Mach. Intell.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1109/TPAMI.2025.3552228"],"source":"https://dblp.org/rec/journals/pami/LiCZZYY25","documentPage":"https://doi.org/10.1109/TPAMI.2025.3552228","type":"Article","doi":"https://doi.org/10.1109/TPAMI.2025.3552228","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/pami/LiCZZYY25","documentUrl":"https://doi.org/10.1109/TPAMI.2025.3552228"},{"key":"journals/tec/XueWGYFFQY25","title":"Heterogeneous Multiagent Zero-Shot Coordination by Coevolution.","year":2025,"yearOfEvent":null,"venue":"IEEE Trans. Evol. Comput.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1109/TEVC.2024.3485177"],"source":"https://dblp.org/rec/journals/tec/XueWGYFFQY25","documentPage":"https://doi.org/10.1109/TEVC.2024.3485177","type":"Article","doi":"https://doi.org/10.1109/TEVC.2024.3485177","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/tec/XueWGYFFQY25","documentUrl":"https://doi.org/10.1109/TEVC.2024.3485177"},{"key":"journals/tmlr/0042CQG0Z025","title":"Efficient Multi-Agent Cooperation Learning through Teammate Lookahead.","year":2025,"yearOfEvent":null,"venue":"Trans. Mach. Learn. Res.","types":["https://dblp.org/rdf/schema#Article"],"dois":[],"source":"https://dblp.org/rec/journals/tmlr/0042CQG0Z025","documentPage":"https://openreview.net/forum?id=CeNNIQ8GJf","type":"Article","doi":null,"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/tmlr/0042CQG0Z025","documentUrl":"https://openreview.net/forum?id=CeNNIQ8GJf"},{"key":"journals/tmlr/PangFWXTYJXCHY25","title":"Interactive Large Language Models for Reliable Answering under Incomplete Context.","year":2025,"yearOfEvent":null,"venue":"Trans. Mach. Learn. Res.","types":["https://dblp.org/rdf/schema#Article"],"dois":[],"source":"https://dblp.org/rec/journals/tmlr/PangFWXTYJXCHY25","documentPage":"https://openreview.net/forum?id=nnlmcxYWlV","type":"Article","doi":null,"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/tmlr/PangFWXTYJXCHY25","documentUrl":"https://openreview.net/forum?id=nnlmcxYWlV"},{"key":"journals/tnn/DingJZGCYY25","title":"Learning to Coordinate With Different Teammates via Team Probing.","year":2025,"yearOfEvent":null,"venue":"IEEE Trans. Neural Networks Learn. Syst.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1109/TNNLS.2025.3563773"],"source":"https://dblp.org/rec/journals/tnn/DingJZGCYY25","documentPage":"https://doi.org/10.1109/TNNLS.2025.3563773","type":"Article","doi":"https://doi.org/10.1109/TNNLS.2025.3563773","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/tnn/DingJZGCYY25","documentUrl":"https://doi.org/10.1109/TNNLS.2025.3563773"},{"key":"journals/tnn/GuanCYZY25","title":"Efficient Communication via Self-Supervised Information Aggregation for Online and Offline Multiagent Reinforcement Learning.","year":2025,"yearOfEvent":null,"venue":"IEEE Trans. Neural Networks Learn. Syst.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1109/TNNLS.2024.3420791"],"source":"https://dblp.org/rec/journals/tnn/GuanCYZY25","documentPage":"https://doi.org/10.1109/TNNLS.2024.3420791","type":"Article","doi":"https://doi.org/10.1109/TNNLS.2024.3420791","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/tnn/GuanCYZY25","documentUrl":"https://doi.org/10.1109/TNNLS.2024.3420791"},{"key":"journals/tnn/PangXJLY25","title":"Reinforcement Learning With Sparse-Executing Action via Sparsity Regularization.","year":2025,"yearOfEvent":null,"venue":"IEEE Trans. Neural Networks Learn. Syst.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1109/TNNLS.2025.3555314"],"source":"https://dblp.org/rec/journals/tnn/PangXJLY25","documentPage":"https://doi.org/10.1109/TNNLS.2025.3555314","type":"Article","doi":"https://doi.org/10.1109/TNNLS.2025.3555314","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/tnn/PangXJLY25","documentUrl":"https://doi.org/10.1109/TNNLS.2025.3555314"},{"key":"journals/tnn/XiaoYLZLY25","title":"Generalizable Offline Multiobjective Reinforcement Learning via Preference-Conditioned Diffuser.","year":2025,"yearOfEvent":null,"venue":"IEEE Trans. Neural Networks Learn. Syst.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1109/TNNLS.2025.3591838"],"source":"https://dblp.org/rec/journals/tnn/XiaoYLZLY25","documentPage":"https://doi.org/10.1109/TNNLS.2025.3591838","type":"Article","doi":"https://doi.org/10.1109/TNNLS.2025.3591838","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/tnn/XiaoYLZLY25","documentUrl":"https://doi.org/10.1109/TNNLS.2025.3591838"},{"key":"journals/tnn/YuanLZZGY25","title":"Multiagent Continual Coordination via Progressive Task Contextualization.","year":2025,"yearOfEvent":null,"venue":"IEEE Trans. Neural Networks Learn. Syst.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1109/TNNLS.2024.3394513"],"source":"https://dblp.org/rec/journals/tnn/YuanLZZGY25","documentPage":"https://doi.org/10.1109/TNNLS.2024.3394513","type":"Article","doi":"https://doi.org/10.1109/TNNLS.2024.3394513","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/tnn/YuanLZZGY25","documentUrl":"https://doi.org/10.1109/TNNLS.2024.3394513"},{"key":"journals/tnn/ZhangLLZYY25","title":"Improving Sample Efficiency of Reinforcement Learning With Background Knowledge From Large Language Models.","year":2025,"yearOfEvent":null,"venue":"IEEE Trans. Neural Networks Learn. Syst.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1109/TNNLS.2025.3590731"],"source":"https://dblp.org/rec/journals/tnn/ZhangLLZYY25","documentPage":"https://doi.org/10.1109/TNNLS.2025.3590731","type":"Article","doi":"https://doi.org/10.1109/TNNLS.2025.3590731","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/tnn/ZhangLLZYY25","documentUrl":"https://doi.org/10.1109/TNNLS.2025.3590731"}],"preprints":[{"key":"journals/corr/abs-2502-04778","title":"Behavior-Regularized Diffusion Policy Optimization for Offline Reinforcement Learning.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2502.04778"],"source":"https://dblp.org/rec/journals/corr/abs-2502-04778","documentPage":"https://doi.org/10.48550/ARXIV.2502.04778","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2502.04778","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2502-04778","documentUrl":"https://doi.org/10.48550/ARXIV.2502.04778","arxivId":"2502.04778","arxivUrl":"https://arxiv.org/abs/2502.04778"},{"key":"journals/corr/abs-2503-04793","title":"Sentence-level Reward Model can Generalize Better for Aligning LLM from Human Preference.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2503.04793"],"source":"https://dblp.org/rec/journals/corr/abs-2503-04793","documentPage":"https://doi.org/10.48550/ARXIV.2503.04793","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2503.04793","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-04793","documentUrl":"https://doi.org/10.48550/ARXIV.2503.04793","arxivId":"2503.04793","arxivUrl":"https://arxiv.org/abs/2503.04793"},{"key":"journals/corr/abs-2503-19267","title":"NeoRL-2: Near Real-World Benchmarks for Offline Reinforcement Learning with Extended Realistic Scenarios.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2503.19267"],"source":"https://dblp.org/rec/journals/corr/abs-2503-19267","documentPage":"https://doi.org/10.48550/ARXIV.2503.19267","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2503.19267","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-19267","documentUrl":"https://doi.org/10.48550/ARXIV.2503.19267","arxivId":"2503.19267","arxivUrl":"https://arxiv.org/abs/2503.19267"},{"key":"journals/corr/abs-2503-21383","title":"Controlling Large Language Model with Latent Actions.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2503.21383"],"source":"https://dblp.org/rec/journals/corr/abs-2503-21383","documentPage":"https://doi.org/10.48550/ARXIV.2503.21383","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2503.21383","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-21383","documentUrl":"https://doi.org/10.48550/ARXIV.2503.21383","arxivId":"2503.21383","arxivUrl":"https://arxiv.org/abs/2503.21383"},{"key":"journals/corr/abs-2505-10010","title":"ImagineBench: Evaluating Reinforcement Learning with Large Language Model Rollouts.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2505.10010"],"source":"https://dblp.org/rec/journals/corr/abs-2505-10010","documentPage":"https://doi.org/10.48550/ARXIV.2505.10010","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2505.10010","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-10010","documentUrl":"https://doi.org/10.48550/ARXIV.2505.10010","arxivId":"2505.10010","arxivUrl":"https://arxiv.org/abs/2505.10010"},{"key":"journals/corr/abs-2505-13425","title":"Learnware of Language Models: Specialized Small Language Models Can Do Big.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2505.13425"],"source":"https://dblp.org/rec/journals/corr/abs-2505-13425","documentPage":"https://doi.org/10.48550/ARXIV.2505.13425","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2505.13425","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-13425","documentUrl":"https://doi.org/10.48550/ARXIV.2505.13425","arxivId":"2505.13425","arxivUrl":"https://arxiv.org/abs/2505.13425"},{"key":"journals/corr/abs-2506-08446","title":"A Survey on Large Language Models for Mathematical Reasoning.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2506.08446"],"source":"https://dblp.org/rec/journals/corr/abs-2506-08446","documentPage":"https://doi.org/10.48550/ARXIV.2506.08446","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2506.08446","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-08446","documentUrl":"https://doi.org/10.48550/ARXIV.2506.08446","arxivId":"2506.08446","arxivUrl":"https://arxiv.org/abs/2506.08446"},{"key":"journals/corr/abs-2506-23235","title":"Generalist Reward Models: Found Inside Large Language Models.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2506.23235"],"source":"https://dblp.org/rec/journals/corr/abs-2506-23235","documentPage":"https://doi.org/10.48550/ARXIV.2506.23235","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2506.23235","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-23235","documentUrl":"https://doi.org/10.48550/ARXIV.2506.23235","arxivId":"2506.23235","arxivUrl":"https://arxiv.org/abs/2506.23235"},{"key":"journals/corr/abs-2509-22402","title":"ReLAM: Learning Anticipation Model for Rewarding Visual Robotic Manipulation.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2509.22402"],"source":"https://dblp.org/rec/journals/corr/abs-2509-22402","documentPage":"https://doi.org/10.48550/ARXIV.2509.22402","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2509.22402","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-22402","documentUrl":"https://doi.org/10.48550/ARXIV.2509.22402","arxivId":"2509.22402","arxivUrl":"https://arxiv.org/abs/2509.22402"},{"key":"journals/corr/abs-2511-10030","title":"Multi-agent In-context Coordination via Decentralized Memory Retrieval.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2511.10030"],"source":"https://dblp.org/rec/journals/corr/abs-2511-10030","documentPage":"https://doi.org/10.48550/ARXIV.2511.10030","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2511.10030","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2511-10030","documentUrl":"https://doi.org/10.48550/ARXIV.2511.10030","arxivId":"2511.10030","arxivUrl":"https://arxiv.org/abs/2511.10030"}],"excludedFormal":[],"excludedOther":[],"excludedHomonyms":[],"unassignedCandidates":[],"retrievedAt":"2026-10-19","querySource":"https://sparql.dblp.org/","method":"DBLP yearOfPublication=2025; Article + Inproceedings; excludes Informal/CoRR and explicit editorial/correction/erratum/preface; unique DBLP record keys within person.","labName":"LAMDA Group","labUrl":"https://www.lamda.nju.edu.cn/","labEvidence":"LAMDA官方个人页明确其为组员；2027年官方拟招生导师名单仍列俞扬。只标组关联，不称其是整个LAMDA唯一负责人。","labSourceUrl":"https://www.lamda.nju.edu.cn/recruit-2027/recruit-2027.html","affiliationZh":"南京大学","sourceWarning":false,"knownPreprintMinimum2025":null,"excludedMisattributed":[],"displayNotes":"身份已经个人或机构主页核对。2025 年正式记录 29 条（会议 16、期刊 13），所有作者位置均计入，不表示主导或贡献份额；预印本 10 条单列，不加总。","labDisplayNotes":"LAMDA 官方个人页列其为组员，2027 年招生导师名单也列有其姓名，据此归组。LAMDA 是多位教师组成的大组，这里不称其为唯一负责人；分组只含本人参与的记录。"},{"index":105,"name":"Li Yuan","nameZh":"袁粒","affiliation":"Peking University","source":"DBLP Knowledge Graph official SPARQL API","profileUrl":"https://dblp.org/pid/98/4583-7","identifier":"98/4583-7","identityEvidence":[{"url":"https://dblp.org/pid/98/4583-7","evidence":"DBLP curated profile affiliations: National University of Singapore, Singapore; Peking University, School of Electronic and Computer Engineering, Beijing, China."},{"url":"https://dblp.org/pid/98/4583-7","evidence":"DBLP curated profile homepages: https://openreview.net/profile?id=~Li_Yuan2; https://yuanli2333.github.io/."}],"count2025":39,"conference2025":32,"journal2025":7,"preprint2025":31,"status":"verified","notes":"Counts are DBLP indexed coauthored records, not first-author counts, laboratory totals, unique scientific discoveries, or quality assessments. DBLP yearOfPublication=2025; yearOfEvent retained and can differ. Conference workshops are included. Preprints are separate and may overlap formal versions.","papers":[{"key":"conf/aaai/0001YC0Z0025","title":"AE-NeRF: Augmenting Event-Based Neural Radiance Fields for Non-ideal Conditions and Larger Scenes.","year":2025,"yearOfEvent":2025,"venue":"AAAI","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1609/AAAI.V39I3.32299"],"source":"https://dblp.org/rec/conf/aaai/0001YC0Z0025","documentPage":"https://doi.org/10.1609/AAAI.V39I3.32299","type":"Inproceedings","doi":"https://doi.org/10.1609/AAAI.V39I3.32299","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/aaai/0001YC0Z0025","documentUrl":"https://doi.org/10.1609/AAAI.V39I3.32299"},{"key":"conf/aaai/0004ZCY0PL025","title":"Cycle3D: High-quality and Consistent Image-to-3D Generation via Generation-Reconstruction Cycle.","year":2025,"yearOfEvent":2025,"venue":"AAAI","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1609/AAAI.V39I7.32787"],"source":"https://dblp.org/rec/conf/aaai/0004ZCY0PL025","documentPage":"https://doi.org/10.1609/AAAI.V39I7.32787","type":"Inproceedings","doi":"https://doi.org/10.1609/AAAI.V39I7.32787","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/aaai/0004ZCY0PL025","documentUrl":"https://doi.org/10.1609/AAAI.V39I7.32787"},{"key":"conf/coling/YangNLYTS025","title":"Is Parameter Collision Hindering Continual Learning in LLMs?","year":2025,"yearOfEvent":2025,"venue":"COLING","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/coling/YangNLYTS025","documentPage":"https://aclanthology.org/2025.coling-main.286/","type":"Inproceedings","doi":null,"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/coling/YangNLYTS025","documentUrl":"https://aclanthology.org/2025.coling-main.286/"},{"key":"conf/cvpr/0001YCZGG0025","title":"RoomPainter: View-Integrated Diffusion for Consistent Indoor Scene Texturing.","year":2025,"yearOfEvent":2025,"venue":"CVPR","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/CVPR52734.2025.00062"],"source":"https://dblp.org/rec/conf/cvpr/0001YCZGG0025","documentPage":"https://openaccess.thecvf.com/content/CVPR2025/html/Huang_RoomPainter_View-Integrated_Diffusion_for_Consistent_Indoor_Scene_Texturing_CVPR_2025_paper.html","type":"Inproceedings","doi":"https://doi.org/10.1109/CVPR52734.2025.00062","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/0001YCZGG0025","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Huang_RoomPainter_View-Integrated_Diffusion_for_Consistent_Indoor_Scene_Texturing_CVPR_2025_paper.html"},{"key":"conf/cvpr/Li0YCCY025","title":"WF-VAE: Enhancing Video VAE by Wavelet-Driven Energy Flow for Latent Video Diffusion Model.","year":2025,"yearOfEvent":2025,"venue":"CVPR","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/CVPR52734.2025.01656"],"source":"https://dblp.org/rec/conf/cvpr/Li0YCCY025","documentPage":"https://openaccess.thecvf.com/content/CVPR2025/html/Li_WF-VAE_Enhancing_Video_VAE_by_Wavelet-Driven_Energy_Flow_for_Latent_CVPR_2025_paper.html","type":"Inproceedings","doi":"https://doi.org/10.1109/CVPR52734.2025.01656","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/Li0YCCY025","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Li_WF-VAE_Enhancing_Video_VAE_by_Wavelet-Driven_Energy_Flow_for_Latent_CVPR_2025_paper.html"},{"key":"conf/cvpr/YanZCGFYDWY25","title":"Generalizing Deepfake Video Detection with Plug-and-Play: Video-Level Blending and Spatiotemporal Adapter Tuning.","year":2025,"yearOfEvent":2025,"venue":"CVPR","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/CVPR52734.2025.01177"],"source":"https://dblp.org/rec/conf/cvpr/YanZCGFYDWY25","documentPage":"https://openaccess.thecvf.com/content/CVPR2025/html/Yan_Generalizing_Deepfake_Video_Detection_with_Plug-and-Play_Video-Level_Blending_and_Spatiotemporal_CVPR_2025_paper.html","type":"Inproceedings","doi":"https://doi.org/10.1109/CVPR52734.2025.01177","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/YanZCGFYDWY25","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Yan_Generalizing_Deepfake_Video_Detection_with_Plug-and-Play_Video-Level_Blending_and_Spatiotemporal_CVPR_2025_paper.html"},{"key":"conf/cvpr/YuanHHGSC0025","title":"Identity-Preserving Text-to-Video Generation by Frequency Decomposition.","year":2025,"yearOfEvent":2025,"venue":"CVPR","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/CVPR52734.2025.01211"],"source":"https://dblp.org/rec/conf/cvpr/YuanHHGSC0025","documentPage":"https://openaccess.thecvf.com/content/CVPR2025/html/Yuan_Identity-Preserving_Text-to-Video_Generation_by_Frequency_Decomposition_CVPR_2025_paper.html","type":"Inproceedings","doi":"https://doi.org/10.1109/CVPR52734.2025.01211","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/YuanHHGSC0025","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Yuan_Identity-Preserving_Text-to-Video_Generation_by_Frequency_Decomposition_CVPR_2025_paper.html"},{"key":"conf/cvpr/ZhangN00Y0YCSY25","title":"UPME: An Unsupervised Peer Review Framework for Multimodal Large Language Model Evaluation.","year":2025,"yearOfEvent":2025,"venue":"CVPR","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/CVPR52734.2025.00856"],"source":"https://dblp.org/rec/conf/cvpr/ZhangN00Y0YCSY25","documentPage":"https://openaccess.thecvf.com/content/CVPR2025/html/Zhang_UPME_An_Unsupervised_Peer_Review_Framework_for_Multimodal_Large_Language_CVPR_2025_paper.html","type":"Inproceedings","doi":"https://doi.org/10.1109/CVPR52734.2025.00856","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/ZhangN00Y0YCSY25","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Zhang_UPME_An_Unsupervised_Peer_Review_Framework_for_Multimodal_Large_Language_CVPR_2025_paper.html"},{"key":"conf/eccv/JinLCLYLJYC24","title":"Local Action-Guided Motion Diffusion Model for Text-to-Motion Generation.","year":2025,"yearOfEvent":2024,"venue":"ECCV (25)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1007/978-3-031-72698-9_23"],"source":"https://dblp.org/rec/conf/eccv/JinLCLYLJYC24","documentPage":"https://doi.org/10.1007/978-3-031-72698-9_23","type":"Inproceedings","doi":"https://doi.org/10.1007/978-3-031-72698-9_23","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/eccv/JinLCLYLJYC24","documentUrl":"https://doi.org/10.1007/978-3-031-72698-9_23"},{"key":"conf/eccv/LiFWSYJYC24","title":"Learning Pseudo 3D Guidance for View-Consistent Texturing with 2D Diffusion.","year":2025,"yearOfEvent":2024,"venue":"ECCV (86)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1007/978-3-031-73016-0_2"],"source":"https://dblp.org/rec/conf/eccv/LiFWSYJYC24","documentPage":"https://doi.org/10.1007/978-3-031-73016-0_2","type":"Inproceedings","doi":"https://doi.org/10.1007/978-3-031-73016-0_2","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/eccv/LiFWSYJYC24","documentUrl":"https://doi.org/10.1007/978-3-031-73016-0_2"},{"key":"conf/eccv/LiJJCLSLY24","title":"FreestyleRet: Retrieving Images from Style-Diversified Queries.","year":2025,"yearOfEvent":2024,"venue":"ECCV (23)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1007/978-3-031-73337-6_15"],"source":"https://dblp.org/rec/conf/eccv/LiJJCLSLY24","documentPage":"https://doi.org/10.1007/978-3-031-73337-6_15","type":"Inproceedings","doi":"https://doi.org/10.1007/978-3-031-73337-6_15","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/eccv/LiJJCLSLY24","documentUrl":"https://doi.org/10.1007/978-3-031-73337-6_15"},{"key":"conf/eccv/YuYCGLHLST24","title":"HiFi-123: Towards High-Fidelity One Image to 3D Content Generation.","year":2025,"yearOfEvent":2024,"venue":"ECCV (73)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1007/978-3-031-73464-9_16"],"source":"https://dblp.org/rec/conf/eccv/YuYCGLHLST24","documentPage":"https://doi.org/10.1007/978-3-031-73464-9_16","type":"Inproceedings","doi":"https://doi.org/10.1007/978-3-031-73464-9_16","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/eccv/YuYCGLHLST24","documentUrl":"https://doi.org/10.1007/978-3-031-73464-9_16"},{"key":"conf/eccv/ZhangTPCJWZNY24","title":"Repaint123: Fast and High-Quality One Image to 3D Generation with Progressive Controllable Repainting.","year":2025,"yearOfEvent":2024,"venue":"ECCV (25)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1007/978-3-031-72698-9_18"],"source":"https://dblp.org/rec/conf/eccv/ZhangTPCJWZNY24","documentPage":"https://doi.org/10.1007/978-3-031-72698-9_18","type":"Inproceedings","doi":"https://doi.org/10.1007/978-3-031-72698-9_18","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/eccv/ZhangTPCJWZNY24","documentUrl":"https://doi.org/10.1007/978-3-031-72698-9_18"},{"key":"conf/icassp/ZhouNZ0Z25","title":"Spiking Transformer with Spatial-Temporal Spiking Self-Attention.","year":2025,"yearOfEvent":2025,"venue":"ICASSP","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/ICASSP49660.2025.10890026"],"source":"https://dblp.org/rec/conf/icassp/ZhouNZ0Z25","documentPage":"https://doi.org/10.1109/ICASSP49660.2025.10890026","type":"Inproceedings","doi":"https://doi.org/10.1109/ICASSP49660.2025.10890026","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/icassp/ZhouNZ0Z25","documentUrl":"https://doi.org/10.1109/ICASSP49660.2025.10890026"},{"key":"conf/iccv/PangZBZTLYY25","title":"DreamDance: Animating Human Images by Enriching 3D Geometry Cues from 2D Poses.","year":2025,"yearOfEvent":2025,"venue":"ICCV","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/ICCV51701.2025.01303"],"source":"https://dblp.org/rec/conf/iccv/PangZBZTLYY25","documentPage":"https://doi.org/10.1109/ICCV51701.2025.01303","type":"Inproceedings","doi":"https://doi.org/10.1109/ICCV51701.2025.01303","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/PangZBZTLYY25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.01303"},{"key":"conf/iccv/XuJWLSSY25","title":"LlaVA-CoT: Let Vision Language Models Reason Step-By-Step.","year":2025,"yearOfEvent":2025,"venue":"ICCV","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/ICCV51701.2025.00202"],"source":"https://dblp.org/rec/conf/iccv/XuJWLSSY25","documentPage":"https://doi.org/10.1109/ICCV51701.2025.00202","type":"Inproceedings","doi":"https://doi.org/10.1109/ICCV51701.2025.00202","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/XuJWLSSY25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.00202"},{"key":"conf/iccv/YuFLTYTCJYYT25","title":"Evagaussians: Event Stream Assisted Gaussian Splatting from Blurry Images.","year":2025,"yearOfEvent":2025,"venue":"ICCV","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/ICCV51701.2025.02298"],"source":"https://dblp.org/rec/conf/iccv/YuFLTYTCJYYT25","documentPage":"https://doi.org/10.1109/ICCV51701.2025.02298","type":"Inproceedings","doi":"https://doi.org/10.1109/ICCV51701.2025.02298","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/YuFLTYTCJYYT25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.02298"},{"key":"conf/iccv/ZhangTHPGLHYZLCY25","title":"Epona: Autoregressive Diffusion World Model for Autonomous Driving.","year":2025,"yearOfEvent":2025,"venue":"ICCV","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/ICCV51701.2025.02527"],"source":"https://dblp.org/rec/conf/iccv/ZhangTHPGLHYZLCY25","documentPage":"https://doi.org/10.1109/ICCV51701.2025.02527","type":"Inproceedings","doi":"https://doi.org/10.1109/ICCV51701.2025.02527","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/ZhangTHPGLHYZLCY25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.02527"},{"key":"conf/iclr/0001Z0Y25","title":"MoE++: Accelerating Mixture-of-Experts Methods with Zero-Computation Experts.","year":2025,"yearOfEvent":2025,"venue":"ICLR","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/iclr/0001Z0Y25","documentPage":"https://openreview.net/forum?id=t7P5BUKcYv","type":"Inproceedings","doi":null,"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iclr/0001Z0Y25","documentUrl":"https://openreview.net/forum?id=t7P5BUKcYv"},{"key":"conf/iclr/NingYLYL0SY25","title":"PiCO: Peer Review in LLMs based on Consistency Optimization.","year":2025,"yearOfEvent":2025,"venue":"ICLR","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/iclr/NingYLYL0SY25","documentPage":"https://openreview.net/forum?id=sfQ6XpApfS","type":"Inproceedings","doi":null,"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iclr/NingYLYL0SY25","documentUrl":"https://openreview.net/forum?id=sfQ6XpApfS"},{"key":"conf/icmcs/ChenLLZWYZCY25","title":"OD-VAE: An Omni-dimensional Video Compressor for Improving Latent Video Diffusion Model.","year":2025,"yearOfEvent":2025,"venue":"ICME","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/ICME59968.2025.11210036"],"source":"https://dblp.org/rec/conf/icmcs/ChenLLZWYZCY25","documentPage":"https://doi.org/10.1109/ICME59968.2025.11210036","type":"Inproceedings","doi":"https://doi.org/10.1109/ICME59968.2025.11210036","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/icmcs/ChenLLZWYZCY25","documentUrl":"https://doi.org/10.1109/ICME59968.2025.11210036"},{"key":"conf/icmcs/WuNWZLY25","title":"OpenDUN: To Discover Unknown Number of Visual Categories.","year":2025,"yearOfEvent":2025,"venue":"ICME","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/ICME59968.2025.11209279"],"source":"https://dblp.org/rec/conf/icmcs/WuNWZLY25","documentPage":"https://doi.org/10.1109/ICME59968.2025.11209279","type":"Inproceedings","doi":"https://doi.org/10.1109/ICME59968.2025.11209279","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/icmcs/WuNWZLY25","documentUrl":"https://doi.org/10.1109/ICME59968.2025.11209279"},{"key":"conf/icml/0001Z0Y25","title":"MoH: Multi-Head Attention as Mixture-of-Head Attention.","year":2025,"yearOfEvent":2025,"venue":"ICML","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/icml/0001Z0Y25","documentPage":"https://proceedings.mlr.press/v267/jin25l.html","type":"Inproceedings","doi":null,"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/icml/0001Z0Y25","documentUrl":"https://proceedings.mlr.press/v267/jin25l.html"},{"key":"conf/icml/0002WJZLCYDW025","title":"Orthogonal Subspace Decomposition for Generalizable AI-Generated Image Detection.","year":2025,"yearOfEvent":2025,"venue":"ICML","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/icml/0002WJZLCYDW025","documentPage":"https://proceedings.mlr.press/v267/yan25b.html","type":"Inproceedings","doi":null,"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/icml/0002WJZLCYDW025","documentUrl":"https://proceedings.mlr.press/v267/yan25b.html"},{"key":"conf/mm/0001TYPZZ0025","title":"E-4DGS: High-Fidelity Dynamic Reconstruction from the Multi-view Event Cameras.","year":2025,"yearOfEvent":2025,"venue":"ACM Multimedia","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1145/3746027.3754777"],"source":"https://dblp.org/rec/conf/mm/0001TYPZZ0025","documentPage":"https://doi.org/10.1145/3746027.3754777","type":"Inproceedings","doi":"https://doi.org/10.1145/3746027.3754777","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/mm/0001TYPZZ0025","documentUrl":"https://doi.org/10.1145/3746027.3754777"},{"key":"conf/mm/ZhouYGC0025","title":"HoloTime: Taming Video Diffusion Models for Panoramic 4D Scene Generation.","year":2025,"yearOfEvent":2025,"venue":"ACM Multimedia","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1145/3746027.3755128"],"source":"https://dblp.org/rec/conf/mm/ZhouYGC0025","documentPage":"https://doi.org/10.1145/3746027.3755128","type":"Inproceedings","doi":"https://doi.org/10.1145/3746027.3755128","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/mm/ZhouYGC0025","documentUrl":"https://doi.org/10.1145/3746027.3755128"},{"key":"conf/nips/LiCFSTYTYL25","title":"Beyond Chemical QA: Evaluating LLM's Chemical Reasoning with Modular Chemical Operations.","year":2025,"yearOfEvent":2025,"venue":"NeurIPS","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/nips/LiCFSTYTYL25","documentPage":"http://papers.nips.cc/paper_files/paper/2025/hash/e0ed6d6c2ec6df05f929b8a67b78513a-Abstract-Datasets_and_Benchmarks_Track.html","type":"Inproceedings","doi":null,"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/nips/LiCFSTYTYL25","documentUrl":"http://papers.nips.cc/paper_files/paper/2025/hash/e0ed6d6c2ec6df05f929b8a67b78513a-Abstract-Datasets_and_Benchmarks_Track.html"},{"key":"conf/nips/LiFTDYTY25","title":"GS2E: Gaussian Splatting is an Effective Data Generator for Event Stream Generation.","year":2025,"yearOfEvent":2025,"venue":"NeurIPS","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/nips/LiFTDYTY25","documentPage":"http://papers.nips.cc/paper_files/paper/2025/hash/5dd2d7a5dba72af7a2d78128e02514f4-Abstract-Datasets_and_Benchmarks_Track.html","type":"Inproceedings","doi":null,"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/nips/LiFTDYTY25","documentUrl":"http://papers.nips.cc/paper_files/paper/2025/hash/5dd2d7a5dba72af7a2d78128e02514f4-Abstract-Datasets_and_Benchmarks_Track.html"},{"key":"conf/nips/LiuNZYWYXSCWY25","title":"CoT-lized Diffusion: Let's Reinforce T2I Generation Step-by-step.","year":2025,"yearOfEvent":2025,"venue":"NeurIPS","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/nips/LiuNZYWYXSCWY25","documentPage":"http://papers.nips.cc/paper_files/paper/2025/hash/ca44b233a4aae1821add654a75f09bfd-Abstract-Conference.html","type":"Inproceedings","doi":null,"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/nips/LiuNZYWYXSCWY25","documentUrl":"http://papers.nips.cc/paper_files/paper/2025/hash/ca44b233a4aae1821add654a75f09bfd-Abstract-Conference.html"},{"key":"conf/nips/YeHLLYYHY25","title":"ImgEdit: A Unified Image Editing Dataset and Benchmark.","year":2025,"yearOfEvent":2025,"venue":"NeurIPS","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/nips/YeHLLYYHY25","documentPage":"http://papers.nips.cc/paper_files/paper/2025/hash/bec783f119b969772c35243b1c801090-Abstract-Datasets_and_Benchmarks_Track.html","type":"Inproceedings","doi":null,"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/nips/YeHLLYYHY25","documentUrl":"http://papers.nips.cc/paper_files/paper/2025/hash/bec783f119b969772c35243b1c801090-Abstract-Datasets_and_Benchmarks_Track.html"},{"key":"conf/nips/YuanHDYHLMLY25","title":"OpenS2V-Nexus: A Detailed Benchmark and Million-Scale Dataset for Subject-to-Video Generation.","year":2025,"yearOfEvent":2025,"venue":"NeurIPS","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/nips/YuanHDYHLMLY25","documentPage":"http://papers.nips.cc/paper_files/paper/2025/hash/dae77d03bd51a5acfe8519848a3af6c9-Abstract-Datasets_and_Benchmarks_Track.html","type":"Inproceedings","doi":null,"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/nips/YuanHDYHLMLY25","documentUrl":"http://papers.nips.cc/paper_files/paper/2025/hash/dae77d03bd51a5acfe8519848a3af6c9-Abstract-Datasets_and_Benchmarks_Track.html"},{"key":"conf/sigir/LiuYPF0JPLLS25","title":"Multi-objective Aligned Bidword Generation Model for E-commerce Search Advertising.","year":2025,"yearOfEvent":2025,"venue":"SIGIR","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1145/3726302.3731952"],"source":"https://dblp.org/rec/conf/sigir/LiuYPF0JPLLS25","documentPage":"https://doi.org/10.1145/3726302.3731952","type":"Inproceedings","doi":"https://doi.org/10.1145/3726302.3731952","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/sigir/LiuYPF0JPLLS25","documentUrl":"https://doi.org/10.1145/3726302.3731952"},{"key":"journals/chinaf/LinLLWLZCCYT25","title":"TaxDiff: taxonomic-guided diffusion model for protein sequence generation.","year":2025,"yearOfEvent":null,"venue":"Sci. China Inf. Sci.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1007/S11432-024-4296-6"],"source":"https://dblp.org/rec/journals/chinaf/LinLLWLZCCYT25","documentPage":"https://doi.org/10.1007/S11432-024-4296-6","type":"Article","doi":"https://doi.org/10.1007/S11432-024-4296-6","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/chinaf/LinLLWLZCCYT25","documentUrl":"https://doi.org/10.1007/S11432-024-4296-6"},{"key":"journals/ijcv/WangYWF25","title":"Learning Box Regression and Mask Segmentation Under Long-Tailed Distribution with Gradient Transfusing.","year":2025,"yearOfEvent":null,"venue":"Int. J. Comput. Vis.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1007/S11263-024-02104-9"],"source":"https://dblp.org/rec/journals/ijcv/WangYWF25","documentPage":"https://doi.org/10.1007/S11263-024-02104-9","type":"Article","doi":"https://doi.org/10.1007/S11263-024-02104-9","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/ijcv/WangYWF25","documentUrl":"https://doi.org/10.1007/S11263-024-02104-9"},{"key":"journals/ncs/LiLYWTWM25","title":"Decoupled peak property learning for efficient and interpretable electronic circular dichroism spectrum prediction.","year":2025,"yearOfEvent":null,"venue":"Nat. Comput. Sci.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1038/S43588-024-00757-7"],"source":"https://dblp.org/rec/journals/ncs/LiLYWTWM25","documentPage":"https://doi.org/10.1038/S43588-024-00757-7","type":"Article","doi":"https://doi.org/10.1038/S43588-024-00757-7","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/ncs/LiLYWTWM25","documentUrl":"https://doi.org/10.1038/S43588-024-00757-7"},{"key":"journals/pami/JinLYYC25","title":"Hierarchical Banzhaf Interaction for General Video-Language Representation Learning.","year":2025,"yearOfEvent":null,"venue":"IEEE Trans. Pattern Anal. Mach. Intell.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1109/TPAMI.2024.3522124"],"source":"https://dblp.org/rec/journals/pami/JinLYYC25","documentPage":"https://doi.org/10.1109/TPAMI.2024.3522124","type":"Article","doi":"https://doi.org/10.1109/TPAMI.2024.3522124","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/pami/JinLYYC25","documentUrl":"https://doi.org/10.1109/TPAMI.2024.3522124"},{"key":"journals/pami/YuanHSXZLCYL25","title":"MagicTime: Time-Lapse Video Generation Models as Metamorphic Simulators.","year":2025,"yearOfEvent":null,"venue":"IEEE Trans. Pattern Anal. Mach. Intell.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1109/TPAMI.2025.3558507"],"source":"https://dblp.org/rec/journals/pami/YuanHSXZLCYL25","documentPage":"https://doi.org/10.1109/TPAMI.2025.3558507","type":"Article","doi":"https://doi.org/10.1109/TPAMI.2025.3558507","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/pami/YuanHSXZLCYL25","documentUrl":"https://doi.org/10.1109/TPAMI.2025.3558507"},{"key":"journals/tamd/ZhouCNYLYLZ25","title":"Spatial-Temporal Spiking Feature Pruning in Spiking Transformer.","year":2025,"yearOfEvent":null,"venue":"IEEE Trans. Cogn. Dev. Syst.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1109/TCDS.2024.3500018"],"source":"https://dblp.org/rec/journals/tamd/ZhouCNYLYLZ25","documentPage":"https://doi.org/10.1109/TCDS.2024.3500018","type":"Article","doi":"https://doi.org/10.1109/TCDS.2024.3500018","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/tamd/ZhouCNYLYLZ25","documentUrl":"https://doi.org/10.1109/TCDS.2024.3500018"},{"key":"journals/tcsv/WangCYYY25","title":"Point Tree Transformer for Point Cloud Registration.","year":2025,"yearOfEvent":null,"venue":"IEEE Trans. Circuits Syst. Video Technol.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1109/TCSVT.2025.3526680"],"source":"https://dblp.org/rec/journals/tcsv/WangCYYY25","documentPage":"https://doi.org/10.1109/TCSVT.2025.3526680","type":"Article","doi":"https://doi.org/10.1109/TCSVT.2025.3526680","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/tcsv/WangCYYY25","documentUrl":"https://doi.org/10.1109/TCSVT.2025.3526680"}],"preprints":[{"key":"journals/corr/abs-2501-02807","title":"AE-NeRF: Augmenting Event-Based Neural Radiance Fields for Non-ideal Conditions and Larger Scene.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2501.02807"],"source":"https://dblp.org/rec/journals/corr/abs-2501-02807","documentPage":"https://doi.org/10.48550/ARXIV.2501.02807","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2501.02807","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2501-02807","documentUrl":"https://doi.org/10.48550/ARXIV.2501.02807","arxivId":"2501.02807","arxivUrl":"https://arxiv.org/abs/2501.02807"},{"key":"journals/corr/abs-2501-07641","title":"GPT as a Monte Carlo Language Tree: A Probabilistic Perspective.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2501.07641"],"source":"https://dblp.org/rec/journals/corr/abs-2501-07641","documentPage":"https://doi.org/10.48550/ARXIV.2501.07641","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2501.07641","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2501-07641","documentUrl":"https://doi.org/10.48550/ARXIV.2501.07641","arxivId":"2501.07641","arxivUrl":"https://arxiv.org/abs/2501.07641"},{"key":"journals/corr/abs-2503-06687","title":"UniGenX: Unified Generation of Sequence and Structure with Autoregressive Diffusion.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2503.06687"],"source":"https://dblp.org/rec/journals/corr/abs-2503-06687","documentPage":"https://doi.org/10.48550/ARXIV.2503.06687","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2503.06687","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-06687","documentUrl":"https://doi.org/10.48550/ARXIV.2503.06687","arxivId":"2503.06687","arxivUrl":"https://arxiv.org/abs/2503.06687"},{"key":"journals/corr/abs-2503-07265","title":"WISE: A World Knowledge-Informed Semantic Evaluation for Text-to-Image Generation.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2503.07265"],"source":"https://dblp.org/rec/journals/corr/abs-2503-07265","documentPage":"https://doi.org/10.48550/ARXIV.2503.07265","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2503.07265","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-07265","documentUrl":"https://doi.org/10.48550/ARXIV.2503.07265","arxivId":"2503.07265","arxivUrl":"https://arxiv.org/abs/2503.07265"},{"key":"journals/corr/abs-2503-09154","title":"SwapAnyone: Consistent and Realistic Video Synthesis for Swapping Any Person into Any Video.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2503.09154"],"source":"https://dblp.org/rec/journals/corr/abs-2503-09154","documentPage":"https://doi.org/10.48550/ARXIV.2503.09154","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2503.09154","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-09154","documentUrl":"https://doi.org/10.48550/ARXIV.2503.09154","arxivId":"2503.09154","arxivUrl":"https://arxiv.org/abs/2503.09154"},{"key":"journals/corr/abs-2503-14941","title":"UPME: An Unsupervised Peer Review Framework for Multimodal Large Language Model Evaluation.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2503.14941"],"source":"https://dblp.org/rec/journals/corr/abs-2503-14941","documentPage":"https://doi.org/10.48550/ARXIV.2503.14941","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2503.14941","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-14941","documentUrl":"https://doi.org/10.48550/ARXIV.2503.14941","arxivId":"2503.14941","arxivUrl":"https://arxiv.org/abs/2503.14941"},{"key":"journals/corr/abs-2503-23162","title":"NeuralGS: Bridging Neural Fields and 3D Gaussian Splatting for Compact 3D Representations.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2503.23162"],"source":"https://dblp.org/rec/journals/corr/abs-2503-23162","documentPage":"https://doi.org/10.48550/ARXIV.2503.23162","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2503.23162","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-23162","documentUrl":"https://doi.org/10.48550/ARXIV.2503.23162","arxivId":"2503.23162","arxivUrl":"https://arxiv.org/abs/2503.23162"},{"key":"journals/corr/abs-2504-02782","title":"GPT-ImgEval: A Comprehensive Benchmark for Diagnosing GPT4o in Image Generation.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2504.02782"],"source":"https://dblp.org/rec/journals/corr/abs-2504-02782","documentPage":"https://doi.org/10.48550/ARXIV.2504.02782","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2504.02782","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2504-02782","documentUrl":"https://doi.org/10.48550/ARXIV.2504.02782","arxivId":"2504.02782","arxivUrl":"https://arxiv.org/abs/2504.02782"},{"key":"journals/corr/abs-2504-12314","title":"How to Detect and Defeat Molecular Mirage: A Metric-Driven Benchmark for Hallucination in LLM-based Molecular Comprehension.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2504.12314"],"source":"https://dblp.org/rec/journals/corr/abs-2504-12314","documentPage":"https://doi.org/10.48550/ARXIV.2504.12314","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2504.12314","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2504-12314","documentUrl":"https://doi.org/10.48550/ARXIV.2504.12314","arxivId":"2504.12314","arxivUrl":"https://arxiv.org/abs/2504.12314"},{"key":"journals/corr/abs-2504-21650","title":"HoloTime: Taming Video Diffusion Models for Panoramic 4D Scene Generation.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2504.21650"],"source":"https://dblp.org/rec/journals/corr/abs-2504-21650","documentPage":"https://doi.org/10.48550/ARXIV.2504.21650","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2504.21650","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2504-21650","documentUrl":"https://doi.org/10.48550/ARXIV.2504.21650","arxivId":"2504.21650","arxivUrl":"https://arxiv.org/abs/2504.21650"},{"key":"journals/corr/abs-2505-07889","title":"BioProBench: Comprehensive Dataset and Benchmark in Biological Protocol Understanding and Reasoning.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2505.07889"],"source":"https://dblp.org/rec/journals/corr/abs-2505-07889","documentPage":"https://doi.org/10.48550/ARXIV.2505.07889","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2505.07889","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-07889","documentUrl":"https://doi.org/10.48550/ARXIV.2505.07889","arxivId":"2505.07889","arxivUrl":"https://arxiv.org/abs/2505.07889"},{"key":"journals/corr/abs-2505-15233","title":"CAD: A General Multimodal Framework for Video Deepfake Detection via Cross-Modal Alignment and Distillation.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2505.15233"],"source":"https://dblp.org/rec/journals/corr/abs-2505-15233","documentPage":"https://doi.org/10.48550/ARXIV.2505.15233","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2505.15233","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-15233","documentUrl":"https://doi.org/10.48550/ARXIV.2505.15233","arxivId":"2505.15233","arxivUrl":"https://arxiv.org/abs/2505.15233"},{"key":"journals/corr/abs-2505-15287","title":"GS2E: Gaussian Splatting is an Effective Data Generator for Event Stream Generation.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2505.15287"],"source":"https://dblp.org/rec/journals/corr/abs-2505-15287","documentPage":"https://doi.org/10.48550/ARXIV.2505.15287","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2505.15287","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-15287","documentUrl":"https://doi.org/10.48550/ARXIV.2505.15287","arxivId":"2505.15287","arxivUrl":"https://arxiv.org/abs/2505.15287"},{"key":"journals/corr/abs-2505-20275","title":"ImgEdit: A Unified Image Editing Dataset and Benchmark.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2505.20275"],"source":"https://dblp.org/rec/journals/corr/abs-2505-20275","documentPage":"https://doi.org/10.48550/ARXIV.2505.20275","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2505.20275","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-20275","documentUrl":"https://doi.org/10.48550/ARXIV.2505.20275","arxivId":"2505.20275","arxivUrl":"https://arxiv.org/abs/2505.20275"},{"key":"journals/corr/abs-2505-20292","title":"OpenS2V-Nexus: A Detailed Benchmark and Million-Scale Dataset for Subject-to-Video Generation.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2505.20292"],"source":"https://dblp.org/rec/journals/corr/abs-2505-20292","documentPage":"https://doi.org/10.48550/ARXIV.2505.20292","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2505.20292","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-20292","documentUrl":"https://doi.org/10.48550/ARXIV.2505.20292","arxivId":"2505.20292","arxivUrl":"https://arxiv.org/abs/2505.20292"},{"key":"journals/corr/abs-2505-20354","title":"Rethinking Text-based Protein Understanding: Retrieval or LLM?","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2505.20354"],"source":"https://dblp.org/rec/journals/corr/abs-2505-20354","documentPage":"https://doi.org/10.48550/ARXIV.2505.20354","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2505.20354","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-20354","documentUrl":"https://doi.org/10.48550/ARXIV.2505.20354","arxivId":"2505.20354","arxivUrl":"https://arxiv.org/abs/2505.20354"},{"key":"journals/corr/abs-2505-21205","title":"Sci-Fi: Symmetric Constraint for Frame Inbetweening.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2505.21205"],"source":"https://dblp.org/rec/journals/corr/abs-2505-21205","documentPage":"https://doi.org/10.48550/ARXIV.2505.21205","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2505.21205","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-21205","documentUrl":"https://doi.org/10.48550/ARXIV.2505.21205","arxivId":"2505.21205","arxivUrl":"https://arxiv.org/abs/2505.21205"},{"key":"journals/corr/abs-2505-21318","title":"Beyond Chemical QA: Evaluating LLM's Chemical Reasoning with Modular Chemical Operations.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2505.21318"],"source":"https://dblp.org/rec/journals/corr/abs-2505-21318","documentPage":"https://doi.org/10.48550/ARXIV.2505.21318","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2505.21318","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-21318","documentUrl":"https://doi.org/10.48550/ARXIV.2505.21318","arxivId":"2505.21318","arxivUrl":"https://arxiv.org/abs/2505.21318"},{"key":"journals/corr/abs-2506-03147","title":"UniWorld-V1: High-Resolution Semantic Encoders for Unified Visual Understanding and Generation.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2506.03147"],"source":"https://dblp.org/rec/journals/corr/abs-2506-03147","documentPage":"https://doi.org/10.48550/ARXIV.2506.03147","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2506.03147","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-03147","documentUrl":"https://doi.org/10.48550/ARXIV.2506.03147","arxivId":"2506.03147","arxivUrl":"https://arxiv.org/abs/2506.03147"},{"key":"journals/corr/abs-2506-03827","title":"Multi-objective Aligned Bidword Generation Model for E-commerce Search Advertising.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2506.03827"],"source":"https://dblp.org/rec/journals/corr/abs-2506-03827","documentPage":"https://doi.org/10.48550/ARXIV.2506.03827","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2506.03827","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-03827","documentUrl":"https://doi.org/10.48550/ARXIV.2506.03827","arxivId":"2506.03827","arxivUrl":"https://arxiv.org/abs/2506.03827"},{"key":"journals/corr/abs-2506-05260","title":"LeanPO: Lean Preference Optimization for Likelihood Alignment in Video-LLMs.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2506.05260"],"source":"https://dblp.org/rec/journals/corr/abs-2506-05260","documentPage":"https://doi.org/10.48550/ARXIV.2506.05260","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2506.05260","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-05260","documentUrl":"https://doi.org/10.48550/ARXIV.2506.05260","arxivId":"2506.05260","arxivUrl":"https://arxiv.org/abs/2506.05260"},{"key":"journals/corr/abs-2506-08473","title":"AsFT: Anchoring Safety During LLM Fine-Tuning Within Narrow Safety Basin.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2506.08473"],"source":"https://dblp.org/rec/journals/corr/abs-2506-08473","documentPage":"https://doi.org/10.48550/ARXIV.2506.08473","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2506.08473","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-08473","documentUrl":"https://doi.org/10.48550/ARXIV.2506.08473","arxivId":"2506.08473","arxivUrl":"https://arxiv.org/abs/2506.08473"},{"key":"journals/corr/abs-2506-24113","title":"Epona: Autoregressive Diffusion World Model for Autonomous Driving.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2506.24113"],"source":"https://dblp.org/rec/journals/corr/abs-2506-24113","documentPage":"https://doi.org/10.48550/ARXIV.2506.24113","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2506.24113","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-24113","documentUrl":"https://doi.org/10.48550/ARXIV.2506.24113","arxivId":"2506.24113","arxivUrl":"https://arxiv.org/abs/2506.24113"},{"key":"journals/corr/abs-2507-03019","title":"Look-Back: Implicit Visual Re-focusing in MLLM Reasoning.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2507.03019"],"source":"https://dblp.org/rec/journals/corr/abs-2507-03019","documentPage":"https://doi.org/10.48550/ARXIV.2507.03019","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2507.03019","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2507-03019","documentUrl":"https://doi.org/10.48550/ARXIV.2507.03019","arxivId":"2507.03019","arxivUrl":"https://arxiv.org/abs/2507.03019"},{"key":"journals/corr/abs-2507-04451","title":"CoT-lized Diffusion: Let's Reinforce T2I Generation Step-by-step.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2507.04451"],"source":"https://dblp.org/rec/journals/corr/abs-2507-04451","documentPage":"https://doi.org/10.48550/ARXIV.2507.04451","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2507.04451","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2507-04451","documentUrl":"https://doi.org/10.48550/ARXIV.2507.04451","arxivId":"2507.04451","arxivUrl":"https://arxiv.org/abs/2507.04451"},{"key":"journals/corr/abs-2508-09912","title":"E-4DGS: High-Fidelity Dynamic Reconstruction from the Multi-view Event Cameras.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2508.09912"],"source":"https://dblp.org/rec/journals/corr/abs-2508-09912","documentPage":"https://doi.org/10.48550/ARXIV.2508.09912","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2508.09912","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-09912","documentUrl":"https://doi.org/10.48550/ARXIV.2508.09912","arxivId":"2508.09912","arxivUrl":"https://arxiv.org/abs/2508.09912"},{"key":"journals/corr/abs-2509-09666","title":"Unified Multimodal Model as Auto-Encoder.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2509.09666"],"source":"https://dblp.org/rec/journals/corr/abs-2509-09666","documentPage":"https://doi.org/10.48550/ARXIV.2509.09666","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2509.09666","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-09666","documentUrl":"https://doi.org/10.48550/ARXIV.2509.09666","arxivId":"2509.09666","arxivUrl":"https://arxiv.org/abs/2509.09666"},{"key":"journals/corr/abs-2509-25187","title":"FlashI2V: Fourier-Guided Latent Shifting Prevents Conditional Image Leakage in Image-to-Video Generation.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2509.25187"],"source":"https://dblp.org/rec/journals/corr/abs-2509-25187","documentPage":"https://doi.org/10.48550/ARXIV.2509.25187","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2509.25187","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-25187","documentUrl":"https://doi.org/10.48550/ARXIV.2509.25187","arxivId":"2509.25187","arxivUrl":"https://arxiv.org/abs/2509.25187"},{"key":"journals/corr/abs-2510-16888","title":"Uniworld-V2: Reinforce Image Editing with Diffusion Negative-aware Finetuning and MLLM Implicit Feedback.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2510.16888"],"source":"https://dblp.org/rec/journals/corr/abs-2510-16888","documentPage":"https://doi.org/10.48550/ARXIV.2510.16888","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2510.16888","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-16888","documentUrl":"https://doi.org/10.48550/ARXIV.2510.16888","arxivId":"2510.16888","arxivUrl":"https://arxiv.org/abs/2510.16888"},{"key":"journals/corr/abs-2511-20561","title":"Does Understanding Inform Generation in Unified Multimodal Models? From Analysis to Path Forward.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2511.20561"],"source":"https://dblp.org/rec/journals/corr/abs-2511-20561","documentPage":"https://doi.org/10.48550/ARXIV.2511.20561","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2511.20561","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2511-20561","documentUrl":"https://doi.org/10.48550/ARXIV.2511.20561","arxivId":"2511.20561","arxivUrl":"https://arxiv.org/abs/2511.20561"},{"key":"journals/corr/abs-2512-10369","title":"Breaking the Vicious Cycle: Coherent 3D Gaussian Splatting from Sparse and Motion-Blurred Views.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2512.10369"],"source":"https://dblp.org/rec/journals/corr/abs-2512-10369","documentPage":"https://doi.org/10.48550/ARXIV.2512.10369","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2512.10369","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-10369","documentUrl":"https://doi.org/10.48550/ARXIV.2512.10369","arxivId":"2512.10369","arxivUrl":"https://arxiv.org/abs/2512.10369"}],"excludedFormal":[],"excludedOther":[],"excludedHomonyms":[],"unassignedCandidates":[],"retrievedAt":"2026-10-19","querySource":"https://sparql.dblp.org/","method":"DBLP yearOfPublication=2025; Article + Inproceedings; excludes Informal/CoRR and explicit editorial/correction/erratum/preface; unique DBLP record keys within person.","labName":"PKU-YUAN-Lab（袁粒课题组）","labUrl":"https://github.com/PKU-YuanGroup","labEvidence":"本人主页将该 GitHub 组织直接标为 GitHub of Lab，组织显示名为 PKU-YUAN-Lab（袁粒课题组-北大深研院）。链接为实验室代码主页。","labSourceUrl":"https://yuanli2333.github.io/","affiliationZh":"北京大学","sourceWarning":false,"knownPreprintMinimum2025":null,"excludedMisattributed":[],"displayNotes":"身份已经个人或机构主页核对。2025 年正式记录 39 条（会议 32、期刊 7），所有作者位置均计入，不表示主导或贡献份额；预印本 31 条单列，不加总。","labDisplayNotes":"本人主页以「GitHub of Lab」链接 PKU-YUAN-Lab（袁粒课题组-北大深研院）组织，据此归组。"},{"index":106,"name":"Xiangyu Yue","nameZh":"岳翔宇","affiliation":"The Chinese University of Hong Kong","source":"DBLP Knowledge Graph official SPARQL API","profileUrl":"https://dblp.org/pid/207/7518","identifier":"207/7518","identityEvidence":[{"url":"https://dblp.org/pid/207/7518","evidence":"DBLP curated profile affiliations: Chinese University of Hong Kong, Department of Information Engineering, Multimedia Lab (MMLab), Hong Kong; University of California, Berkeley, Department of Electrical Engineering and Computer Sciences, Berkeley, CA, USA."},{"url":"https://dblp.org/pid/207/7518","evidence":"DBLP curated profile homepages: https://openreview.net/profile?id=~Xiangyu_Yue1; https://xyue.io/."}],"count2025":28,"conference2025":27,"journal2025":1,"preprint2025":45,"status":"verified","notes":"Counts are DBLP indexed coauthored records, not first-author counts, laboratory totals, unique scientific discoveries, or quality assessments. DBLP yearOfPublication=2025; yearOfEvent retained and can differ. Conference workshops are included. Preprints are separate and may overlap formal versions.","papers":[{"key":"conf/aaai/LiuY00025","title":"Training Matting Models Without Alpha Labels.","year":2025,"yearOfEvent":2025,"venue":"AAAI","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1609/AAAI.V39I6.32597"],"source":"https://dblp.org/rec/conf/aaai/LiuY00025","documentPage":"https://doi.org/10.1609/AAAI.V39I6.32597","type":"Inproceedings","doi":"https://doi.org/10.1609/AAAI.V39I6.32597","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/aaai/LiuY00025","documentUrl":"https://doi.org/10.1609/AAAI.V39I6.32597"},{"key":"conf/acl/JiangGPTZ0025","title":"HiddenDetect: Detecting Jailbreak Attacks against Multimodal Large Language Models via Monitoring Hidden States.","year":2025,"yearOfEvent":2025,"venue":"ACL (1)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.18653/V1/2025.ACL-LONG.724"],"source":"https://dblp.org/rec/conf/acl/JiangGPTZ0025","documentPage":"https://doi.org/10.18653/V1/2025.ACL-LONG.724","type":"Inproceedings","doi":"https://doi.org/10.18653/V1/2025.ACL-LONG.724","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/acl/JiangGPTZ0025","documentUrl":"https://doi.org/10.18653/V1/2025.ACL-LONG.724"},{"key":"conf/ccs/FanZ00000Z25","title":"DivTrackee versus DynTracker: Promoting Diversity in Anti-Facial Recognition against Dynamic FR Strategy.","year":2025,"yearOfEvent":2025,"venue":"CCS","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1145/3719027.3744867"],"source":"https://dblp.org/rec/conf/ccs/FanZ00000Z25","documentPage":"https://doi.org/10.1145/3719027.3744867","type":"Inproceedings","doi":"https://doi.org/10.1145/3719027.3744867","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/ccs/FanZ00000Z25","documentUrl":"https://doi.org/10.1145/3719027.3744867"},{"key":"conf/cvpr/0002HLL025","title":"RAP: Retrieval-Augmented Personalization for Multimodal Large Language Models.","year":2025,"yearOfEvent":2025,"venue":"CVPR","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/CVPR52734.2025.01355"],"source":"https://dblp.org/rec/conf/cvpr/0002HLL025","documentPage":"https://openaccess.thecvf.com/content/CVPR2025/html/Hao_RAP_Retrieval-Augmented_Personalization_for_Multimodal_Large_Language_Models_CVPR_2025_paper.html","type":"Inproceedings","doi":"https://doi.org/10.1109/CVPR52734.2025.01355","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/0002HLL025","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Hao_RAP_Retrieval-Augmented_Personalization_for_Multimodal_Large_Language_Models_CVPR_2025_paper.html"},{"key":"conf/cvpr/CaiCLLZZSY25","title":"DiTCtrl: Exploring Attention Control in Multi-Modal Diffusion Transformer for Tuning-Free Multi-Prompt Longer Video Generation.","year":2025,"yearOfEvent":2025,"venue":"CVPR","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/CVPR52734.2025.00727"],"source":"https://dblp.org/rec/conf/cvpr/CaiCLLZZSY25","documentPage":"https://openaccess.thecvf.com/content/CVPR2025/html/Cai_DiTCtrl_Exploring_Attention_Control_in_Multi-Modal_Diffusion_Transformer_for_Tuning-Free_CVPR_2025_paper.html","type":"Inproceedings","doi":"https://doi.org/10.1109/CVPR52734.2025.00727","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/CaiCLLZZSY25","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Cai_DiTCtrl_Exploring_Attention_Control_in_Multi-Modal_Diffusion_Transformer_for_Tuning-Free_CVPR_2025_paper.html"},{"key":"conf/cvpr/CongWM025","title":"SemGeoMo: Dynamic Contextual Human Motion Generation with Semantic and Geometric Guidance.","year":2025,"yearOfEvent":2025,"venue":"CVPR","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/CVPR52734.2025.01636"],"source":"https://dblp.org/rec/conf/cvpr/CongWM025","documentPage":"https://openaccess.thecvf.com/content/CVPR2025/html/Cong_SemGeoMo_Dynamic_Contextual_Human_Motion_Generation_with_Semantic_and_Geometric_CVPR_2025_paper.html","type":"Inproceedings","doi":"https://doi.org/10.1109/CVPR52734.2025.01636","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/CongWM025","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Cong_SemGeoMo_Dynamic_Contextual_Human_Motion_Generation_with_Semantic_and_Geometric_CVPR_2025_paper.html"},{"key":"conf/cvpr/TangMSS0L0O025","title":"UniSTD: Towards Unified Spatio-Temporal Learning across Diverse Disciplines.","year":2025,"yearOfEvent":2025,"venue":"CVPR","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/CVPR52734.2025.02720"],"source":"https://dblp.org/rec/conf/cvpr/TangMSS0L0O025","documentPage":"https://openaccess.thecvf.com/content/CVPR2025/html/Tang_UniSTD_Towards_Unified_Spatio-Temporal_Learning_across_Diverse_Disciplines_CVPR_2025_paper.html","type":"Inproceedings","doi":"https://doi.org/10.1109/CVPR52734.2025.02720","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/TangMSS0L0O025","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Tang_UniSTD_Towards_Unified_Spatio-Temporal_Learning_across_Diverse_Disciplines_CVPR_2025_paper.html"},{"key":"conf/eccv/YuanZGYSQC24","title":"Reg-TTA3D: Better Regression Makes Better Test-Time Adaptive 3D Object Detection.","year":2025,"yearOfEvent":2024,"venue":"ECCV (43)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1007/978-3-031-72775-7_12"],"source":"https://dblp.org/rec/conf/eccv/YuanZGYSQC24","documentPage":"https://doi.org/10.1007/978-3-031-72775-7_12","type":"Inproceedings","doi":"https://doi.org/10.1007/978-3-031-72775-7_12","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/eccv/YuanZGYSQC24","documentUrl":"https://doi.org/10.1007/978-3-031-72775-7_12"},{"key":"conf/eccv/ZhangZDJY24","title":"Online Vectorized HD Map Construction Using Geometry.","year":2025,"yearOfEvent":2024,"venue":"ECCV (49)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1007/978-3-031-72967-6_5"],"source":"https://dblp.org/rec/conf/eccv/ZhangZDJY24","documentPage":"https://doi.org/10.1007/978-3-031-72967-6_5","type":"Inproceedings","doi":"https://doi.org/10.1007/978-3-031-72967-6_5","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/eccv/ZhangZDJY24","documentUrl":"https://doi.org/10.1007/978-3-031-72967-6_5"},{"key":"conf/iccv/HeLXLKGXSSGY25","title":"SynFER: Towards Boosting Facial Expression Recognition With Synthetic Data.","year":2025,"yearOfEvent":2025,"venue":"ICCV","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/ICCV51701.2025.00949"],"source":"https://dblp.org/rec/conf/iccv/HeLXLKGXSSGY25","documentPage":"https://doi.org/10.1109/ICCV51701.2025.00949","type":"Inproceedings","doi":"https://doi.org/10.1109/ICCV51701.2025.00949","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/HeLXLKGXSSGY25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.00949"},{"key":"conf/iccv/JiangLZCY25","title":"FairGen: Enhancing Fairness in Text-to-Image Diffusion Models via Self-Discovering Latent Directions.","year":2025,"yearOfEvent":2025,"venue":"ICCV","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/ICCV51701.2025.01711"],"source":"https://dblp.org/rec/conf/iccv/JiangLZCY25","documentPage":"https://doi.org/10.1109/ICCV51701.2025.01711","type":"Inproceedings","doi":"https://doi.org/10.1109/ICCV51701.2025.01711","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/JiangLZCY25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.01711"},{"key":"conf/iccv/LaiZZLWSYLHLJGY25","title":"Unleashing Vecset Diffusion Model for Fast Shape Generation.","year":2025,"yearOfEvent":2025,"venue":"ICCV","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/ICCV51701.2025.00243"],"source":"https://dblp.org/rec/conf/iccv/LaiZZLWSYLHLJGY25","documentPage":"https://doi.org/10.1109/ICCV51701.2025.00243","type":"Inproceedings","doi":"https://doi.org/10.1109/ICCV51701.2025.00243","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/LaiZZLWSYLHLJGY25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.00243"},{"key":"conf/iccv/LiFGY25","title":"HYPDAE: Hyperbolic Diffusion Autoencoders for Hierarchical Few-Shot Image Generation.","year":2025,"yearOfEvent":2025,"venue":"ICCV","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/ICCV51701.2025.01590"],"source":"https://dblp.org/rec/conf/iccv/LiFGY25","documentPage":"https://doi.org/10.1109/ICCV51701.2025.01590","type":"Inproceedings","doi":"https://doi.org/10.1109/ICCV51701.2025.01590","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/LiFGY25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.01590"},{"key":"conf/iccv/LiZGYL25","title":"Breaking the Encoder Barrier for Seamless Video-Language Understanding.","year":2025,"yearOfEvent":2025,"venue":"ICCV","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/ICCV51701.2025.02151"],"source":"https://dblp.org/rec/conf/iccv/LiZGYL25","documentPage":"https://doi.org/10.1109/ICCV51701.2025.02151","type":"Inproceedings","doi":"https://doi.org/10.1109/ICCV51701.2025.02151","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/LiZGYL25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.02151"},{"key":"conf/iccv/PengLYZXZBMWZSCZY25","title":"Chimera: Improving Generalist Model with Domain-Specific Experts.","year":2025,"yearOfEvent":2025,"venue":"ICCV","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/ICCV51701.2025.00289"],"source":"https://dblp.org/rec/conf/iccv/PengLYZXZBMWZSCZY25","documentPage":"https://doi.org/10.1109/ICCV51701.2025.00289","type":"Inproceedings","doi":"https://doi.org/10.1109/ICCV51701.2025.00289","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/PengLYZXZBMWZSCZY25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.00289"},{"key":"conf/iccv/WuWYMGZOT25","title":"CMT: A Cascade MAR with Topology Predictor for Multimodal Conditional CAD Generation.","year":2025,"yearOfEvent":2025,"venue":"ICCV","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/ICCV51701.2025.00659"],"source":"https://dblp.org/rec/conf/iccv/WuWYMGZOT25","documentPage":"https://doi.org/10.1109/ICCV51701.2025.00659","type":"Inproceedings","doi":"https://doi.org/10.1109/ICCV51701.2025.00659","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/WuWYMGZOT25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.00659"},{"key":"conf/iccv/YuZLZDY25","title":"From Easy to Hard: Progressive Active Learning Framework for Infrared Small Target Detection with Single Point Supervision.","year":2025,"yearOfEvent":2025,"venue":"ICCV","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/ICCV51701.2025.00249"],"source":"https://dblp.org/rec/conf/iccv/YuZLZDY25","documentPage":"https://doi.org/10.1109/ICCV51701.2025.00249","type":"Inproceedings","doi":"https://doi.org/10.1109/ICCV51701.2025.00249","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/YuZLZDY25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.00249"},{"key":"conf/iccv/ZhangJLY25","title":"Learning Beyond Still Frames: Scaling Vision-Language Models with Video.","year":2025,"yearOfEvent":2025,"venue":"ICCV","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/ICCV51701.2025.02082"],"source":"https://dblp.org/rec/conf/iccv/ZhangJLY25","documentPage":"https://doi.org/10.1109/ICCV51701.2025.02082","type":"Inproceedings","doi":"https://doi.org/10.1109/ICCV51701.2025.02082","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/ZhangJLY25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.02082"},{"key":"conf/iccv/ZhangLLY25","title":"Scaling Omni-Modal Pretraining with Multimodal Context: Advancing Universal Representation Learning Across Modalities.","year":2025,"yearOfEvent":2025,"venue":"ICCV","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/ICCV51701.2025.00132"],"source":"https://dblp.org/rec/conf/iccv/ZhangLLY25","documentPage":"https://doi.org/10.1109/ICCV51701.2025.00132","type":"Inproceedings","doi":"https://doi.org/10.1109/ICCV51701.2025.00132","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/ZhangLLY25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.00132"},{"key":"conf/iclr/HuangDWQY025","title":"Unposed Sparse Views Room Layout Reconstruction in the Age of Pretrain Model.","year":2025,"yearOfEvent":2025,"venue":"ICLR","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/iclr/HuangDWQY025","documentPage":"https://openreview.net/forum?id=DugT77rRhW","type":"Inproceedings","doi":null,"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iclr/HuangDWQY025","documentUrl":"https://openreview.net/forum?id=DugT77rRhW"},{"key":"conf/icml/Hu0Q0CW025","title":"Divide and Conquer: Grounding LLMs as Efficient Decision-Making Agents via Offline Hierarchical Reinforcement Learning.","year":2025,"yearOfEvent":2025,"venue":"ICML","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/icml/Hu0Q0CW025","documentPage":"https://proceedings.mlr.press/v267/hu25q.html","type":"Inproceedings","doi":null,"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/icml/Hu0Q0CW025","documentUrl":"https://proceedings.mlr.press/v267/hu25q.html"},{"key":"conf/nips/ChenFLLYYW25","title":"Fira: Can We Achieve Full-rank Training of LLMs Under Low-rank Constraint?","year":2025,"yearOfEvent":2025,"venue":"NeurIPS","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/nips/ChenFLLYYW25","documentPage":"http://papers.nips.cc/paper_files/paper/2025/hash/aeae2c860cbe283ef73344c4ecd52567-Abstract-Conference.html","type":"Inproceedings","doi":null,"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/nips/ChenFLLYYW25","documentUrl":"http://papers.nips.cc/paper_files/paper/2025/hash/aeae2c860cbe283ef73344c4ecd52567-Abstract-Conference.html"},{"key":"conf/nips/FengGLGWPWZWY25","title":"Video-R1: Reinforcing Video Reasoning in MLLMs.","year":2025,"yearOfEvent":2025,"venue":"NeurIPS","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/nips/FengGLGWPWZWY25","documentPage":"http://papers.nips.cc/paper_files/paper/2025/hash/8eb3976840e08b80dda9667562574246-Abstract-Conference.html","type":"Inproceedings","doi":null,"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/nips/FengGLGWPWZWY25","documentUrl":"http://papers.nips.cc/paper_files/paper/2025/hash/8eb3976840e08b80dda9667562574246-Abstract-Conference.html"},{"key":"conf/nips/HanCZWZYHYJ25","title":"Vision as a Dialect: Unifying Visual Understanding and Generation via Text-Aligned Representations.","year":2025,"yearOfEvent":2025,"venue":"NeurIPS","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/nips/HanCZWZYHYJ25","documentPage":"http://papers.nips.cc/paper_files/paper/2025/hash/e87b1e06be8c3594c810e8991e77ea40-Abstract-Conference.html","type":"Inproceedings","doi":null,"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/nips/HanCZWZYHYJ25","documentUrl":"http://papers.nips.cc/paper_files/paper/2025/hash/e87b1e06be8c3594c810e8991e77ea40-Abstract-Conference.html"},{"key":"conf/nips/LiuY25","title":"Learning to Integrate Diffusion ODEs by Averaging the Derivatives.","year":2025,"yearOfEvent":2025,"venue":"NeurIPS","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/nips/LiuY25","documentPage":"http://papers.nips.cc/paper_files/paper/2025/hash/c226d7bd4d9a3542a95c6a738e18463b-Abstract-Conference.html","type":"Inproceedings","doi":null,"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/nips/LiuY25","documentUrl":"http://papers.nips.cc/paper_files/paper/2025/hash/c226d7bd4d9a3542a95c6a738e18463b-Abstract-Conference.html"},{"key":"conf/nips/WangBYOZ25","title":"Native-Resolution Image Synthesis.","year":2025,"yearOfEvent":2025,"venue":"NeurIPS","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/nips/WangBYOZ25","documentPage":"http://papers.nips.cc/paper_files/paper/2025/hash/15dce910311b9bd82ca24f634148519a-Abstract-Conference.html","type":"Inproceedings","doi":null,"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/nips/WangBYOZ25","documentUrl":"http://papers.nips.cc/paper_files/paper/2025/hash/15dce910311b9bd82ca24f634148519a-Abstract-Conference.html"},{"key":"conf/nips/YangCGCSJLGYC25","title":"ReSim: Reliable World Simulation for Autonomous Driving.","year":2025,"yearOfEvent":2025,"venue":"NeurIPS","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/nips/YangCGCSJLGYC25","documentPage":"http://papers.nips.cc/paper_files/paper/2025/hash/f502981cbe221d857ad409450a7917c3-Abstract-Conference.html","type":"Inproceedings","doi":null,"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/nips/YangCGCSJLGYC25","documentUrl":"http://papers.nips.cc/paper_files/paper/2025/hash/f502981cbe221d857ad409450a7917c3-Abstract-Conference.html"},{"key":"journals/pami/ZhangDY25","title":"Scaling Up Your Kernels: Large Kernel Design in ConvNets Toward Universal Representations.","year":2025,"yearOfEvent":null,"venue":"IEEE Trans. Pattern Anal. Mach. Intell.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1109/TPAMI.2025.3600702"],"source":"https://dblp.org/rec/journals/pami/ZhangDY25","documentPage":"https://doi.org/10.1109/TPAMI.2025.3600702","type":"Article","doi":"https://doi.org/10.1109/TPAMI.2025.3600702","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/pami/ZhangDY25","documentUrl":"https://doi.org/10.1109/TPAMI.2025.3600702"}],"preprints":[{"key":"journals/corr/abs-2501-06533","title":"DivTrackee versus DynTracker: Promoting Diversity in Anti-Facial Recognition against Dynamic FR Strategy.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2501.06533"],"source":"https://dblp.org/rec/journals/corr/abs-2501-06533","documentPage":"https://doi.org/10.48550/ARXIV.2501.06533","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2501.06533","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2501-06533","documentUrl":"https://doi.org/10.48550/ARXIV.2501.06533","arxivId":"2501.06533","arxivUrl":"https://arxiv.org/abs/2501.06533"},{"key":"journals/corr/abs-2502-11555","title":"Equilibrate RLHF: Towards Balancing Helpfulness-Safety Trade-off in Large Language Models.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2502.11555"],"source":"https://dblp.org/rec/journals/corr/abs-2502-11555","documentPage":"https://doi.org/10.48550/ARXIV.2502.11555","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2502.11555","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2502-11555","documentUrl":"https://doi.org/10.48550/ARXIV.2502.11555","arxivId":"2502.11555","arxivUrl":"https://arxiv.org/abs/2502.11555"},{"key":"journals/corr/abs-2502-14744","title":"HiddenDetect: Detecting Jailbreak Attacks against Large Vision-Language Models via Monitoring Hidden States.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2502.14744"],"source":"https://dblp.org/rec/journals/corr/abs-2502-14744","documentPage":"https://doi.org/10.48550/ARXIV.2502.14744","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2502.14744","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2502-14744","documentUrl":"https://doi.org/10.48550/ARXIV.2502.14744","arxivId":"2502.14744","arxivUrl":"https://arxiv.org/abs/2502.14744"},{"key":"journals/corr/abs-2502-16707","title":"Reflective Planning: Vision-Language Models for Multi-Stage Long-Horizon Robotic Manipulation.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2502.16707"],"source":"https://dblp.org/rec/journals/corr/abs-2502-16707","documentPage":"https://doi.org/10.48550/ARXIV.2502.16707","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2502.16707","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2502-16707","documentUrl":"https://doi.org/10.48550/ARXIV.2502.16707","arxivId":"2502.16707","arxivUrl":"https://arxiv.org/abs/2502.16707"},{"key":"journals/corr/abs-2502-16779","title":"Unposed Sparse Views Room Layout Reconstruction in the Age of Pretrain Model.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2502.16779"],"source":"https://dblp.org/rec/journals/corr/abs-2502-16779","documentPage":"https://doi.org/10.48550/ARXIV.2502.16779","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2502.16779","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2502-16779","documentUrl":"https://doi.org/10.48550/ARXIV.2502.16779","arxivId":"2502.16779","arxivUrl":"https://arxiv.org/abs/2502.16779"},{"key":"journals/corr/abs-2503-01291","title":"SemGeoMo: Dynamic Contextual Human Motion Generation with Semantic and Geometric Guidance.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2503.01291"],"source":"https://dblp.org/rec/journals/corr/abs-2503-01291","documentPage":"https://doi.org/10.48550/ARXIV.2503.01291","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2503.01291","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-01291","documentUrl":"https://doi.org/10.48550/ARXIV.2503.01291","arxivId":"2503.01291","arxivUrl":"https://arxiv.org/abs/2503.01291"},{"key":"journals/corr/abs-2503-16302","title":"Unleashing Vecset Diffusion Model for Fast Shape Generation.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2503.16302"],"source":"https://dblp.org/rec/journals/corr/abs-2503-16302","documentPage":"https://doi.org/10.48550/ARXIV.2503.16302","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2503.16302","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-16302","documentUrl":"https://doi.org/10.48550/ARXIV.2503.16302","arxivId":"2503.16302","arxivUrl":"https://arxiv.org/abs/2503.16302"},{"key":"journals/corr/abs-2503-18422","title":"Breaking the Encoder Barrier for Seamless Video-Language Understanding.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2503.18422"],"source":"https://dblp.org/rec/journals/corr/abs-2503-18422","documentPage":"https://doi.org/10.48550/ARXIV.2503.18422","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2503.18422","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-18422","documentUrl":"https://doi.org/10.48550/ARXIV.2503.18422","arxivId":"2503.18422","arxivUrl":"https://arxiv.org/abs/2503.18422"},{"key":"journals/corr/abs-2503-20748","title":"UniSTD: Towards Unified Spatio-Temporal Learning across Diverse Disciplines.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2503.20748"],"source":"https://dblp.org/rec/journals/corr/abs-2503-20748","documentPage":"https://doi.org/10.48550/ARXIV.2503.20748","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2503.20748","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-20748","documentUrl":"https://doi.org/10.48550/ARXIV.2503.20748","arxivId":"2503.20748","arxivUrl":"https://arxiv.org/abs/2503.20748"},{"key":"journals/corr/abs-2503-21776","title":"Video-R1: Reinforcing Video Reasoning in MLLMs.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2503.21776"],"source":"https://dblp.org/rec/journals/corr/abs-2503-21776","documentPage":"https://doi.org/10.48550/ARXIV.2503.21776","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2503.21776","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-21776","documentUrl":"https://doi.org/10.48550/ARXIV.2503.21776","arxivId":"2503.21776","arxivUrl":"https://arxiv.org/abs/2503.21776"},{"key":"journals/corr/abs-2504-10443","title":"Multimodal Long Video Modeling Based on Temporal Dynamic Context.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2504.10443"],"source":"https://dblp.org/rec/journals/corr/abs-2504-10443","documentPage":"https://doi.org/10.48550/ARXIV.2504.10443","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2504.10443","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2504-10443","documentUrl":"https://doi.org/10.48550/ARXIV.2504.10443","arxivId":"2504.10443","arxivUrl":"https://arxiv.org/abs/2504.10443"},{"key":"journals/corr/abs-2504-20830","title":"CMT: A Cascade MAR with Topology Predictor for Multimodal Conditional CAD Generation.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2504.20830"],"source":"https://dblp.org/rec/journals/corr/abs-2504-20830","documentPage":"https://doi.org/10.48550/ARXIV.2504.20830","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2504.20830","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2504-20830","documentUrl":"https://doi.org/10.48550/ARXIV.2504.20830","arxivId":"2504.20830","arxivUrl":"https://arxiv.org/abs/2504.20830"},{"key":"journals/corr/abs-2505-14502","title":"Learning to Integrate Diffusion ODEs by Averaging the Derivatives.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2505.14502"],"source":"https://dblp.org/rec/journals/corr/abs-2505-14502","documentPage":"https://doi.org/10.48550/ARXIV.2505.14502","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2505.14502","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-14502","documentUrl":"https://doi.org/10.48550/ARXIV.2505.14502","arxivId":"2505.14502","arxivUrl":"https://arxiv.org/abs/2505.14502"},{"key":"journals/corr/abs-2505-16938","title":"NovelSeek: When Agent Becomes the Scientist - Building Closed-Loop System from Hypothesis to Verification.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2505.16938"],"source":"https://dblp.org/rec/journals/corr/abs-2505-16938","documentPage":"https://doi.org/10.48550/ARXIV.2505.16938","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2505.16938","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-16938","documentUrl":"https://doi.org/10.48550/ARXIV.2505.16938","arxivId":"2505.16938","arxivUrl":"https://arxiv.org/abs/2505.16938"},{"key":"journals/corr/abs-2505-17018","title":"SophiaVL-R1: Reinforcing MLLMs Reasoning with Thinking Reward.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2505.17018"],"source":"https://dblp.org/rec/journals/corr/abs-2505-17018","documentPage":"https://doi.org/10.48550/ARXIV.2505.17018","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2505.17018","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-17018","documentUrl":"https://doi.org/10.48550/ARXIV.2505.17018","arxivId":"2505.17018","arxivUrl":"https://arxiv.org/abs/2505.17018"},{"key":"journals/corr/abs-2505-19761","title":"Divide and Conquer: Grounding LLMs as Efficient Decision-Making Agents via Offline Hierarchical Reinforcement Learning.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2505.19761"],"source":"https://dblp.org/rec/journals/corr/abs-2505-19761","documentPage":"https://doi.org/10.48550/ARXIV.2505.19761","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2505.19761","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-19761","documentUrl":"https://doi.org/10.48550/ARXIV.2505.19761","arxivId":"2505.19761","arxivUrl":"https://arxiv.org/abs/2505.19761"},{"key":"journals/corr/abs-2505-21327","title":"MME-Reasoning: A Comprehensive Benchmark for Logical Reasoning in MLLMs.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2505.21327"],"source":"https://dblp.org/rec/journals/corr/abs-2505-21327","documentPage":"https://doi.org/10.48550/ARXIV.2505.21327","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2505.21327","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-21327","documentUrl":"https://doi.org/10.48550/ARXIV.2505.21327","arxivId":"2505.21327","arxivUrl":"https://arxiv.org/abs/2505.21327"},{"key":"journals/corr/abs-2505-23764","title":"MMSI-Bench: A Benchmark for Multi-Image Spatial Intelligence.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2505.23764"],"source":"https://dblp.org/rec/journals/corr/abs-2505-23764","documentPage":"https://doi.org/10.48550/ARXIV.2505.23764","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2505.23764","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-23764","documentUrl":"https://doi.org/10.48550/ARXIV.2505.23764","arxivId":"2505.23764","arxivUrl":"https://arxiv.org/abs/2505.23764"},{"key":"journals/corr/abs-2506-03131","title":"Native-Resolution Image Synthesis.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2506.03131"],"source":"https://dblp.org/rec/journals/corr/abs-2506-03131","documentPage":"https://doi.org/10.48550/ARXIV.2506.03131","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2506.03131","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-03131","documentUrl":"https://doi.org/10.48550/ARXIV.2506.03131","arxivId":"2506.03131","arxivUrl":"https://arxiv.org/abs/2506.03131"},{"key":"journals/corr/abs-2506-09981","title":"ReSim: Reliable World Simulation for Autonomous Driving.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2506.09981"],"source":"https://dblp.org/rec/journals/corr/abs-2506-09981","documentPage":"https://doi.org/10.48550/ARXIV.2506.09981","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2506.09981","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-09981","documentUrl":"https://doi.org/10.48550/ARXIV.2506.09981","arxivId":"2506.09981","arxivUrl":"https://arxiv.org/abs/2506.09981"},{"key":"journals/corr/abs-2506-12430","title":"Pushing the Limits of Safety: A Technical Report on the ATLAS Challenge 2025.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2506.12430"],"source":"https://dblp.org/rec/journals/corr/abs-2506-12430","documentPage":"https://doi.org/10.48550/ARXIV.2506.12430","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2506.12430","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-12430","documentUrl":"https://doi.org/10.48550/ARXIV.2506.12430","arxivId":"2506.12430","arxivUrl":"https://arxiv.org/abs/2506.12430"},{"key":"journals/corr/abs-2506-18898","title":"Vision as a Dialect: Unifying Visual Understanding and Generation via Text-Aligned Representations.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2506.18898"],"source":"https://dblp.org/rec/journals/corr/abs-2506-18898","documentPage":"https://doi.org/10.48550/ARXIV.2506.18898","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2506.18898","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-18898","documentUrl":"https://doi.org/10.48550/ARXIV.2506.18898","arxivId":"2506.18898","arxivUrl":"https://arxiv.org/abs/2506.18898"},{"key":"journals/corr/abs-2506-19257","title":"MSR-Align: Policy-Grounded Multimodal Alignment for Safety-Aware Reasoning in Vision-Language Models.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2506.19257"],"source":"https://dblp.org/rec/journals/corr/abs-2506-19257","documentPage":"https://doi.org/10.48550/ARXIV.2506.19257","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2506.19257","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-19257","documentUrl":"https://doi.org/10.48550/ARXIV.2506.19257","arxivId":"2506.19257","arxivUrl":"https://arxiv.org/abs/2506.19257"},{"key":"journals/corr/abs-2507-19478","title":"MMBench-GUI: Hierarchical Multi-Platform Evaluation Framework for GUI Agents.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2507.19478"],"source":"https://dblp.org/rec/journals/corr/abs-2507-19478","documentPage":"https://doi.org/10.48550/ARXIV.2507.19478","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2507.19478","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2507-19478","documentUrl":"https://doi.org/10.48550/ARXIV.2507.19478","arxivId":"2507.19478","arxivUrl":"https://arxiv.org/abs/2507.19478"},{"key":"journals/corr/abs-2507-22827","title":"ScreenCoder: Advancing Visual-to-Code Generation for Front-End Automation via Modular Multimodal Agents.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2507.22827"],"source":"https://dblp.org/rec/journals/corr/abs-2507-22827","documentPage":"https://doi.org/10.48550/ARXIV.2507.22827","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2507.22827","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2507-22827","documentUrl":"https://doi.org/10.48550/ARXIV.2507.22827","arxivId":"2507.22827","arxivUrl":"https://arxiv.org/abs/2507.22827"},{"key":"journals/corr/abs-2509-04394","title":"Transition Models: Rethinking the Generative Learning Objective.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2509.04394"],"source":"https://dblp.org/rec/journals/corr/abs-2509-04394","documentPage":"https://doi.org/10.48550/ARXIV.2509.04394","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2509.04394","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-04394","documentUrl":"https://doi.org/10.48550/ARXIV.2509.04394","arxivId":"2509.04394","arxivUrl":"https://arxiv.org/abs/2509.04394"},{"key":"journals/corr/abs-2509-15221","title":"ScaleCUA: Scaling Open-Source Computer Use Agents with Cross-Platform Data.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2509.15221"],"source":"https://dblp.org/rec/journals/corr/abs-2509-15221","documentPage":"https://doi.org/10.48550/ARXIV.2509.15221","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2509.15221","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-15221","documentUrl":"https://doi.org/10.48550/ARXIV.2509.15221","arxivId":"2509.15221","arxivUrl":"https://arxiv.org/abs/2509.15221"},{"key":"journals/corr/abs-2509-21320","title":"SciReasoner: Laying the Scientific Reasoning Ground Across Disciplines.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2509.21320"],"source":"https://dblp.org/rec/journals/corr/abs-2509-21320","documentPage":"https://doi.org/10.48550/ARXIV.2509.21320","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2509.21320","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-21320","documentUrl":"https://doi.org/10.48550/ARXIV.2509.21320","arxivId":"2509.21320","arxivUrl":"https://arxiv.org/abs/2509.21320"},{"key":"journals/corr/abs-2510-01546","title":"Growing Visual Generative Capacity for Pre-Trained MLLMs.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2510.01546"],"source":"https://dblp.org/rec/journals/corr/abs-2510-01546","documentPage":"https://doi.org/10.48550/ARXIV.2510.01546","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2510.01546","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-01546","documentUrl":"https://doi.org/10.48550/ARXIV.2510.01546","arxivId":"2510.01546","arxivUrl":"https://arxiv.org/abs/2510.01546"},{"key":"journals/corr/abs-2510-08555","title":"VideoCanvas: Unified Video Completion from Arbitrary Spatiotemporal Patches via In-Context Conditioning.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2510.08555"],"source":"https://dblp.org/rec/journals/corr/abs-2510-08555","documentPage":"https://doi.org/10.48550/ARXIV.2510.08555","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2510.08555","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-08555","documentUrl":"https://doi.org/10.48550/ARXIV.2510.08555","arxivId":"2510.08555","arxivUrl":"https://arxiv.org/abs/2510.08555"},{"key":"journals/corr/abs-2510-09606","title":"SpaceVista: All-Scale Visual Spatial Reasoning from mm to km.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2510.09606"],"source":"https://dblp.org/rec/journals/corr/abs-2510-09606","documentPage":"https://doi.org/10.48550/ARXIV.2510.09606","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2510.09606","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-09606","documentUrl":"https://doi.org/10.48550/ARXIV.2510.09606","arxivId":"2510.09606","arxivUrl":"https://arxiv.org/abs/2510.09606"},{"key":"journals/corr/abs-2510-10518","title":"VR-Thinker: Boosting Video Reward Models through Thinking-with-Image Reasoning.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2510.10518"],"source":"https://dblp.org/rec/journals/corr/abs-2510-10518","documentPage":"https://doi.org/10.48550/ARXIV.2510.10518","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2510.10518","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-10518","documentUrl":"https://doi.org/10.48550/ARXIV.2510.10518","arxivId":"2510.10518","arxivUrl":"https://arxiv.org/abs/2510.10518"},{"key":"journals/corr/abs-2511-16317","title":"NaTex: Seamless Texture Generation as Latent Color Diffusion.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2511.16317"],"source":"https://dblp.org/rec/journals/corr/abs-2511-16317","documentPage":"https://doi.org/10.48550/ARXIV.2511.16317","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2511.16317","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2511-16317","documentUrl":"https://doi.org/10.48550/ARXIV.2511.16317","arxivId":"2511.16317","arxivUrl":"https://arxiv.org/abs/2511.16317"},{"key":"journals/corr/abs-2511-17731","title":"VisReason: A Large-Scale Dataset for Visual Chain-of-Thought Reasoning.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2511.17731"],"source":"https://dblp.org/rec/journals/corr/abs-2511-17731","documentPage":"https://doi.org/10.48550/ARXIV.2511.17731","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2511.17731","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2511-17731","documentUrl":"https://doi.org/10.48550/ARXIV.2511.17731","arxivId":"2511.17731","arxivUrl":"https://arxiv.org/abs/2511.17731"},{"key":"journals/corr/abs-2511-18780","title":"ConceptGuard: Proactive Safety in Text-and-Image-to-Video Generation through Multimodal Risk Detection.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2511.18780"],"source":"https://dblp.org/rec/journals/corr/abs-2511-18780","documentPage":"https://doi.org/10.48550/ARXIV.2511.18780","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2511.18780","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2511-18780","documentUrl":"https://doi.org/10.48550/ARXIV.2511.18780","arxivId":"2511.18780","arxivUrl":"https://arxiv.org/abs/2511.18780"},{"key":"journals/corr/abs-2511-20646","title":"3D-Aware Multi-Task Learning with Cross-View Correlations for Dense Scene Understanding.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2511.20646"],"source":"https://dblp.org/rec/journals/corr/abs-2511-20646","documentPage":"https://doi.org/10.48550/ARXIV.2511.20646","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2511.20646","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2511-20646","documentUrl":"https://doi.org/10.48550/ARXIV.2511.20646","arxivId":"2511.20646","arxivUrl":"https://arxiv.org/abs/2511.20646"},{"key":"journals/corr/abs-2511-23476","title":"Thinking by Doing: Building Efficient World Model Reasoning in LLMs via Multi-turn Interaction.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2511.23476"],"source":"https://dblp.org/rec/journals/corr/abs-2511-23476","documentPage":"https://doi.org/10.48550/ARXIV.2511.23476","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2511.23476","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2511-23476","documentUrl":"https://doi.org/10.48550/ARXIV.2511.23476","arxivId":"2511.23476","arxivUrl":"https://arxiv.org/abs/2511.23476"},{"key":"journals/corr/abs-2512-03043","title":"OneThinker: All-in-one Reasoning Model for Image and Video.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2512.03043"],"source":"https://dblp.org/rec/journals/corr/abs-2512-03043","documentPage":"https://doi.org/10.48550/ARXIV.2512.03043","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2512.03043","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-03043","documentUrl":"https://doi.org/10.48550/ARXIV.2512.03043","arxivId":"2512.03043","arxivUrl":"https://arxiv.org/abs/2512.03043"},{"key":"journals/corr/abs-2512-03052","title":"LATTICE: Democratize High-Fidelity 3D Generation at Scale.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2512.03052"],"source":"https://dblp.org/rec/journals/corr/abs-2512-03052","documentPage":"https://doi.org/10.48550/ARXIV.2512.03052","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2512.03052","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-03052","documentUrl":"https://doi.org/10.48550/ARXIV.2512.03052","arxivId":"2512.03052","arxivUrl":"https://arxiv.org/abs/2512.03052"},{"key":"journals/corr/abs-2512-05511","title":"Rethinking Infrared Small Target Detection: A Foundation-Driven Efficient Paradigm.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2512.05511"],"source":"https://dblp.org/rec/journals/corr/abs-2512-05511","documentPage":"https://doi.org/10.48550/ARXIV.2512.05511","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2512.05511","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-05511","documentUrl":"https://doi.org/10.48550/ARXIV.2512.05511","arxivId":"2512.05511","arxivUrl":"https://arxiv.org/abs/2512.05511"},{"key":"journals/corr/abs-2512-05530","title":"MIND: Multi-rationale INtegrated Discriminative Reasoning Framework for Multi-modal Large Models.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2512.05530"],"source":"https://dblp.org/rec/journals/corr/abs-2512-05530","documentPage":"https://doi.org/10.48550/ARXIV.2512.05530","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2512.05530","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-05530","documentUrl":"https://doi.org/10.48550/ARXIV.2512.05530","arxivId":"2512.05530","arxivUrl":"https://arxiv.org/abs/2512.05530"},{"key":"journals/corr/abs-2512-16279","title":"QuadSentinel: Sequent Safety for Machine-Checkable Control in Multi-agent Systems.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2512.16279"],"source":"https://dblp.org/rec/journals/corr/abs-2512-16279","documentPage":"https://doi.org/10.48550/ARXIV.2512.16279","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2512.16279","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-16279","documentUrl":"https://doi.org/10.48550/ARXIV.2512.16279","arxivId":"2512.16279","arxivUrl":"https://arxiv.org/abs/2512.16279"},{"key":"journals/corr/abs-2512-16295","title":"OS-Oracle: A Comprehensive Framework for Cross-Platform GUI Critic Models.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2512.16295"],"source":"https://dblp.org/rec/journals/corr/abs-2512-16295","documentPage":"https://doi.org/10.48550/ARXIV.2512.16295","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2512.16295","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-16295","documentUrl":"https://doi.org/10.48550/ARXIV.2512.16295","arxivId":"2512.16295","arxivUrl":"https://arxiv.org/abs/2512.16295"},{"key":"journals/corr/abs-2512-16918","title":"AdaTooler-V: Adaptive Tool-Use for Images and Videos.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2512.16918"],"source":"https://dblp.org/rec/journals/corr/abs-2512-16918","documentPage":"https://doi.org/10.48550/ARXIV.2512.16918","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2512.16918","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-16918","documentUrl":"https://doi.org/10.48550/ARXIV.2512.16918","arxivId":"2512.16918","arxivUrl":"https://arxiv.org/abs/2512.16918"},{"key":"journals/corr/abs-2512-18772","title":"In-Context Audio Control of Video Diffusion Transformers.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2512.18772"],"source":"https://dblp.org/rec/journals/corr/abs-2512-18772","documentPage":"https://doi.org/10.48550/ARXIV.2512.18772","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2512.18772","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-18772","documentUrl":"https://doi.org/10.48550/ARXIV.2512.18772","arxivId":"2512.18772","arxivUrl":"https://arxiv.org/abs/2512.18772"}],"excludedFormal":[],"excludedOther":[],"excludedHomonyms":[],"unassignedCandidates":[],"retrievedAt":"2026-10-19","querySource":"https://sparql.dblp.org/","method":"DBLP yearOfPublication=2025; Article + Inproceedings; excludes Informal/CoRR and explicit editorial/correction/erratum/preface; unique DBLP record keys within person.","labName":"Multimedia Laboratory（MMLab）","labUrl":"https://mmlab.ie.cuhk.edu.hk/","labEvidence":"本人当前主页任职栏及自述均明确列为港中文 Multimedia Laboratory (MMLab)。","labSourceUrl":"https://xyue.io/","affiliationZh":"香港中文大学","sourceWarning":false,"knownPreprintMinimum2025":null,"excludedMisattributed":[],"displayNotes":"身份已经个人或机构主页核对。2025 年正式记录 28 条（会议 27、期刊 1），所有作者位置均计入，不表示主导或贡献份额；预印本 45 条单列，不加总。","labDisplayNotes":"本人主页的任职栏与自述都写明港中文 Multimedia Laboratory（MMLab）。与李鸿升、薛天帆同组；因李鸿升暂无总数，整组不画柱。"},{"index":107,"name":"Chao Zhang","nameZh":"张超","affiliation":"Tsinghua University","source":"DBLP Knowledge Graph official SPARQL API","profileUrl":null,"identifier":null,"identityEvidence":[{"url":"https://www.cs.tsinghua.edu.cn/csen/info/1310/4365.htm","evidence":"One Chao Zhang is an associate professor in network security, DBLP 94/3019-8."},{"url":"https://web.ee.tsinghua.edu.cn/zhangchao1/en/index/8507/list/index.htm","evidence":"Another Chao Zhang is an associate professor in electronic engineering, Cambridge PhD, DBLP 94/3019-31. Statement lists no department or link, so identity is unresolved."}],"count2025":null,"conference2025":null,"journal2025":null,"preprint2025":null,"status":"unresolved_identity","notes":"Counts are DBLP indexed coauthored records, not first-author counts, laboratory totals, unique scientific discoveries, or quality assessments. DBLP yearOfPublication=2025; yearOfEvent retained and can differ. Conference workshops are included. Preprints are separate and may overlap formal versions. At least two Tsinghua associate professors have the exact same Chinese and English name. Original signatory list gives no department or personal link. No PID chosen and no count reported.","papers":[],"preprints":[],"excludedFormal":[],"excludedOther":[],"excludedHomonyms":[],"unassignedCandidates":[],"retrievedAt":"2026-10-19","querySource":"https://sparql.dblp.org/","method":"DBLP yearOfPublication=2025; Article + Inproceedings; excludes Informal/CoRR and explicit editorial/correction/erratum/preface; unique DBLP record keys within person.","labName":null,"labUrl":null,"labEvidence":"原联署名单没有系所或本人链接，至少存在两位相符的清华张超副教授；身份未消歧，不分配任何候选人的Lab。","labSourceUrl":null,"affiliationZh":"清华大学","sourceWarning":false,"knownPreprintMinimum2025":null,"excludedMisattributed":[],"knownMinimum2025":null,"displayNotes":"清华大学至少有两位同名的张超副教授，计算机系网络安全方向与电子工程系各一位。原名单只写了姓名、职称和学校，不足以排除其中任何一位，因此未选定 DBLP 档案，不报告任何数字，这绝非零。我们没有用研究方向、发文多少或其他联署者来推断。","labDisplayNotes":"身份未定，不能借用任何一位同名者的主页来指定实验室。"},{"index":108,"name":"Chi Zhang","nameZh":"张驰","affiliation":"Westlake University","source":"DBLP Knowledge Graph official SPARQL API","profileUrl":"https://dblp.org/pid/91/195-7","identifier":"91/195-7","identityEvidence":[{"url":"https://dblp.org/pid/91/195-7","evidence":"DBLP curated profile affiliations: Nanyang Technological University, School of Computer Science and Engineering, Singapore; Tencent, China; Westlake University, School of Engineering, Hangzhou, China."},{"url":"https://dblp.org/pid/91/195-7","evidence":"DBLP curated profile homepages: https://icoz69.github.io/; https://openreview.net/profile?id=~Chi_Zhang13."},{"url":"https://icoz69.github.io/","evidence":"Personal Westlake faculty page confirms retained publication titles; public ORCID 0000-0001-6344-2824 directly links this page and appears in retained author signatures."},{"url":"https://pub.orcid.org/v3.0/0000-0001-6344-2824/person","evidence":"ORCID personal URL points to icoz69.github.io."},{"url":"https://api.crossref.org/works/10.1109%2FTIFS.2025.3586468","evidence":"Detecting Deceptive Behavior assigns Chi Zhang to Xidian University with different ORCID 0009-0009-4457-0893; it is excluded."},{"url":"https://papers.nips.cc/paper_files/paper/2025/file/5e27f5d8ecd30ac6235892ef97676e78-Paper-Conference.pdf","evidence":"CAS-Spec assigns Chi Zhang to TeleAI and the chinatelecom.cn email domain."},{"url":"https://icaigc.org/committee.html","evidence":"TeleAI Chi Zhang has a Columbia PhD and Tsinghua degrees, a different biography from the intended Westlake faculty member, whose doctorate was at NTU."}],"count2025":16,"conference2025":15,"journal2025":1,"preprint2025":null,"status":"verified_manual","notes":"Counts are DBLP indexed coauthored records, not first-author counts, laboratory totals, unique scientific discoveries, or quality assessments. DBLP yearOfPublication=2025; yearOfEvent retained and can differ. Conference workshops are included. Preprints are separate and may overlap formal versions. Formal 2025 records were reviewed individually after detected DBLP homonyms were excluded. The preprint pool is still incomplete and its total is withheld independently.","papers":[{"key":"conf/chi/ZhangYLLHCHF025","title":"AppAgent: Multimodal Agents as Smartphone Users.","year":2025,"yearOfEvent":2025,"venue":"CHI","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1145/3706598.3713600"],"source":"https://dblp.org/rec/conf/chi/ZhangYLLHCHF025","documentPage":"https://doi.org/10.1145/3706598.3713600","type":"Inproceedings","doi":"https://doi.org/10.1145/3706598.3713600","authorSignatures":[{"orcid":"https://orcid.org/0000-0001-6344-2824","inst":"https://dblp.org/inst/12/029","instLabel":"Tencent"},{"orcid":"https://orcid.org/0000-0001-6344-2824","inst":"https://dblp.org/inst/12/203","instLabel":"Westlake University (WIAS)"}],"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/chi/ZhangYLLHCHF025","documentUrl":"https://doi.org/10.1145/3706598.3713600"},{"key":"conf/cvpr/ChengMZCPZWF00P25","title":"MVPaint: Synchronized Multi-View Diffusion for Painting Anything 3D.","year":2025,"yearOfEvent":2025,"venue":"CVPR","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/CVPR52734.2025.00063"],"source":"https://dblp.org/rec/conf/cvpr/ChengMZCPZWF00P25","documentPage":"https://openaccess.thecvf.com/content/CVPR2025/html/Cheng_MVPaint_Synchronized_Multi-View_Diffusion_for_Painting_Anything_3D_CVPR_2025_paper.html","type":"Inproceedings","doi":"https://doi.org/10.1109/CVPR52734.2025.00063","authorSignatures":[{"orcid":"https://orcid.org/0000-0001-6344-2824","inst":"https://dblp.org/inst/12/203","instLabel":"Westlake University (WIAS)"}],"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/ChengMZCPZWF00P25","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Cheng_MVPaint_Synchronized_Multi-View_Diffusion_for_Painting_Anything_3D_CVPR_2025_paper.html"},{"key":"conf/cvpr/ChenWC0YZYFLHL25","title":"CADCrafter: Generating Computer-Aided Design Models from Unconstrained Images.","year":2025,"yearOfEvent":2025,"venue":"CVPR","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/CVPR52734.2025.01034"],"source":"https://dblp.org/rec/conf/cvpr/ChenWC0YZYFLHL25","documentPage":"https://openaccess.thecvf.com/content/CVPR2025/html/Chen_CADCrafter_Generating_Computer-Aided_Design_Models_from_Unconstrained_Images_CVPR_2025_paper.html","type":"Inproceedings","doi":"https://doi.org/10.1109/CVPR52734.2025.01034","authorSignatures":[{"orcid":"https://orcid.org/0000-0001-6344-2824","inst":"https://dblp.org/inst/12/203","instLabel":"Westlake University (WIAS)"}],"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/ChenWC0YZYFLHL25","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Chen_CADCrafter_Generating_Computer-Aided_Design_Models_from_Unconstrained_Images_CVPR_2025_paper.html"},{"key":"conf/cvpr/HanLCYWDLDFLZZL25","title":"Video-Bench: Human-Aligned Video Generation Benchmark.","year":2025,"yearOfEvent":2025,"venue":"CVPR","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/CVPR52734.2025.01757"],"source":"https://dblp.org/rec/conf/cvpr/HanLCYWDLDFLZZL25","documentPage":"https://openaccess.thecvf.com/content/CVPR2025/html/Han_Video-Bench_Human-Aligned_Video_Generation_Benchmark_CVPR_2025_paper.html","type":"Inproceedings","doi":"https://doi.org/10.1109/CVPR52734.2025.01757","authorSignatures":[{"orcid":"https://orcid.org/0000-0001-6344-2824","inst":"https://dblp.org/inst/12/203","instLabel":"Westlake University (WIAS)"}],"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/HanLCYWDLDFLZZL25","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Han_Video-Bench_Human-Aligned_Video_Generation_Benchmark_CVPR_2025_paper.html"},{"key":"conf/eccv/JiangCZYLYF24","title":"MotionChain: Conversational Motion Controllers via Multimodal Prompts.","year":2025,"yearOfEvent":2024,"venue":"ECCV (26)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1007/978-3-031-73347-5_4"],"source":"https://dblp.org/rec/conf/eccv/JiangCZYLYF24","documentPage":"https://doi.org/10.1007/978-3-031-73347-5_4","type":"Inproceedings","doi":"https://doi.org/10.1007/978-3-031-73347-5_4","authorSignatures":[{"orcid":"https://orcid.org/0000-0001-6344-2824","inst":"https://dblp.org/inst/12/029","instLabel":"Tencent"}],"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/eccv/JiangCZYLYF24","documentUrl":"https://doi.org/10.1007/978-3-031-73347-5_4"},{"key":"conf/iccv/ChenWLWCZZL25","title":"MeshAnything V2: Artist-Created Mesh Generation with Adjacent Mesh Tokenization.","year":2025,"yearOfEvent":2025,"venue":"ICCV","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/ICCV51701.2025.01292"],"source":"https://dblp.org/rec/conf/iccv/ChenWLWCZZL25","documentPage":"https://doi.org/10.1109/ICCV51701.2025.01292","type":"Inproceedings","doi":"https://doi.org/10.1109/ICCV51701.2025.01292","authorSignatures":[{"inst":"https://dblp.org/inst/12/203","instLabel":"Westlake University (WIAS)"}],"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/ChenWLWCZZL25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.01292"},{"key":"conf/iccv/LiaoZWYLZ25","title":"Motionagent: Fine-Grained Controllable Video Generation via Motion Field Agent.","year":2025,"yearOfEvent":2025,"venue":"ICCV","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/ICCV51701.2025.01052"],"source":"https://dblp.org/rec/conf/iccv/LiaoZWYLZ25","documentPage":"https://doi.org/10.1109/ICCV51701.2025.01052","type":"Inproceedings","doi":"https://doi.org/10.1109/ICCV51701.2025.01052","authorSignatures":[{"orcid":"https://orcid.org/0000-0001-6344-2824","inst":"https://dblp.org/inst/12/203","instLabel":"Westlake University (WIAS)"}],"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/LiaoZWYLZ25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.01052"},{"key":"conf/iclr/Chen0HYCTC0YL025","title":"MeshAnything: Artist-Created Mesh Generation with Autoregressive Transformers.","year":2025,"yearOfEvent":2025,"venue":"ICLR","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/iclr/Chen0HYCTC0YL025","documentPage":"https://openreview.net/forum?id=KGZAs8VcOM","type":"Inproceedings","doi":null,"authorSignatures":[{}],"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iclr/Chen0HYCTC0YL025","documentUrl":"https://openreview.net/forum?id=KGZAs8VcOM"},{"key":"conf/ijcnn/HanZCYYWYFZ25","title":"A Multimodal LLM for Chart Understanding and Generation.","year":2025,"yearOfEvent":2025,"venue":"IJCNN","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/IJCNN64981.2025.11227777"],"source":"https://dblp.org/rec/conf/ijcnn/HanZCYYWYFZ25","documentPage":"https://doi.org/10.1109/IJCNN64981.2025.11227777","type":"Inproceedings","doi":"https://doi.org/10.1109/IJCNN64981.2025.11227777","authorSignatures":[{"orcid":"https://orcid.org/0000-0001-6344-2824","inst":"https://dblp.org/inst/12/029","instLabel":"Tencent"}],"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/ijcnn/HanZCYYWYFZ25","documentUrl":"https://doi.org/10.1109/IJCNN64981.2025.11227777"},{"key":"conf/mm/SongWSZTF025","title":"DreamFrame: Enhancing Video Understanding via Automatically Generated QA and Style-Consistent Keyframes.","year":2025,"yearOfEvent":2025,"venue":"ACM Multimedia","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1145/3746027.3758252"],"source":"https://dblp.org/rec/conf/mm/SongWSZTF025","documentPage":"https://doi.org/10.1145/3746027.3758252","type":"Inproceedings","doi":"https://doi.org/10.1145/3746027.3758252","authorSignatures":[{"orcid":"https://orcid.org/0000-0001-6344-2824","inst":"https://dblp.org/inst/12/203","instLabel":"Westlake University (WIAS)"}],"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/mm/SongWSZTF025","documentUrl":"https://doi.org/10.1145/3746027.3758252"},{"key":"conf/mm/ZhuangJZYZZ25","title":"Learning to Be a Doctor: Searching for Effective Medical Agent Architectures.","year":2025,"yearOfEvent":2025,"venue":"ACM Multimedia","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1145/3746027.3755559"],"source":"https://dblp.org/rec/conf/mm/ZhuangJZYZZ25","documentPage":"https://doi.org/10.1145/3746027.3755559","type":"Inproceedings","doi":"https://doi.org/10.1145/3746027.3755559","authorSignatures":[{"orcid":"https://orcid.org/0000-0001-6344-2824","inst":"https://dblp.org/inst/12/203","instLabel":"Westlake University (WIAS)"}],"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/mm/ZhuangJZYZZ25","documentUrl":"https://doi.org/10.1145/3746027.3755559"},{"key":"conf/nips/WangZLYZ25","title":"Adaptive Stochastic Coefficients for Accelerating Diffusion Sampling.","year":2025,"yearOfEvent":2025,"venue":"NeurIPS","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/nips/WangZLYZ25","documentPage":"http://papers.nips.cc/paper_files/paper/2025/hash/1fd14e129b6a0af09b01359fb0d0bbda-Abstract-Conference.html","type":"Inproceedings","doi":null,"authorSignatures":[{}],"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/nips/WangZLYZ25","documentUrl":"http://papers.nips.cc/paper_files/paper/2025/hash/1fd14e129b6a0af09b01359fb0d0bbda-Abstract-Conference.html"},{"key":"journals/tmm/YinCZJZLYC25","title":"ShapeGPT: 3D Shape Generation With a Unified Multi-Modal Language Model.","year":2025,"yearOfEvent":null,"venue":"IEEE Trans. Multim.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1109/TMM.2025.3535389"],"source":"https://dblp.org/rec/journals/tmm/YinCZJZLYC25","documentPage":"https://doi.org/10.1109/TMM.2025.3535389","type":"Article","doi":"https://doi.org/10.1109/TMM.2025.3535389","authorSignatures":[{"orcid":"https://orcid.org/0000-0001-6344-2824","inst":"https://dblp.org/inst/12/029","instLabel":"Tencent"}],"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/tmm/YinCZJZLYC25","documentUrl":"https://doi.org/10.1109/TMM.2025.3535389"},{"key":"conf/eccv/LiCZCZYLYC24","title":"M3DBench: Towards Omni 3D Assistant with Interleaved Multi-modal Instructions.","year":2025,"yearOfEvent":2024,"venue":"ECCV (58)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1007/978-3-031-73636-0_3"],"source":"https://dblp.org/rec/conf/eccv/LiCZCZYLYC24","documentPage":"https://doi.org/10.1007/978-3-031-73636-0_3","type":"Inproceedings","doi":"https://doi.org/10.1007/978-3-031-73636-0_3","authorSignatures":[{"orcid":"https://orcid.org/0000-0001-6344-2824","inst":"https://dblp.org/inst/12/029","instLabel":"Tencent"}],"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/eccv/LiCZCZYLYC24","documentUrl":"https://doi.org/10.1007/978-3-031-73636-0_3"},{"key":"conf/eccv/YangCCZXYLL24","title":"Learn to Optimize Denoising Scores: A Unified and Improved Diffusion Prior for 3D Generation.","year":2025,"yearOfEvent":2024,"venue":"ECCV (44)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1007/978-3-031-72784-9_8"],"source":"https://dblp.org/rec/conf/eccv/YangCCZXYLL24","documentPage":"https://doi.org/10.1007/978-3-031-72784-9_8","type":"Inproceedings","doi":"https://doi.org/10.1007/978-3-031-72784-9_8","authorSignatures":[{"orcid":"https://orcid.org/0000-0001-6344-2824","inst":"https://dblp.org/inst/12/203","instLabel":"Westlake University (WIAS)"}],"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/eccv/YangCCZXYLL24","documentUrl":"https://doi.org/10.1007/978-3-031-72784-9_8"},{"key":"conf/icmcs/LiZJYFCCFCW25","title":"Adaptive Mobile Agent for Dynamic Interactions.","year":2025,"yearOfEvent":2025,"venue":"ICME","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/ICME59968.2025.11209947"],"source":"https://dblp.org/rec/conf/icmcs/LiZJYFCCFCW25","documentPage":"https://doi.org/10.1109/ICME59968.2025.11209947","type":"Inproceedings","doi":"https://doi.org/10.1109/ICME59968.2025.11209947","authorSignatures":[{"orcid":"https://orcid.org/0000-0001-6344-2824","inst":"https://dblp.org/inst/12/203","instLabel":"Westlake University (WIAS)"}],"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/icmcs/LiZJYFCCFCW25","documentUrl":"https://doi.org/10.1109/ICME59968.2025.11209947"}],"preprints":[{"key":"journals/corr/abs-2502-03207","title":"MotionAgent: Fine-grained Controllable Video Generation via Motion Field Agent.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2502.03207"],"source":"https://dblp.org/rec/journals/corr/abs-2502-03207","documentPage":"https://doi.org/10.48550/ARXIV.2502.03207","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2502.03207","authorSignatures":[{"orcid":"https://orcid.org/0000-0001-6344-2824"}],"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2502-03207","documentUrl":"https://doi.org/10.48550/ARXIV.2502.03207","arxivId":"2502.03207","arxivUrl":"https://arxiv.org/abs/2502.03207"},{"key":"journals/corr/abs-2502-19204","title":"Distill Any Depth: Distillation Creates a Stronger Monocular Depth Estimator.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2502.19204"],"source":"https://dblp.org/rec/journals/corr/abs-2502-19204","documentPage":"https://doi.org/10.48550/ARXIV.2502.19204","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2502.19204","authorSignatures":[{"orcid":"https://orcid.org/0000-0001-6344-2824"}],"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2502-19204","documentUrl":"https://doi.org/10.48550/ARXIV.2502.19204","arxivId":"2502.19204","arxivUrl":"https://arxiv.org/abs/2502.19204"},{"key":"journals/corr/abs-2503-02268","title":"AppAgentX: Evolving GUI Agents as Proficient Smartphone Users.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2503.02268"],"source":"https://dblp.org/rec/journals/corr/abs-2503-02268","documentPage":"https://doi.org/10.48550/ARXIV.2503.02268","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2503.02268","authorSignatures":[{"orcid":"https://orcid.org/0000-0001-6344-2824"}],"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-02268","documentUrl":"https://doi.org/10.48550/ARXIV.2503.02268","arxivId":"2503.02268","arxivUrl":"https://arxiv.org/abs/2503.02268"},{"key":"journals/corr/abs-2504-04753","title":"CADCrafter: Generating Computer-Aided Design Models from Unconstrained Images.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2504.04753"],"source":"https://dblp.org/rec/journals/corr/abs-2504-04753","documentPage":"https://doi.org/10.48550/ARXIV.2504.04753","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2504.04753","authorSignatures":[{"orcid":"https://orcid.org/0000-0001-6344-2824"}],"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2504-04753","documentUrl":"https://doi.org/10.48550/ARXIV.2504.04753","arxivId":"2504.04753","arxivUrl":"https://arxiv.org/abs/2504.04753"},{"key":"journals/corr/abs-2504-04907","title":"Video-Bench: Human-Aligned Video Generation Benchmark.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2504.04907"],"source":"https://dblp.org/rec/journals/corr/abs-2504-04907","documentPage":"https://doi.org/10.48550/ARXIV.2504.04907","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2504.04907","authorSignatures":[{"orcid":"https://orcid.org/0000-0001-6344-2824"}],"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2504-04907","documentUrl":"https://doi.org/10.48550/ARXIV.2504.04907","arxivId":"2504.04907","arxivUrl":"https://arxiv.org/abs/2504.04907"},{"key":"journals/corr/abs-2504-11301","title":"Learning to Be A Doctor: Searching for Effective Medical Agent Architectures.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2504.11301"],"source":"https://dblp.org/rec/journals/corr/abs-2504-11301","documentPage":"https://doi.org/10.48550/ARXIV.2504.11301","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2504.11301","authorSignatures":[{"orcid":"https://orcid.org/0000-0001-6344-2824"}],"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2504-11301","documentUrl":"https://doi.org/10.48550/ARXIV.2504.11301","arxivId":"2504.11301","arxivUrl":"https://arxiv.org/abs/2504.11301"},{"key":"journals/corr/abs-2505-24862","title":"ViStoryBench: Comprehensive Benchmark Suite for Story Visualization.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2505.24862"],"source":"https://dblp.org/rec/journals/corr/abs-2505-24862","documentPage":"https://doi.org/10.48550/ARXIV.2505.24862","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2505.24862","authorSignatures":[{"orcid":"https://orcid.org/0000-0001-6344-2824"}],"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-24862","documentUrl":"https://doi.org/10.48550/ARXIV.2505.24862","arxivId":"2505.24862","arxivUrl":"https://arxiv.org/abs/2505.24862"},{"key":"journals/corr/abs-2506-05046","title":"FlowDirector: Training-Free Flow Steering for Precise Text-to-Video Editing.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2506.05046"],"source":"https://dblp.org/rec/journals/corr/abs-2506-05046","documentPage":"https://doi.org/10.48550/ARXIV.2506.05046","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2506.05046","authorSignatures":[{"orcid":"https://orcid.org/0000-0001-6344-2824"}],"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-05046","documentUrl":"https://doi.org/10.48550/ARXIV.2506.05046","arxivId":"2506.05046","arxivUrl":"https://arxiv.org/abs/2506.05046"},{"key":"journals/corr/abs-2507-17745","title":"Ultra3D: Efficient and High-Fidelity 3D Generation with Part Attention.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2507.17745"],"source":"https://dblp.org/rec/journals/corr/abs-2507-17745","documentPage":"https://doi.org/10.48550/ARXIV.2507.17745","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2507.17745","authorSignatures":[{}],"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2507-17745","documentUrl":"https://doi.org/10.48550/ARXIV.2507.17745","arxivId":"2507.17745","arxivUrl":"https://arxiv.org/abs/2507.17745"},{"key":"journals/corr/abs-2509-11062","title":"Auto-Slides: An Interactive Multi-Agent System for Creating and Customizing Research Presentations.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2509.11062"],"source":"https://dblp.org/rec/journals/corr/abs-2509-11062","documentPage":"https://doi.org/10.48550/ARXIV.2509.11062","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2509.11062","authorSignatures":[{"orcid":"https://orcid.org/0000-0001-6344-2824"}],"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-11062","documentUrl":"https://doi.org/10.48550/ARXIV.2509.11062","arxivId":"2509.11062","arxivUrl":"https://arxiv.org/abs/2509.11062"},{"key":"journals/corr/abs-2511-22533","title":"Fast3Dcache: Training-free 3D Geometry Synthesis Acceleration.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2511.22533"],"source":"https://dblp.org/rec/journals/corr/abs-2511-22533","documentPage":"https://doi.org/10.48550/ARXIV.2511.22533","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2511.22533","authorSignatures":[{"orcid":"https://orcid.org/0000-0001-6344-2824"}],"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2511-22533","documentUrl":"https://doi.org/10.48550/ARXIV.2511.22533","arxivId":"2511.22533","arxivUrl":"https://arxiv.org/abs/2511.22533"},{"key":"journals/corr/abs-2503-07076","title":"NFIG: Autoregressive Image Generation with Next-Frequency Prediction.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2503.07076"],"source":"https://dblp.org/rec/journals/corr/abs-2503-07076","documentPage":"https://doi.org/10.48550/ARXIV.2503.07076","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2503.07076","authorSignatures":[{"orcid":"https://orcid.org/0000-0001-6344-2824"}],"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-07076","documentUrl":"https://doi.org/10.48550/ARXIV.2503.07076","arxivId":"2503.07076","arxivUrl":"https://arxiv.org/abs/2503.07076"},{"key":"journals/corr/abs-2507-16010","title":"FW-VTON: Flattening-and-Warping for Person-to-Person Virtual Try-on.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2507.16010"],"source":"https://dblp.org/rec/journals/corr/abs-2507-16010","documentPage":"https://doi.org/10.48550/ARXIV.2507.16010","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2507.16010","authorSignatures":[{"orcid":"https://orcid.org/0000-0001-6344-2824"}],"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2507-16010","documentUrl":"https://doi.org/10.48550/ARXIV.2507.16010","arxivId":"2507.16010","arxivUrl":"https://arxiv.org/abs/2507.16010"},{"key":"journals/corr/abs-2508-03334","title":"Macro-from-Micro Planning for High-Quality and Parallelized Autoregressive Long Video Generation.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2508.03334"],"source":"https://dblp.org/rec/journals/corr/abs-2508-03334","documentPage":"https://doi.org/10.48550/ARXIV.2508.03334","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2508.03334","authorSignatures":[{"orcid":"https://orcid.org/0000-0001-6344-2824"}],"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-03334","documentUrl":"https://doi.org/10.48550/ARXIV.2508.03334","arxivId":"2508.03334","arxivUrl":"https://arxiv.org/abs/2508.03334"},{"key":"journals/corr/abs-2508-08789","title":"Never Compromise to Vulnerabilities: A Comprehensive Survey on AI Governance.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2508.08789"],"source":"https://dblp.org/rec/journals/corr/abs-2508-08789","documentPage":"https://doi.org/10.48550/ARXIV.2508.08789","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2508.08789","authorSignatures":[{"orcid":"https://orcid.org/0000-0001-6344-2824"}],"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-08789","documentUrl":"https://doi.org/10.48550/ARXIV.2508.08789","arxivId":"2508.08789","arxivUrl":"https://arxiv.org/abs/2508.08789"},{"key":"journals/corr/abs-2508-09702","title":"M3\\PDB: A Multimodal, Multi-Label, Multilingual Prompt Database for Speech Generation.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2508.09702"],"source":"https://dblp.org/rec/journals/corr/abs-2508-09702","documentPage":"https://doi.org/10.48550/ARXIV.2508.09702","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2508.09702","authorSignatures":[{"orcid":"https://orcid.org/0000-0001-6344-2824"}],"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-09702","documentUrl":"https://doi.org/10.48550/ARXIV.2508.09702","arxivId":"2508.09702","arxivUrl":"https://arxiv.org/abs/2508.09702"},{"key":"journals/corr/abs-2508-12918","title":"FoleySpace: Vision-Aligned Binaural Spatial Audio Generation.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2508.12918"],"source":"https://dblp.org/rec/journals/corr/abs-2508-12918","documentPage":"https://doi.org/10.48550/ARXIV.2508.12918","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2508.12918","authorSignatures":[{"orcid":"https://orcid.org/0000-0001-6344-2824"}],"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-12918","documentUrl":"https://doi.org/10.48550/ARXIV.2508.12918","arxivId":"2508.12918","arxivUrl":"https://arxiv.org/abs/2508.12918"},{"key":"journals/corr/abs-2509-15130","title":"WorldForge: Unlocking Emergent 3D/4D Generation in Video Diffusion Model via Training-Free Guidance.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2509.15130"],"source":"https://dblp.org/rec/journals/corr/abs-2509-15130","documentPage":"https://doi.org/10.48550/ARXIV.2509.15130","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2509.15130","authorSignatures":[{"orcid":"https://orcid.org/0000-0001-6344-2824"}],"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-15130","documentUrl":"https://doi.org/10.48550/ARXIV.2509.15130","arxivId":"2509.15130","arxivUrl":"https://arxiv.org/abs/2509.15130"},{"key":"journals/corr/abs-2511-12578","title":"TempoMaster: Efficient Long Video Generation via Next-Frame-Rate Prediction.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2511.12578"],"source":"https://dblp.org/rec/journals/corr/abs-2511-12578","documentPage":"https://doi.org/10.48550/ARXIV.2511.12578","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2511.12578","authorSignatures":[{"orcid":"https://orcid.org/0000-0001-6344-2824"}],"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2511-12578","documentUrl":"https://doi.org/10.48550/ARXIV.2511.12578","arxivId":"2511.12578","arxivUrl":"https://arxiv.org/abs/2511.12578"},{"key":"journals/corr/abs-2511-18919","title":"Learning What to Trust: Bayesian Prior-Guided Optimization for Visual Generation.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2511.18919"],"source":"https://dblp.org/rec/journals/corr/abs-2511-18919","documentPage":"https://doi.org/10.48550/ARXIV.2511.18919","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2511.18919","authorSignatures":[{"orcid":"https://orcid.org/0000-0001-6344-2824"}],"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2511-18919","documentUrl":"https://doi.org/10.48550/ARXIV.2511.18919","arxivId":"2511.18919","arxivUrl":"https://arxiv.org/abs/2511.18919"},{"key":"journals/corr/abs-2512-21894","title":"Rare Word Recognition and Translation Without Fine-Tuning via Task Vector in Speech Models.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2512.21894"],"source":"https://dblp.org/rec/journals/corr/abs-2512-21894","documentPage":"https://doi.org/10.48550/ARXIV.2512.21894","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2512.21894","authorSignatures":[{"orcid":"https://orcid.org/0000-0001-6344-2824"}],"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-21894","documentUrl":"https://doi.org/10.48550/ARXIV.2512.21894","arxivId":"2512.21894","arxivUrl":"https://arxiv.org/abs/2512.21894"}],"excludedFormal":[],"excludedOther":[],"excludedHomonyms":[{"key":"conf/nips/NingSXGZZL25","title":"CAS-Spec: Cascade Adaptive Self-Speculative Decoding for On-the-Fly Lossless Inference Acceleration of LLMs.","year":2025,"yearOfEvent":2025,"venue":"NeurIPS","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/nips/NingSXGZZL25","documentPage":"http://papers.nips.cc/paper_files/paper/2025/hash/5e27f5d8ecd30ac6235892ef97676e78-Abstract-Conference.html","type":"Inproceedings","doi":null,"authorSignatures":[{}],"exclusionReason":"Original paper assigns Chi Zhang to TeleAI; conference biography identifies the TeleAI researcher as a Columbia PhD, not the NTU-trained Westlake signatory.","exclusionSource":"https://papers.nips.cc/paper_files/paper/2025/file/5e27f5d8ecd30ac6235892ef97676e78-Paper-Conference.pdf","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/nips/NingSXGZZL25","documentUrl":"http://papers.nips.cc/paper_files/paper/2025/hash/5e27f5d8ecd30ac6235892ef97676e78-Abstract-Conference.html"},{"key":"journals/corr/abs-2510-26843","title":"CAS-Spec: Cascade Adaptive Self-Speculative Decoding for On-the-Fly Lossless Inference Acceleration of LLMs.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2510.26843"],"source":"https://dblp.org/rec/journals/corr/abs-2510-26843","documentPage":"https://doi.org/10.48550/ARXIV.2510.26843","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2510.26843","authorSignatures":[{"orcid":"https://orcid.org/0000-0001-6344-2824"}],"exclusionReason":"Original paper assigns Chi Zhang to TeleAI; conference biography identifies the TeleAI researcher as a Columbia PhD, not the NTU-trained Westlake signatory.","exclusionSource":"https://papers.nips.cc/paper_files/paper/2025/file/5e27f5d8ecd30ac6235892ef97676e78-Paper-Conference.pdf","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-26843","documentUrl":"https://doi.org/10.48550/ARXIV.2510.26843"},{"key":"journals/tifs/ZhuZHWLY25","title":"Detecting Deceptive Behavior via Learning Relation-Aware Visual Representations.","year":2025,"yearOfEvent":null,"venue":"IEEE Trans. Inf. Forensics Secur.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1109/TIFS.2025.3586468"],"source":"https://dblp.org/rec/journals/tifs/ZhuZHWLY25","documentPage":"https://doi.org/10.1109/TIFS.2025.3586468","type":"Article","doi":"https://doi.org/10.1109/TIFS.2025.3586468","authorSignatures":[{"orcid":"https://orcid.org/0009-0009-4457-0893","inst":"https://dblp.org/inst/1/778","instLabel":"Xidian University"}],"exclusionReason":"Publisher-deposited author metadata assigns Chi Zhang to Xidian University and ORCID 0009-0009-4457-0893, not the Westlake author.","exclusionSource":"https://api.crossref.org/works/10.1109%2FTIFS.2025.3586468","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/tifs/ZhuZHWLY25","documentUrl":"https://doi.org/10.1109/TIFS.2025.3586468"}],"unassignedCandidates":[{"key":"journals/corr/abs-2509-25275","title":"VoiceBridge: Designing Latent Bridge Models for General Speech Restoration at Scale.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2509.25275"],"source":"https://dblp.org/rec/journals/corr/abs-2509-25275","documentPage":"https://doi.org/10.48550/ARXIV.2509.25275","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2509.25275","authorSignatures":[{}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-25275","documentUrl":"https://doi.org/10.48550/ARXIV.2509.25275"}],"retrievedAt":"2026-10-19","querySource":"https://sparql.dblp.org/","method":"DBLP yearOfPublication=2025; Article + Inproceedings; excludes Informal/CoRR and explicit editorial/correction/erratum/preface; unique DBLP record keys within person.","preprintStatus":"partial_identity_review","preprintLowerBound2025":21,"sourceWarning":true,"labName":"AGI Lab, Westlake University","labUrl":"https://github.com/Westlake-AGI-Lab","labEvidence":"本人主页明确称其为西湖大学 PI、领导 AGI Lab，并直接链接该实验室 GitHub 组织；这里的链接是实验室代码主页。","labSourceUrl":"https://icoz69.github.io/","affiliationZh":"西湖大学","knownPreprintMinimum2025":21,"excludedMisattributed":[{"key":"conf/nips/NingSXGZZL25","title":"CAS-Spec: Cascade Adaptive Self-Speculative Decoding for On-the-Fly Lossless Inference Acceleration of LLMs.","year":2025,"yearOfEvent":2025,"venue":"NeurIPS","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/nips/NingSXGZZL25","documentPage":"http://papers.nips.cc/paper_files/paper/2025/hash/5e27f5d8ecd30ac6235892ef97676e78-Abstract-Conference.html","type":"Inproceedings","doi":null,"authorSignatures":[{}],"exclusionReason":"Original paper assigns Chi Zhang to TeleAI; conference biography identifies the TeleAI researcher as a Columbia PhD, not the NTU-trained Westlake signatory.","exclusionSource":"https://papers.nips.cc/paper_files/paper/2025/file/5e27f5d8ecd30ac6235892ef97676e78-Paper-Conference.pdf","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/nips/NingSXGZZL25","documentUrl":"http://papers.nips.cc/paper_files/paper/2025/hash/5e27f5d8ecd30ac6235892ef97676e78-Abstract-Conference.html"},{"key":"journals/corr/abs-2510-26843","title":"CAS-Spec: Cascade Adaptive Self-Speculative Decoding for On-the-Fly Lossless Inference Acceleration of LLMs.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2510.26843"],"source":"https://dblp.org/rec/journals/corr/abs-2510-26843","documentPage":"https://doi.org/10.48550/ARXIV.2510.26843","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2510.26843","authorSignatures":[{"orcid":"https://orcid.org/0000-0001-6344-2824"}],"exclusionReason":"Original paper assigns Chi Zhang to TeleAI; conference biography identifies the TeleAI researcher as a Columbia PhD, not the NTU-trained Westlake signatory.","exclusionSource":"https://papers.nips.cc/paper_files/paper/2025/file/5e27f5d8ecd30ac6235892ef97676e78-Paper-Conference.pdf","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-26843","documentUrl":"https://doi.org/10.48550/ARXIV.2510.26843"},{"key":"journals/tifs/ZhuZHWLY25","title":"Detecting Deceptive Behavior via Learning Relation-Aware Visual Representations.","year":2025,"yearOfEvent":null,"venue":"IEEE Trans. Inf. Forensics Secur.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1109/TIFS.2025.3586468"],"source":"https://dblp.org/rec/journals/tifs/ZhuZHWLY25","documentPage":"https://doi.org/10.1109/TIFS.2025.3586468","type":"Article","doi":"https://doi.org/10.1109/TIFS.2025.3586468","authorSignatures":[{"orcid":"https://orcid.org/0009-0009-4457-0893","inst":"https://dblp.org/inst/1/778","instLabel":"Xidian University"}],"exclusionReason":"Publisher-deposited author metadata assigns Chi Zhang to Xidian University and ORCID 0009-0009-4457-0893, not the Westlake author.","exclusionSource":"https://api.crossref.org/works/10.1109%2FTIFS.2025.3586468","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/tifs/ZhuZHWLY25","documentUrl":"https://doi.org/10.1109/TIFS.2025.3586468"}],"displayNotes":"检出的 DBLP 同名记录已排除，2025 年的正式记录已逐条复核。计入 16 条（会议 15、期刊 1），所有作者位置均计入。预印本候选池尚不完整，暂不给出总数，这不是零。","labDisplayNotes":"个人主页写明其为西湖大学 PI、领导 AGI Lab，并链接实验室的 GitHub 组织，据此归组。"},{"index":109,"name":"Guofeng Zhang","nameZh":"章国锋","affiliation":"Zhejiang University","source":"DBLP Knowledge Graph official SPARQL API","profileUrl":"https://dblp.org/pid/78/5389-1","identifier":"78/5389-1","identityEvidence":[{"url":"https://dblp.org/pid/78/5389-1","evidence":"DBLP curated profile affiliations: Zhejiang University, The State Key Lab of CAD and CG, Hangzhou, China."},{"url":"https://dblp.org/pid/78/5389-1","evidence":"DBLP curated profile homepages: http://www.cad.zju.edu.cn/home/gfzhang/."}],"count2025":39,"conference2025":29,"journal2025":10,"preprint2025":17,"status":"verified","notes":"Counts are DBLP indexed coauthored records, not first-author counts, laboratory totals, unique scientific discoveries, or quality assessments. DBLP yearOfPublication=2025; yearOfEvent retained and can differ. Conference workshops are included. Preprints are separate and may overlap formal versions.","papers":[{"key":"conf/3dim/ChenLZ25","title":"OpticFusion: Multi-Modal Neural Implicit 3D Reconstruction of Microstructures by Fusing White Light Interferometry and Optical Microscopy.","year":2025,"yearOfEvent":2025,"venue":"3DV","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/3DV66043.2025.00014"],"source":"https://dblp.org/rec/conf/3dim/ChenLZ25","documentPage":"https://doi.org/10.1109/3DV66043.2025.00014","type":"Inproceedings","doi":"https://doi.org/10.1109/3DV66043.2025.00014","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/3dim/ChenLZ25","documentUrl":"https://doi.org/10.1109/3DV66043.2025.00014"},{"key":"conf/aaai/ChenYWCHO00025","title":"GigaGS: 3D Gaussian Based Planar Representation for Large-Scene Surface Reconstruction.","year":2025,"yearOfEvent":2025,"venue":"AAAI","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1609/AAAI.V39I2.32206"],"source":"https://dblp.org/rec/conf/aaai/ChenYWCHO00025","documentPage":"https://doi.org/10.1609/AAAI.V39I2.32206","type":"Inproceedings","doi":"https://doi.org/10.1609/AAAI.V39I2.32206","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/aaai/ChenYWCHO00025","documentUrl":"https://doi.org/10.1609/AAAI.V39I2.32206"},{"key":"conf/chi/ZhangBP0I025","title":"Through the Lens of Privacy: Exploring Privacy Protection in Vision-Language Model Interactions on Smart Glasses.","year":2025,"yearOfEvent":2025,"venue":"CHI Extended Abstracts","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1145/3706599.3720234"],"source":"https://dblp.org/rec/conf/chi/ZhangBP0I025","documentPage":"https://doi.org/10.1145/3706599.3720234","type":"Inproceedings","doi":"https://doi.org/10.1145/3706599.3720234","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/chi/ZhangBP0I025","documentUrl":"https://doi.org/10.1145/3706599.3720234"},{"key":"conf/cvpr/Bao0YS0PC25","title":"Free360: Layered Gaussian Splatting for Unbounded 360-Degree View Synthesis from Extremely Sparse and Unposed Views.","year":2025,"yearOfEvent":2025,"venue":"CVPR","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/CVPR52734.2025.01527"],"source":"https://dblp.org/rec/conf/cvpr/Bao0YS0PC25","documentPage":"https://openaccess.thecvf.com/content/CVPR2025/html/Bao_Free360_Layered_Gaussian_Splatting_for_Unbounded_360-Degree_View_Synthesis_from_CVPR_2025_paper.html","type":"Inproceedings","doi":"https://doi.org/10.1109/CVPR52734.2025.01527","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/Bao0YS0PC25","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Bao_Free360_Layered_Gaussian_Splatting_for_Unbounded_360-Degree_View_Synthesis_from_CVPR_2025_paper.html"},{"key":"conf/cvpr/Guo00B025","title":"SGFormer: Satellite-Ground Fusion for 3D Semantic Scene Completion.","year":2025,"yearOfEvent":2025,"venue":"CVPR","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/CVPR52734.2025.01114"],"source":"https://dblp.org/rec/conf/cvpr/Guo00B025","documentPage":"https://openaccess.thecvf.com/content/CVPR2025/html/Guo_SGFormer_Satellite-Ground_Fusion_for_3D_Semantic_Scene_Completion_CVPR_2025_paper.html","type":"Inproceedings","doi":"https://doi.org/10.1109/CVPR52734.2025.01114","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/Guo00B025","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Guo_SGFormer_Satellite-Ground_Fusion_for_3D_Semantic_Scene_Completion_CVPR_2025_paper.html"},{"key":"conf/cvpr/HuangYSY025","title":"From Sparse to Dense: Camera Relocalization with Scene-Specific Detector from Feature Gaussian Splatting.","year":2025,"yearOfEvent":2025,"venue":"CVPR","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/CVPR52734.2025.02520"],"source":"https://dblp.org/rec/conf/cvpr/HuangYSY025","documentPage":"https://openaccess.thecvf.com/content/CVPR2025/html/Huang_From_Sparse_to_Dense_Camera_Relocalization_with_Scene-Specific_Detector_from_CVPR_2025_paper.html","type":"Inproceedings","doi":"https://doi.org/10.1109/CVPR52734.2025.02520","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/HuangYSY025","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Huang_From_Sparse_to_Dense_Camera_Relocalization_with_Scene-Specific_Detector_from_CVPR_2025_paper.html"},{"key":"conf/cvpr/SongJZLZ0Q25","title":"Prior-free 3D Object Tracking.","year":2025,"yearOfEvent":2025,"venue":"CVPR","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/CVPR52734.2025.00120"],"source":"https://dblp.org/rec/conf/cvpr/SongJZLZ0Q25","documentPage":"https://openaccess.thecvf.com/content/CVPR2025/html/Song_Prior-free_3D_Object_Tracking_CVPR_2025_paper.html","type":"Inproceedings","doi":"https://doi.org/10.1109/CVPR52734.2025.00120","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/SongJZLZ0Q25","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Song_Prior-free_3D_Object_Tracking_CVPR_2025_paper.html"},{"key":"conf/cvpr/ZhaiLLPH025","title":"PanoGS: Gaussian-based Panoptic Segmentation for 3D Open Vocabulary Scene Understanding.","year":2025,"yearOfEvent":2025,"venue":"CVPR","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/CVPR52734.2025.01317"],"source":"https://dblp.org/rec/conf/cvpr/ZhaiLLPH025","documentPage":"https://openaccess.thecvf.com/content/CVPR2025/html/Zhai_PanoGS_Gaussian-based_Panoptic_Segmentation_for_3D_Open_Vocabulary_Scene_Understanding_CVPR_2025_paper.html","type":"Inproceedings","doi":"https://doi.org/10.1109/CVPR52734.2025.01317","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/ZhaiLLPH025","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Zhai_PanoGS_Gaussian-based_Panoptic_Segmentation_for_3D_Open_Vocabulary_Scene_Understanding_CVPR_2025_paper.html"},{"key":"conf/cvpr/ZhaiYLXHPXCWY0L25","title":"StarGen: A Spatiotemporal Autoregression Framework with Video Diffusion Model for Scalable and Controllable Scene Generation.","year":2025,"yearOfEvent":2025,"venue":"CVPR","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/CVPR52734.2025.02498"],"source":"https://dblp.org/rec/conf/cvpr/ZhaiYLXHPXCWY0L25","documentPage":"https://openaccess.thecvf.com/content/CVPR2025/html/Zhai_StarGen_A_Spatiotemporal_Autoregression_Framework_with_Video_Diffusion_Model_for_CVPR_2025_paper.html","type":"Inproceedings","doi":"https://doi.org/10.1109/CVPR52734.2025.02498","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/ZhaiYLXHPXCWY0L25","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Zhai_StarGen_A_Spatiotemporal_Autoregression_Framework_with_Video_Diffusion_Model_for_CVPR_2025_paper.html"},{"key":"conf/eccv/HuCFLYBZC24","title":"CG-SLAM: Efficient Dense RGB-D SLAM in a Consistent Uncertainty-Aware 3D Gaussian Field.","year":2025,"yearOfEvent":2024,"venue":"ECCV (25)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1007/978-3-031-72698-9_6"],"source":"https://dblp.org/rec/conf/eccv/HuCFLYBZC24","documentPage":"https://doi.org/10.1007/978-3-031-72698-9_6","type":"Inproceedings","doi":"https://doi.org/10.1007/978-3-031-72698-9_6","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/eccv/HuCFLYBZC24","documentUrl":"https://doi.org/10.1007/978-3-031-72698-9_6"},{"key":"conf/eccv/LiSHCBSWSBCZL24","title":"BlinkVision: A Benchmark for Optical Flow, Scene Flow and Point Tracking Estimation Using RGB Frames and Events.","year":2025,"yearOfEvent":2024,"venue":"ECCV (67)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1007/978-3-031-72855-6_2"],"source":"https://dblp.org/rec/conf/eccv/LiSHCBSWSBCZL24","documentPage":"https://doi.org/10.1007/978-3-031-72855-6_2","type":"Inproceedings","doi":"https://doi.org/10.1007/978-3-031-72855-6_2","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/eccv/LiSHCBSWSBCZL24","documentUrl":"https://doi.org/10.1007/978-3-031-72855-6_2"},{"key":"conf/eccv/WangWZX24","title":"Learning 3D Geometry and Feature Consistent Gaussian Splatting for Object Removal.","year":2025,"yearOfEvent":2024,"venue":"ECCV (3)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1007/978-3-031-72646-0_1"],"source":"https://dblp.org/rec/conf/eccv/WangWZX24","documentPage":"https://doi.org/10.1007/978-3-031-72646-0_1","type":"Inproceedings","doi":"https://doi.org/10.1007/978-3-031-72646-0_1","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/eccv/WangWZX24","documentUrl":"https://doi.org/10.1007/978-3-031-72646-0_1"},{"key":"conf/iccv/FangCLMDLZWZZDCL25","title":"Creation-Mmbench: Assessing Context-Aware Creative Intelligence in Mllms.","year":2025,"yearOfEvent":2025,"venue":"ICCV","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/ICCV51701.2025.00049"],"source":"https://dblp.org/rec/conf/iccv/FangCLMDLZWZZDCL25","documentPage":"https://doi.org/10.1109/ICCV51701.2025.00049","type":"Inproceedings","doi":"https://doi.org/10.1109/ICCV51701.2025.00049","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/FangCLMDLZWZZDCL25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.00049"},{"key":"conf/iccv/PanZZXJZ25","title":"Liberated-Gs: 3D Gaussian Splatting Independent From Sfm Point Clouds.","year":2025,"yearOfEvent":2025,"venue":"ICCV","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/ICCV51701.2025.02476"],"source":"https://dblp.org/rec/conf/iccv/PanZZXJZ25","documentPage":"https://doi.org/10.1109/ICCV51701.2025.02476","type":"Inproceedings","doi":"https://doi.org/10.1109/ICCV51701.2025.02476","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/PanZZXJZ25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.02476"},{"key":"conf/iccv/ShenLCLHBCZ25","title":"BlinkTrack: Feature Tracking Over 80 FPS via Events and Images.","year":2025,"yearOfEvent":2025,"venue":"ICCV","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/ICCV51701.2025.00868"],"source":"https://dblp.org/rec/conf/iccv/ShenLCLHBCZ25","documentPage":"https://doi.org/10.1109/ICCV51701.2025.00868","type":"Inproceedings","doi":"https://doi.org/10.1109/ICCV51701.2025.00868","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/ShenLCLHBCZ25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.00868"},{"key":"conf/iccv/WangHBZBCZ25","title":"LightCity: An Urban Dataset for Outdoor Inverse Rendering and Reconstruction Under Multi-Illumination Conditions.","year":2025,"yearOfEvent":2025,"venue":"ICCV","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/ICCV51701.2025.02457"],"source":"https://dblp.org/rec/conf/iccv/WangHBZBCZ25","documentPage":"https://doi.org/10.1109/ICCV51701.2025.02457","type":"Inproceedings","doi":"https://doi.org/10.1109/ICCV51701.2025.02457","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/WangHBZBCZ25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.02457"},{"key":"conf/iccv/ZhangPXZZJZ25","title":"Tile-Wise Vs. Image-Wise: Random-Tile Loss and Training Paradigm for Gaussian Splatting.","year":2025,"yearOfEvent":2025,"venue":"ICCV","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/ICCV51701.2025.02499"],"source":"https://dblp.org/rec/conf/iccv/ZhangPXZZJZ25","documentPage":"https://doi.org/10.1109/ICCV51701.2025.02499","type":"Inproceedings","doi":"https://doi.org/10.1109/ICCV51701.2025.02499","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/ZhangPXZZJZ25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.02499"},{"key":"conf/iclr/TangYWHB0025","title":"ND-SDF: Learning Normal Deflection Fields for High-Fidelity Indoor Reconstruction.","year":2025,"yearOfEvent":2025,"venue":"ICLR","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/iclr/TangYWHB0025","documentPage":"https://openreview.net/forum?id=4HRRcqE9SU","type":"Inproceedings","doi":null,"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iclr/TangYWHB0025","documentUrl":"https://openreview.net/forum?id=4HRRcqE9SU"},{"key":"conf/icra/PanLFZBZ25","title":"Scalable Multi-Session Visual SLAM in Large-Scale Scenes with Subgraph Optimization.","year":2025,"yearOfEvent":2025,"venue":"ICRA","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/ICRA55743.2025.11128582"],"source":"https://dblp.org/rec/conf/icra/PanLFZBZ25","documentPage":"https://doi.org/10.1109/ICRA55743.2025.11128582","type":"Inproceedings","doi":"https://doi.org/10.1109/ICRA55743.2025.11128582","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/icra/PanLFZBZ25","documentUrl":"https://doi.org/10.1109/ICRA55743.2025.11128582"},{"key":"conf/icra/ZhaiZLPHCBZ25","title":"Neuraloc: Visual Localization in Neural Implicit Map With Dual Complementary Features.","year":2025,"yearOfEvent":2025,"venue":"ICRA","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/ICRA55743.2025.11127718"],"source":"https://dblp.org/rec/conf/icra/ZhaiZLPHCBZ25","documentPage":"https://doi.org/10.1109/ICRA55743.2025.11127718","type":"Inproceedings","doi":"https://doi.org/10.1109/ICRA55743.2025.11127718","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/icra/ZhaiZLPHCBZ25","documentUrl":"https://doi.org/10.1109/ICRA55743.2025.11127718"},{"key":"conf/icxr/Chen0C024","title":"Learning Dynamic Cloth Deformation for Virtual Try-on.","year":2025,"yearOfEvent":2024,"venue":"ICXR","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1007/978-981-96-3679-2_5"],"source":"https://dblp.org/rec/conf/icxr/Chen0C024","documentPage":"https://doi.org/10.1007/978-981-96-3679-2_5","type":"Inproceedings","doi":"https://doi.org/10.1007/978-981-96-3679-2_5","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/icxr/Chen0C024","documentUrl":"https://doi.org/10.1007/978-981-96-3679-2_5"},{"key":"conf/iros/ChenGPSZBC25","title":"DW-VIO: Deep Weighted Visual-Inertial Odometry.","year":2025,"yearOfEvent":2025,"venue":"IROS","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/IROS60139.2025.11246552"],"source":"https://dblp.org/rec/conf/iros/ChenGPSZBC25","documentPage":"https://doi.org/10.1109/IROS60139.2025.11246552","type":"Inproceedings","doi":"https://doi.org/10.1109/IROS60139.2025.11246552","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iros/ChenGPSZBC25","documentUrl":"https://doi.org/10.1109/IROS60139.2025.11246552"},{"key":"conf/iros/HuangPLZXZ25","title":"Real-Time Consistent Monocular Depth Recovery System for Dynamic Environments.","year":2025,"yearOfEvent":2025,"venue":"IROS","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/IROS60139.2025.11246257"],"source":"https://dblp.org/rec/conf/iros/HuangPLZXZ25","documentPage":"https://doi.org/10.1109/IROS60139.2025.11246257","type":"Inproceedings","doi":"https://doi.org/10.1109/IROS60139.2025.11246257","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iros/HuangPLZXZ25","documentUrl":"https://doi.org/10.1109/IROS60139.2025.11246257"},{"key":"conf/iros/NiSLZBZ25","title":"ETO+: Revisit the Refinement Stage in Efficient Feature Matching.","year":2025,"yearOfEvent":2025,"venue":"IROS","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/IROS60139.2025.11246247"],"source":"https://dblp.org/rec/conf/iros/NiSLZBZ25","documentPage":"https://doi.org/10.1109/IROS60139.2025.11246247","type":"Inproceedings","doi":"https://doi.org/10.1109/IROS60139.2025.11246247","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iros/NiSLZBZ25","documentUrl":"https://doi.org/10.1109/IROS60139.2025.11246247"},{"key":"conf/mm/ZhanLHC0CDH025","title":"CoProSketch: Controllable and Progressive Sketch Generation with Diffusion Model.","year":2025,"yearOfEvent":2025,"venue":"ACM Multimedia","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1145/3746027.3755437"],"source":"https://dblp.org/rec/conf/mm/ZhanLHC0CDH025","documentPage":"https://doi.org/10.1145/3746027.3755437","type":"Inproceedings","doi":"https://doi.org/10.1145/3746027.3755437","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/mm/ZhanLHC0CDH025","documentUrl":"https://doi.org/10.1145/3746027.3755437"},{"key":"conf/nips/LiXYLSWZHL25","title":"NopeRoomGS: Indoor 3D Gaussian Splatting Optimization without Camera Pose Input.","year":2025,"yearOfEvent":2025,"venue":"NeurIPS","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/nips/LiXYLSWZHL25","documentPage":"http://papers.nips.cc/paper_files/paper/2025/hash/464012c83279e19be4cd42c25f341c92-Abstract-Conference.html","type":"Inproceedings","doi":null,"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/nips/LiXYLSWZHL25","documentUrl":"http://papers.nips.cc/paper_files/paper/2025/hash/464012c83279e19be4cd42c25f341c92-Abstract-Conference.html"},{"key":"conf/nips/ZhangBCZDBCZ25","title":"AtlasGS: Atlanta-world Guided Surface Reconstruction with Implicit Structured Gaussians.","year":2025,"yearOfEvent":2025,"venue":"NeurIPS","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/nips/ZhangBCZDBCZ25","documentPage":"http://papers.nips.cc/paper_files/paper/2025/hash/171bbefe4954adf5d2758cfc27b7cad4-Abstract-Conference.html","type":"Inproceedings","doi":null,"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/nips/ZhangBCZDBCZ25","documentUrl":"http://papers.nips.cc/paper_files/paper/2025/hash/171bbefe4954adf5d2758cfc27b7cad4-Abstract-Conference.html"},{"key":"conf/siggrapha/ChenLDWLH0Y25","title":"GS-RoadPatching: Inpainting Gaussians via 3D Searching and Placing for Driving Scenes.","year":2025,"yearOfEvent":2025,"venue":"SIGGRAPH Asia","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1145/3757377.3763892"],"source":"https://dblp.org/rec/conf/siggrapha/ChenLDWLH0Y25","documentPage":"https://doi.org/10.1145/3757377.3763892","type":"Inproceedings","doi":"https://doi.org/10.1145/3757377.3763892","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/siggrapha/ChenLDWLH0Y25","documentUrl":"https://doi.org/10.1145/3757377.3763892"},{"key":"conf/siggrapha/PanLYZ025","title":"EGG-Fusion: Efficient 3D Reconstruction with Geometry-aware Gaussian Surfel on the Fly.","year":2025,"yearOfEvent":2025,"venue":"SIGGRAPH Asia","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1145/3757377.3763878"],"source":"https://dblp.org/rec/conf/siggrapha/PanLYZ025","documentPage":"https://doi.org/10.1145/3757377.3763878","type":"Inproceedings","doi":"https://doi.org/10.1145/3757377.3763878","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/siggrapha/PanLYZ025","documentUrl":"https://doi.org/10.1145/3757377.3763878"},{"key":"journals/eaai/MingYWCFXZ25","title":"Benchmarking neural radiance fields for autonomous robots: An overview.","year":2025,"yearOfEvent":null,"venue":"Eng. Appl. Artif. Intell.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1016/J.ENGAPPAI.2024.109685"],"source":"https://dblp.org/rec/journals/eaai/MingYWCFXZ25","documentPage":"https://doi.org/10.1016/J.ENGAPPAI.2024.109685","type":"Article","doi":"https://doi.org/10.1016/J.ENGAPPAI.2024.109685","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/eaai/MingYWCFXZ25","documentUrl":"https://doi.org/10.1016/J.ENGAPPAI.2024.109685"},{"key":"journals/pami/BaoLYSBCZZ25","title":"NeuMesh++: Toward Versatile and Efficient Volumetric Editing With Disentangled Neural Mesh-Based Implicit Field.","year":2025,"yearOfEvent":null,"venue":"IEEE Trans. Pattern Anal. Mach. Intell.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1109/TPAMI.2025.3600473"],"source":"https://dblp.org/rec/journals/pami/BaoLYSBCZZ25","documentPage":"https://doi.org/10.1109/TPAMI.2025.3600473","type":"Article","doi":"https://doi.org/10.1109/TPAMI.2025.3600473","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/pami/BaoLYSBCZZ25","documentUrl":"https://doi.org/10.1109/TPAMI.2025.3600473"},{"key":"journals/ral/MingMDYFZK25","title":"SLC$^{2}$-SLAM: Semantic-Guided Loop Closure Using Shared Latent Code for NeRF SLAM.","year":2025,"yearOfEvent":null,"venue":"IEEE Robotics Autom. Lett.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1109/LRA.2025.3553352"],"source":"https://dblp.org/rec/journals/ral/MingMDYFZK25","documentPage":"https://doi.org/10.1109/LRA.2025.3553352","type":"Article","doi":"https://doi.org/10.1109/LRA.2025.3553352","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/ral/MingMDYFZK25","documentUrl":"https://doi.org/10.1109/LRA.2025.3553352"},{"key":"journals/tcsv/CuiYWZZHL25","title":"StreetSurfGS: Scalable Urban Street Surface Reconstruction With Planar-Based Gaussian Splatting.","year":2025,"yearOfEvent":null,"venue":"IEEE Trans. Circuits Syst. Video Technol.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1109/TCSVT.2025.3551719"],"source":"https://dblp.org/rec/journals/tcsv/CuiYWZZHL25","documentPage":"https://doi.org/10.1109/TCSVT.2025.3551719","type":"Article","doi":"https://doi.org/10.1109/TCSVT.2025.3551719","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/tcsv/CuiYWZZHL25","documentUrl":"https://doi.org/10.1109/TCSVT.2025.3551719"},{"key":"journals/tcsv/PangZZWHZL25","title":"Zero6DOT: Zero-Shot 6D Object Pose Tracking With Monocular RGB Video.","year":2025,"yearOfEvent":null,"venue":"IEEE Trans. Circuits Syst. Video Technol.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1109/TCSVT.2025.3577617"],"source":"https://dblp.org/rec/journals/tcsv/PangZZWHZL25","documentPage":"https://doi.org/10.1109/TCSVT.2025.3577617","type":"Article","doi":"https://doi.org/10.1109/TCSVT.2025.3577617","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/tcsv/PangZZWHZL25","documentUrl":"https://doi.org/10.1109/TCSVT.2025.3577617"},{"key":"journals/tii/WangPYLZLTZ25","title":"MFF-SDD: A Bidirectional Guidance and Multiscale Multimodal Fusion Model for Small Defect Detection in Industrial Films.","year":2025,"yearOfEvent":null,"venue":"IEEE Trans. Ind. Informatics","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1109/TII.2025.3606880"],"source":"https://dblp.org/rec/journals/tii/WangPYLZLTZ25","documentPage":"https://doi.org/10.1109/TII.2025.3606880","type":"Article","doi":"https://doi.org/10.1109/TII.2025.3606880","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/tii/WangPYLZLTZ25","documentUrl":"https://doi.org/10.1109/TII.2025.3606880"},{"key":"journals/tip/WangWYZ25","title":"CloCap-GS: Clothed Human Performance Capture With 3D Gaussian Splatting.","year":2025,"yearOfEvent":null,"venue":"IEEE Trans. Image Process.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1109/TIP.2025.3592534"],"source":"https://dblp.org/rec/journals/tip/WangWYZ25","documentPage":"https://doi.org/10.1109/TIP.2025.3592534","type":"Article","doi":"https://doi.org/10.1109/TIP.2025.3592534","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/tip/WangWYZ25","documentUrl":"https://doi.org/10.1109/TIP.2025.3592534"},{"key":"journals/tvcg/ChenLYWXZWLBZ25","title":"PGSR: Planar-Based Gaussian Splatting for Efficient and High-Fidelity Surface Reconstruction.","year":2025,"yearOfEvent":null,"venue":"IEEE Trans. Vis. Comput. Graph.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1109/TVCG.2024.3494046"],"source":"https://dblp.org/rec/journals/tvcg/ChenLYWXZWLBZ25","documentPage":"https://doi.org/10.1109/TVCG.2024.3494046","type":"Article","doi":"https://doi.org/10.1109/TVCG.2024.3494046","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/tvcg/ChenLYWXZWLBZ25","documentUrl":"https://doi.org/10.1109/TVCG.2024.3494046"},{"key":"journals/tvcg/XieCQYLCZWBZ25","title":"Depth Completion With Multiple Balanced Bases and Confidence for Dense Monocular SLAM.","year":2025,"yearOfEvent":null,"venue":"IEEE Trans. Vis. Comput. Graph.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1109/TVCG.2024.3431926"],"source":"https://dblp.org/rec/journals/tvcg/XieCQYLCZWBZ25","documentPage":"https://doi.org/10.1109/TVCG.2024.3431926","type":"Article","doi":"https://doi.org/10.1109/TVCG.2024.3431926","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/tvcg/XieCQYLCZWBZ25","documentUrl":"https://doi.org/10.1109/TVCG.2024.3431926"},{"key":"journals/tvcg/ZhaiZZLHCBZ25","title":"SplatLoc: 3D Gaussian Splatting-based Visual Localization for Augmented Reality.","year":2025,"yearOfEvent":null,"venue":"IEEE Trans. Vis. Comput. Graph.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1109/TVCG.2025.3549563"],"source":"https://dblp.org/rec/journals/tvcg/ZhaiZZLHCBZ25","documentPage":"https://doi.org/10.1109/TVCG.2025.3549563","type":"Article","doi":"https://doi.org/10.1109/TVCG.2025.3549563","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/tvcg/ZhaiZZLHCBZ25","documentUrl":"https://doi.org/10.1109/TVCG.2025.3549563"}],"preprints":[{"key":"journals/corr/abs-2501-05763","title":"StarGen: A Spatiotemporal Autoregression Framework with Video Diffusion Model for Scalable and Controllable Scene Generation.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2501.05763"],"source":"https://dblp.org/rec/journals/corr/abs-2501-05763","documentPage":"https://doi.org/10.48550/ARXIV.2501.05763","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2501.05763","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2501-05763","documentUrl":"https://doi.org/10.48550/ARXIV.2501.05763","arxivId":"2501.05763","arxivUrl":"https://arxiv.org/abs/2501.05763"},{"key":"journals/corr/abs-2501-08880","title":"SLC2-SLAM: Semantic-guided Loop Closure with Shared Latent Code for NeRF SLAM.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2501.08880"],"source":"https://dblp.org/rec/journals/corr/abs-2501-08880","documentPage":"https://doi.org/10.48550/ARXIV.2501.08880","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2501.08880","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2501-08880","documentUrl":"https://doi.org/10.48550/ARXIV.2501.08880","arxivId":"2501.08880","arxivUrl":"https://arxiv.org/abs/2501.08880"},{"key":"journals/corr/abs-2501-09259","title":"OpticFusion: Multi-Modal Neural Implicit 3D Reconstruction of Microstructures by Fusing White Light Interferometry and Optical Microscopy.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2501.09259"],"source":"https://dblp.org/rec/journals/corr/abs-2501-09259","documentPage":"https://doi.org/10.48550/ARXIV.2501.09259","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2501.09259","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2501-09259","documentUrl":"https://doi.org/10.48550/ARXIV.2501.09259","arxivId":"2501.09259","arxivUrl":"https://arxiv.org/abs/2501.09259"},{"key":"journals/corr/abs-2502-01297","title":"XR-VIO: High-precision Visual Inertial Odometry with Fast Initialization for XR Applications.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2502.01297"],"source":"https://dblp.org/rec/journals/corr/abs-2502-01297","documentPage":"https://doi.org/10.48550/ARXIV.2502.01297","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2502.01297","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2502-01297","documentUrl":"https://doi.org/10.48550/ARXIV.2502.01297","arxivId":"2502.01297","arxivUrl":"https://arxiv.org/abs/2502.01297"},{"key":"journals/corr/abs-2503-06117","title":"NeuraLoc: Visual Localization in Neural Implicit Map with Dual Complementary Features.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2503.06117"],"source":"https://dblp.org/rec/journals/corr/abs-2503-06117","documentPage":"https://doi.org/10.48550/ARXIV.2503.06117","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2503.06117","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-06117","documentUrl":"https://doi.org/10.48550/ARXIV.2503.06117","arxivId":"2503.06117","arxivUrl":"https://arxiv.org/abs/2503.06117"},{"key":"journals/corr/abs-2503-14478","title":"Creation-MMBench: Assessing Context-Aware Creative Intelligence in MLLM.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2503.14478"],"source":"https://dblp.org/rec/journals/corr/abs-2503-14478","documentPage":"https://doi.org/10.48550/ARXIV.2503.14478","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2503.14478","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-14478","documentUrl":"https://doi.org/10.48550/ARXIV.2503.14478","arxivId":"2503.14478","arxivUrl":"https://arxiv.org/abs/2503.14478"},{"key":"journals/corr/abs-2503-16825","title":"SGFormer: Satellite-Ground Fusion for 3D Semantic Scene Completion.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2503.16825"],"source":"https://dblp.org/rec/journals/corr/abs-2503-16825","documentPage":"https://doi.org/10.48550/ARXIV.2503.16825","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2503.16825","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-16825","documentUrl":"https://doi.org/10.48550/ARXIV.2503.16825","arxivId":"2503.16825","arxivUrl":"https://arxiv.org/abs/2503.16825"},{"key":"journals/corr/abs-2503-18107","title":"PanoGS: Gaussian-based Panoptic Segmentation for 3D Open Vocabulary Scene Understanding.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2503.18107"],"source":"https://dblp.org/rec/journals/corr/abs-2503-18107","documentPage":"https://doi.org/10.48550/ARXIV.2503.18107","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2503.18107","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-18107","documentUrl":"https://doi.org/10.48550/ARXIV.2503.18107","arxivId":"2503.18107","arxivUrl":"https://arxiv.org/abs/2503.18107"},{"key":"journals/corr/abs-2503-19358","title":"From Sparse to Dense: Camera Relocalization with Scene-Specific Detector from Feature Gaussian Splatting.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2503.19358"],"source":"https://dblp.org/rec/journals/corr/abs-2503-19358","documentPage":"https://doi.org/10.48550/ARXIV.2503.19358","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2503.19358","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-19358","documentUrl":"https://doi.org/10.48550/ARXIV.2503.19358","arxivId":"2503.19358","arxivUrl":"https://arxiv.org/abs/2503.19358"},{"key":"journals/corr/abs-2503-24382","title":"Free360: Layered Gaussian Splatting for Unbounded 360-Degree View Synthesis from Extremely Sparse and Unposed Views.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2503.24382"],"source":"https://dblp.org/rec/journals/corr/abs-2503-24382","documentPage":"https://doi.org/10.48550/ARXIV.2503.24382","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2503.24382","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-24382","documentUrl":"https://doi.org/10.48550/ARXIV.2503.24382","arxivId":"2503.24382","arxivUrl":"https://arxiv.org/abs/2503.24382"},{"key":"journals/corr/abs-2504-08259","title":"CoProSketch: Controllable and Progressive Sketch Generation with Diffusion Model.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2504.08259"],"source":"https://dblp.org/rec/journals/corr/abs-2504-08259","documentPage":"https://doi.org/10.48550/ARXIV.2504.08259","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2504.08259","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2504-08259","documentUrl":"https://doi.org/10.48550/ARXIV.2504.08259","arxivId":"2504.08259","arxivUrl":"https://arxiv.org/abs/2504.08259"},{"key":"journals/corr/abs-2508-04728","title":"Neural Field-Based 3D Surface Reconstruction of Microstructures from Multi-Detector Signals in Scanning Electron Microscopy.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2508.04728"],"source":"https://dblp.org/rec/journals/corr/abs-2508-04728","documentPage":"https://doi.org/10.48550/ARXIV.2508.04728","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2508.04728","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-04728","documentUrl":"https://doi.org/10.48550/ARXIV.2508.04728","arxivId":"2508.04728","arxivUrl":"https://arxiv.org/abs/2508.04728"},{"key":"journals/corr/abs-2509-19937","title":"GS-RoadPatching: Inpainting Gaussians via 3D Searching and Placing for Driving Scenes.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2509.19937"],"source":"https://dblp.org/rec/journals/corr/abs-2509-19937","documentPage":"https://doi.org/10.48550/ARXIV.2509.19937","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2509.19937","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-19937","documentUrl":"https://doi.org/10.48550/ARXIV.2509.19937","arxivId":"2509.19937","arxivUrl":"https://arxiv.org/abs/2509.19937"},{"key":"journals/corr/abs-2510-25129","title":"AtlasGS: Atlanta-world Guided Surface Reconstruction with Implicit Structured Gaussians.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2510.25129"],"source":"https://dblp.org/rec/journals/corr/abs-2510-25129","documentPage":"https://doi.org/10.48550/ARXIV.2510.25129","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2510.25129","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-25129","documentUrl":"https://doi.org/10.48550/ARXIV.2510.25129","arxivId":"2510.25129","arxivUrl":"https://arxiv.org/abs/2510.25129"},{"key":"journals/corr/abs-2511-17185","title":"PostCam: Camera-Controllable Novel-View Video Generation with Query-Shared Cross-Attention.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2511.17185"],"source":"https://dblp.org/rec/journals/corr/abs-2511-17185","documentPage":"https://doi.org/10.48550/ARXIV.2511.17185","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2511.17185","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2511-17185","documentUrl":"https://doi.org/10.48550/ARXIV.2511.17185","arxivId":"2511.17185","arxivUrl":"https://arxiv.org/abs/2511.17185"},{"key":"journals/corr/abs-2511-17904","title":"CUS-GS: A Compact Unified Structured Gaussian Splatting Framework for Multimodal Scene Representation.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2511.17904"],"source":"https://dblp.org/rec/journals/corr/abs-2511-17904","documentPage":"https://doi.org/10.48550/ARXIV.2511.17904","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2511.17904","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2511-17904","documentUrl":"https://doi.org/10.48550/ARXIV.2511.17904","arxivId":"2511.17904","arxivUrl":"https://arxiv.org/abs/2511.17904"},{"key":"journals/corr/abs-2512-01296","title":"EGG-Fusion: Efficient 3D Reconstruction with Geometry-aware Gaussian Surfel on the Fly.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2512.01296"],"source":"https://dblp.org/rec/journals/corr/abs-2512-01296","documentPage":"https://doi.org/10.48550/ARXIV.2512.01296","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2512.01296","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-01296","documentUrl":"https://doi.org/10.48550/ARXIV.2512.01296","arxivId":"2512.01296","arxivUrl":"https://arxiv.org/abs/2512.01296"}],"excludedFormal":[],"excludedOther":[],"excludedHomonyms":[],"unassignedCandidates":[],"retrievedAt":"2026-10-19","querySource":"https://sparql.dblp.org/","method":"DBLP yearOfPublication=2025; Article + Inproceedings; excludes Informal/CoRR and explicit editorial/correction/erratum/preface; unique DBLP record keys within person.","labName":"Computer Vision Group, State Key Lab of CAD&CG","labUrl":null,"labEvidence":"本人主页明确称自己为浙江大学 CAD&CG 国家重点实验室 Computer Vision Group 核心成员。没有把其个人记录替代全组或整个重点实验室产量。","labSourceUrl":"http://www.cad.zju.edu.cn/home/gfzhang/","affiliationZh":"浙江大学","sourceWarning":false,"knownPreprintMinimum2025":null,"excludedMisattributed":[],"displayNotes":"身份已经个人或机构主页核对。2025 年正式记录 39 条（会议 29、期刊 10），所有作者位置均计入，不表示主导或贡献份额；预印本 17 条单列，不加总。","labDisplayNotes":"本人主页称其为 CAD&CG 全国重点实验室计算机视觉组的核心成员。这里按共同的上级实验室与崔兆鹏、沈春华、周晓巍合为一组（112 条）；不把其个人记录当作视觉组或全实验室的产量。"},{"index":110,"name":"Li Zhang","nameZh":"张力","affiliation":"Fudan University","source":"DBLP Knowledge Graph official SPARQL API","profileUrl":"https://dblp.org/pid/89/5992-40","identifier":"89/5992-40","identityEvidence":[{"url":"https://dblp.org/pid/89/5992-40","evidence":"DBLP curated profile affiliations: Fudan University, School of Data Science, Shanghai Key Lab of Intelligent Information Processing, Shanghai, China; Queen Mary University of London, UK; University of Oxford, Department of Engineering Science, UK."},{"url":"https://dblp.org/pid/89/5992-40","evidence":"DBLP curated profile homepages: http://www.robots.ox.ac.uk/~lz/."}],"count2025":26,"conference2025":21,"journal2025":5,"preprint2025":18,"status":"verified","notes":"Counts are DBLP indexed coauthored records, not first-author counts, laboratory totals, unique scientific discoveries, or quality assessments. DBLP yearOfPublication=2025; yearOfEvent retained and can differ. Conference workshops are included. Preprints are separate and may overlap formal versions.","papers":[{"key":"conf/cvpr/000300V0ZZ25","title":"Improving Gaussian Splatting with Localized Points Management.","year":2025,"yearOfEvent":2025,"venue":"CVPR","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/CVPR52734.2025.02021"],"source":"https://dblp.org/rec/conf/cvpr/000300V0ZZ25","documentPage":"https://openaccess.thecvf.com/content/CVPR2025/html/Yang_Improving_Gaussian_Splatting_with_Localized_Points_Management_CVPR_2025_paper.html","type":"Inproceedings","doi":"https://doi.org/10.1109/CVPR52734.2025.02021","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/000300V0ZZ25","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Yang_Improving_Gaussian_Splatting_with_Localized_Points_Management_CVPR_2025_paper.html"},{"key":"conf/cvpr/GuW0Z25","title":"TensoFlow: Tensorial Flow-based Sampler for Inverse Rendering.","year":2025,"yearOfEvent":2025,"venue":"CVPR","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/CVPR52734.2025.00055"],"source":"https://dblp.org/rec/conf/cvpr/GuW0Z25","documentPage":"https://openaccess.thecvf.com/content/CVPR2025/html/Gu_TensoFlow_Tensorial_Flow-based_Sampler_for_Inverse_Rendering_CVPR_2025_paper.html","type":"Inproceedings","doi":"https://doi.org/10.1109/CVPR52734.2025.00055","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/GuW0Z25","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Gu_TensoFlow_Tensorial_Flow-based_Sampler_for_Inverse_Rendering_CVPR_2025_paper.html"},{"key":"conf/cvpr/GuWZY025","title":"IRGS: Inter-Reflective Gaussian Splatting with 2D Gaussian Ray Tracing.","year":2025,"yearOfEvent":2025,"venue":"CVPR","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/CVPR52734.2025.01022"],"source":"https://dblp.org/rec/conf/cvpr/GuWZY025","documentPage":"https://openaccess.thecvf.com/content/CVPR2025/html/Gu_IRGS_Inter-Reflective_Gaussian_Splatting_with_2D_Gaussian_Ray_Tracing_CVPR_2025_paper.html","type":"Inproceedings","doi":"https://doi.org/10.1109/CVPR52734.2025.01022","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/GuWZY025","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Gu_IRGS_Inter-Reflective_Gaussian_Splatting_with_2D_Gaussian_Ray_Tracing_CVPR_2025_paper.html"},{"key":"conf/cvpr/LiGLZDCZTZW0Z0Z25","title":"UniScene: Unified Occupancy-centric Driving Scene Generation.","year":2025,"yearOfEvent":2025,"venue":"CVPR","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/CVPR52734.2025.01118"],"source":"https://dblp.org/rec/conf/cvpr/LiGLZDCZTZW0Z0Z25","documentPage":"https://openaccess.thecvf.com/content/CVPR2025/html/Li_UniScene_Unified_Occupancy-centric_Driving_Scene_Generation_CVPR_2025_paper.html","type":"Inproceedings","doi":"https://doi.org/10.1109/CVPR52734.2025.01118","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/LiGLZDCZTZW0Z0Z25","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Li_UniScene_Unified_Occupancy-centric_Driving_Scene_Generation_CVPR_2025_paper.html"},{"key":"conf/cvpr/ZhangSJZ25","title":"Bridging Past and Future: End-to-End Autonomous Driving with Historical Prediction and Planning.","year":2025,"yearOfEvent":2025,"venue":"CVPR","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/CVPR52734.2025.00643"],"source":"https://dblp.org/rec/conf/cvpr/ZhangSJZ25","documentPage":"https://openaccess.thecvf.com/content/CVPR2025/html/Zhang_Bridging_Past_and_Future_End-to-End_Autonomous_Driving_with_Historical_Prediction_CVPR_2025_paper.html","type":"Inproceedings","doi":"https://doi.org/10.1109/CVPR52734.2025.00643","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/ZhangSJZ25","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Zhang_Bridging_Past_and_Future_End-to-End_Autonomous_Driving_with_Historical_Prediction_CVPR_2025_paper.html"},{"key":"conf/eccv/GaoGLLZCZY24","title":"Relightable 3D Gaussians: Realistic Point Cloud Relighting with BRDF Decomposition and Ray Tracing.","year":2025,"yearOfEvent":2024,"venue":"ECCV (45)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1007/978-3-031-72995-9_5"],"source":"https://dblp.org/rec/conf/eccv/GaoGLLZCZY24","documentPage":"https://doi.org/10.1007/978-3-031-72995-9_5","type":"Inproceedings","doi":"https://doi.org/10.1007/978-3-031-72995-9_5","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/eccv/GaoGLLZCZY24","documentUrl":"https://doi.org/10.1007/978-3-031-72995-9_5"},{"key":"conf/eccv/LuHYZZ24","title":"WoVoGen: World Volume-Aware Diffusion for Controllable Multi-camera Driving Scene Generation.","year":2025,"yearOfEvent":2024,"venue":"ECCV (80)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1007/978-3-031-72989-8_19"],"source":"https://dblp.org/rec/conf/eccv/LuHYZZ24","documentPage":"https://doi.org/10.1007/978-3-031-72989-8_19","type":"Inproceedings","doi":"https://doi.org/10.1007/978-3-031-72989-8_19","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/eccv/LuHYZZ24","documentUrl":"https://doi.org/10.1007/978-3-031-72989-8_19"},{"key":"conf/eccv/NiePWCHXZ24","title":"Reason2Drive: Towards Interpretable and Chain-Based Reasoning for Autonomous Driving.","year":2025,"yearOfEvent":2024,"venue":"ECCV (26)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1007/978-3-031-73347-5_17"],"source":"https://dblp.org/rec/conf/eccv/NiePWCHXZ24","documentPage":"https://doi.org/10.1007/978-3-031-73347-5_17","type":"Inproceedings","doi":"https://doi.org/10.1007/978-3-031-73347-5_17","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/eccv/NiePWCHXZ24","documentUrl":"https://doi.org/10.1007/978-3-031-73347-5_17"},{"key":"conf/icassp/YuanGWXZ25","title":"Brick-Diffusion: Generating Long Videos with Brick-to-Wall Denoising.","year":2025,"yearOfEvent":2025,"venue":"ICASSP","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/ICASSP49660.2025.10888199"],"source":"https://dblp.org/rec/conf/icassp/YuanGWXZ25","documentPage":"https://doi.org/10.1109/ICASSP49660.2025.10888199","type":"Inproceedings","doi":"https://doi.org/10.1109/ICASSP49660.2025.10888199","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/icassp/YuanGWXZ25","documentUrl":"https://doi.org/10.1109/ICASSP49660.2025.10888199"},{"key":"conf/iccv/MaJCZ25","title":"BézierGS: Dynamic Urban Scene Reconstruction with Bézier Curve Gaussian Splatting.","year":2025,"yearOfEvent":2025,"venue":"ICCV","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/ICCV51701.2025.02367"],"source":"https://dblp.org/rec/conf/iccv/MaJCZ25","documentPage":"https://doi.org/10.1109/ICCV51701.2025.02367","type":"Inproceedings","doi":"https://doi.org/10.1109/ICCV51701.2025.02367","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/MaJCZ25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.02367"},{"key":"conf/iccv/YangPYZZ25","title":"Driving View Synthesis on Free-Form Trajectories with Generative Prior.","year":2025,"yearOfEvent":2025,"venue":"ICCV","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/ICCV51701.2025.02607"],"source":"https://dblp.org/rec/conf/iccv/YangPYZZ25","documentPage":"https://doi.org/10.1109/ICCV51701.2025.02607","type":"Inproceedings","doi":"https://doi.org/10.1109/ICCV51701.2025.02607","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/YangPYZZ25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.02607"},{"key":"conf/iclr/0003GC025","title":"GS-LiDAR: Generating Realistic LiDAR Point Clouds with Panoramic Gaussian Splatting.","year":2025,"yearOfEvent":2025,"venue":"ICLR","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/iclr/0003GC025","documentPage":"https://openreview.net/forum?id=RMaRBE9s2H","type":"Inproceedings","doi":null,"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iclr/0003GC025","documentUrl":"https://openreview.net/forum?id=RMaRBE9s2H"},{"key":"conf/iclr/YangPGZ25","title":"Diffusion2: Dynamic 3D Content Generation via Score Composition of Video and Multi-view Diffusion Models.","year":2025,"yearOfEvent":2025,"venue":"ICLR","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/iclr/YangPGZ25","documentPage":"https://openreview.net/forum?id=fectsEG2GU","type":"Inproceedings","doi":null,"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iclr/YangPGZ25","documentUrl":"https://openreview.net/forum?id=fectsEG2GU"},{"key":"conf/iclr/YaoZGZ025","title":"Reflective Gaussian Splatting.","year":2025,"yearOfEvent":2025,"venue":"ICLR","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/iclr/YaoZGZ025","documentPage":"https://openreview.net/forum?id=xPxHQHDH2u","type":"Inproceedings","doi":null,"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iclr/YaoZGZ025","documentUrl":"https://openreview.net/forum?id=xPxHQHDH2u"},{"key":"conf/iclr/YuanGWZXZ25","title":"FreqPrior: Improving Video Diffusion Models with Frequency Filtering Gaussian Noise.","year":2025,"yearOfEvent":2025,"venue":"ICLR","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/iclr/YuanGWZXZ25","documentPage":"https://openreview.net/forum?id=8x0SGbCpzs","type":"Inproceedings","doi":null,"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iclr/YuanGWZXZ25","documentUrl":"https://openreview.net/forum?id=8x0SGbCpzs"},{"key":"conf/mm/HuangXSFYSZ25","title":"MS-Road: Towards Spatiotemporal-Consistent Large-Scale Road Reconstruction.","year":2025,"yearOfEvent":2025,"venue":"ACM Multimedia","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1145/3746027.3754831"],"source":"https://dblp.org/rec/conf/mm/HuangXSFYSZ25","documentPage":"https://doi.org/10.1145/3746027.3754831","type":"Inproceedings","doi":"https://doi.org/10.1145/3746027.3754831","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/mm/HuangXSFYSZ25","documentUrl":"https://doi.org/10.1145/3746027.3754831"},{"key":"conf/nips/NieWHXZ25","title":"Towards Unified Multimodal Interleaved Generation via Group Relative Policy Optimization.","year":2025,"yearOfEvent":2025,"venue":"NeurIPS","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/nips/NieWHXZ25","documentPage":"http://papers.nips.cc/paper_files/paper/2025/hash/0850848de2a37c65a055bf489ba63480-Abstract-Conference.html","type":"Inproceedings","doi":null,"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/nips/NieWHXZ25","documentUrl":"http://papers.nips.cc/paper_files/paper/2025/hash/0850848de2a37c65a055bf489ba63480-Abstract-Conference.html"},{"key":"conf/nips/SongJLZZ25","title":"UniMotion: A Unified Motion Framework for Simulation, Prediction and Planning.","year":2025,"yearOfEvent":2025,"venue":"NeurIPS","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/nips/SongJLZZ25","documentPage":"http://papers.nips.cc/paper_files/paper/2025/hash/b0499a1aecf036d42074d03f621d7864-Abstract-Conference.html","type":"Inproceedings","doi":null,"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/nips/SongJLZZ25","documentUrl":"http://papers.nips.cc/paper_files/paper/2025/hash/b0499a1aecf036d42074d03f621d7864-Abstract-Conference.html"},{"key":"conf/nips/ZhangCXHMCZYCHQ25","title":"From Flatland to Space: Teaching Vision-Language Models to Perceive and Reason in 3D.","year":2025,"yearOfEvent":2025,"venue":"NeurIPS","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/nips/ZhangCXHMCZYCHQ25","documentPage":"http://papers.nips.cc/paper_files/paper/2025/hash/e3a0db7c0a191854c176af1d20cdec80-Abstract-Datasets_and_Benchmarks_Track.html","type":"Inproceedings","doi":null,"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/nips/ZhangCXHMCZYCHQ25","documentUrl":"http://papers.nips.cc/paper_files/paper/2025/hash/e3a0db7c0a191854c176af1d20cdec80-Abstract-Datasets_and_Benchmarks_Track.html"},{"key":"conf/nips/ZhangCXHZYCHQXZ25","title":"4D-VLA: Spatiotemporal Vision-Language-Action Pretraining with Cross-Scene Calibration.","year":2025,"yearOfEvent":2025,"venue":"NeurIPS","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/nips/ZhangCXHZYCHQXZ25","documentPage":"http://papers.nips.cc/paper_files/paper/2025/hash/30b9c38b9ebeee281cd2bc41d39bf0e7-Abstract-Conference.html","type":"Inproceedings","doi":null,"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/nips/ZhangCXHZYCHQXZ25","documentUrl":"http://papers.nips.cc/paper_files/paper/2025/hash/30b9c38b9ebeee281cd2bc41d39bf0e7-Abstract-Conference.html"},{"key":"conf/nips/ZhangSLZDZ25","title":"Future-Aware End-to-End Driving: Bidirectional Modeling of Trajectory Planning and Scene Evolution.","year":2025,"yearOfEvent":2025,"venue":"NeurIPS","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/nips/ZhangSLZDZ25","documentPage":"http://papers.nips.cc/paper_files/paper/2025/hash/0ee633a6ade45eab4276352b3ee79c7a-Abstract-Conference.html","type":"Inproceedings","doi":null,"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/nips/ZhangSLZDZ25","documentUrl":"http://papers.nips.cc/paper_files/paper/2025/hash/0ee633a6ade45eab4276352b3ee79c7a-Abstract-Conference.html"},{"key":"journals/ijcv/MaZFZ25","title":"Preconditioned Score-Based Generative Models.","year":2025,"yearOfEvent":null,"venue":"Int. J. Comput. Vis.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1007/S11263-025-02410-W"],"source":"https://dblp.org/rec/journals/ijcv/MaZFZ25","documentPage":"https://doi.org/10.1007/S11263-025-02410-W","type":"Article","doi":"https://doi.org/10.1007/S11263-025-02410-W","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/ijcv/MaZFZ25","documentUrl":"https://doi.org/10.1007/S11263-025-02410-W"},{"key":"journals/ijcv/NieCXZ25","title":"LaneCorrect: Self-Supervised Lane Detection.","year":2025,"yearOfEvent":null,"venue":"Int. J. Comput. Vis.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1007/S11263-025-02417-3"],"source":"https://dblp.org/rec/journals/ijcv/NieCXZ25","documentPage":"https://doi.org/10.1007/S11263-025-02417-3","type":"Article","doi":"https://doi.org/10.1007/S11263-025-02417-3","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/ijcv/NieCXZ25","documentUrl":"https://doi.org/10.1007/S11263-025-02417-3"},{"key":"journals/ijcv/WanHLYZ25","title":"SeaFormer++: Squeeze-Enhanced Axial Transformer for Mobile Visual Recognition.","year":2025,"yearOfEvent":null,"venue":"Int. J. Comput. Vis.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1007/S11263-025-02345-2"],"source":"https://dblp.org/rec/journals/ijcv/WanHLYZ25","documentPage":"https://doi.org/10.1007/S11263-025-02345-2","type":"Article","doi":"https://doi.org/10.1007/S11263-025-02345-2","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/ijcv/WanHLYZ25","documentUrl":"https://doi.org/10.1007/S11263-025-02345-2"},{"key":"journals/pami/ChenZXLZLZ25","title":"S-NeRF++: Autonomous Driving Simulation via Neural Reconstruction and Generation.","year":2025,"yearOfEvent":null,"venue":"IEEE Trans. Pattern Anal. Mach. Intell.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1109/TPAMI.2025.3543072"],"source":"https://dblp.org/rec/journals/pami/ChenZXLZLZ25","documentPage":"https://doi.org/10.1109/TPAMI.2025.3543072","type":"Article","doi":"https://doi.org/10.1109/TPAMI.2025.3543072","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/pami/ChenZXLZLZ25","documentUrl":"https://doi.org/10.1109/TPAMI.2025.3543072"},{"key":"journals/pami/YangSLZZT25","title":"DeepInteraction++: Multi-Modality Interaction for Autonomous Driving.","year":2025,"yearOfEvent":null,"venue":"IEEE Trans. Pattern Anal. Mach. Intell.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1109/TPAMI.2025.3565194"],"source":"https://dblp.org/rec/journals/pami/YangSLZZT25","documentPage":"https://doi.org/10.1109/TPAMI.2025.3565194","type":"Article","doi":"https://doi.org/10.1109/TPAMI.2025.3565194","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/pami/YangSLZZT25","documentUrl":"https://doi.org/10.1109/TPAMI.2025.3565194"}],"preprints":[{"key":"journals/corr/abs-2501-02741","title":"Brick-Diffusion: Generating Long Videos with Brick-to-Wall Denoising.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2501.02741"],"source":"https://dblp.org/rec/journals/corr/abs-2501-02741","documentPage":"https://doi.org/10.48550/ARXIV.2501.02741","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2501.02741","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2501-02741","documentUrl":"https://doi.org/10.48550/ARXIV.2501.02741","arxivId":"2501.02741","arxivUrl":"https://arxiv.org/abs/2501.02741"},{"key":"journals/corr/abs-2501-13971","title":"GS-LiDAR: Generating Realistic LiDAR Point Clouds with Panoramic Gaussian Splatting.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2501.13971"],"source":"https://dblp.org/rec/journals/corr/abs-2501-13971","documentPage":"https://doi.org/10.48550/ARXIV.2501.13971","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2501.13971","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2501-13971","documentUrl":"https://doi.org/10.48550/ARXIV.2501.13971","arxivId":"2501.13971","arxivUrl":"https://arxiv.org/abs/2501.13971"},{"key":"journals/corr/abs-2502-03496","title":"FreqPrior: Improving Video Diffusion Models with Frequency Filtering Gaussian Noise.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2502.03496"],"source":"https://dblp.org/rec/journals/corr/abs-2502-03496","documentPage":"https://doi.org/10.48550/ARXIV.2502.03496","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2502.03496","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2502-03496","documentUrl":"https://doi.org/10.48550/ARXIV.2502.03496","arxivId":"2502.03496","arxivUrl":"https://arxiv.org/abs/2502.03496"},{"key":"journals/corr/abs-2503-14182","title":"Bridging Past and Future: End-to-End Autonomous Driving with Historical Prediction and Planning.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2503.14182"],"source":"https://dblp.org/rec/journals/corr/abs-2503-14182","documentPage":"https://doi.org/10.48550/ARXIV.2503.14182","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2503.14182","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-14182","documentUrl":"https://doi.org/10.48550/ARXIV.2503.14182","arxivId":"2503.14182","arxivUrl":"https://arxiv.org/abs/2503.14182"},{"key":"journals/corr/abs-2503-18328","title":"TensoFlow: Tensorial Flow-based Sampler for Inverse Rendering.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2503.18328"],"source":"https://dblp.org/rec/journals/corr/abs-2503-18328","documentPage":"https://doi.org/10.48550/ARXIV.2503.18328","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2503.18328","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-18328","documentUrl":"https://doi.org/10.48550/ARXIV.2503.18328","arxivId":"2503.18328","arxivUrl":"https://arxiv.org/abs/2503.18328"},{"key":"journals/corr/abs-2503-22976","title":"From Flatland to Space: Teaching Vision-Language Models to Perceive and Reason in 3D.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2503.22976"],"source":"https://dblp.org/rec/journals/corr/abs-2503-22976","documentPage":"https://doi.org/10.48550/ARXIV.2503.22976","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2503.22976","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-22976","documentUrl":"https://doi.org/10.48550/ARXIV.2503.22976","arxivId":"2503.22976","arxivUrl":"https://arxiv.org/abs/2503.22976"},{"key":"journals/corr/abs-2505-16902","title":"RealEngine: Simulating Autonomous Driving in Realistic Context.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2505.16902"],"source":"https://dblp.org/rec/journals/corr/abs-2505-16902","documentPage":"https://doi.org/10.48550/ARXIV.2505.16902","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2505.16902","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-16902","documentUrl":"https://doi.org/10.48550/ARXIV.2505.16902","arxivId":"2505.16902","arxivUrl":"https://arxiv.org/abs/2505.16902"},{"key":"journals/corr/abs-2506-22099","title":"BézierGS: Dynamic Urban Scene Reconstruction with Bézier Curve Gaussian Splatting.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2506.22099"],"source":"https://dblp.org/rec/journals/corr/abs-2506-22099","documentPage":"https://doi.org/10.48550/ARXIV.2506.22099","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2506.22099","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-22099","documentUrl":"https://doi.org/10.48550/ARXIV.2506.22099","arxivId":"2506.22099","arxivUrl":"https://arxiv.org/abs/2506.22099"},{"key":"journals/corr/abs-2506-22242","title":"4D-VLA: Spatiotemporal Vision-Language-Action Pretraining with Cross-Scene Calibration.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2506.22242"],"source":"https://dblp.org/rec/journals/corr/abs-2506-22242","documentPage":"https://doi.org/10.48550/ARXIV.2506.22242","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2506.22242","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-22242","documentUrl":"https://doi.org/10.48550/ARXIV.2506.22242","arxivId":"2506.22242","arxivUrl":"https://arxiv.org/abs/2506.22242"},{"key":"journals/corr/abs-2507-17342","title":"DeMo++: Motion Decoupling for Autonomous Driving.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2507.17342"],"source":"https://dblp.org/rec/journals/corr/abs-2507-17342","documentPage":"https://doi.org/10.48550/ARXIV.2507.17342","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2507.17342","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2507-17342","documentUrl":"https://doi.org/10.48550/ARXIV.2507.17342","arxivId":"2507.17342","arxivUrl":"https://arxiv.org/abs/2507.17342"},{"key":"journals/corr/abs-2508-11428","title":"ImagiDrive: A Unified Imagination-and-Planning Framework for Autonomous Driving.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2508.11428"],"source":"https://dblp.org/rec/journals/corr/abs-2508-11428","documentPage":"https://doi.org/10.48550/ARXIV.2508.11428","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2508.11428","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-11428","documentUrl":"https://doi.org/10.48550/ARXIV.2508.11428","arxivId":"2508.11428","arxivUrl":"https://arxiv.org/abs/2508.11428"},{"key":"journals/corr/abs-2508-11488","title":"Perception in Plan: Coupled Perception and Planning for End-to-End Autonomous Driving.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2508.11488"],"source":"https://dblp.org/rec/journals/corr/abs-2508-11488","documentPage":"https://doi.org/10.48550/ARXIV.2508.11488","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2508.11488","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-11488","documentUrl":"https://doi.org/10.48550/ARXIV.2508.11488","arxivId":"2508.11488","arxivUrl":"https://arxiv.org/abs/2508.11488"},{"key":"journals/corr/abs-2508-11492","title":"Relative Position Matters: Trajectory Prediction and Planning with Polar Representation.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2508.11492"],"source":"https://dblp.org/rec/journals/corr/abs-2508-11492","documentPage":"https://doi.org/10.48550/ARXIV.2508.11492","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2508.11492","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-11492","documentUrl":"https://doi.org/10.48550/ARXIV.2508.11492","arxivId":"2508.11492","arxivUrl":"https://arxiv.org/abs/2508.11492"},{"key":"journals/corr/abs-2508-11952","title":"UniUGG: Unified 3D Understanding and Generation via Geometric-Semantic Encoding.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2508.11952"],"source":"https://dblp.org/rec/journals/corr/abs-2508-11952","documentPage":"https://doi.org/10.48550/ARXIV.2508.11952","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2508.11952","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-11952","documentUrl":"https://doi.org/10.48550/ARXIV.2508.11952","arxivId":"2508.11952","arxivUrl":"https://arxiv.org/abs/2508.11952"},{"key":"journals/corr/abs-2508-12404","title":"LMAD: Integrated End-to-End Vision-Language Model for Explainable Autonomous Driving.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2508.12404"],"source":"https://dblp.org/rec/journals/corr/abs-2508-12404","documentPage":"https://doi.org/10.48550/ARXIV.2508.12404","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2508.12404","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-12404","documentUrl":"https://doi.org/10.48550/ARXIV.2508.12404","arxivId":"2508.12404","arxivUrl":"https://arxiv.org/abs/2508.12404"},{"key":"journals/corr/abs-2510-11092","title":"Future-Aware End-to-End Driving: Bidirectional Modeling of Trajectory Planning and Scene Evolution.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2510.11092"],"source":"https://dblp.org/rec/journals/corr/abs-2510-11092","documentPage":"https://doi.org/10.48550/ARXIV.2510.11092","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2510.11092","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-11092","documentUrl":"https://doi.org/10.48550/ARXIV.2510.11092","arxivId":"2510.11092","arxivUrl":"https://arxiv.org/abs/2510.11092"},{"key":"journals/corr/abs-2510-13800","title":"Reasoning in Space via Grounding in the World.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2510.13800"],"source":"https://dblp.org/rec/journals/corr/abs-2510-13800","documentPage":"https://doi.org/10.48550/ARXIV.2510.13800","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2510.13800","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-13800","documentUrl":"https://doi.org/10.48550/ARXIV.2510.13800","arxivId":"2510.13800","arxivUrl":"https://arxiv.org/abs/2510.13800"},{"key":"journals/corr/abs-2512-23147","title":"GeoTeacher: Geometry-Guided Semi-Supervised 3D Object Detection.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2512.23147"],"source":"https://dblp.org/rec/journals/corr/abs-2512-23147","documentPage":"https://doi.org/10.48550/ARXIV.2512.23147","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2512.23147","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-23147","documentUrl":"https://doi.org/10.48550/ARXIV.2512.23147","arxivId":"2512.23147","arxivUrl":"https://arxiv.org/abs/2512.23147"}],"excludedFormal":[],"excludedOther":[],"excludedHomonyms":[],"unassignedCandidates":[],"retrievedAt":"2026-10-19","querySource":"https://sparql.dblp.org/","method":"DBLP yearOfPublication=2025; Article + Inproceedings; excludes Informal/CoRR and explicit editorial/correction/erratum/preface; unique DBLP record keys within person.","labName":"Logos Robotics Group","labUrl":"https://github.com/logosroboticsgroup","labEvidence":"本人旧Oxford主页转向新个人主页；新主页明确称其在复旦领导 Logos Robotics Group，并直接链接该GitHub组织。旧 Zhang Vision Group 仍有网页，但本次优先采用本人当前页面现称。","labSourceUrl":"https://lzrobots.github.io/","affiliationZh":"复旦大学","sourceWarning":false,"knownPreprintMinimum2025":null,"excludedMisattributed":[],"displayNotes":"身份已经个人或机构主页核对。2025 年正式记录 26 条（会议 21、期刊 5），所有作者位置均计入，不表示主导或贡献份额；预印本 18 条单列，不加总。","labDisplayNotes":"本人新主页写明其在复旦领导 Logos Robotics Group，并链接团队 GitHub，据此归组；旧牛津主页已停更，旧的 Zhang Vision Group 网站不再采用。"},{"index":111,"name":"Zhaoxiang Zhang","nameZh":"张兆翔","affiliation":"Institute of Automation, Chinese Academy of Sciences","source":"DBLP Knowledge Graph official SPARQL API","profileUrl":"https://dblp.org/pid/55/2285-1","identifier":"55/2285-1","identityEvidence":[{"url":"https://dblp.org/pid/55/2285-1","evidence":"DBLP curated profile affiliations: Beihang University, School of Computer Science and Engineering, Laboratory of Intelligent Recognition and Image Processing, Beijing, China; Chinese Academy of Sciences, Hong Kong Institute of Science & Innovation, Centre for Artificial Intelligence and Robotics, Hong Kong; Chinese Academy of Sciences, Institute of Automation, Center for Research on Intelligent Perception and Computing (CRIPAC), National Laboratory of Pattern Recognition (NLPR), Beijing, China; Chinese Academy of Sciences, Institute of Automation, National Laboratory of Pattern Recognition, Beijing, China; University of Chinese Academy of Sciences, School of Artificial Intelligence, Beijing, China."},{"url":"https://dblp.org/pid/55/2285-1","evidence":"DBLP curated profile homepages: https://zhaoxiangzhang.net/."}],"count2025":50,"conference2025":40,"journal2025":10,"preprint2025":62,"status":"verified","notes":"Counts are DBLP indexed coauthored records, not first-author counts, laboratory totals, unique scientific discoveries, or quality assessments. DBLP yearOfPublication=2025; yearOfEvent retained and can differ. Conference workshops are included. Preprints are separate and may overlap formal versions.","papers":[{"key":"conf/aaai/ChenJTL0L025","title":"FIRM: Flexible Interactive Reflection ReMoval.","year":2025,"yearOfEvent":2025,"venue":"AAAI","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1609/AAAI.V39I2.32222"],"source":"https://dblp.org/rec/conf/aaai/ChenJTL0L025","documentPage":"https://doi.org/10.1609/AAAI.V39I2.32222","type":"Inproceedings","doi":"https://doi.org/10.1609/AAAI.V39I2.32222","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/aaai/ChenJTL0L025","documentUrl":"https://doi.org/10.1609/AAAI.V39I2.32222"},{"key":"conf/aaai/Zhou0HZLLP025","title":"SceneX: Procedural Controllable Large-Scale Scene Generation.","year":2025,"yearOfEvent":2025,"venue":"AAAI","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1609/AAAI.V39I10.33174"],"source":"https://dblp.org/rec/conf/aaai/Zhou0HZLLP025","documentPage":"https://doi.org/10.1609/AAAI.V39I10.33174","type":"Inproceedings","doi":"https://doi.org/10.1609/AAAI.V39I10.33174","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/aaai/Zhou0HZLLP025","documentUrl":"https://doi.org/10.1609/AAAI.V39I10.33174"},{"key":"conf/acl/0016MF0025","title":"C2KD: Cross-layer and Cross-head Knowledge Distillation for Small Language Model-based Recommendation.","year":2025,"yearOfEvent":2025,"venue":"ACL (Findings)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.18653/V1/2025.FINDINGS-ACL.917"],"source":"https://dblp.org/rec/conf/acl/0016MF0025","documentPage":"https://doi.org/10.18653/V1/2025.FINDINGS-ACL.917","type":"Inproceedings","doi":"https://doi.org/10.18653/V1/2025.FINDINGS-ACL.917","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/acl/0016MF0025","documentUrl":"https://doi.org/10.18653/V1/2025.FINDINGS-ACL.917"},{"key":"conf/acl/HeLLWB0P0ZS025","title":"Can Large Language Models Detect Errors in Long Chain-of-Thought Reasoning?","year":2025,"yearOfEvent":2025,"venue":"ACL (1)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.18653/V1/2025.ACL-LONG.905"],"source":"https://dblp.org/rec/conf/acl/HeLLWB0P0ZS025","documentPage":"https://doi.org/10.18653/V1/2025.ACL-LONG.905","type":"Inproceedings","doi":"https://doi.org/10.18653/V1/2025.ACL-LONG.905","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/acl/HeLLWB0P0ZS025","documentUrl":"https://doi.org/10.18653/V1/2025.ACL-LONG.905"},{"key":"conf/acl/HuangCLXHSXYLZC25","title":"OpenCoder: The Open Cookbook for Top-Tier Code Large Language Models.","year":2025,"yearOfEvent":2025,"venue":"ACL (1)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.18653/V1/2025.ACL-LONG.1591"],"source":"https://dblp.org/rec/conf/acl/HuangCLXHSXYLZC25","documentPage":"https://doi.org/10.18653/V1/2025.ACL-LONG.1591","type":"Inproceedings","doi":"https://doi.org/10.18653/V1/2025.ACL-LONG.1591","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/acl/HuangCLXHSXYLZC25","documentUrl":"https://doi.org/10.18653/V1/2025.ACL-LONG.1591"},{"key":"conf/acl/LiCSC0025","title":"AutoGUI: Scaling GUI Grounding with Automatic Functionality Annotations from LLMs.","year":2025,"yearOfEvent":2025,"venue":"ACL (1)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.18653/V1/2025.ACL-LONG.510"],"source":"https://dblp.org/rec/conf/acl/LiCSC0025","documentPage":"https://doi.org/10.18653/V1/2025.ACL-LONG.510","type":"Inproceedings","doi":"https://doi.org/10.18653/V1/2025.ACL-LONG.510","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/acl/LiCSC0025","documentUrl":"https://doi.org/10.18653/V1/2025.ACL-LONG.510"},{"key":"conf/acl/LiuDLYLZZCWK0WZ25","title":"M2RC-EVAL: Massively Multilingual Repository-level Code Completion Evaluation.","year":2025,"yearOfEvent":2025,"venue":"ACL (1)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.18653/V1/2025.ACL-LONG.763"],"source":"https://dblp.org/rec/conf/acl/LiuDLYLZZCWK0WZ25","documentPage":"https://doi.org/10.18653/V1/2025.ACL-LONG.763","type":"Inproceedings","doi":"https://doi.org/10.18653/V1/2025.ACL-LONG.763","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/acl/LiuDLYLZZCWK0WZ25","documentUrl":"https://doi.org/10.18653/V1/2025.ACL-LONG.763"},{"key":"conf/cvpr/FanZWLZ25","title":"FreeSim: Toward Free-viewpoint Camera Simulation in Driving Scenes.","year":2025,"yearOfEvent":2025,"venue":"CVPR","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/CVPR52734.2025.01121"],"source":"https://dblp.org/rec/conf/cvpr/FanZWLZ25","documentPage":"https://openaccess.thecvf.com/content/CVPR2025/html/Fan_FreeSim_Toward_Free-viewpoint_Camera_Simulation_in_Driving_Scenes_CVPR_2025_paper.html","type":"Inproceedings","doi":"https://doi.org/10.1109/CVPR52734.2025.01121","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/FanZWLZ25","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Fan_FreeSim_Toward_Free-viewpoint_Camera_Simulation_in_Driving_Scenes_CVPR_2025_paper.html"},{"key":"conf/cvpr/ZhouFH000025","title":"FlexDrive: Toward Trajectory Flexibility in Driving Scene Gaussian Splatting Reconstruction and Rendering.","year":2025,"yearOfEvent":2025,"venue":"CVPR","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/CVPR52734.2025.00152"],"source":"https://dblp.org/rec/conf/cvpr/ZhouFH000025","documentPage":"https://openaccess.thecvf.com/content/CVPR2025/html/Zhou_FlexDrive_Toward_Trajectory_Flexibility_in_Driving_Scene_Gaussian_Splatting_Reconstruction_CVPR_2025_paper.html","type":"Inproceedings","doi":"https://doi.org/10.1109/CVPR52734.2025.00152","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/ZhouFH000025","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Zhou_FlexDrive_Toward_Trajectory_Flexibility_in_Driving_Scene_Gaussian_Splatting_Reconstruction_CVPR_2025_paper.html"},{"key":"conf/eccv/ChenWLZC24","title":"Expanding Scene Graph Boundaries: Fully Open-Vocabulary Scene Graph Generation via Visual-Concept Alignment and Retention.","year":2025,"yearOfEvent":2024,"venue":"ECCV (66)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1007/978-3-031-72848-8_7"],"source":"https://dblp.org/rec/conf/eccv/ChenWLZC24","documentPage":"https://doi.org/10.1007/978-3-031-72848-8_7","type":"Inproceedings","doi":"https://doi.org/10.1007/978-3-031-72848-8_7","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/eccv/ChenWLZC24","documentUrl":"https://doi.org/10.1007/978-3-031-72848-8_7"},{"key":"conf/eccv/LiFZ24","title":"Point-Supervised Panoptic Segmentation via Estimating Pseudo Labels from Learnable Distance.","year":2025,"yearOfEvent":2024,"venue":"ECCV (16)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1007/978-3-031-72640-8_6"],"source":"https://dblp.org/rec/conf/eccv/LiFZ24","documentPage":"https://doi.org/10.1007/978-3-031-72640-8_6","type":"Inproceedings","doi":"https://doi.org/10.1007/978-3-031-72640-8_6","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/eccv/LiFZ24","documentUrl":"https://doi.org/10.1007/978-3-031-72640-8_6"},{"key":"conf/eccv/LiuLFWPZ24","title":"CityGaussian: Real-Time High-Quality Large-Scale Scene Rendering with Gaussians.","year":2025,"yearOfEvent":2024,"venue":"ECCV (16)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1007/978-3-031-72640-8_15"],"source":"https://dblp.org/rec/conf/eccv/LiuLFWPZ24","documentPage":"https://doi.org/10.1007/978-3-031-72640-8_15","type":"Inproceedings","doi":"https://doi.org/10.1007/978-3-031-72640-8_15","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/eccv/LiuLFWPZ24","documentUrl":"https://doi.org/10.1007/978-3-031-72640-8_15"},{"key":"conf/eccv/WangHCZ24","title":"OneTrack: Demystifying the Conflict Between Detection and Tracking in End-to-End 3D Trackers.","year":2025,"yearOfEvent":2024,"venue":"ECCV (7)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1007/978-3-031-72667-5_22"],"source":"https://dblp.org/rec/conf/eccv/WangHCZ24","documentPage":"https://doi.org/10.1007/978-3-031-72667-5_22","type":"Inproceedings","doi":"https://doi.org/10.1007/978-3-031-72667-5_22","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/eccv/WangHCZ24","documentUrl":"https://doi.org/10.1007/978-3-031-72667-5_22"},{"key":"conf/eccv/WangWLZLZ24","title":"Open Vocabulary 3D Scene Understanding via Geometry Guided Self-Distillation.","year":2025,"yearOfEvent":2024,"venue":"ECCV (15)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1007/978-3-031-72633-0_25"],"source":"https://dblp.org/rec/conf/eccv/WangWLZLZ24","documentPage":"https://doi.org/10.1007/978-3-031-72633-0_25","type":"Inproceedings","doi":"https://doi.org/10.1007/978-3-031-72633-0_25","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/eccv/WangWLZLZ24","documentUrl":"https://doi.org/10.1007/978-3-031-72633-0_25"},{"key":"conf/eccv/YuWCZ24","title":"Monocular Occupancy Prediction for Scalable Indoor Scenes.","year":2025,"yearOfEvent":2024,"venue":"ECCV (30)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1007/978-3-031-73404-5_3"],"source":"https://dblp.org/rec/conf/eccv/YuWCZ24","documentPage":"https://doi.org/10.1007/978-3-031-73404-5_3","type":"Inproceedings","doi":"https://doi.org/10.1007/978-3-031-73404-5_3","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/eccv/YuWCZ24","documentUrl":"https://doi.org/10.1007/978-3-031-73404-5_3"},{"key":"conf/eccv/ZhangFCZLZ24","title":"General Geometry-Aware Weakly Supervised 3D Object Detection.","year":2025,"yearOfEvent":2024,"venue":"ECCV (51)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1007/978-3-031-72983-6_17"],"source":"https://dblp.org/rec/conf/eccv/ZhangFCZLZ24","documentPage":"https://doi.org/10.1007/978-3-031-72983-6_17","type":"Inproceedings","doi":"https://doi.org/10.1007/978-3-031-72983-6_17","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/eccv/ZhangFCZLZ24","documentUrl":"https://doi.org/10.1007/978-3-031-72983-6_17"},{"key":"conf/eccv/ZhanLLZC24","title":"CSOT: Cross-scan Object Transfer for Semi-Supervised LiDAR Object Detection.","year":2025,"yearOfEvent":2024,"venue":"ECCV (17)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1007/978-3-031-72643-9_20"],"source":"https://dblp.org/rec/conf/eccv/ZhanLLZC24","documentPage":"https://doi.org/10.1007/978-3-031-72643-9_20","type":"Inproceedings","doi":"https://doi.org/10.1007/978-3-031-72643-9_20","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/eccv/ZhanLLZC24","documentUrl":"https://doi.org/10.1007/978-3-031-72643-9_20"},{"key":"conf/emnlp/WangZXZLZWSLLQZZZXFH25","title":"MIO: A Foundation Model on Multimodal Tokens.","year":2025,"yearOfEvent":2025,"venue":"EMNLP","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.18653/V1/2025.EMNLP-MAIN.255"],"source":"https://dblp.org/rec/conf/emnlp/WangZXZLZWSLLQZZZXFH25","documentPage":"https://doi.org/10.18653/V1/2025.EMNLP-MAIN.255","type":"Inproceedings","doi":"https://doi.org/10.18653/V1/2025.EMNLP-MAIN.255","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/emnlp/WangZXZLZWSLLQZZZXFH25","documentUrl":"https://doi.org/10.18653/V1/2025.EMNLP-MAIN.255"},{"key":"conf/globecom/ZhaoZCHYZ25","title":"SflLLM: Efficient Split Federated Learning for Large Language Model over Wireless Networks.","year":2025,"yearOfEvent":2025,"venue":"GLOBECOM","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/GLOBECOM59602.2025.11432069"],"source":"https://dblp.org/rec/conf/globecom/ZhaoZCHYZ25","documentPage":"https://doi.org/10.1109/GLOBECOM59602.2025.11432069","type":"Inproceedings","doi":"https://doi.org/10.1109/GLOBECOM59602.2025.11432069","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/globecom/ZhaoZCHYZ25","documentUrl":"https://doi.org/10.1109/GLOBECOM59602.2025.11432069"},{"key":"conf/icb/MaZQCGQZL25","title":"DiffSpeaker: Speech-Driven 3D Facial Animation with Diffusion Transformer.","year":2025,"yearOfEvent":2025,"venue":"IJCB","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/IJCB65343.2025.11411575"],"source":"https://dblp.org/rec/conf/icb/MaZQCGQZL25","documentPage":"https://doi.org/10.1109/IJCB65343.2025.11411575","type":"Inproceedings","doi":"https://doi.org/10.1109/IJCB65343.2025.11411575","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/icb/MaZQCGQZL25","documentUrl":"https://doi.org/10.1109/IJCB65343.2025.11411575"},{"key":"conf/iccv/ChenWZ25","title":"DrivingGPT: Unifying Driving World Modeling and Planning with Multi-Modal Autoregressive Transformers.","year":2025,"yearOfEvent":2025,"venue":"ICCV","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/ICCV51701.2025.02496"],"source":"https://dblp.org/rec/conf/iccv/ChenWZ25","documentPage":"https://doi.org/10.1109/ICCV51701.2025.02496","type":"Inproceedings","doi":"https://doi.org/10.1109/ICCV51701.2025.02496","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/ChenWZ25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.02496"},{"key":"conf/iccv/HeLYQZCZZYW25","title":"DexVLG: Dexterous Vision-Language-Grasp Model at Scale.","year":2025,"yearOfEvent":2025,"venue":"ICCV","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/ICCV51701.2025.01322"],"source":"https://dblp.org/rec/conf/iccv/HeLYQZCZZYW25","documentPage":"https://doi.org/10.1109/ICCV51701.2025.01322","type":"Inproceedings","doi":"https://doi.org/10.1109/ICCV51701.2025.01322","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/HeLYQZCZZYW25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.01322"},{"key":"conf/iccv/LinCJYFZZZ25","title":"MCOP: Multi-UAV Collaborative Occupancy Prediction.","year":2025,"yearOfEvent":2025,"venue":"ICCV","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/ICCV51701.2025.02529"],"source":"https://dblp.org/rec/conf/iccv/LinCJYFZZZ25","documentPage":"https://doi.org/10.1109/ICCV51701.2025.02529","type":"Inproceedings","doi":"https://doi.org/10.1109/ICCV51701.2025.02529","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/LinCJYFZZZ25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.02529"},{"key":"conf/iccv/LiSCJCLZ25","title":"UIPro: Unleashing Superior Interaction Capability for GUI Agents.","year":2025,"yearOfEvent":2025,"venue":"ICCV","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/ICCV51701.2025.00158"],"source":"https://dblp.org/rec/conf/iccv/LiSCJCLZ25","documentPage":"https://doi.org/10.1109/ICCV51701.2025.00158","type":"Inproceedings","doi":"https://doi.org/10.1109/ICCV51701.2025.00158","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/LiSCJCLZ25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.00158"},{"key":"conf/iccv/LiWLHFZ25","title":"End-to-End Driving with Online Trajectory Evaluation via BEV World Model.","year":2025,"yearOfEvent":2025,"venue":"ICCV","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/ICCV51701.2025.02519"],"source":"https://dblp.org/rec/conf/iccv/LiWLHFZ25","documentPage":"https://doi.org/10.1109/ICCV51701.2025.02519","type":"Inproceedings","doi":"https://doi.org/10.1109/ICCV51701.2025.02519","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/LiWLHFZ25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.02519"},{"key":"conf/iccv/WangZWFZZ25","title":"Ross3d: Reconstructive Visual Instruction Tuning With 3D-Awareness.","year":2025,"yearOfEvent":2025,"venue":"ICCV","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/ICCV51701.2025.00866"],"source":"https://dblp.org/rec/conf/iccv/WangZWFZZ25","documentPage":"https://doi.org/10.1109/ICCV51701.2025.00866","type":"Inproceedings","doi":"https://doi.org/10.1109/ICCV51701.2025.00866","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/WangZWFZZ25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.00866"},{"key":"conf/iccv/YangFLWZ25","title":"LayerAnimate: Layer-Level Control for Animation.","year":2025,"yearOfEvent":2025,"venue":"ICCV","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/ICCV51701.2025.01011"],"source":"https://dblp.org/rec/conf/iccv/YangFLWZ25","documentPage":"https://doi.org/10.1109/ICCV51701.2025.01011","type":"Inproceedings","doi":"https://doi.org/10.1109/ICCV51701.2025.01011","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/YangFLWZ25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.01011"},{"key":"conf/iclr/0347LMP025","title":"CityGaussianV2: Efficient and Geometrically Accurate Reconstruction for Large-Scale Scenes.","year":2025,"yearOfEvent":2025,"venue":"ICLR","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/iclr/0347LMP025","documentPage":"https://openreview.net/forum?id=a3ptUbuzbW","type":"Inproceedings","doi":null,"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iclr/0347LMP025","documentUrl":"https://openreview.net/forum?id=a3ptUbuzbW"},{"key":"conf/iclr/ChaiL0YJLS0RGWW25","title":"McEval: Massively Multilingual Code Evaluation.","year":2025,"yearOfEvent":2025,"venue":"ICLR","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/iclr/ChaiL0YJLS0RGWW25","documentPage":"https://openreview.net/forum?id=UunCPtPOlZ","type":"Inproceedings","doi":null,"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iclr/ChaiL0YJLS0RGWW25","documentUrl":"https://openreview.net/forum?id=UunCPtPOlZ"},{"key":"conf/iclr/LiF00C0T25","title":"Enhancing End-to-End Autonomous Driving with Latent World Model.","year":2025,"yearOfEvent":2025,"venue":"ICLR","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/iclr/LiF00C0T25","documentPage":"https://openreview.net/forum?id=fd2u60ryG0","type":"Inproceedings","doi":null,"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iclr/LiF00C0T25","documentUrl":"https://openreview.net/forum?id=fd2u60ryG0"},{"key":"conf/iclr/WangFWC025","title":"FreeVS: Generative View Synthesis on Free Driving Trajectory.","year":2025,"yearOfEvent":2025,"venue":"ICLR","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/iclr/WangFWC025","documentPage":"https://openreview.net/forum?id=dTGH9vUVdf","type":"Inproceedings","doi":null,"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iclr/WangFWC025","documentUrl":"https://openreview.net/forum?id=dTGH9vUVdf"},{"key":"conf/iclr/WangWWLSPDZWPZG25","title":"MTU-Bench: A Multi-granularity Tool-Use Benchmark for Large Language Models.","year":2025,"yearOfEvent":2025,"venue":"ICLR","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/iclr/WangWWLSPDZWPZG25","documentPage":"https://openreview.net/forum?id=6guG2OlXsr","type":"Inproceedings","doi":null,"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iclr/WangWWLSPDZWPZG25","documentUrl":"https://openreview.net/forum?id=6guG2OlXsr"},{"key":"conf/iclr/WangZZWG0025","title":"Reconstructive Visual Instruction Tuning.","year":2025,"yearOfEvent":2025,"venue":"ICLR","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/iclr/WangZZWG0025","documentPage":"https://openreview.net/forum?id=8q9NOMzRDg","type":"Inproceedings","doi":null,"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iclr/WangZZWG0025","documentUrl":"https://openreview.net/forum?id=8q9NOMzRDg"},{"key":"conf/icmcs/WangQAYLZ25","title":"Language-Conditioned Waypoint Predictor for Continuous Vision-and-Language Navigation.","year":2025,"yearOfEvent":2025,"venue":"ICME","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/ICME59968.2025.11209085"],"source":"https://dblp.org/rec/conf/icmcs/WangQAYLZ25","documentPage":"https://doi.org/10.1109/ICME59968.2025.11209085","type":"Inproceedings","doi":"https://doi.org/10.1109/ICME59968.2025.11209085","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/icmcs/WangQAYLZ25","documentUrl":"https://doi.org/10.1109/ICME59968.2025.11209085"},{"key":"conf/ijcai/Zou00025","title":"Top-Down Guidance for Learning Object-Centric Representations.","year":2025,"yearOfEvent":2025,"venue":"IJCAI","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.24963/IJCAI.2025/284"],"source":"https://dblp.org/rec/conf/ijcai/Zou00025","documentPage":"https://doi.org/10.24963/IJCAI.2025/284","type":"Inproceedings","doi":"https://doi.org/10.24963/IJCAI.2025/284","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/ijcai/Zou00025","documentUrl":"https://doi.org/10.24963/IJCAI.2025/284"},{"key":"conf/nips/LiuLTLYNFPZ25","title":"TC-Light: Temporally Coherent Generative Rendering for Realistic World Transfer.","year":2025,"yearOfEvent":2025,"venue":"NeurIPS","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/nips/LiuLTLYNFPZ25","documentPage":"http://papers.nips.cc/paper_files/paper/2025/hash/49f42aafbcce59b2665640cb9f3d794f-Abstract-Conference.html","type":"Inproceedings","doi":null,"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/nips/LiuLTLYNFPZ25","documentUrl":"http://papers.nips.cc/paper_files/paper/2025/hash/49f42aafbcce59b2665640cb9f3d794f-Abstract-Conference.html"},{"key":"conf/nips/LiZMYZGLLWYWQSZ25","title":"OmniBench: Towards The Future of Universal Omni-Language Models.","year":2025,"yearOfEvent":2025,"venue":"NeurIPS","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/nips/LiZMYZGLLWYWQSZ25","documentPage":"http://papers.nips.cc/paper_files/paper/2025/hash/2c7c4a12a9dcf7dace9896d08154c705-Abstract-Datasets_and_Benchmarks_Track.html","type":"Inproceedings","doi":null,"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/nips/LiZMYZGLLWYWQSZ25","documentUrl":"http://papers.nips.cc/paper_files/paper/2025/hash/2c7c4a12a9dcf7dace9896d08154c705-Abstract-Datasets_and_Benchmarks_Track.html"},{"key":"conf/nips/PengWZWWZYLWWLJ25","title":"MVU-Eval: Towards Multi-Video Understanding Evaluation for Multimodal LLMs.","year":2025,"yearOfEvent":2025,"venue":"NeurIPS","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/nips/PengWZWWZYLWWLJ25","documentPage":"http://papers.nips.cc/paper_files/paper/2025/hash/4dbb159f2c68b359b3b6ed7dd039481c-Abstract-Datasets_and_Benchmarks_Track.html","type":"Inproceedings","doi":null,"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/nips/PengWZWWZYLWWLJ25","documentUrl":"http://papers.nips.cc/paper_files/paper/2025/hash/4dbb159f2c68b359b3b6ed7dd039481c-Abstract-Datasets_and_Benchmarks_Track.html"},{"key":"conf/nips/ShangCWLZ25","title":"DriveDPO: Policy Learning via Safety DPO For End-to-End Autonomous Driving.","year":2025,"yearOfEvent":2025,"venue":"NeurIPS","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/nips/ShangCWLZ25","documentPage":"http://papers.nips.cc/paper_files/paper/2025/hash/750337e1301941f81ae31a90e0a1c181-Abstract-Conference.html","type":"Inproceedings","doi":null,"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/nips/ShangCWLZ25","documentUrl":"http://papers.nips.cc/paper_files/paper/2025/hash/750337e1301941f81ae31a90e0a1c181-Abstract-Conference.html"},{"key":"conf/nips/ShiYLBCZMWWHSZL25","title":"KORGym: A Dynamic Game Platform for LLM Reasoning Evaluation.","year":2025,"yearOfEvent":2025,"venue":"NeurIPS","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/nips/ShiYLBCZMWWHSZL25","documentPage":"http://papers.nips.cc/paper_files/paper/2025/hash/ebfa4297cd6419f64efe86f657ba49d0-Abstract-Conference.html","type":"Inproceedings","doi":null,"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/nips/ShiYLBCZMWWHSZL25","documentUrl":"http://papers.nips.cc/paper_files/paper/2025/hash/ebfa4297cd6419f64efe86f657ba49d0-Abstract-Conference.html"},{"key":"journals/bib/ZhangSZZZZWW25","title":"KansformerEPI: a deep learning framework integrating KAN and transformer for predicting enhancer-promoter interactions.","year":2025,"yearOfEvent":null,"venue":"Briefings Bioinform.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1093/BIB/BBAF272"],"source":"https://dblp.org/rec/journals/bib/ZhangSZZZZWW25","documentPage":"https://doi.org/10.1093/BIB/BBAF272","type":"Article","doi":"https://doi.org/10.1093/BIB/BBAF272","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/bib/ZhangSZZZZWW25","documentUrl":"https://doi.org/10.1093/BIB/BBAF272"},{"key":"journals/chinaf/TangWZLZ25","title":"ROLA: real-world object-centric learning with attention optimization.","year":2025,"yearOfEvent":null,"venue":"Sci. China Inf. Sci.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1007/S11432-024-4342-6"],"source":"https://dblp.org/rec/journals/chinaf/TangWZLZ25","documentPage":"https://doi.org/10.1007/S11432-024-4342-6","type":"Article","doi":"https://doi.org/10.1007/S11432-024-4342-6","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/chinaf/TangWZLZ25","documentUrl":"https://doi.org/10.1007/S11432-024-4342-6"},{"key":"journals/ijautcomp/GuanSZ25","title":"LiDAR-camera Cooperative Semantic Segmentation.","year":2025,"yearOfEvent":null,"venue":"Mach. Intell. Res.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1007/S11633-024-1508-2"],"source":"https://dblp.org/rec/journals/ijautcomp/GuanSZ25","documentPage":"https://doi.org/10.1007/S11633-024-1508-2","type":"Article","doi":"https://doi.org/10.1007/S11633-024-1508-2","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/ijautcomp/GuanSZ25","documentUrl":"https://doi.org/10.1007/S11633-024-1508-2"},{"key":"journals/ijautcomp/ZhangWHWWZZLL25","title":"A Survey on Personalized Content Synthesis with Diffusion Models.","year":2025,"yearOfEvent":null,"venue":"Mach. Intell. Res.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1007/S11633-025-1563-3"],"source":"https://dblp.org/rec/journals/ijautcomp/ZhangWHWWZZLL25","documentPage":"https://doi.org/10.1007/S11633-025-1563-3","type":"Article","doi":"https://doi.org/10.1007/S11633-025-1563-3","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/ijautcomp/ZhangWHWWZZLL25","documentUrl":"https://doi.org/10.1007/S11633-025-1563-3"},{"key":"journals/ijcv/WangSFLWWZ25","title":"Pulling Target to Source: A New Perspective on Domain Adaptive Semantic Segmentation.","year":2025,"yearOfEvent":null,"venue":"Int. J. Comput. Vis.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1007/S11263-024-02285-3"],"source":"https://dblp.org/rec/journals/ijcv/WangSFLWWZ25","documentPage":"https://doi.org/10.1007/S11263-024-02285-3","type":"Article","doi":"https://doi.org/10.1007/S11263-024-02285-3","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/ijcv/WangSFLWWZ25","documentUrl":"https://doi.org/10.1007/S11263-024-02285-3"},{"key":"journals/ijcv/WangWSFWZ25","title":"Using Unreliable Pseudo-Labels for Label-Efficient Semantic Segmentation.","year":2025,"yearOfEvent":null,"venue":"Int. J. Comput. Vis.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1007/S11263-024-02229-X"],"source":"https://dblp.org/rec/journals/ijcv/WangWSFWZ25","documentPage":"https://doi.org/10.1007/S11263-024-02229-X","type":"Article","doi":"https://doi.org/10.1007/S11263-024-02229-X","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/ijcv/WangWSFWZ25","documentUrl":"https://doi.org/10.1007/S11263-024-02229-X"},{"key":"journals/pami/FanWWZ25","title":"FSD V2: Improving Fully Sparse 3D Object Detection With Virtual Voxels.","year":2025,"yearOfEvent":null,"venue":"IEEE Trans. Pattern Anal. Mach. Intell.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1109/TPAMI.2024.3502456"],"source":"https://dblp.org/rec/journals/pami/FanWWZ25","documentPage":"https://doi.org/10.1109/TPAMI.2024.3502456","type":"Article","doi":"https://doi.org/10.1109/TPAMI.2024.3502456","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/pami/FanWWZ25","documentUrl":"https://doi.org/10.1109/TPAMI.2024.3502456"},{"key":"journals/pami/WangCZ25","title":"Uncertain Object Representation for Image-Based 3D Object Perception.","year":2025,"yearOfEvent":null,"venue":"IEEE Trans. Pattern Anal. Mach. Intell.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1109/TPAMI.2025.3568120"],"source":"https://dblp.org/rec/journals/pami/WangCZ25","documentPage":"https://doi.org/10.1109/TPAMI.2025.3568120","type":"Article","doi":"https://doi.org/10.1109/TPAMI.2025.3568120","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/pami/WangCZ25","documentUrl":"https://doi.org/10.1109/TPAMI.2025.3568120"},{"key":"journals/pami/WangFWSWZZ25","title":"Bootstrap Masked Visual Modeling via Hard Patch Mining.","year":2025,"yearOfEvent":null,"venue":"IEEE Trans. Pattern Anal. Mach. Intell.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1109/TPAMI.2025.3557001"],"source":"https://dblp.org/rec/journals/pami/WangFWSWZZ25","documentPage":"https://doi.org/10.1109/TPAMI.2025.3557001","type":"Article","doi":"https://doi.org/10.1109/TPAMI.2025.3557001","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/pami/WangFWSWZZ25","documentUrl":"https://doi.org/10.1109/TPAMI.2025.3557001"},{"key":"journals/tnn/HaoGZ25","title":"VAG: A Uniform Model for Cross-Modal Visual-Audio Mutual Generation.","year":2025,"yearOfEvent":null,"venue":"IEEE Trans. Neural Networks Learn. Syst.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1109/TNNLS.2022.3161314"],"source":"https://dblp.org/rec/journals/tnn/HaoGZ25","documentPage":"https://doi.org/10.1109/TNNLS.2022.3161314","type":"Article","doi":"https://doi.org/10.1109/TNNLS.2022.3161314","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/tnn/HaoGZ25","documentUrl":"https://doi.org/10.1109/TNNLS.2022.3161314"}],"preprints":[{"key":"journals/corr/abs-2501-08295","title":"LayerAnimate: Layer-specific Control for Animation.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2501.08295"],"source":"https://dblp.org/rec/journals/corr/abs-2501-08295","documentPage":"https://doi.org/10.48550/ARXIV.2501.08295","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2501.08295","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2501-08295","documentUrl":"https://doi.org/10.48550/ARXIV.2501.08295","arxivId":"2501.08295","arxivUrl":"https://arxiv.org/abs/2501.08295"},{"key":"journals/corr/abs-2501-09368","title":"Aligning Instruction Tuning with Pre-training.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2501.09368"],"source":"https://dblp.org/rec/journals/corr/abs-2501-09368","documentPage":"https://doi.org/10.48550/ARXIV.2501.09368","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2501.09368","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2501-09368","documentUrl":"https://doi.org/10.48550/ARXIV.2501.09368","arxivId":"2501.09368","arxivUrl":"https://arxiv.org/abs/2501.09368"},{"key":"journals/corr/abs-2501-09705","title":"Practical Continual Forgetting for Pre-trained Vision Models.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2501.09705"],"source":"https://dblp.org/rec/journals/corr/abs-2501-09705","documentPage":"https://doi.org/10.48550/ARXIV.2501.09705","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2501.09705","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2501-09705","documentUrl":"https://doi.org/10.48550/ARXIV.2501.09705","arxivId":"2501.09705","arxivUrl":"https://arxiv.org/abs/2501.09705"},{"key":"journals/corr/abs-2502-01977","title":"AutoGUI: Scaling GUI Grounding with Automatic Functionality Annotations from LLMs.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2502.01977"],"source":"https://dblp.org/rec/journals/corr/abs-2502-01977","documentPage":"https://doi.org/10.48550/ARXIV.2502.01977","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2502.01977","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2502-01977","documentUrl":"https://doi.org/10.48550/ARXIV.2502.01977","arxivId":"2502.01977","arxivUrl":"https://arxiv.org/abs/2502.01977"},{"key":"journals/corr/abs-2502-06635","title":"Steel-LLM:From Scratch to Open Source - A Personal Journey in Building a Chinese-Centric LLM.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2502.06635"],"source":"https://dblp.org/rec/journals/corr/abs-2502-06635","documentPage":"https://doi.org/10.48550/ARXIV.2502.06635","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2502.06635","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2502-06635","documentUrl":"https://doi.org/10.48550/ARXIV.2502.06635","arxivId":"2502.06635","arxivUrl":"https://arxiv.org/abs/2502.06635"},{"key":"journals/corr/abs-2502-08234","title":"Learning Human Skill Generators at Key-Step Levels.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2502.08234"],"source":"https://dblp.org/rec/journals/corr/abs-2502-08234","documentPage":"https://doi.org/10.48550/ARXIV.2502.08234","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2502.08234","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2502-08234","documentUrl":"https://doi.org/10.48550/ARXIV.2502.08234","arxivId":"2502.08234","arxivUrl":"https://arxiv.org/abs/2502.08234"},{"key":"journals/corr/abs-2502-09963","title":"Generating on Generated: An Approach Towards Self-Evolving Diffusion Models.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2502.09963"],"source":"https://dblp.org/rec/journals/corr/abs-2502-09963","documentPage":"https://doi.org/10.48550/ARXIV.2502.09963","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2502.09963","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2502-09963","documentUrl":"https://doi.org/10.48550/ARXIV.2502.09963","arxivId":"2502.09963","arxivUrl":"https://arxiv.org/abs/2502.09963"},{"key":"journals/corr/abs-2502-16614","title":"CodeCriticBench: A Holistic Code Critique Benchmark for Large Language Models.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2502.16614"],"source":"https://dblp.org/rec/journals/corr/abs-2502-16614","documentPage":"https://doi.org/10.48550/ARXIV.2502.16614","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2502.16614","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2502-16614","documentUrl":"https://doi.org/10.48550/ARXIV.2502.16614","arxivId":"2502.16614","arxivUrl":"https://arxiv.org/abs/2502.16614"},{"key":"journals/corr/abs-2502-19361","title":"Can Large Language Models Detect Errors in Long Chain-of-Thought Reasoning?","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2502.19361"],"source":"https://dblp.org/rec/journals/corr/abs-2502-19361","documentPage":"https://doi.org/10.48550/ARXIV.2502.19361","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2502.19361","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2502-19361","documentUrl":"https://doi.org/10.48550/ARXIV.2502.19361","arxivId":"2502.19361","arxivUrl":"https://arxiv.org/abs/2502.19361"},{"key":"journals/corr/abs-2502-21093","title":"FlexDrive: Toward Trajectory Flexibility in Driving Scene Reconstruction and Rendering.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2502.21093"],"source":"https://dblp.org/rec/journals/corr/abs-2502-21093","documentPage":"https://doi.org/10.48550/ARXIV.2502.21093","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2502.21093","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2502-21093","documentUrl":"https://doi.org/10.48550/ARXIV.2502.21093","arxivId":"2502.21093","arxivUrl":"https://arxiv.org/abs/2502.21093"},{"key":"journals/corr/abs-2503-08638","title":"YuE: Scaling Open Foundation Models for Long-Form Music Generation.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2503.08638"],"source":"https://dblp.org/rec/journals/corr/abs-2503-08638","documentPage":"https://doi.org/10.48550/ARXIV.2503.08638","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2503.08638","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-08638","documentUrl":"https://doi.org/10.48550/ARXIV.2503.08638","arxivId":"2503.08638","arxivUrl":"https://arxiv.org/abs/2503.08638"},{"key":"journals/corr/abs-2503-11028","title":"EmoDiffusion: Enhancing Emotional 3D Facial Animation with Latent Diffusion Models.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2503.11028"],"source":"https://dblp.org/rec/journals/corr/abs-2503-11028","documentPage":"https://doi.org/10.48550/ARXIV.2503.11028","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2503.11028","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-11028","documentUrl":"https://doi.org/10.48550/ARXIV.2503.11028","arxivId":"2503.11028","arxivUrl":"https://arxiv.org/abs/2503.11028"},{"key":"journals/corr/abs-2503-15990","title":"ECKGBench: Benchmarking Large Language Models in E-commerce Leveraging Knowledge Graph.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2503.15990"],"source":"https://dblp.org/rec/journals/corr/abs-2503-15990","documentPage":"https://doi.org/10.48550/ARXIV.2503.15990","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2503.15990","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-15990","documentUrl":"https://doi.org/10.48550/ARXIV.2503.15990","arxivId":"2503.15990","arxivUrl":"https://arxiv.org/abs/2503.15990"},{"key":"journals/corr/abs-2503-17407","title":"A Comprehensive Survey on Long Context Language Modeling.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2503.17407"],"source":"https://dblp.org/rec/journals/corr/abs-2503-17407","documentPage":"https://doi.org/10.48550/ARXIV.2503.17407","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2503.17407","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-17407","documentUrl":"https://doi.org/10.48550/ARXIV.2503.17407","arxivId":"2503.17407","arxivUrl":"https://arxiv.org/abs/2503.17407"},{"key":"journals/corr/abs-2503-18511","title":"Global Convergence of Continual Learning on Non-IID Data.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2503.18511"],"source":"https://dblp.org/rec/journals/corr/abs-2503-18511","documentPage":"https://doi.org/10.48550/ARXIV.2503.18511","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2503.18511","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-18511","documentUrl":"https://doi.org/10.48550/ARXIV.2503.18511","arxivId":"2503.18511","arxivUrl":"https://arxiv.org/abs/2503.18511"},{"key":"journals/corr/abs-2504-01901","title":"Ross3D: Reconstructive Visual Instruction Tuning with 3D-Awareness.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2504.01901"],"source":"https://dblp.org/rec/journals/corr/abs-2504-01901","documentPage":"https://doi.org/10.48550/ARXIV.2504.01901","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2504.01901","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2504-01901","documentUrl":"https://doi.org/10.48550/ARXIV.2504.01901","arxivId":"2504.01901","arxivUrl":"https://arxiv.org/abs/2504.01901"},{"key":"journals/corr/abs-2504-01941","title":"End-to-End Driving with Online Trajectory Evaluation via BEV World Model.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2504.01941"],"source":"https://dblp.org/rec/journals/corr/abs-2504-01941","documentPage":"https://doi.org/10.48550/ARXIV.2504.01941","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2504.01941","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2504-01941","documentUrl":"https://doi.org/10.48550/ARXIV.2504.01941","arxivId":"2504.01941","arxivUrl":"https://arxiv.org/abs/2504.01941"},{"key":"journals/corr/abs-2504-14545","title":"TrustLoRA: Low-Rank Adaptation for Failure Detection under Out-of-distribution Data.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2504.14545"],"source":"https://dblp.org/rec/journals/corr/abs-2504-14545","documentPage":"https://doi.org/10.48550/ARXIV.2504.14545","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2504.14545","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2504-14545","documentUrl":"https://doi.org/10.48550/ARXIV.2504.14545","arxivId":"2504.14545","arxivUrl":"https://arxiv.org/abs/2504.14545"},{"key":"journals/corr/abs-2504-14727","title":"Semi-parametric Memory Consolidation: Towards Brain-like Deep Continual Learning.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2504.14727"],"source":"https://dblp.org/rec/journals/corr/abs-2504-14727","documentPage":"https://doi.org/10.48550/ARXIV.2504.14727","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2504.14727","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2504-14727","documentUrl":"https://doi.org/10.48550/ARXIV.2504.14727","arxivId":"2504.14727","arxivUrl":"https://arxiv.org/abs/2504.14727"},{"key":"journals/corr/abs-2505-12808","title":"Decentralized Arena: Towards Democratic and Scalable Automatic Evaluation of Language Models.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2505.12808"],"source":"https://dblp.org/rec/journals/corr/abs-2505-12808","documentPage":"https://doi.org/10.48550/ARXIV.2505.12808","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2505.12808","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-12808","documentUrl":"https://doi.org/10.48550/ARXIV.2505.12808","arxivId":"2505.12808","arxivUrl":"https://arxiv.org/abs/2505.12808"},{"key":"journals/corr/abs-2505-14552","title":"KORGym: A Dynamic Game Platform for LLM Reasoning Evaluation.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2505.14552"],"source":"https://dblp.org/rec/journals/corr/abs-2505-14552","documentPage":"https://doi.org/10.48550/ARXIV.2505.14552","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2505.14552","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-14552","documentUrl":"https://doi.org/10.48550/ARXIV.2505.14552","arxivId":"2505.14552","arxivUrl":"https://arxiv.org/abs/2505.14552"},{"key":"journals/corr/abs-2506-05453","title":"MLLM-CL: Continual Learning for Multimodal Large Language Models.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2506.05453"],"source":"https://dblp.org/rec/journals/corr/abs-2506-05453","documentPage":"https://doi.org/10.48550/ARXIV.2506.05453","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2506.05453","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-05453","documentUrl":"https://doi.org/10.48550/ARXIV.2506.05453","arxivId":"2506.05453","arxivUrl":"https://arxiv.org/abs/2506.05453"},{"key":"journals/corr/abs-2506-18904","title":"TC-Light: Temporally Coherent Generative Rendering for Realistic World Transfer.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2506.18904"],"source":"https://dblp.org/rec/journals/corr/abs-2506-18904","documentPage":"https://doi.org/10.48550/ARXIV.2506.18904","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2506.18904","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-18904","documentUrl":"https://doi.org/10.48550/ARXIV.2506.18904","arxivId":"2506.18904","arxivUrl":"https://arxiv.org/abs/2506.18904"},{"key":"journals/corr/abs-2506-19850","title":"Unified Vision-Language-Action Model.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2506.19850"],"source":"https://dblp.org/rec/journals/corr/abs-2506-19850","documentPage":"https://doi.org/10.48550/ARXIV.2506.19850","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2506.19850","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-19850","documentUrl":"https://doi.org/10.48550/ARXIV.2506.19850","arxivId":"2506.19850","arxivUrl":"https://arxiv.org/abs/2506.19850"},{"key":"journals/corr/abs-2506-22291","title":"RoomCraft: Controllable and Complete 3D Indoor Scene Generation.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2506.22291"],"source":"https://dblp.org/rec/journals/corr/abs-2506-22291","documentPage":"https://doi.org/10.48550/ARXIV.2506.22291","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2506.22291","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-22291","documentUrl":"https://doi.org/10.48550/ARXIV.2506.22291","arxivId":"2506.22291","arxivUrl":"https://arxiv.org/abs/2506.22291"},{"key":"journals/corr/abs-2506-23090","title":"Multi-task Offline Reinforcement Learning for Online Advertising in Recommender Systems.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2506.23090"],"source":"https://dblp.org/rec/journals/corr/abs-2506-23090","documentPage":"https://doi.org/10.48550/ARXIV.2506.23090","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2506.23090","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-23090","documentUrl":"https://doi.org/10.48550/ARXIV.2506.23090","arxivId":"2506.23090","arxivUrl":"https://arxiv.org/abs/2506.23090"},{"key":"journals/corr/abs-2507-02747","title":"DexVLG: Dexterous Vision-Language-Grasp Model at Scale.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2507.02747"],"source":"https://dblp.org/rec/journals/corr/abs-2507-02747","documentPage":"https://doi.org/10.48550/ARXIV.2507.02747","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2507.02747","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2507-02747","documentUrl":"https://doi.org/10.48550/ARXIV.2507.02747","arxivId":"2507.02747","arxivUrl":"https://arxiv.org/abs/2507.02747"},{"key":"journals/corr/abs-2507-06181","title":"CriticLean: Critic-Guided Reinforcement Learning for Mathematical Formalization.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2507.06181"],"source":"https://dblp.org/rec/journals/corr/abs-2507-06181","documentPage":"https://doi.org/10.48550/ARXIV.2507.06181","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2507.06181","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2507-06181","documentUrl":"https://doi.org/10.48550/ARXIV.2507.06181","arxivId":"2507.06181","arxivUrl":"https://arxiv.org/abs/2507.06181"},{"key":"journals/corr/abs-2507-06203","title":"A Survey on Latent Reasoning.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2507.06203"],"source":"https://dblp.org/rec/journals/corr/abs-2507-06203","documentPage":"https://doi.org/10.48550/ARXIV.2507.06203","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2507.06203","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2507-06203","documentUrl":"https://doi.org/10.48550/ARXIV.2507.06203","arxivId":"2507.06203","arxivUrl":"https://arxiv.org/abs/2507.06203"},{"key":"journals/corr/abs-2507-07999","title":"Traceable Evidence Enhanced Visual Grounded Reasoning: Evaluation and Methodology.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2507.07999"],"source":"https://dblp.org/rec/journals/corr/abs-2507-07999","documentPage":"https://doi.org/10.48550/ARXIV.2507.07999","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2507.07999","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2507-07999","documentUrl":"https://doi.org/10.48550/ARXIV.2507.07999","arxivId":"2507.07999","arxivUrl":"https://arxiv.org/abs/2507.07999"},{"key":"journals/corr/abs-2507-18311","title":"Improving Large Vision-Language Models' Understanding for Field Data.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2507.18311"],"source":"https://dblp.org/rec/journals/corr/abs-2507-18311","documentPage":"https://doi.org/10.48550/ARXIV.2507.18311","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2507.18311","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2507-18311","documentUrl":"https://doi.org/10.48550/ARXIV.2507.18311","arxivId":"2507.18311","arxivUrl":"https://arxiv.org/abs/2507.18311"},{"key":"journals/corr/abs-2508-10881","title":"ToonComposer: Streamlining Cartoon Production with Generative Post-Keyframing.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2508.10881"],"source":"https://dblp.org/rec/journals/corr/abs-2508-10881","documentPage":"https://doi.org/10.48550/ARXIV.2508.10881","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2508.10881","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-10881","documentUrl":"https://doi.org/10.48550/ARXIV.2508.10881","arxivId":"2508.10881","arxivUrl":"https://arxiv.org/abs/2508.10881"},{"key":"journals/corr/abs-2508-13186","title":"MM-BrowseComp: A Comprehensive Benchmark for Multimodal Browsing Agents.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2508.13186"],"source":"https://dblp.org/rec/journals/corr/abs-2508-13186","documentPage":"https://doi.org/10.48550/ARXIV.2508.13186","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2508.13186","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-13186","documentUrl":"https://doi.org/10.48550/ARXIV.2508.13186","arxivId":"2508.13186","arxivUrl":"https://arxiv.org/abs/2508.13186"},{"key":"journals/corr/abs-2508-14507","title":"DeepTelecom: A Digital-Twin Deep Learning Dataset for Channel and MIMO Applications.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2508.14507"],"source":"https://dblp.org/rec/journals/corr/abs-2508-14507","documentPage":"https://doi.org/10.48550/ARXIV.2508.14507","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2508.14507","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-14507","documentUrl":"https://doi.org/10.48550/ARXIV.2508.14507","arxivId":"2508.14507","arxivUrl":"https://arxiv.org/abs/2508.14507"},{"key":"journals/corr/abs-2508-17832","title":"HLG: Comprehensive 3D Room Construction via Hierarchical Layout Generation.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2508.17832"],"source":"https://dblp.org/rec/journals/corr/abs-2508-17832","documentPage":"https://doi.org/10.48550/ARXIV.2508.17832","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2508.17832","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-17832","documentUrl":"https://doi.org/10.48550/ARXIV.2508.17832","arxivId":"2508.17832","arxivUrl":"https://arxiv.org/abs/2508.17832"},{"key":"journals/corr/abs-2509-17328","title":"UIPro: Unleashing Superior Interaction Capability For GUI Agents.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2509.17328"],"source":"https://dblp.org/rec/journals/corr/abs-2509-17328","documentPage":"https://doi.org/10.48550/ARXIV.2509.17328","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2509.17328","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-17328","documentUrl":"https://doi.org/10.48550/ARXIV.2509.17328","arxivId":"2509.17328","arxivUrl":"https://arxiv.org/abs/2509.17328"},{"key":"journals/corr/abs-2509-17940","title":"DriveDPO: Policy Learning via Safety DPO For End-to-End Autonomous Driving.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2509.17940"],"source":"https://dblp.org/rec/journals/corr/abs-2509-17940","documentPage":"https://doi.org/10.48550/ARXIV.2509.17940","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2509.17940","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-17940","documentUrl":"https://doi.org/10.48550/ARXIV.2509.17940","arxivId":"2509.17940","arxivUrl":"https://arxiv.org/abs/2509.17940"},{"key":"journals/corr/abs-2509-23852","title":"SIG-Chat: Spatial Intent-Guided Conversational Gesture Generation Involving How, When and Where.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2509.23852"],"source":"https://dblp.org/rec/journals/corr/abs-2509-23852","documentPage":"https://doi.org/10.48550/ARXIV.2509.23852","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2509.23852","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-23852","documentUrl":"https://doi.org/10.48550/ARXIV.2509.23852","arxivId":"2509.23852","arxivUrl":"https://arxiv.org/abs/2509.23852"},{"key":"journals/corr/abs-2509-23967","title":"HiPO: Hybrid Policy Optimization for Dynamic Reasoning in LLMs.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2509.23967"],"source":"https://dblp.org/rec/journals/corr/abs-2509-23967","documentPage":"https://doi.org/10.48550/ARXIV.2509.23967","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2509.23967","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-23967","documentUrl":"https://doi.org/10.48550/ARXIV.2509.23967","arxivId":"2509.23967","arxivUrl":"https://arxiv.org/abs/2509.23967"},{"key":"journals/corr/abs-2509-25191","title":"VGGT-X: When VGGT Meets Dense Novel View Synthesis.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2509.25191"],"source":"https://dblp.org/rec/journals/corr/abs-2509-25191","documentPage":"https://doi.org/10.48550/ARXIV.2509.25191","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2509.25191","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-25191","documentUrl":"https://doi.org/10.48550/ARXIV.2509.25191","arxivId":"2509.25191","arxivUrl":"https://arxiv.org/abs/2509.25191"},{"key":"journals/corr/abs-2510-06207","title":"EmbodiedCoder: Parameterized Embodied Mobile Manipulation via Modern Coding Model.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2510.06207"],"source":"https://dblp.org/rec/journals/corr/abs-2510-06207","documentPage":"https://doi.org/10.48550/ARXIV.2510.06207","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2510.06207","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-06207","documentUrl":"https://doi.org/10.48550/ARXIV.2510.06207","arxivId":"2510.06207","arxivUrl":"https://arxiv.org/abs/2510.06207"},{"key":"journals/corr/abs-2510-10689","title":"OmniVideoBench: Towards Audio-Visual Understanding Evaluation for Omni MLLMs.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2510.10689"],"source":"https://dblp.org/rec/journals/corr/abs-2510-10689","documentPage":"https://doi.org/10.48550/ARXIV.2510.10689","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2510.10689","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-10689","documentUrl":"https://doi.org/10.48550/ARXIV.2510.10689","arxivId":"2510.10689","arxivUrl":"https://arxiv.org/abs/2510.10689"},{"key":"journals/corr/abs-2510-12679","title":"MCOP: Multi-UAV Collaborative Occupancy Prediction.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2510.12679"],"source":"https://dblp.org/rec/journals/corr/abs-2510-12679","documentPage":"https://doi.org/10.48550/ARXIV.2510.12679","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2510.12679","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-12679","documentUrl":"https://doi.org/10.48550/ARXIV.2510.12679","arxivId":"2510.12679","arxivUrl":"https://arxiv.org/abs/2510.12679"},{"key":"journals/corr/abs-2510-12796","title":"DriveVLA-W0: World Models Amplify Data Scaling Law in Autonomous Driving.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2510.12796"],"source":"https://dblp.org/rec/journals/corr/abs-2510-12796","documentPage":"https://doi.org/10.48550/ARXIV.2510.12796","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2510.12796","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-12796","documentUrl":"https://doi.org/10.48550/ARXIV.2510.12796","arxivId":"2510.12796","arxivUrl":"https://arxiv.org/abs/2510.12796"},{"key":"journals/corr/abs-2510-17095","title":"GSPlane: Concise and Accurate Planar Reconstruction via Structured Representation.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2510.17095"],"source":"https://dblp.org/rec/journals/corr/abs-2510-17095","documentPage":"https://doi.org/10.48550/ARXIV.2510.17095","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2510.17095","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-17095","documentUrl":"https://doi.org/10.48550/ARXIV.2510.17095","arxivId":"2510.17095","arxivUrl":"https://arxiv.org/abs/2510.17095"},{"key":"journals/corr/abs-2510-18250","title":"ssToken: Self-modulated and Semantic-aware Token Selection for LLM Fine-tuning.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2510.18250"],"source":"https://dblp.org/rec/journals/corr/abs-2510-18250","documentPage":"https://doi.org/10.48550/ARXIV.2510.18250","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2510.18250","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-18250","documentUrl":"https://doi.org/10.48550/ARXIV.2510.18250","arxivId":"2510.18250","arxivUrl":"https://arxiv.org/abs/2510.18250"},{"key":"journals/corr/abs-2510-18726","title":"IF-VidCap: Can Video Caption Models Follow Instructions?","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2510.18726"],"source":"https://dblp.org/rec/journals/corr/abs-2510-18726","documentPage":"https://doi.org/10.48550/ARXIV.2510.18726","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2510.18726","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-18726","documentUrl":"https://doi.org/10.48550/ARXIV.2510.18726","arxivId":"2510.18726","arxivUrl":"https://arxiv.org/abs/2510.18726"},{"key":"journals/corr/abs-2510-18876","title":"Grasp Any Region: Towards Precise, Contextual Pixel Understanding for Multimodal LLMs.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2510.18876"],"source":"https://dblp.org/rec/journals/corr/abs-2510-18876","documentPage":"https://doi.org/10.48550/ARXIV.2510.18876","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2510.18876","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-18876","documentUrl":"https://doi.org/10.48550/ARXIV.2510.18876","arxivId":"2510.18876","arxivUrl":"https://arxiv.org/abs/2510.18876"},{"key":"journals/corr/abs-2510-24106","title":"UniField: Joint Multi-Domain Training for Universal Surface Pressure Modeling.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2510.24106"],"source":"https://dblp.org/rec/journals/corr/abs-2510-24106","documentPage":"https://doi.org/10.48550/ARXIV.2510.24106","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2510.24106","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-24106","documentUrl":"https://doi.org/10.48550/ARXIV.2510.24106","arxivId":"2510.24106","arxivUrl":"https://arxiv.org/abs/2510.24106"},{"key":"journals/corr/abs-2510-24717","title":"Uniform Discrete Diffusion with Metric Path for Video Generation.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2510.24717"],"source":"https://dblp.org/rec/journals/corr/abs-2510-24717","documentPage":"https://doi.org/10.48550/ARXIV.2510.24717","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2510.24717","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-24717","documentUrl":"https://doi.org/10.48550/ARXIV.2510.24717","arxivId":"2510.24717","arxivUrl":"https://arxiv.org/abs/2510.24717"},{"key":"journals/corr/abs-2511-05459","title":"SWE-Compass: Towards Unified Evaluation of Agentic Coding Abilities for Large Language Models.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2511.05459"],"source":"https://dblp.org/rec/journals/corr/abs-2511-05459","documentPage":"https://doi.org/10.48550/ARXIV.2511.05459","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2511.05459","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2511-05459","documentUrl":"https://doi.org/10.48550/ARXIV.2511.05459","arxivId":"2511.05459","arxivUrl":"https://arxiv.org/abs/2511.05459"},{"key":"journals/corr/abs-2511-07250","title":"MVU-Eval: Towards Multi-Video Understanding Evaluation for Multimodal LLMs.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2511.07250"],"source":"https://dblp.org/rec/journals/corr/abs-2511-07250","documentPage":"https://doi.org/10.48550/ARXIV.2511.07250","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2511.07250","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2511-07250","documentUrl":"https://doi.org/10.48550/ARXIV.2511.07250","arxivId":"2511.07250","arxivUrl":"https://arxiv.org/abs/2511.07250"},{"key":"journals/corr/abs-2511-15122","title":"Multi-Aspect Cross-modal Quantization for Generative Recommendation.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2511.15122"],"source":"https://dblp.org/rec/journals/corr/abs-2511-15122","documentPage":"https://doi.org/10.48550/ARXIV.2511.15122","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2511.15122","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2511-15122","documentUrl":"https://doi.org/10.48550/ARXIV.2511.15122","arxivId":"2511.15122","arxivUrl":"https://arxiv.org/abs/2511.15122"},{"key":"journals/corr/abs-2511-18538","title":"From Code Foundation Models to Agents and Applications: A Comprehensive Survey and Practical Guide to Code Intelligence.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2511.18538"],"source":"https://dblp.org/rec/journals/corr/abs-2511-18538","documentPage":"https://doi.org/10.48550/ARXIV.2511.18538","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2511.18538","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2511-18538","documentUrl":"https://doi.org/10.48550/ARXIV.2511.18538","arxivId":"2511.18538","arxivUrl":"https://arxiv.org/abs/2511.18538"},{"key":"journals/corr/abs-2511-21161","title":"MarketGen: A Scalable Simulation Platform with Auto-Generated Embodied Supermarket Environments.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2511.21161"],"source":"https://dblp.org/rec/journals/corr/abs-2511-21161","documentPage":"https://doi.org/10.48550/ARXIV.2511.21161","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2511.21161","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2511-21161","documentUrl":"https://doi.org/10.48550/ARXIV.2511.21161","arxivId":"2511.21161","arxivUrl":"https://arxiv.org/abs/2511.21161"},{"key":"journals/corr/abs-2512-04501","title":"One-Step Generative Channel Estimation via Average Velocity Field.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2512.04501"],"source":"https://dblp.org/rec/journals/corr/abs-2512-04501","documentPage":"https://doi.org/10.48550/ARXIV.2512.04501","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2512.04501","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-04501","documentUrl":"https://doi.org/10.48550/ARXIV.2512.04501","arxivId":"2512.04501","arxivUrl":"https://arxiv.org/abs/2512.04501"},{"key":"journals/corr/abs-2512-12730","title":"NL2Repo-Bench: Towards Long-Horizon Repository Generation Evaluation of Coding Agents.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2512.12730"],"source":"https://dblp.org/rec/journals/corr/abs-2512-12730","documentPage":"https://doi.org/10.48550/ARXIV.2512.12730","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2512.12730","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-12730","documentUrl":"https://doi.org/10.48550/ARXIV.2512.12730","arxivId":"2512.12730","arxivUrl":"https://arxiv.org/abs/2512.12730"},{"key":"journals/corr/abs-2512-15649","title":"VTCBench: Can Vision-Language Models Understand Long Context with Vision-Text Compression?","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2512.15649"],"source":"https://dblp.org/rec/journals/corr/abs-2512-15649","documentPage":"https://doi.org/10.48550/ARXIV.2512.15649","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2512.15649","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-15649","documentUrl":"https://doi.org/10.48550/ARXIV.2512.15649","arxivId":"2512.15649","arxivUrl":"https://arxiv.org/abs/2512.15649"},{"key":"journals/corr/abs-2512-21094","title":"T2AV-Compass: Towards Unified Evaluation for Text-to-Audio-Video Generation.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2512.21094"],"source":"https://dblp.org/rec/journals/corr/abs-2512-21094","documentPage":"https://doi.org/10.48550/ARXIV.2512.21094","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2512.21094","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-21094","documentUrl":"https://doi.org/10.48550/ARXIV.2512.21094","arxivId":"2512.21094","arxivUrl":"https://arxiv.org/abs/2512.21094"},{"key":"journals/corr/abs-2512-23300","title":"AI4Reading: Chinese Audiobook Interpretation System Based on Multi-Agent Collaboration.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2512.23300"],"source":"https://dblp.org/rec/journals/corr/abs-2512-23300","documentPage":"https://doi.org/10.48550/ARXIV.2512.23300","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2512.23300","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-23300","documentUrl":"https://doi.org/10.48550/ARXIV.2512.23300","arxivId":"2512.23300","arxivUrl":"https://arxiv.org/abs/2512.23300"},{"key":"journals/corr/abs-2512-24157","title":"Training Report of TeleChat3-MoE.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2512.24157"],"source":"https://dblp.org/rec/journals/corr/abs-2512-24157","documentPage":"https://doi.org/10.48550/ARXIV.2512.24157","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2512.24157","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-24157","documentUrl":"https://doi.org/10.48550/ARXIV.2512.24157","arxivId":"2512.24157","arxivUrl":"https://arxiv.org/abs/2512.24157"},{"key":"journals/corr/abs-2512-24867","title":"Encyclo-K: Evaluating LLMs with Dynamically Composed Knowledge Statements.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2512.24867"],"source":"https://dblp.org/rec/journals/corr/abs-2512-24867","documentPage":"https://doi.org/10.48550/ARXIV.2512.24867","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2512.24867","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-24867","documentUrl":"https://doi.org/10.48550/ARXIV.2512.24867","arxivId":"2512.24867","arxivUrl":"https://arxiv.org/abs/2512.24867"}],"excludedFormal":[],"excludedOther":[],"excludedHomonyms":[],"unassignedCandidates":[],"retrievedAt":"2026-10-19","querySource":"https://sparql.dblp.org/","method":"DBLP yearOfPublication=2025; Article + Inproceedings; excludes Informal/CoRR and explicit editorial/correction/erratum/preface; unique DBLP record keys within person.","labName":"生物启发的智能计算研究组（BRAVE GROUP）","labUrl":"https://zhaoxiangzhang.net/lab/","labEvidence":"本人网站Lab页以该专名为标题，研究队伍明确列研究员张兆翔；因此采用具体研究组名，而非更大的模式识别实验室。","labSourceUrl":"https://zhaoxiangzhang.net/lab/","affiliationZh":"中科院自动化所","sourceWarning":false,"knownPreprintMinimum2025":null,"excludedMisattributed":[],"displayNotes":"身份已经个人或机构主页核对。2025 年正式记录 50 条（会议 40、期刊 10），所有作者位置均计入，不表示主导或贡献份额；预印本 62 条单列，不加总。","labDisplayNotes":"本人网站的 Lab 页以「生物启发的智能计算研究组（BRAVE GROUP）」为题，并列其为研究员，据此归组；采用这个具体的研究组，而不是更大的模式识别实验室。"},{"index":112,"name":"Hang Zhao","nameZh":"赵行","affiliation":"Tsinghua University","source":"DBLP Knowledge Graph official SPARQL API","profileUrl":"https://dblp.org/pid/31/2950-21","identifier":"31/2950-21","identityEvidence":[{"url":"https://dblp.org/pid/31/2950-21","evidence":"DBLP curated profile affiliations: Massachusetts Institute of Technology (MIT), Computer Science & Artificial Intelligence Laboratory (CSAIL), Cambridge, MA, USA; Shanghai Qi Zhi Institute, Shanghai, China; Tsinghua University, Institute for Interdisciplinary Information Sciences (IIIS), MARS Lab, Beijing, China; Waymo LLC, Mountain View, CA, USA."},{"url":"https://dblp.org/pid/31/2950-21","evidence":"DBLP curated profile homepages: https://hangzhaomit.github.io/; https://iiis.tsinghua.edu.cn/en/People/Faculty/ZhaoHang.htm."}],"count2025":21,"conference2025":19,"journal2025":2,"preprint2025":29,"status":"verified","notes":"Counts are DBLP indexed coauthored records, not first-author counts, laboratory totals, unique scientific discoveries, or quality assessments. DBLP yearOfPublication=2025; yearOfEvent retained and can differ. Conference workshops are included. Preprints are separate and may overlap formal versions.","papers":[{"key":"conf/eccv/YeJXLZ24","title":"CVT-Occ: Cost Volume Temporal Fusion for 3D Occupancy Prediction.","year":2025,"yearOfEvent":2024,"venue":"ECCV (73)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1007/978-3-031-73464-9_23"],"source":"https://dblp.org/rec/conf/eccv/YeJXLZ24","documentPage":"https://doi.org/10.1007/978-3-031-73464-9_23","type":"Inproceedings","doi":"https://doi.org/10.1007/978-3-031-73464-9_23","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/eccv/YeJXLZ24","documentUrl":"https://doi.org/10.1007/978-3-031-73464-9_23"},{"key":"conf/iccv/ChenQYLZ25","title":"LONG3R: Long Sequence Streaming 3D Reconstruction.","year":2025,"yearOfEvent":2025,"venue":"ICCV","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/ICCV51701.2025.00501"],"source":"https://dblp.org/rec/conf/iccv/ChenQYLZ25","documentPage":"https://doi.org/10.1109/ICCV51701.2025.00501","type":"Inproceedings","doi":"https://doi.org/10.1109/ICCV51701.2025.00501","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/ChenQYLZ25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.00501"},{"key":"conf/iccv/YeQZGZZZ25","title":"GS-Occ3D: Scaling Vision-Only Occupancy Reconstruction with Gaussian Splatting.","year":2025,"yearOfEvent":2025,"venue":"ICCV","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/ICCV51701.2025.02405"],"source":"https://dblp.org/rec/conf/iccv/YeQZGZZZ25","documentPage":"https://doi.org/10.1109/ICCV51701.2025.02405","type":"Inproceedings","doi":"https://doi.org/10.1109/ICCV51701.2025.02405","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/YeQZGZZZ25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.02405"},{"key":"conf/icra/ChenLYJLZ25","title":"TrackOcc: Camera-Based 4D Panoptic Occupancy Tracking.","year":2025,"yearOfEvent":2025,"venue":"ICRA","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/ICRA55743.2025.11128437"],"source":"https://dblp.org/rec/conf/icra/ChenLYJLZ25","documentPage":"https://doi.org/10.1109/ICRA55743.2025.11128437","type":"Inproceedings","doi":"https://doi.org/10.1109/ICRA55743.2025.11128437","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/icra/ChenLYJLZ25","documentUrl":"https://doi.org/10.1109/ICRA55743.2025.11128437"},{"key":"conf/icra/SunWZNWXZJLZ25","title":"Generalizing Motion Planners with Mixture of Experts for Autonomous Driving.","year":2025,"yearOfEvent":2025,"venue":"ICRA","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/ICRA55743.2025.11127274"],"source":"https://dblp.org/rec/conf/icra/SunWZNWXZJLZ25","documentPage":"https://doi.org/10.1109/ICRA55743.2025.11127274","type":"Inproceedings","doi":"https://doi.org/10.1109/ICRA55743.2025.11127274","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/icra/SunWZNWXZJLZ25","documentUrl":"https://doi.org/10.1109/ICRA55743.2025.11127274"},{"key":"conf/icra/WangLYMLYZZ25","title":"Diffusion-Based Generative Models for 3D Occupancy Prediction in Autonomous Driving.","year":2025,"yearOfEvent":2025,"venue":"ICRA","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/ICRA55743.2025.11128716"],"source":"https://dblp.org/rec/conf/icra/WangLYMLYZZ25","documentPage":"https://doi.org/10.1109/ICRA55743.2025.11128716","type":"Inproceedings","doi":"https://doi.org/10.1109/ICRA55743.2025.11128716","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/icra/WangLYMLYZZ25","documentUrl":"https://doi.org/10.1109/ICRA55743.2025.11128716"},{"key":"conf/icra/ZhangLZCLQWZWZZ25","title":"Chameleon: Fast-Slow Neuro-Symbolic Lane Topology Extraction.","year":2025,"yearOfEvent":2025,"venue":"ICRA","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/ICRA55743.2025.11127684"],"source":"https://dblp.org/rec/conf/icra/ZhangLZCLQWZWZZ25","documentPage":"https://doi.org/10.1109/ICRA55743.2025.11127684","type":"Inproceedings","doi":"https://doi.org/10.1109/ICRA55743.2025.11127684","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/icra/ZhangLZCLQWZWZZ25","documentUrl":"https://doi.org/10.1109/ICRA55743.2025.11127684"},{"key":"conf/icra/ZhuHMZ25","title":"Robust Robot Walker: Learning Agile Locomotion over Tiny Traps.","year":2025,"yearOfEvent":2025,"venue":"ICRA","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/ICRA55743.2025.11128309"],"source":"https://dblp.org/rec/conf/icra/ZhuHMZ25","documentPage":"https://doi.org/10.1109/ICRA55743.2025.11128309","type":"Inproceedings","doi":"https://doi.org/10.1109/ICRA55743.2025.11128309","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/icra/ZhuHMZ25","documentUrl":"https://doi.org/10.1109/ICRA55743.2025.11128309"},{"key":"conf/icra/ZhuLMLXZ25","title":"SARO: Space-Aware Robot System for Terrain Crossing via Vision-Language Model.","year":2025,"yearOfEvent":2025,"venue":"ICRA","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/ICRA55743.2025.11128428"],"source":"https://dblp.org/rec/conf/icra/ZhuLMLXZ25","documentPage":"https://doi.org/10.1109/ICRA55743.2025.11128428","type":"Inproceedings","doi":"https://doi.org/10.1109/ICRA55743.2025.11128428","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/icra/ZhuLMLXZ25","documentUrl":"https://doi.org/10.1109/ICRA55743.2025.11128428"},{"key":"conf/iros/DuanZZS25","title":"Playful DoggyBot: Learning Agile and Precise Quadrupedal Locomotion.","year":2025,"yearOfEvent":2025,"venue":"IROS","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/IROS60139.2025.11245880"],"source":"https://dblp.org/rec/conf/iros/DuanZZS25","documentPage":"https://doi.org/10.1109/IROS60139.2025.11245880","type":"Inproceedings","doi":"https://doi.org/10.1109/IROS60139.2025.11245880","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iros/DuanZZS25","documentUrl":"https://doi.org/10.1109/IROS60139.2025.11245880"},{"key":"conf/iros/HuangZDZ25","title":"MoE-Loco: Mixture of Experts for Multitask Locomotion.","year":2025,"yearOfEvent":2025,"venue":"IROS","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/IROS60139.2025.11246585"],"source":"https://dblp.org/rec/conf/iros/HuangZDZ25","documentPage":"https://doi.org/10.1109/IROS60139.2025.11246585","type":"Inproceedings","doi":"https://doi.org/10.1109/IROS60139.2025.11246585","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iros/HuangZDZ25","documentUrl":"https://doi.org/10.1109/IROS60139.2025.11246585"},{"key":"conf/iros/LiZQLLWLZGLCZZ25","title":"Reusing Attention for One-stage Lane Topology Understanding.","year":2025,"yearOfEvent":2025,"venue":"IROS","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/IROS60139.2025.11246905"],"source":"https://dblp.org/rec/conf/iros/LiZQLLWLZGLCZZ25","documentPage":"https://doi.org/10.1109/IROS60139.2025.11246905","type":"Inproceedings","doi":"https://doi.org/10.1109/IROS60139.2025.11246905","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iros/LiZQLLWLZGLCZZ25","documentUrl":"https://doi.org/10.1109/IROS60139.2025.11246905"},{"key":"conf/iros/XuZLYCGZSPMJSYZTLYZ25","title":"CRUISE: Cooperative Reconstruction and Editing in V2X Scenarios using Gaussian Splatting.","year":2025,"yearOfEvent":2025,"venue":"IROS","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/IROS60139.2025.11246201"],"source":"https://dblp.org/rec/conf/iros/XuZLYCGZSPMJSYZTLYZ25","documentPage":"https://doi.org/10.1109/IROS60139.2025.11246201","type":"Inproceedings","doi":"https://doi.org/10.1109/IROS60139.2025.11246201","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iros/XuZLYCGZSPMJSYZTLYZ25","documentUrl":"https://doi.org/10.1109/IROS60139.2025.11246201"},{"key":"conf/iros/YuanJZSZG25","title":"RoboEngine: Plug-and-Play Robot Data Augmentation with Semantic Robot Segmentation and Background Generation.","year":2025,"yearOfEvent":2025,"venue":"IROS","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/IROS60139.2025.11247097"],"source":"https://dblp.org/rec/conf/iros/YuanJZSZG25","documentPage":"https://doi.org/10.1109/IROS60139.2025.11247097","type":"Inproceedings","doi":"https://doi.org/10.1109/IROS60139.2025.11247097","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iros/YuanJZSZG25","documentUrl":"https://doi.org/10.1109/IROS60139.2025.11247097"},{"key":"conf/iros/ZhangQZZGCGWLLGLZZ25","title":"Delving into Mapping Uncertainty for Mapless Trajectory Prediction.","year":2025,"yearOfEvent":2025,"venue":"IROS","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/IROS60139.2025.11247498"],"source":"https://dblp.org/rec/conf/iros/ZhangQZZGCGWLLGLZZ25","documentPage":"https://doi.org/10.1109/IROS60139.2025.11247498","type":"Inproceedings","doi":"https://doi.org/10.1109/IROS60139.2025.11247498","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iros/ZhangQZZGCGWLLGLZZ25","documentUrl":"https://doi.org/10.1109/IROS60139.2025.11247498"},{"key":"conf/nips/ChiGLLLLYYWLWHS25","title":"Impromptu VLA: Open Weights and Open Data for Driving Vision-Language-Action Models.","year":2025,"yearOfEvent":2025,"venue":"NeurIPS","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/nips/ChiGLLLLYYWLWHS25","documentPage":"http://papers.nips.cc/paper_files/paper/2025/hash/6e4f0c8c6890899e2206585c3cfba4d1-Abstract-Datasets_and_Benchmarks_Track.html","type":"Inproceedings","doi":null,"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/nips/ChiGLLLLYYWLWHS25","documentUrl":"http://papers.nips.cc/paper_files/paper/2025/hash/6e4f0c8c6890899e2206585c3cfba4d1-Abstract-Datasets_and_Benchmarks_Track.html"},{"key":"conf/nips/DongLLZH25","title":"Conditioning Matters: Training Diffusion Policies is Faster Than You Think.","year":2025,"yearOfEvent":2025,"venue":"NeurIPS","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/nips/DongLLZH25","documentPage":"http://papers.nips.cc/paper_files/paper/2025/hash/ad6363efb7af02f7db13d087c7e649bd-Abstract-Conference.html","type":"Inproceedings","doi":null,"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/nips/DongLLZH25","documentUrl":"http://papers.nips.cc/paper_files/paper/2025/hash/ad6363efb7af02f7db13d087c7e649bd-Abstract-Conference.html"},{"key":"conf/nips/JiangZZLSWS25","title":"Rectifying Soft-Label Entangled Bias in Long-Tailed Dataset Distillation.","year":2025,"yearOfEvent":2025,"venue":"NeurIPS","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/nips/JiangZZLSWS25","documentPage":"http://papers.nips.cc/paper_files/paper/2025/hash/c07bc8b520aa87326b015b0da6a70b48-Abstract-Conference.html","type":"Inproceedings","doi":null,"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/nips/JiangZZLSWS25","documentUrl":"http://papers.nips.cc/paper_files/paper/2025/hash/c07bc8b520aa87326b015b0da6a70b48-Abstract-Conference.html"},{"key":"conf/wacv/MaYC0XKWMCRLZZH25","title":"Position: Prospective of Autonomous Driving - Multimodal LLMs, World Models, Embodied Intelligence, AI Alignment, and Mamba.","year":2025,"yearOfEvent":2025,"venue":"WACV (Workshops)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/WACVW65960.2025.00114"],"source":"https://dblp.org/rec/conf/wacv/MaYC0XKWMCRLZZH25","documentPage":"https://doi.org/10.1109/WACVW65960.2025.00114","type":"Inproceedings","doi":"https://doi.org/10.1109/WACVW65960.2025.00114","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/wacv/MaYC0XKWMCRLZZH25","documentUrl":"https://doi.org/10.1109/WACVW65960.2025.00114"},{"key":"journals/ijairr/ZhangYPYMCXZZ25","title":"Morpheus: A Neural-Driven Animatronic Face with Hybrid Actuation and Diverse Emotion Control.","year":2025,"yearOfEvent":null,"venue":"Int. J. Artif. Intell. Robotics Res.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1142/S2972335325500048"],"source":"https://dblp.org/rec/journals/ijairr/ZhangYPYMCXZZ25","documentPage":"https://doi.org/10.1142/S2972335325500048","type":"Article","doi":"https://doi.org/10.1142/S2972335325500048","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/ijairr/ZhangYPYMCXZZ25","documentUrl":"https://doi.org/10.1142/S2972335325500048"},{"key":"journals/ral/ZhuMLYHZ25","title":"VR-Robo: A Real-to-Sim-to-Real Framework for Visual Robot Navigation and Locomotion.","year":2025,"yearOfEvent":null,"venue":"IEEE Robotics Autom. Lett.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1109/LRA.2025.3575648"],"source":"https://dblp.org/rec/journals/ral/ZhuMLYHZ25","documentPage":"https://doi.org/10.1109/LRA.2025.3575648","type":"Article","doi":"https://doi.org/10.1109/LRA.2025.3575648","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/ral/ZhuMLYHZ25","documentUrl":"https://doi.org/10.1109/LRA.2025.3575648"}],"preprints":[{"key":"journals/corr/abs-2502-01465","title":"Embrace Collisions: Humanoid Shadowing for Deployable Contact-Agnostics Motions.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2502.01465"],"source":"https://dblp.org/rec/journals/corr/abs-2502-01465","documentPage":"https://doi.org/10.48550/ARXIV.2502.01465","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2502.01465","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2502-01465","documentUrl":"https://doi.org/10.48550/ARXIV.2502.01465","arxivId":"2502.01465","arxivUrl":"https://arxiv.org/abs/2502.01465"},{"key":"journals/corr/abs-2502-01481","title":"Explaining Context Length Scaling and Bounds for Language Models.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2502.01481"],"source":"https://dblp.org/rec/journals/corr/abs-2502-01481","documentPage":"https://doi.org/10.48550/ARXIV.2502.01481","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2502.01481","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2502-01481","documentUrl":"https://doi.org/10.48550/ARXIV.2502.01481","arxivId":"2502.01481","arxivUrl":"https://arxiv.org/abs/2502.01481"},{"key":"journals/corr/abs-2502-01536","title":"VR-Robo: A Real-to-Sim-to-Real Framework for Visual Robot Navigation and Locomotion.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2502.01536"],"source":"https://dblp.org/rec/journals/corr/abs-2502-01536","documentPage":"https://doi.org/10.48550/ARXIV.2502.01536","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2502.01536","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2502-01536","documentUrl":"https://doi.org/10.48550/ARXIV.2502.01536","arxivId":"2502.01536","arxivUrl":"https://arxiv.org/abs/2502.01536"},{"key":"journals/corr/abs-2503-07485","title":"Chameleon: Fast-slow Neuro-symbolic Lane Topology Extraction.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2503.07485"],"source":"https://dblp.org/rec/journals/corr/abs-2503-07485","documentPage":"https://doi.org/10.48550/ARXIV.2503.07485","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2503.07485","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-07485","documentUrl":"https://doi.org/10.48550/ARXIV.2503.07485","arxivId":"2503.07485","arxivUrl":"https://arxiv.org/abs/2503.07485"},{"key":"journals/corr/abs-2503-08471","title":"TrackOcc: Camera-based 4D Panoptic Occupancy Tracking.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2503.08471"],"source":"https://dblp.org/rec/journals/corr/abs-2503-08471","documentPage":"https://doi.org/10.48550/ARXIV.2503.08471","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2503.08471","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-08471","documentUrl":"https://doi.org/10.48550/ARXIV.2503.08471","arxivId":"2503.08471","arxivUrl":"https://arxiv.org/abs/2503.08471"},{"key":"journals/corr/abs-2503-08564","title":"MoE-Loco: Mixture of Experts for Multitask Locomotion.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2503.08564"],"source":"https://dblp.org/rec/journals/corr/abs-2503-08564","documentPage":"https://doi.org/10.48550/ARXIV.2503.08564","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2503.08564","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-08564","documentUrl":"https://doi.org/10.48550/ARXIV.2503.08564","arxivId":"2503.08564","arxivUrl":"https://arxiv.org/abs/2503.08564"},{"key":"journals/corr/abs-2503-10434","title":"Finetuning Generative Trajectory Model with Reinforcement Learning from Human Feedback.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2503.10434"],"source":"https://dblp.org/rec/journals/corr/abs-2503-10434","documentPage":"https://doi.org/10.48550/ARXIV.2503.10434","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2503.10434","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-10434","documentUrl":"https://doi.org/10.48550/ARXIV.2503.10434","arxivId":"2503.10434","arxivUrl":"https://arxiv.org/abs/2503.10434"},{"key":"journals/corr/abs-2503-18738","title":"RoboEngine: Plug-and-Play Robot Data Augmentation with Semantic Robot Segmentation and Background Generation.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2503.18738"],"source":"https://dblp.org/rec/journals/corr/abs-2503-18738","documentPage":"https://doi.org/10.48550/ARXIV.2503.18738","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2503.18738","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-18738","documentUrl":"https://doi.org/10.48550/ARXIV.2503.18738","arxivId":"2503.18738","arxivUrl":"https://arxiv.org/abs/2503.18738"},{"key":"journals/corr/abs-2505-11123","title":"Conditioning Matters: Training Diffusion Policies is Faster Than You Think.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2505.11123"],"source":"https://dblp.org/rec/journals/corr/abs-2505-11123","documentPage":"https://doi.org/10.48550/ARXIV.2505.11123","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2505.11123","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-11123","documentUrl":"https://doi.org/10.48550/ARXIV.2505.11123","arxivId":"2505.11123","arxivUrl":"https://arxiv.org/abs/2505.11123"},{"key":"journals/corr/abs-2505-15880","title":"Challenger: Affordable Adversarial Driving Video Generation.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2505.15880"],"source":"https://dblp.org/rec/journals/corr/abs-2505-15880","documentPage":"https://doi.org/10.48550/ARXIV.2505.15880","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2505.15880","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-15880","documentUrl":"https://doi.org/10.48550/ARXIV.2505.15880","arxivId":"2505.15880","arxivUrl":"https://arxiv.org/abs/2505.15880"},{"key":"journals/corr/abs-2505-23115","title":"Diffusion-Based Generative Models for 3D Occupancy Prediction in Autonomous Driving.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2505.23115"],"source":"https://dblp.org/rec/journals/corr/abs-2505-23115","documentPage":"https://doi.org/10.48550/ARXIV.2505.23115","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2505.23115","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-23115","documentUrl":"https://doi.org/10.48550/ARXIV.2505.23115","arxivId":"2505.23115","arxivUrl":"https://arxiv.org/abs/2505.23115"},{"key":"journals/corr/abs-2505-23757","title":"Impromptu VLA: Open Weights and Open Data for Driving Vision-Language-Action Models.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2505.23757"],"source":"https://dblp.org/rec/journals/corr/abs-2505-23757","documentPage":"https://doi.org/10.48550/ARXIV.2505.23757","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2505.23757","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-23757","documentUrl":"https://doi.org/10.48550/ARXIV.2505.23757","arxivId":"2505.23757","arxivUrl":"https://arxiv.org/abs/2505.23757"},{"key":"journals/corr/abs-2506-03079","title":"ORV: 4D Occupancy-centric Robot Video Generation.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2506.03079"],"source":"https://dblp.org/rec/journals/corr/abs-2506-03079","documentPage":"https://doi.org/10.48550/ARXIV.2506.03079","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2506.03079","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-03079","documentUrl":"https://doi.org/10.48550/ARXIV.2506.03079","arxivId":"2506.03079","arxivUrl":"https://arxiv.org/abs/2506.03079"},{"key":"journals/corr/abs-2507-16331","title":"Re:Form - Reducing Human Priors in Scalable Formal Software Verification with RL in LLMs: A Preliminary Study on Dafny.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2507.16331"],"source":"https://dblp.org/rec/journals/corr/abs-2507-16331","documentPage":"https://doi.org/10.48550/ARXIV.2507.16331","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2507.16331","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2507-16331","documentUrl":"https://doi.org/10.48550/ARXIV.2507.16331","arxivId":"2507.16331","arxivUrl":"https://arxiv.org/abs/2507.16331"},{"key":"journals/corr/abs-2507-16645","title":"Morpheus: A Neural-driven Animatronic Face with Hybrid Actuation and Diverse Emotion Control.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2507.16645"],"source":"https://dblp.org/rec/journals/corr/abs-2507-16645","documentPage":"https://doi.org/10.48550/ARXIV.2507.16645","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2507.16645","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2507-16645","documentUrl":"https://doi.org/10.48550/ARXIV.2507.16645","arxivId":"2507.16645","arxivUrl":"https://arxiv.org/abs/2507.16645"},{"key":"journals/corr/abs-2507-17617","title":"Reusing Attention for One-stage Lane Topology Understanding.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2507.17617"],"source":"https://dblp.org/rec/journals/corr/abs-2507-17617","documentPage":"https://doi.org/10.48550/ARXIV.2507.17617","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2507.17617","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2507-17617","documentUrl":"https://doi.org/10.48550/ARXIV.2507.17617","arxivId":"2507.17617","arxivUrl":"https://arxiv.org/abs/2507.17617"},{"key":"journals/corr/abs-2507-18255","title":"LONG3R: Long Sequence Streaming 3D Reconstruction.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2507.18255"],"source":"https://dblp.org/rec/journals/corr/abs-2507-18255","documentPage":"https://doi.org/10.48550/ARXIV.2507.18255","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2507.18255","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2507-18255","documentUrl":"https://doi.org/10.48550/ARXIV.2507.18255","arxivId":"2507.18255","arxivUrl":"https://arxiv.org/abs/2507.18255"},{"key":"journals/corr/abs-2507-18473","title":"CRUISE: Cooperative Reconstruction and Editing in V2X Scenarios using Gaussian Splatting.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2507.18473"],"source":"https://dblp.org/rec/journals/corr/abs-2507-18473","documentPage":"https://doi.org/10.48550/ARXIV.2507.18473","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2507.18473","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2507-18473","documentUrl":"https://doi.org/10.48550/ARXIV.2507.18473","arxivId":"2507.18473","arxivUrl":"https://arxiv.org/abs/2507.18473"},{"key":"journals/corr/abs-2507-18498","title":"Delving into Mapping Uncertainty for Mapless Trajectory Prediction.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2507.18498"],"source":"https://dblp.org/rec/journals/corr/abs-2507-18498","documentPage":"https://doi.org/10.48550/ARXIV.2507.18498","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2507.18498","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2507-18498","documentUrl":"https://doi.org/10.48550/ARXIV.2507.18498","arxivId":"2507.18498","arxivUrl":"https://arxiv.org/abs/2507.18498"},{"key":"journals/corr/abs-2507-19451","title":"GS-Occ3D: Scaling Vision-only Occupancy Reconstruction for Autonomous Driving with Gaussian Splatting.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2507.19451"],"source":"https://dblp.org/rec/journals/corr/abs-2507-19451","documentPage":"https://doi.org/10.48550/ARXIV.2507.19451","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2507.19451","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2507-19451","documentUrl":"https://doi.org/10.48550/ARXIV.2507.19451","arxivId":"2507.19451","arxivUrl":"https://arxiv.org/abs/2507.19451"},{"key":"journals/corr/abs-2507-20879","title":"DriveAgent-R1: Advancing VLM-based Autonomous Driving with Hybrid Thinking and Active Perception.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2507.20879"],"source":"https://dblp.org/rec/journals/corr/abs-2507-20879","documentPage":"https://doi.org/10.48550/ARXIV.2507.20879","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2507.20879","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2507-20879","documentUrl":"https://doi.org/10.48550/ARXIV.2507.20879","arxivId":"2507.20879","arxivUrl":"https://arxiv.org/abs/2507.20879"},{"key":"journals/corr/abs-2509-00576","title":"Galaxea Open-World Dataset and G0 Dual-System VLA Model.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2509.00576"],"source":"https://dblp.org/rec/journals/corr/abs-2509-00576","documentPage":"https://doi.org/10.48550/ARXIV.2509.00576","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2509.00576","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-00576","documentUrl":"https://doi.org/10.48550/ARXIV.2509.00576","arxivId":"2509.00576","arxivUrl":"https://arxiv.org/abs/2509.00576"},{"key":"journals/corr/abs-2509-20109","title":"Discrete Diffusion for Reflective Vision-Language-Action Models in Autonomous Driving.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2509.20109"],"source":"https://dblp.org/rec/journals/corr/abs-2509-20109","documentPage":"https://doi.org/10.48550/ARXIV.2509.20109","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2509.20109","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-20109","documentUrl":"https://doi.org/10.48550/ARXIV.2509.20109","arxivId":"2509.20109","arxivUrl":"https://arxiv.org/abs/2509.20109"},{"key":"journals/corr/abs-2509-26219","title":"Beyond Pixels: Efficient Dataset Distillation via Sparse Gaussian Representation.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2509.26219"],"source":"https://dblp.org/rec/journals/corr/abs-2509-26219","documentPage":"https://doi.org/10.48550/ARXIV.2509.26219","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2509.26219","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-26219","documentUrl":"https://doi.org/10.48550/ARXIV.2509.26219","arxivId":"2509.26219","arxivUrl":"https://arxiv.org/abs/2509.26219"},{"key":"journals/corr/abs-2510-13375","title":"DepthVLA: Enhancing Vision-Language-Action Models with Depth-Aware Spatial Reasoning.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2510.13375"],"source":"https://dblp.org/rec/journals/corr/abs-2510-13375","documentPage":"https://doi.org/10.48550/ARXIV.2510.13375","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2510.13375","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-13375","documentUrl":"https://doi.org/10.48550/ARXIV.2510.13375","arxivId":"2510.13375","arxivUrl":"https://arxiv.org/abs/2510.13375"},{"key":"journals/corr/abs-2511-17441","title":"RoboCOIN: An Open-Sourced Bimanual Robotic Data COllection for INtegrated Manipulation.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2511.17441"],"source":"https://dblp.org/rec/journals/corr/abs-2511-17441","documentPage":"https://doi.org/10.48550/ARXIV.2511.17441","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2511.17441","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2511-17441","documentUrl":"https://doi.org/10.48550/ARXIV.2511.17441","arxivId":"2511.17441","arxivUrl":"https://arxiv.org/abs/2511.17441"},{"key":"journals/corr/abs-2511-17914","title":"Rectifying Soft-Label Entangled Bias in Long-Tailed Dataset Distillation.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2511.17914"],"source":"https://dblp.org/rec/journals/corr/abs-2511-17914","documentPage":"https://doi.org/10.48550/ARXIV.2511.17914","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2511.17914","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2511-17914","documentUrl":"https://doi.org/10.48550/ARXIV.2511.17914","arxivId":"2511.17914","arxivUrl":"https://arxiv.org/abs/2511.17914"},{"key":"journals/corr/abs-2512-04552","title":"RRPO: Robust Reward Policy Optimization for LLM-based Emotional TTS.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2512.04552"],"source":"https://dblp.org/rec/journals/corr/abs-2512-04552","documentPage":"https://doi.org/10.48550/ARXIV.2512.04552","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2512.04552","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-04552","documentUrl":"https://doi.org/10.48550/ARXIV.2512.04552","arxivId":"2512.04552","arxivUrl":"https://arxiv.org/abs/2512.04552"},{"key":"journals/corr/abs-2512-04952","title":"FASTer: Toward Efficient Autoregressive Vision Language Action Modeling via Neural Action Tokenization.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2512.04952"],"source":"https://dblp.org/rec/journals/corr/abs-2512-04952","documentPage":"https://doi.org/10.48550/ARXIV.2512.04952","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2512.04952","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-04952","documentUrl":"https://doi.org/10.48550/ARXIV.2512.04952","arxivId":"2512.04952","arxivUrl":"https://arxiv.org/abs/2512.04952"}],"excludedFormal":[],"excludedOther":[],"excludedHomonyms":[],"unassignedCandidates":[],"retrievedAt":"2026-10-19","querySource":"https://sparql.dblp.org/","method":"DBLP yearOfPublication=2025; Article + Inproceedings; excludes Informal/CoRR and explicit editorial/correction/erratum/preface; unique DBLP record keys within person.","labName":"MARS Lab, Tsinghua University","labUrl":"https://group.iiis.tsinghua.edu.cn/~marslab/","labEvidence":"本人主页两处明确写 Principal Investigator / PI of MARS Lab，且给出清华官方域名实验室链接。未自行扩展缩写。","labSourceUrl":"https://hangzhaomit.github.io/","affiliationZh":"清华大学","sourceWarning":false,"knownPreprintMinimum2025":null,"excludedMisattributed":[],"displayNotes":"身份已经个人或机构主页核对。2025 年正式记录 21 条（会议 19、期刊 2），所有作者位置均计入，不表示主导或贡献份额；预印本 29 条单列，不加总。","labDisplayNotes":"本人主页写明其为 MARS Lab 的 PI，并链接清华官方域名下的实验室网站，据此归组；它与上科大、武汉大学的 MARS 是不同团队。"},{"index":113,"name":"Hengshuang Zhao","nameZh":"赵恒爽","affiliation":"The University of Hong Kong","source":"DBLP Knowledge Graph official SPARQL API","profileUrl":"https://dblp.org/pid/185/7848","identifier":"185/7848","identityEvidence":[{"url":"https://i.cs.hku.hk/~hszhao/","evidence":"University personal site identifies HKU assistant professor Hengshuang Zhao; 20 current 2025 DBLP titles match the page, including StableDepth / ViLLa / HaploVL."},{"url":"https://dblp.org/rec/conf/iccv/ZhouLTCDZTZB25","evidence":"DBLP paper author signature connects this profile to University of Hong Kong (HKU)."},{"url":"https://dblp.org/rec/conf/siggraph/TuCLZ25","evidence":"DBLP paper author signature connects this profile to University of Hong Kong (HKU) and https://orcid.org/0000-0001-8277-2706."}],"count2025":49,"conference2025":43,"journal2025":6,"preprint2025":44,"status":"verified","notes":"Counts are DBLP indexed coauthored records, not first-author counts, laboratory totals, unique scientific discoveries, or quality assessments. DBLP yearOfPublication=2025; yearOfEvent retained and can differ. Conference workshops are included. Preprints are separate and may overlap formal versions.","papers":[{"key":"conf/cvpr/0001ZHHYZCJ0Z025","title":"SpatialCLIP: Learning 3D-aware Image Representations from Spatially Discriminative Language.","year":2025,"yearOfEvent":2025,"venue":"CVPR","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/CVPR52734.2025.02761"],"source":"https://dblp.org/rec/conf/cvpr/0001ZHHYZCJ0Z025","documentPage":"https://openaccess.thecvf.com/content/CVPR2025/html/Wang_SpatialCLIP_Learning_3D-aware_Image_Representations_from_Spatially_Discriminative_Language_CVPR_2025_paper.html","type":"Inproceedings","doi":"https://doi.org/10.1109/CVPR52734.2025.02761","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/0001ZHHYZCJ0Z025","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Wang_SpatialCLIP_Learning_3D-aware_Image_Representations_from_Spatially_Discriminative_Language_CVPR_2025_paper.html"},{"key":"conf/cvpr/0002DFSXYENZS25","title":"Sonata: Self-Supervised Learning of Reliable Point Representations.","year":2025,"yearOfEvent":2025,"venue":"CVPR","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/CVPR52734.2025.02067"],"source":"https://dblp.org/rec/conf/cvpr/0002DFSXYENZS25","documentPage":"https://openaccess.thecvf.com/content/CVPR2025/html/Wu_Sonata_Self-Supervised_Learning_of_Reliable_Point_Representations_CVPR_2025_paper.html","type":"Inproceedings","doi":"https://doi.org/10.1109/CVPR52734.2025.02067","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/0002DFSXYENZS25","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Wu_Sonata_Self-Supervised_Learning_of_Reliable_Point_Representations_CVPR_2025_paper.html"},{"key":"conf/cvpr/CaoZ0ABZ025","title":"PanDA: Towards Panoramic Depth Anything with Unlabeled Panoramas and Mobius Spatial Augmentation.","year":2025,"yearOfEvent":2025,"venue":"CVPR","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/CVPR52734.2025.00100"],"source":"https://dblp.org/rec/conf/cvpr/CaoZ0ABZ025","documentPage":"https://openaccess.thecvf.com/content/CVPR2025/html/Cao_PanDA_Towards_Panoramic_Depth_Anything_with_Unlabeled_Panoramas_and_Mobius_CVPR_2025_paper.html","type":"Inproceedings","doi":"https://doi.org/10.1109/CVPR52734.2025.00100","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/CaoZ0ABZ025","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Cao_PanDA_Towards_Panoramic_Depth_Anything_with_Unlabeled_Panoramas_and_Mobius_CVPR_2025_paper.html"},{"key":"conf/cvpr/ChenGHLTXWZZYWX25","title":"EMOVA: Empowering Language Models to See, Hear and Speak with Vivid Emotions.","year":2025,"yearOfEvent":2025,"venue":"CVPR","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/CVPR52734.2025.00513"],"source":"https://dblp.org/rec/conf/cvpr/ChenGHLTXWZZYWX25","documentPage":"https://openaccess.thecvf.com/content/CVPR2025/html/Chen_EMOVA_Empowering_Language_Models_to_See_Hear_and_Speak_with_CVPR_2025_paper.html","type":"Inproceedings","doi":"https://doi.org/10.1109/CVPR52734.2025.00513","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/ChenGHLTXWZZYWX25","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Chen_EMOVA_Empowering_Language_Models_to_See_Hear_and_Speak_with_CVPR_2025_paper.html"},{"key":"conf/cvpr/ChenZZZKL00Z0D025","title":"UniReal: Universal Image Generation and Editing via Learning Real-world Dynamics.","year":2025,"yearOfEvent":2025,"venue":"CVPR","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/CVPR52734.2025.01166"],"source":"https://dblp.org/rec/conf/cvpr/ChenZZZKL00Z0D025","documentPage":"https://openaccess.thecvf.com/content/CVPR2025/html/Chen_UniReal_Universal_Image_Generation_and_Editing_via_Learning_Real-world_Dynamics_CVPR_2025_paper.html","type":"Inproceedings","doi":"https://doi.org/10.1109/CVPR52734.2025.01166","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/ChenZZZKL00Z0D025","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Chen_UniReal_Universal_Image_Generation_and_Editing_via_Learning_Real-world_Dynamics_CVPR_2025_paper.html"},{"key":"conf/cvpr/HuangDWHLZXHZL25","title":"HiRes-LLaVA: Restoring Fragmentation Input in High-Resolution Large Vision-Language Models.","year":2025,"yearOfEvent":2025,"venue":"CVPR","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/CVPR52734.2025.02775"],"source":"https://dblp.org/rec/conf/cvpr/HuangDWHLZXHZL25","documentPage":"https://openaccess.thecvf.com/content/CVPR2025/html/Huang_HiRes-LLaVA_Restoring_Fragmentation_Input_in_High-Resolution_Large_Vision-Language_Models_CVPR_2025_paper.html","type":"Inproceedings","doi":"https://doi.org/10.1109/CVPR52734.2025.02775","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/HuangDWHLZXHZL25","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Huang_HiRes-LLaVA_Restoring_Fragmentation_Input_in_High-Resolution_Large_Vision-Language_Models_CVPR_2025_paper.html"},{"key":"conf/cvpr/XuB0LXWWZ25","title":"DriveGPT4-V2: Harnessing Large Language Model Capabilities for Enhanced Closed-Loop Autonomous Driving.","year":2025,"yearOfEvent":2025,"venue":"CVPR","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/CVPR52734.2025.01609"],"source":"https://dblp.org/rec/conf/cvpr/XuB0LXWWZ25","documentPage":"https://openaccess.thecvf.com/content/CVPR2025/html/Xu_DriveGPT4-V2_Harnessing_Large_Language_Model_Capabilities_for_Enhanced_Closed-Loop_Autonomous_CVPR_2025_paper.html","type":"Inproceedings","doi":"https://doi.org/10.1109/CVPR52734.2025.01609","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/XuB0LXWWZ25","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Xu_DriveGPT4-V2_Harnessing_Large_Language_Model_Capabilities_for_Enhanced_Closed-Loop_Autonomous_CVPR_2025_paper.html"},{"key":"conf/cvpr/YuanPRLH0ZLCL25","title":"Empowering Large Language Models with 3D Situation Awareness.","year":2025,"yearOfEvent":2025,"venue":"CVPR","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/CVPR52734.2025.01810"],"source":"https://dblp.org/rec/conf/cvpr/YuanPRLH0ZLCL25","documentPage":"https://openaccess.thecvf.com/content/CVPR2025/html/Yuan_Empowering_Large_Language_Models_with_3D_Situation_Awareness_CVPR_2025_paper.html","type":"Inproceedings","doi":"https://doi.org/10.1109/CVPR52734.2025.01810","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/YuanPRLH0ZLCL25","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Yuan_Empowering_Large_Language_Models_with_3D_Situation_Awareness_CVPR_2025_paper.html"},{"key":"conf/eccv/ChenLCFLSZ24","title":"LivePhoto: Real Image Animation with Text-Guided Motion Control.","year":2025,"yearOfEvent":2024,"venue":"ECCV (18)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1007/978-3-031-72649-1_27"],"source":"https://dblp.org/rec/conf/eccv/ChenLCFLSZ24","documentPage":"https://doi.org/10.1007/978-3-031-72649-1_27","type":"Inproceedings","doi":"https://doi.org/10.1007/978-3-031-72649-1_27","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/eccv/ChenLCFLSZ24","documentUrl":"https://doi.org/10.1007/978-3-031-72649-1_27"},{"key":"conf/eccv/HuangWCZZL24","title":"OpenIns3D: Snap and Lookup for 3D Open-Vocabulary Instance Segmentation.","year":2025,"yearOfEvent":2024,"venue":"ECCV (62)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1007/978-3-031-73033-7_10"],"source":"https://dblp.org/rec/conf/eccv/HuangWCZZL24","documentPage":"https://doi.org/10.1007/978-3-031-73033-7_10","type":"Inproceedings","doi":"https://doi.org/10.1007/978-3-031-73033-7_10","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/eccv/HuangWCZZL24","documentUrl":"https://doi.org/10.1007/978-3-031-73033-7_10"},{"key":"conf/eccv/TangTLHZZLJ24","title":"Mind the Interference: Retaining Pre-trained Knowledge in Parameter Efficient Continual Learning of Vision-Language Models.","year":2025,"yearOfEvent":2024,"venue":"ECCV (36)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1007/978-3-031-72764-1_20"],"source":"https://dblp.org/rec/conf/eccv/TangTLHZZLJ24","documentPage":"https://doi.org/10.1007/978-3-031-72764-1_20","type":"Inproceedings","doi":"https://doi.org/10.1007/978-3-031-72764-1_20","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/eccv/TangTLHZZLJ24","documentUrl":"https://doi.org/10.1007/978-3-031-72764-1_20"},{"key":"conf/eccv/WangLLZW24","title":"OV-Uni3DETR: Towards Unified Open-Vocabulary 3D Object Detection via Cycle-Modality Propagation.","year":2025,"yearOfEvent":2024,"venue":"ECCV (47)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1007/978-3-031-72970-6_5"],"source":"https://dblp.org/rec/conf/eccv/WangLLZW24","documentPage":"https://doi.org/10.1007/978-3-031-72970-6_5","type":"Inproceedings","doi":"https://doi.org/10.1007/978-3-031-72970-6_5","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/eccv/WangLLZW24","documentUrl":"https://doi.org/10.1007/978-3-031-72970-6_5"},{"key":"conf/eccv/XuWZ24","title":"InsMapper: Exploring Inner-Instance Information for Vectorized HD Mapping.","year":2025,"yearOfEvent":2024,"venue":"ECCV (34)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1007/978-3-031-72754-2_17"],"source":"https://dblp.org/rec/conf/eccv/XuWZ24","documentPage":"https://doi.org/10.1007/978-3-031-72754-2_17","type":"Inproceedings","doi":"https://doi.org/10.1007/978-3-031-72754-2_17","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/eccv/XuWZ24","documentUrl":"https://doi.org/10.1007/978-3-031-72754-2_17"},{"key":"conf/eccv/ZhangHLHZ24","title":"Pixel-GS: Density Control with Pixel-Aware Gradient for 3D Gaussian Splatting.","year":2025,"yearOfEvent":2024,"venue":"ECCV (19)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1007/978-3-031-72655-2_19"],"source":"https://dblp.org/rec/conf/eccv/ZhangHLHZ24","documentPage":"https://doi.org/10.1007/978-3-031-72655-2_19","type":"Inproceedings","doi":"https://doi.org/10.1007/978-3-031-72655-2_19","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/eccv/ZhangHLHZ24","documentUrl":"https://doi.org/10.1007/978-3-031-72655-2_19"},{"key":"conf/eccv/ZhuCWZJ24","title":"LogoSticker: Inserting Logos Into Diffusion Models for Customized Generation.","year":2025,"yearOfEvent":2024,"venue":"ECCV (60)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1007/978-3-031-73027-6_21"],"source":"https://dblp.org/rec/conf/eccv/ZhuCWZJ24","documentPage":"https://doi.org/10.1007/978-3-031-73027-6_21","type":"Inproceedings","doi":"https://doi.org/10.1007/978-3-031-73027-6_21","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/eccv/ZhuCWZJ24","documentUrl":"https://doi.org/10.1007/978-3-031-73027-6_21"},{"key":"conf/emnlp/ZhuCWYZJ25","title":"Enhancing LLM Knowledge Learning through Generalization.","year":2025,"yearOfEvent":2025,"venue":"EMNLP (Findings)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.18653/V1/2025.FINDINGS-EMNLP.469"],"source":"https://dblp.org/rec/conf/emnlp/ZhuCWYZJ25","documentPage":"https://doi.org/10.18653/V1/2025.FINDINGS-EMNLP.469","type":"Inproceedings","doi":"https://doi.org/10.18653/V1/2025.FINDINGS-EMNLP.469","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/emnlp/ZhuCWYZJ25","documentUrl":"https://doi.org/10.18653/V1/2025.FINDINGS-EMNLP.469"},{"key":"conf/iccv/WangCXJLSZ25","title":"DiffDoctor: Diagnosing Image Diffusion Models Before Treating.","year":2025,"yearOfEvent":2025,"venue":"ICCV","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/ICCV51701.2025.01758"],"source":"https://dblp.org/rec/conf/iccv/WangCXJLSZ25","documentPage":"https://doi.org/10.1109/ICCV51701.2025.01758","type":"Inproceedings","doi":"https://doi.org/10.1109/ICCV51701.2025.01758","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/WangCXJLSZ25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.01758"},{"key":"conf/iccv/ZhangYYYGLZ25","title":"StableDepth: Scene-Consistent and Scale-Invariant Monocular Depth.","year":2025,"yearOfEvent":2025,"venue":"ICCV","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/ICCV51701.2025.00664"],"source":"https://dblp.org/rec/conf/iccv/ZhangYYYGLZ25","documentPage":"https://doi.org/10.1109/ICCV51701.2025.00664","type":"Inproceedings","doi":"https://doi.org/10.1109/ICCV51701.2025.00664","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/ZhangYYYGLZ25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.00664"},{"key":"conf/iccv/ZhaoZWWZ25","title":"DisCo: Towards Distinct and Coherent Visual Encapsulation in Video MLLMs.","year":2025,"yearOfEvent":2025,"venue":"ICCV","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/ICCV51701.2025.02016"],"source":"https://dblp.org/rec/conf/iccv/ZhaoZWWZ25","documentPage":"https://doi.org/10.1109/ICCV51701.2025.02016","type":"Inproceedings","doi":"https://doi.org/10.1109/ICCV51701.2025.02016","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/ZhaoZWWZ25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.02016"},{"key":"conf/iccv/ZhengQCWWZ25","title":"ViLLa: Video Reasoning Segmentation with Large Language Model.","year":2025,"yearOfEvent":2025,"venue":"ICCV","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/ICCV51701.2025.02197"],"source":"https://dblp.org/rec/conf/iccv/ZhengQCWWZ25","documentPage":"https://doi.org/10.1109/ICCV51701.2025.02197","type":"Inproceedings","doi":"https://doi.org/10.1109/ICCV51701.2025.02197","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/ZhengQCWWZ25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.02197"},{"key":"conf/iccv/ZhouLTCDZTZB25","title":"HERMES: A Unified Self-Driving World Model for Simultaneous 3D Scene Understanding and Generation.","year":2025,"yearOfEvent":2025,"venue":"ICCV","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/ICCV51701.2025.02582"],"source":"https://dblp.org/rec/conf/iccv/ZhouLTCDZTZB25","documentPage":"https://doi.org/10.1109/ICCV51701.2025.02582","type":"Inproceedings","doi":"https://doi.org/10.1109/ICCV51701.2025.02582","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/ZhouLTCDZTZB25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.02582"},{"key":"conf/iclr/0001ZHZL0CJ0Z025","title":"OmniBind: Large-scale Omni Multimodal Representation via Binding Spaces.","year":2025,"yearOfEvent":2025,"venue":"ICLR","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/iclr/0001ZHZL0CJ0Z025","documentPage":"https://openreview.net/forum?id=l2izo0z7gu","type":"Inproceedings","doi":null,"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iclr/0001ZHZL0CJ0Z025","documentUrl":"https://openreview.net/forum?id=l2izo0z7gu"},{"key":"conf/icml/0001ZPDZ025","title":"Orient Anything: Learning Robust Object Orientation Estimation from Rendering 3D Models.","year":2025,"yearOfEvent":2025,"venue":"ICML","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/icml/0001ZPDZ025","documentPage":"https://proceedings.mlr.press/v267/wang25er.html","type":"Inproceedings","doi":null,"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/icml/0001ZPDZ025","documentUrl":"https://proceedings.mlr.press/v267/wang25er.html"},{"key":"conf/icml/00410XHGSZ25","title":"HaploVL: A Single-Transformer Baseline for Multi-Modal Understanding.","year":2025,"yearOfEvent":2025,"venue":"ICML","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/icml/00410XHGSZ25","documentPage":"https://proceedings.mlr.press/v267/yang25ab.html","type":"Inproceedings","doi":null,"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/icml/00410XHGSZ25","documentUrl":"https://proceedings.mlr.press/v267/yang25ab.html"},{"key":"conf/icml/Li00LZ25","title":"LARM: Large Auto-Regressive Model for Long-Horizon Embodied Intelligence.","year":2025,"yearOfEvent":2025,"venue":"ICML","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/icml/Li00LZ25","documentPage":"https://proceedings.mlr.press/v267/li25dj.html","type":"Inproceedings","doi":null,"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/icml/Li00LZ25","documentUrl":"https://proceedings.mlr.press/v267/li25dj.html"},{"key":"conf/icml/Liao0Z0Z25","title":"BOOD: Boundary-based Out-Of-Distribution Data Generation.","year":2025,"yearOfEvent":2025,"venue":"ICML","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/icml/Liao0Z0Z25","documentPage":"https://proceedings.mlr.press/v267/liao25g.html","type":"Inproceedings","doi":null,"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/icml/Liao0Z0Z25","documentUrl":"https://proceedings.mlr.press/v267/liao25g.html"},{"key":"conf/icml/LiRYZ00BZ25","title":"VIP: Vision Instructed Pre-training for Robotic Manipulation.","year":2025,"yearOfEvent":2025,"venue":"ICML","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/icml/LiRYZ00BZ25","documentPage":"https://proceedings.mlr.press/v267/li25by.html","type":"Inproceedings","doi":null,"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/icml/LiRYZ00BZ25","documentUrl":"https://proceedings.mlr.press/v267/li25by.html"},{"key":"conf/icml/ZhuCW0ZJ25","title":"TGDPO: Harnessing Token-Level Reward Guidance for Enhancing Direct Preference Optimization.","year":2025,"yearOfEvent":2025,"venue":"ICML","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/icml/ZhuCW0ZJ25","documentPage":"https://proceedings.mlr.press/v267/zhu25c.html","type":"Inproceedings","doi":null,"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/icml/ZhuCW0ZJ25","documentUrl":"https://proceedings.mlr.press/v267/zhu25c.html"},{"key":"conf/nips/ChenZLWXLBZ25","title":"MiCo: Multi-image Contrast for Reinforcement Visual Reasoning.","year":2025,"yearOfEvent":2025,"venue":"NeurIPS","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/nips/ChenZLWXLBZ25","documentPage":"http://papers.nips.cc/paper_files/paper/2025/hash/0fbbc5129cafcee8530223b8565561ac-Abstract-Conference.html","type":"Inproceedings","doi":null,"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/nips/ChenZLWXLBZ25","documentUrl":"http://papers.nips.cc/paper_files/paper/2025/hash/0fbbc5129cafcee8530223b8565561ac-Abstract-Conference.html"},{"key":"conf/nips/ChuHCZXxWYLZLZY25","title":"Wan-Move: Motion-controllable Video Generation via Latent Trajectory Guidance.","year":2025,"yearOfEvent":2025,"venue":"NeurIPS","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/nips/ChuHCZXxWYLZLZY25","documentPage":"http://papers.nips.cc/paper_files/paper/2025/hash/00b67df24009747e8bbed4c2c6f9c825-Abstract-Conference.html","type":"Inproceedings","doi":null,"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/nips/ChuHCZXxWYLZLZY25","documentUrl":"http://papers.nips.cc/paper_files/paper/2025/hash/00b67df24009747e8bbed4c2c6f9c825-Abstract-Conference.html"},{"key":"conf/nips/HuangWZZNL25","title":"LiteReality: Graphics-Ready 3D Scene Reconstruction from RGB-D Scans.","year":2025,"yearOfEvent":2025,"venue":"NeurIPS","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/nips/HuangWZZNL25","documentPage":"http://papers.nips.cc/paper_files/paper/2025/hash/ee4bfd01b0b7278aaa8c8127632f4635-Abstract-Conference.html","type":"Inproceedings","doi":null,"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/nips/HuangWZZNL25","documentUrl":"http://papers.nips.cc/paper_files/paper/2025/hash/ee4bfd01b0b7278aaa8c8127632f4635-Abstract-Conference.html"},{"key":"conf/nips/MiaoFZGLYQCWZ25","title":"ROSE: Remove Objects with Side Effects in Videos.","year":2025,"yearOfEvent":2025,"venue":"NeurIPS","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/nips/MiaoFZGLYQCWZ25","documentPage":"http://papers.nips.cc/paper_files/paper/2025/hash/db2808c312de68420ef20f055b726549-Abstract-Conference.html","type":"Inproceedings","doi":null,"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/nips/MiaoFZGLYQCWZ25","documentUrl":"http://papers.nips.cc/paper_files/paper/2025/hash/db2808c312de68420ef20f055b726549-Abstract-Conference.html"},{"key":"conf/nips/TuLCBWZ25","title":"PlayerOne: Egocentric World Simulator.","year":2025,"yearOfEvent":2025,"venue":"NeurIPS","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/nips/TuLCBWZ25","documentPage":"http://papers.nips.cc/paper_files/paper/2025/hash/d607a260b3bc0b9a704a1a04dd64040a-Abstract-Conference.html","type":"Inproceedings","doi":null,"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/nips/TuLCBWZ25","documentUrl":"http://papers.nips.cc/paper_files/paper/2025/hash/d607a260b3bc0b9a704a1a04dd64040a-Abstract-Conference.html"},{"key":"conf/nips/WangXZPDZZ25","title":"GenSpace: Benchmarking Spatially-Aware Image Generation.","year":2025,"yearOfEvent":2025,"venue":"NeurIPS","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/nips/WangXZPDZZ25","documentPage":"http://papers.nips.cc/paper_files/paper/2025/hash/4e582b104248a396a703646755071329-Abstract-Datasets_and_Benchmarks_Track.html","type":"Inproceedings","doi":null,"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/nips/WangXZPDZZ25","documentUrl":"http://papers.nips.cc/paper_files/paper/2025/hash/4e582b104248a396a703646755071329-Abstract-Datasets_and_Benchmarks_Track.html"},{"key":"conf/nips/WangZXWPDZZ25","title":"Orient Anything V2: Unifying Orientation and Rotation Understanding.","year":2025,"yearOfEvent":2025,"venue":"NeurIPS","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/nips/WangZXWPDZZ25","documentPage":"http://papers.nips.cc/paper_files/paper/2025/hash/4bda4364bf10a454769fdbeb8c02df16-Abstract-Conference.html","type":"Inproceedings","doi":null,"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/nips/WangZXWPDZZ25","documentUrl":"http://papers.nips.cc/paper_files/paper/2025/hash/4bda4364bf10a454769fdbeb8c02df16-Abstract-Conference.html"},{"key":"conf/nips/YangLLWLMYZJ25","title":"VisionThink: Smart and Efficient Vision Language Model via Reinforcement Learning.","year":2025,"yearOfEvent":2025,"venue":"NeurIPS","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/nips/YangLLWLMYZJ25","documentPage":"http://papers.nips.cc/paper_files/paper/2025/hash/88be023075a5a3ff3dc3b5d26623fa22-Abstract-Conference.html","type":"Inproceedings","doi":null,"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/nips/YangLLWLMYZJ25","documentUrl":"http://papers.nips.cc/paper_files/paper/2025/hash/88be023075a5a3ff3dc3b5d26623fa22-Abstract-Conference.html"},{"key":"conf/nips/ZhangWLWTWZ25","title":"Concerto: Joint 2D-3D Self-Supervised Learning Emerges Spatial Representations.","year":2025,"yearOfEvent":2025,"venue":"NeurIPS","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/nips/ZhangWLWTWZ25","documentPage":"http://papers.nips.cc/paper_files/paper/2025/hash/649a31f2cb31a73b92c68b15bbf44442-Abstract-Conference.html","type":"Inproceedings","doi":null,"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/nips/ZhangWLWTWZ25","documentUrl":"http://papers.nips.cc/paper_files/paper/2025/hash/649a31f2cb31a73b92c68b15bbf44442-Abstract-Conference.html"},{"key":"conf/nips/ZhengQCWWZ25","title":"Seg-VAR: Image Segmentation with Visual Autoregressive Modeling.","year":2025,"yearOfEvent":2025,"venue":"NeurIPS","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/nips/ZhengQCWWZ25","documentPage":"http://papers.nips.cc/paper_files/paper/2025/hash/f25602918e8a0d0c86e3c752ecfbbaa1-Abstract-Conference.html","type":"Inproceedings","doi":null,"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/nips/ZhengQCWWZ25","documentUrl":"http://papers.nips.cc/paper_files/paper/2025/hash/f25602918e8a0d0c86e3c752ecfbbaa1-Abstract-Conference.html"},{"key":"conf/siggraph/Ji00TWZ25","title":"LayerFlow: A Unified Model for Layer-aware Video Generation.","year":2025,"yearOfEvent":2025,"venue":"SIGGRAPH (Conference Paper Track)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1145/3721238.3730662"],"source":"https://dblp.org/rec/conf/siggraph/Ji00TWZ25","documentPage":"https://doi.org/10.1145/3721238.3730662","type":"Inproceedings","doi":"https://doi.org/10.1145/3721238.3730662","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/siggraph/Ji00TWZ25","documentUrl":"https://doi.org/10.1145/3721238.3730662"},{"key":"conf/siggraph/JiW000Z25","title":"FashionComposer: Compositional Fashion Image Generation.","year":2025,"yearOfEvent":2025,"venue":"SIGGRAPH (Conference Paper Track)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1145/3721238.3730663"],"source":"https://dblp.org/rec/conf/siggraph/JiW000Z25","documentPage":"https://doi.org/10.1145/3721238.3730663","type":"Inproceedings","doi":"https://doi.org/10.1145/3721238.3730663","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/siggraph/JiW000Z25","documentUrl":"https://doi.org/10.1145/3721238.3730663"},{"key":"conf/siggraph/TuCLZ25","title":"DreamMask: Boosting Open-vocabulary Panoptic Segmentation with Synthetic Data.","year":2025,"yearOfEvent":2025,"venue":"SIGGRAPH (Conference Paper Track)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1145/3721238.3730684"],"source":"https://dblp.org/rec/conf/siggraph/TuCLZ25","documentPage":"https://doi.org/10.1145/3721238.3730684","type":"Inproceedings","doi":"https://doi.org/10.1145/3721238.3730684","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/siggraph/TuCLZ25","documentUrl":"https://doi.org/10.1145/3721238.3730684"},{"key":"conf/siggraph/TuLCJBZ25","title":"VideoAnydoor: High-fidelity Video Object Insertion with Precise Motion Control.","year":2025,"yearOfEvent":2025,"venue":"SIGGRAPH (Conference Paper Track)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1145/3721238.3730647"],"source":"https://dblp.org/rec/conf/siggraph/TuLCJBZ25","documentPage":"https://doi.org/10.1145/3721238.3730647","type":"Inproceedings","doi":"https://doi.org/10.1145/3721238.3730647","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/siggraph/TuLCJBZ25","documentUrl":"https://doi.org/10.1145/3721238.3730647"},{"key":"conf/siggrapha/WangC00Z25","title":"DiffCamera: Arbitrary Refocusing on Images.","year":2025,"yearOfEvent":2025,"venue":"SIGGRAPH Asia","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1145/3757377.3763827"],"source":"https://dblp.org/rec/conf/siggrapha/WangC00Z25","documentPage":"https://doi.org/10.1145/3757377.3763827","type":"Inproceedings","doi":"https://doi.org/10.1145/3757377.3763827","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/siggrapha/WangC00Z25","documentUrl":"https://doi.org/10.1145/3757377.3763827"},{"key":"journals/pami/ChenHLSZZ25","title":"AnyDoor: Zero-Shot Image Customization With Region-to-Region Reference.","year":2025,"yearOfEvent":null,"venue":"IEEE Trans. Pattern Anal. Mach. Intell.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1109/TPAMI.2025.3562237"],"source":"https://dblp.org/rec/journals/pami/ChenHLSZZ25","documentPage":"https://doi.org/10.1109/TPAMI.2025.3562237","type":"Article","doi":"https://doi.org/10.1109/TPAMI.2025.3562237","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/pami/ChenHLSZZ25","documentUrl":"https://doi.org/10.1109/TPAMI.2025.3562237"},{"key":"journals/pami/LiXLZ25","title":"Toward Unified 3D Object Detection via Algorithm and Data Unification.","year":2025,"yearOfEvent":null,"venue":"IEEE Trans. Pattern Anal. Mach. Intell.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1109/TPAMI.2025.3574363"],"source":"https://dblp.org/rec/journals/pami/LiXLZ25","documentPage":"https://doi.org/10.1109/TPAMI.2025.3574363","type":"Article","doi":"https://doi.org/10.1109/TPAMI.2025.3574363","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/pami/LiXLZ25","documentUrl":"https://doi.org/10.1109/TPAMI.2025.3574363"},{"key":"journals/pami/WangLCLTZW25","title":"UniDetector: Towards Universal Object Detection With Heterogeneous Supervision.","year":2025,"yearOfEvent":null,"venue":"IEEE Trans. Pattern Anal. Mach. Intell.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1109/TPAMI.2024.3411595"],"source":"https://dblp.org/rec/journals/pami/WangLCLTZW25","documentPage":"https://doi.org/10.1109/TPAMI.2024.3411595","type":"Article","doi":"https://doi.org/10.1109/TPAMI.2024.3411595","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/pami/WangLCLTZW25","documentUrl":"https://doi.org/10.1109/TPAMI.2024.3411595"},{"key":"journals/pami/YangWYTCZT25","title":"Language-Aware Vision Transformer for Referring Segmentation.","year":2025,"yearOfEvent":null,"venue":"IEEE Trans. Pattern Anal. Mach. Intell.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1109/TPAMI.2024.3468640"],"source":"https://dblp.org/rec/journals/pami/YangWYTCZT25","documentPage":"https://doi.org/10.1109/TPAMI.2024.3468640","type":"Article","doi":"https://doi.org/10.1109/TPAMI.2024.3468640","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/pami/YangWYTCZT25","documentUrl":"https://doi.org/10.1109/TPAMI.2024.3468640"},{"key":"journals/pami/YangZZ25","title":"UniMatch V2: Pushing the Limit of Semi-Supervised Semantic Segmentation.","year":2025,"yearOfEvent":null,"venue":"IEEE Trans. Pattern Anal. Mach. Intell.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1109/TPAMI.2025.3528453"],"source":"https://dblp.org/rec/journals/pami/YangZZ25","documentPage":"https://doi.org/10.1109/TPAMI.2025.3528453","type":"Article","doi":"https://doi.org/10.1109/TPAMI.2025.3528453","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/pami/YangZZ25","documentUrl":"https://doi.org/10.1109/TPAMI.2025.3528453"},{"key":"journals/pami/ZhuYWHZHZSQHO25","title":"PonderV2: Improved 3D Representation With a Universal Pre-Training Paradigm.","year":2025,"yearOfEvent":null,"venue":"IEEE Trans. Pattern Anal. Mach. Intell.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1109/TPAMI.2025.3561598"],"source":"https://dblp.org/rec/journals/pami/ZhuYWHZHZSQHO25","documentPage":"https://doi.org/10.1109/TPAMI.2025.3561598","type":"Article","doi":"https://doi.org/10.1109/TPAMI.2025.3561598","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/pami/ZhuYWHZHZSQHO25","documentUrl":"https://doi.org/10.1109/TPAMI.2025.3561598"}],"preprints":[{"key":"journals/corr/abs-2501-01427","title":"VideoAnydoor: High-fidelity Video Object Insertion with Precise Motion Control.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2501.01427"],"source":"https://dblp.org/rec/journals/corr/abs-2501-01427","documentPage":"https://doi.org/10.48550/ARXIV.2501.01427","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2501.01427","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2501-01427","documentUrl":"https://doi.org/10.48550/ARXIV.2501.01427","arxivId":"2501.01427","arxivUrl":"https://arxiv.org/abs/2501.01427"},{"key":"journals/corr/abs-2501-01428","title":"GPT4Scene: Understand 3D Scenes from Videos with Vision-Language Models.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2501.01428"],"source":"https://dblp.org/rec/journals/corr/abs-2501-01428","documentPage":"https://doi.org/10.48550/ARXIV.2501.01428","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2501.01428","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2501-01428","documentUrl":"https://doi.org/10.48550/ARXIV.2501.01428","arxivId":"2501.01428","arxivUrl":"https://arxiv.org/abs/2501.01428"},{"key":"journals/corr/abs-2501-02048","title":"DreamMask: Boosting Open-vocabulary Panoptic Segmentation with Synthetic Data.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2501.02048"],"source":"https://dblp.org/rec/journals/corr/abs-2501-02048","documentPage":"https://doi.org/10.48550/ARXIV.2501.02048","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2501.02048","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2501-02048","documentUrl":"https://doi.org/10.48550/ARXIV.2501.02048","arxivId":"2501.02048","arxivUrl":"https://arxiv.org/abs/2501.02048"},{"key":"journals/corr/abs-2501-12382","title":"DiffDoctor: Diagnosing Image Diffusion Models Before Treating.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2501.12382"],"source":"https://dblp.org/rec/journals/corr/abs-2501-12382","documentPage":"https://doi.org/10.48550/ARXIV.2501.12382","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2501.12382","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2501-12382","documentUrl":"https://doi.org/10.48550/ARXIV.2501.12382","arxivId":"2501.12382","arxivUrl":"https://arxiv.org/abs/2501.12382"},{"key":"journals/corr/abs-2501-14729","title":"HERMES: A Unified Self-Driving World Model for Simultaneous 3D Scene Understanding and Generation.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2501.14729"],"source":"https://dblp.org/rec/journals/corr/abs-2501-14729","documentPage":"https://doi.org/10.48550/ARXIV.2501.14729","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2501.14729","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2501-14729","documentUrl":"https://doi.org/10.48550/ARXIV.2501.14729","arxivId":"2501.14729","arxivUrl":"https://arxiv.org/abs/2501.14729"},{"key":"journals/corr/abs-2503-03705","title":"Effective LLM Knowledge Learning via Model Generalization.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2503.03705"],"source":"https://dblp.org/rec/journals/corr/abs-2503-03705","documentPage":"https://doi.org/10.48550/ARXIV.2503.03705","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2503.03705","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-03705","documentUrl":"https://doi.org/10.48550/ARXIV.2503.03705","arxivId":"2503.03705","arxivUrl":"https://arxiv.org/abs/2503.03705"},{"key":"journals/corr/abs-2503-08575","title":"Modular Customization of Diffusion Models via Blockwise-Parameterized Low-Rank Adaptation.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2503.08575"],"source":"https://dblp.org/rec/journals/corr/abs-2503-08575","documentPage":"https://doi.org/10.48550/ARXIV.2503.08575","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2503.08575","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-08575","documentUrl":"https://doi.org/10.48550/ARXIV.2503.08575","arxivId":"2503.08575","arxivUrl":"https://arxiv.org/abs/2503.08575"},{"key":"journals/corr/abs-2503-14694","title":"HaploVL: A Single-Transformer Baseline for Multi-Modal Understanding.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2503.14694"],"source":"https://dblp.org/rec/journals/corr/abs-2503-14694","documentPage":"https://doi.org/10.48550/ARXIV.2503.14694","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2503.14694","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-14694","documentUrl":"https://doi.org/10.48550/ARXIV.2503.14694","arxivId":"2503.14694","arxivUrl":"https://arxiv.org/abs/2503.14694"},{"key":"journals/corr/abs-2503-16429","title":"Sonata: Self-Supervised Learning of Reliable Point Representations.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2503.16429"],"source":"https://dblp.org/rec/journals/corr/abs-2503-16429","documentPage":"https://doi.org/10.48550/ARXIV.2503.16429","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2503.16429","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-16429","documentUrl":"https://doi.org/10.48550/ARXIV.2503.16429","arxivId":"2503.16429","arxivUrl":"https://arxiv.org/abs/2503.16429"},{"key":"journals/corr/abs-2503-23024","title":"Empowering Large Language Models with 3D Situation Awareness.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2503.23024"],"source":"https://dblp.org/rec/journals/corr/abs-2503-23024","documentPage":"https://doi.org/10.48550/ARXIV.2503.23024","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2503.23024","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-23024","documentUrl":"https://doi.org/10.48550/ARXIV.2503.23024","arxivId":"2503.23024","arxivUrl":"https://arxiv.org/abs/2503.23024"},{"key":"journals/corr/abs-2504-01934","title":"ILLUME+: Illuminating Unified MLLM with Dual Visual Tokenization and Diffusion Refinement.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2504.01934"],"source":"https://dblp.org/rec/journals/corr/abs-2504-01934","documentPage":"https://doi.org/10.48550/ARXIV.2504.01934","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2504.01934","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2504-01934","documentUrl":"https://doi.org/10.48550/ARXIV.2504.01934","arxivId":"2504.01934","arxivUrl":"https://arxiv.org/abs/2504.01934"},{"key":"journals/corr/abs-2505-10565","title":"Depth Anything with Any Prior.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2505.10565"],"source":"https://dblp.org/rec/journals/corr/abs-2505-10565","documentPage":"https://doi.org/10.48550/ARXIV.2505.10565","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2505.10565","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-10565","documentUrl":"https://doi.org/10.48550/ARXIV.2505.10565","arxivId":"2505.10565","arxivUrl":"https://arxiv.org/abs/2505.10565"},{"key":"journals/corr/abs-2505-24870","title":"GenSpace: Benchmarking Spatially-Aware Image Generation.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2505.24870"],"source":"https://dblp.org/rec/journals/corr/abs-2505-24870","documentPage":"https://doi.org/10.48550/ARXIV.2505.24870","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2505.24870","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-24870","documentUrl":"https://doi.org/10.48550/ARXIV.2505.24870","arxivId":"2505.24870","arxivUrl":"https://arxiv.org/abs/2505.24870"},{"key":"journals/corr/abs-2506-04228","title":"LayerFlow: A Unified Model for Layer-aware Video Generation.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2506.04228"],"source":"https://dblp.org/rec/journals/corr/abs-2506-04228","documentPage":"https://doi.org/10.48550/ARXIV.2506.04228","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2506.04228","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-04228","documentUrl":"https://doi.org/10.48550/ARXIV.2506.04228","arxivId":"2506.04228","arxivUrl":"https://arxiv.org/abs/2506.04228"},{"key":"journals/corr/abs-2506-09995","title":"PlayerOne: Egocentric World Simulator.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2506.09995"],"source":"https://dblp.org/rec/journals/corr/abs-2506-09995","documentPage":"https://doi.org/10.48550/ARXIV.2506.09995","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2506.09995","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-09995","documentUrl":"https://doi.org/10.48550/ARXIV.2506.09995","arxivId":"2506.09995","arxivUrl":"https://arxiv.org/abs/2506.09995"},{"key":"journals/corr/abs-2506-14574","title":"TGDPO: Harnessing Token-Level Reward Guidance for Enhancing Direct Preference Optimization.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2506.14574"],"source":"https://dblp.org/rec/journals/corr/abs-2506-14574","documentPage":"https://doi.org/10.48550/ARXIV.2506.14574","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2506.14574","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-14574","documentUrl":"https://doi.org/10.48550/ARXIV.2506.14574","arxivId":"2506.14574","arxivUrl":"https://arxiv.org/abs/2506.14574"},{"key":"journals/corr/abs-2506-14686","title":"FocalClick-XL: Towards Unified and High-quality Interactive Segmentation.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2506.14686"],"source":"https://dblp.org/rec/journals/corr/abs-2506-14686","documentPage":"https://doi.org/10.48550/ARXIV.2506.14686","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2506.14686","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-14686","documentUrl":"https://doi.org/10.48550/ARXIV.2506.14686","arxivId":"2506.14686","arxivUrl":"https://arxiv.org/abs/2506.14686"},{"key":"journals/corr/abs-2506-17221","title":"VLN-R1: Vision-Language Navigation via Reinforcement Fine-Tuning.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2506.17221"],"source":"https://dblp.org/rec/journals/corr/abs-2506-17221","documentPage":"https://doi.org/10.48550/ARXIV.2506.17221","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2506.17221","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-17221","documentUrl":"https://doi.org/10.48550/ARXIV.2506.17221","arxivId":"2506.17221","arxivUrl":"https://arxiv.org/abs/2506.17221"},{"key":"journals/corr/abs-2506-22434","title":"MiCo: Multi-image Contrast for Reinforcement Visual Reasoning.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2506.22434"],"source":"https://dblp.org/rec/journals/corr/abs-2506-22434","documentPage":"https://doi.org/10.48550/ARXIV.2506.22434","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2506.22434","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-22434","documentUrl":"https://doi.org/10.48550/ARXIV.2506.22434","arxivId":"2506.22434","arxivUrl":"https://arxiv.org/abs/2506.22434"},{"key":"journals/corr/abs-2507-02299","title":"DreamComposer++: Empowering Diffusion Models with Multi-View Conditions for 3D Content Generation.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2507.02299"],"source":"https://dblp.org/rec/journals/corr/abs-2507-02299","documentPage":"https://doi.org/10.48550/ARXIV.2507.02299","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2507.02299","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2507-02299","documentUrl":"https://doi.org/10.48550/ARXIV.2507.02299","arxivId":"2507.02299","arxivUrl":"https://arxiv.org/abs/2507.02299"},{"key":"journals/corr/abs-2507-02860","title":"Less is Enough: Training-Free Video Diffusion Acceleration via Runtime-Adaptive Caching.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2507.02860"],"source":"https://dblp.org/rec/journals/corr/abs-2507-02860","documentPage":"https://doi.org/10.48550/ARXIV.2507.02860","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2507.02860","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2507-02860","documentUrl":"https://doi.org/10.48550/ARXIV.2507.02860","arxivId":"2507.02860","arxivUrl":"https://arxiv.org/abs/2507.02860"},{"key":"journals/corr/abs-2507-02861","title":"LiteReality: Graphics-Ready 3D Scene Reconstruction from RGB-D Scans.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2507.02861"],"source":"https://dblp.org/rec/journals/corr/abs-2507-02861","documentPage":"https://doi.org/10.48550/ARXIV.2507.02861","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2507.02861","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2507-02861","documentUrl":"https://doi.org/10.48550/ARXIV.2507.02861","arxivId":"2507.02861","arxivUrl":"https://arxiv.org/abs/2507.02861"},{"key":"journals/corr/abs-2507-10302","title":"DisCo: Towards Distinct and Coherent Visual Encapsulation in Video MLLMs.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2507.10302"],"source":"https://dblp.org/rec/journals/corr/abs-2507-10302","documentPage":"https://doi.org/10.48550/ARXIV.2507.10302","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2507.10302","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2507-10302","documentUrl":"https://doi.org/10.48550/ARXIV.2507.10302","arxivId":"2507.10302","arxivUrl":"https://arxiv.org/abs/2507.10302"},{"key":"journals/corr/abs-2507-13348","title":"VisionThink: Smart and Efficient Vision Language Model via Reinforcement Learning.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2507.13348"],"source":"https://dblp.org/rec/journals/corr/abs-2507-13348","documentPage":"https://doi.org/10.48550/ARXIV.2507.13348","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2507.13348","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2507-13348","documentUrl":"https://doi.org/10.48550/ARXIV.2507.13348","arxivId":"2507.13348","arxivUrl":"https://arxiv.org/abs/2507.13348"},{"key":"journals/corr/abs-2508-00350","title":"BOOD: Boundary-based Out-Of-Distribution Data Generation.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2508.00350"],"source":"https://dblp.org/rec/journals/corr/abs-2508-00350","documentPage":"https://doi.org/10.48550/ARXIV.2508.00350","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2508.00350","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-00350","documentUrl":"https://doi.org/10.48550/ARXIV.2508.00350","arxivId":"2508.00350","arxivUrl":"https://arxiv.org/abs/2508.00350"},{"key":"journals/corr/abs-2508-09454","title":"Animate-X++: Universal Character Image Animation with Dynamic Backgrounds.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2508.09454"],"source":"https://dblp.org/rec/journals/corr/abs-2508-09454","documentPage":"https://doi.org/10.48550/ARXIV.2508.09454","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2508.09454","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-09454","documentUrl":"https://doi.org/10.48550/ARXIV.2508.09454","arxivId":"2508.09454","arxivUrl":"https://arxiv.org/abs/2508.09454"},{"key":"journals/corr/abs-2508-11256","title":"Generalized Decoupled Learning for Enhancing Open-Vocabulary Dense Perception.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2508.11256"],"source":"https://dblp.org/rec/journals/corr/abs-2508-11256","documentPage":"https://doi.org/10.48550/ARXIV.2508.11256","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2508.11256","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-11256","documentUrl":"https://doi.org/10.48550/ARXIV.2508.11256","arxivId":"2508.11256","arxivUrl":"https://arxiv.org/abs/2508.11256"},{"key":"journals/corr/abs-2508-14042","title":"Train Once, Deploy Anywhere: Realize Data-Efficient Dynamic Object Manipulation.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2508.14042"],"source":"https://dblp.org/rec/journals/corr/abs-2508-14042","documentPage":"https://doi.org/10.48550/ARXIV.2508.14042","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2508.14042","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-14042","documentUrl":"https://doi.org/10.48550/ARXIV.2508.14042","arxivId":"2508.14042","arxivUrl":"https://arxiv.org/abs/2508.14042"},{"key":"journals/corr/abs-2508-18633","title":"ROSE: Remove Objects with Side Effects in Videos.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2508.18633"],"source":"https://dblp.org/rec/journals/corr/abs-2508-18633","documentPage":"https://doi.org/10.48550/ARXIV.2508.18633","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2508.18633","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-18633","documentUrl":"https://doi.org/10.48550/ARXIV.2508.18633","arxivId":"2508.18633","arxivUrl":"https://arxiv.org/abs/2508.18633"},{"key":"journals/corr/abs-2509-07969","title":"Mini-o3: Scaling Up Reasoning Patterns and Interaction Turns for Visual Search.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2509.07969"],"source":"https://dblp.org/rec/journals/corr/abs-2509-07969","documentPage":"https://doi.org/10.48550/ARXIV.2509.07969","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2509.07969","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-07969","documentUrl":"https://doi.org/10.48550/ARXIV.2509.07969","arxivId":"2509.07969","arxivUrl":"https://arxiv.org/abs/2509.07969"},{"key":"journals/corr/abs-2509-26599","title":"DiffCamera: Arbitrary Refocusing on Images.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2509.26599"],"source":"https://dblp.org/rec/journals/corr/abs-2509-26599","documentPage":"https://doi.org/10.48550/ARXIV.2509.26599","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2509.26599","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-26599","documentUrl":"https://doi.org/10.48550/ARXIV.2509.26599","arxivId":"2509.26599","arxivUrl":"https://arxiv.org/abs/2509.26599"},{"key":"journals/corr/abs-2510-05095","title":"From Noisy Traces to Stable Gradients: Bias-Variance Optimized Preference Optimization for Aligning Large Reasoning Models.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2510.05095"],"source":"https://dblp.org/rec/journals/corr/abs-2510-05095","documentPage":"https://doi.org/10.48550/ARXIV.2510.05095","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2510.05095","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-05095","documentUrl":"https://doi.org/10.48550/ARXIV.2510.05095","arxivId":"2510.05095","arxivUrl":"https://arxiv.org/abs/2510.05095"},{"key":"journals/corr/abs-2510-06214","title":"Stratified GRPO: Handling Structural Heterogeneity in Reinforcement Learning of LLM Search Agents.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2510.06214"],"source":"https://dblp.org/rec/journals/corr/abs-2510-06214","documentPage":"https://doi.org/10.48550/ARXIV.2510.06214","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2510.06214","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-06214","documentUrl":"https://doi.org/10.48550/ARXIV.2510.06214","arxivId":"2510.06214","arxivUrl":"https://arxiv.org/abs/2510.06214"},{"key":"journals/corr/abs-2510-13809","title":"PhysMaster: Mastering Physical Representation for Video Generation via Reinforcement Learning.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2510.13809"],"source":"https://dblp.org/rec/journals/corr/abs-2510-13809","documentPage":"https://doi.org/10.48550/ARXIV.2510.13809","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2510.13809","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-13809","documentUrl":"https://doi.org/10.48550/ARXIV.2510.13809","arxivId":"2510.13809","arxivUrl":"https://arxiv.org/abs/2510.13809"},{"key":"journals/corr/abs-2510-23607","title":"Concerto: Joint 2D-3D Self-Supervised Learning Emerges Spatial Representations.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2510.23607"],"source":"https://dblp.org/rec/journals/corr/abs-2510-23607","documentPage":"https://doi.org/10.48550/ARXIV.2510.23607","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2510.23607","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-23607","documentUrl":"https://doi.org/10.48550/ARXIV.2510.23607","arxivId":"2510.23607","arxivUrl":"https://arxiv.org/abs/2510.23607"},{"key":"journals/corr/abs-2511-01768","title":"UniLION: Towards Unified Autonomous Driving Model with Linear Group RNNs.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2511.01768"],"source":"https://dblp.org/rec/journals/corr/abs-2511-01768","documentPage":"https://doi.org/10.48550/ARXIV.2511.01768","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2511.01768","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2511-01768","documentUrl":"https://doi.org/10.48550/ARXIV.2511.01768","arxivId":"2511.01768","arxivUrl":"https://arxiv.org/abs/2511.01768"},{"key":"journals/corr/abs-2511-05491","title":"Visual Spatial Tuning.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2511.05491"],"source":"https://dblp.org/rec/journals/corr/abs-2511-05491","documentPage":"https://doi.org/10.48550/ARXIV.2511.05491","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2511.05491","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2511-05491","documentUrl":"https://doi.org/10.48550/ARXIV.2511.05491","arxivId":"2511.05491","arxivUrl":"https://arxiv.org/abs/2511.05491"},{"key":"journals/corr/abs-2511-12594","title":"Seg-VAR: Image Segmentation with Visual Autoregressive Modeling.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2511.12594"],"source":"https://dblp.org/rec/journals/corr/abs-2511-12594","documentPage":"https://doi.org/10.48550/ARXIV.2511.12594","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2511.12594","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2511-12594","documentUrl":"https://doi.org/10.48550/ARXIV.2511.12594","arxivId":"2511.12594","arxivUrl":"https://arxiv.org/abs/2511.12594"},{"key":"journals/corr/abs-2512-08765","title":"Wan-Move: Motion-controllable Video Generation via Latent Trajectory Guidance.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2512.08765"],"source":"https://dblp.org/rec/journals/corr/abs-2512-08765","documentPage":"https://doi.org/10.48550/ARXIV.2512.08765","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2512.08765","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-08765","documentUrl":"https://doi.org/10.48550/ARXIV.2512.08765","arxivId":"2512.08765","arxivUrl":"https://arxiv.org/abs/2512.08765"},{"key":"journals/corr/abs-2512-12751","title":"GenieDrive: Towards Physics-Aware Driving World Model with 4D Occupancy Guided Video Generation.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2512.12751"],"source":"https://dblp.org/rec/journals/corr/abs-2512-12751","documentPage":"https://doi.org/10.48550/ARXIV.2512.12751","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2512.12751","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-12751","documentUrl":"https://doi.org/10.48550/ARXIV.2512.12751","arxivId":"2512.12751","arxivUrl":"https://arxiv.org/abs/2512.12751"},{"key":"journals/corr/abs-2512-12799","title":"DrivePI: Spatial-aware 4D MLLM for Unified Autonomous Driving Understanding, Perception, Prediction and Planning.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2512.12799"],"source":"https://dblp.org/rec/journals/corr/abs-2512-12799","documentPage":"https://doi.org/10.48550/ARXIV.2512.12799","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2512.12799","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-12799","documentUrl":"https://doi.org/10.48550/ARXIV.2512.12799","arxivId":"2512.12799","arxivUrl":"https://arxiv.org/abs/2512.12799"},{"key":"journals/corr/abs-2512-14699","title":"MemFlow: Flowing Adaptive Memory for Consistent and Efficient Long Video Narratives.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2512.14699"],"source":"https://dblp.org/rec/journals/corr/abs-2512-14699","documentPage":"https://doi.org/10.48550/ARXIV.2512.14699","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2512.14699","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-14699","documentUrl":"https://doi.org/10.48550/ARXIV.2512.14699","arxivId":"2512.14699","arxivUrl":"https://arxiv.org/abs/2512.14699"},{"key":"journals/corr/abs-2512-15715","title":"In Pursuit of Pixel Supervision for Visual Pre-training.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2512.15715"],"source":"https://dblp.org/rec/journals/corr/abs-2512-15715","documentPage":"https://doi.org/10.48550/ARXIV.2512.15715","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2512.15715","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-15715","documentUrl":"https://doi.org/10.48550/ARXIV.2512.15715","arxivId":"2512.15715","arxivUrl":"https://arxiv.org/abs/2512.15715"},{"key":"journals/corr/abs-2512-16905","title":"Alchemist: Unlocking Efficiency in Text-to-Image Model Training via Meta-Gradient Data Selection.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2512.16905"],"source":"https://dblp.org/rec/journals/corr/abs-2512-16905","documentPage":"https://doi.org/10.48550/ARXIV.2512.16905","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2512.16905","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-16905","documentUrl":"https://doi.org/10.48550/ARXIV.2512.16905","arxivId":"2512.16905","arxivUrl":"https://arxiv.org/abs/2512.16905"}],"excludedFormal":[{"key":"journals/tcsv/WangZWYC25","title":"Guest Editorial Introduction to the Special Issue on Segment Anything for Videos and Beyond.","year":2025,"yearOfEvent":null,"venue":"IEEE Trans. Circuits Syst. Video Technol.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1109/TCSVT.2025.3551468"],"source":"https://dblp.org/rec/journals/tcsv/WangZWYC25","documentPage":"https://doi.org/10.1109/TCSVT.2025.3551468","type":"Article","doi":"https://doi.org/10.1109/TCSVT.2025.3551468","exclusionReason":"Explicit editorial, correction, erratum or preface; excluded from research-paper count.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/tcsv/WangZWYC25","documentUrl":"https://doi.org/10.1109/TCSVT.2025.3551468"}],"excludedOther":[],"excludedHomonyms":[],"unassignedCandidates":[],"retrievedAt":"2026-10-19","querySource":"https://sparql.dblp.org/","method":"DBLP yearOfPublication=2025; Article + Inproceedings; excludes Informal/CoRR and explicit editorial/correction/erratum/preface; unique DBLP record keys within person.","labName":"Super Artificial Intelligence Lab（SAIL）","labUrl":"https://sail.ai.hku.hk","labEvidence":"本人香港大学主页明确称其领导 Super Artificial Intelligence Lab（SAIL），该名称直接链接 sail.ai.hku.hk。","labSourceUrl":"https://i.cs.hku.hk/~hszhao/","affiliationZh":"香港大学","sourceWarning":false,"knownPreprintMinimum2025":null,"excludedMisattributed":[],"displayNotes":"身份已经个人或机构主页核对。2025 年正式记录 49 条（会议 43、期刊 6），所有作者位置均计入，不表示主导或贡献份额；预印本 44 条单列，不加总。","labDisplayNotes":"港大的本人主页写明其领导 Super Artificial Intelligence Lab（SAIL），并直接链接，据此归组；它与中山大学郭裕兰的 SAIL 是不同实验室。"},{"index":114,"name":"Qian Zheng","nameZh":"郑乾","affiliation":"Zhejiang University","source":"DBLP Knowledge Graph official SPARQL API","profileUrl":"https://dblp.org/pid/28/8138","identifier":"28/8138","identityEvidence":[{"url":"https://q-zh.github.io/","evidence":"Personal website identifies 郑乾, Zhejiang Computer Science, previous ROSE Lab NTU; confirmed 2025 papers matched by full titles. DBLP PID 28/8138 is a disambiguation page containing medical and other homonyms."}],"count2025":null,"conference2025":null,"journal2025":null,"preprint2025":null,"status":"partial_identity_review","notes":"Counts are DBLP indexed coauthored records, not first-author counts, laboratory totals, unique scientific discoveries, or quality assessments. DBLP yearOfPublication=2025; yearOfEvent retained and can differ. Conference workshops are included. Preprints are separate and may overlap formal versions. Mixed / unassigned DBLP profile. Main counts withheld pending review of every remaining candidate; retained papers establish a verified lower bound only. Do not present this lower bound as an exact annual total.","papers":[{"key":"conf/aaai/ChenLMTZ025","title":"EvHDR-NeRF: Building High Dynamic Range Radiance Fields with Single Exposure Images and Events.","year":2025,"yearOfEvent":2025,"venue":"AAAI","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1609/AAAI.V39I3.32238"],"source":"https://dblp.org/rec/conf/aaai/ChenLMTZ025","documentPage":"https://doi.org/10.1609/AAAI.V39I3.32238","type":"Inproceedings","doi":"https://doi.org/10.1609/AAAI.V39I3.32238","authorSignatures":[{}],"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/aaai/ChenLMTZ025","documentUrl":"https://doi.org/10.1609/AAAI.V39I3.32238"},{"key":"conf/aaai/YanLCMTZ025","title":"EvSTVSR: Event Guided Space-Time Video Super-Resolution.","year":2025,"yearOfEvent":2025,"venue":"AAAI","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1609/AAAI.V39I9.32983"],"source":"https://dblp.org/rec/conf/aaai/YanLCMTZ025","documentPage":"https://doi.org/10.1609/AAAI.V39I9.32983","type":"Inproceedings","doi":"https://doi.org/10.1609/AAAI.V39I9.32983","authorSignatures":[{}],"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/aaai/YanLCMTZ025","documentUrl":"https://doi.org/10.1609/AAAI.V39I9.32983"},{"key":"conf/iccv/LiuCYMTZP25","title":"E-NeMF: Event-based Neural Motion Field for Novel Space-time View Synthesis of Dynamic Scenes.","year":2025,"yearOfEvent":2025,"venue":"ICCV","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/ICCV51701.2025.01010"],"source":"https://dblp.org/rec/conf/iccv/LiuCYMTZP25","documentPage":"https://doi.org/10.1109/ICCV51701.2025.01010","type":"Inproceedings","doi":"https://doi.org/10.1109/ICCV51701.2025.01010","authorSignatures":[{"inst":"https://dblp.org/inst/1/584","instLabel":"Zhejiang University (ZJU)"},{"inst":"https://dblp.org/inst/7/744","instLabel":"Zhejiang University of Science and Technology (ZUST)"}],"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/LiuCYMTZP25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.01010"},{"key":"conf/icml/YanWMTZ025","title":"Training High Performance Spiking Neural Network by Temporal Model Calibration.","year":2025,"yearOfEvent":2025,"venue":"ICML","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/icml/YanWMTZ025","documentPage":"https://proceedings.mlr.press/v267/yan25c.html","type":"Inproceedings","doi":null,"authorSignatures":[{}],"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/icml/YanWMTZ025","documentUrl":"https://proceedings.mlr.press/v267/yan25c.html"}],"preprints":[],"excludedFormal":[],"excludedOther":[],"excludedHomonyms":[],"unassignedCandidates":[{"key":"conf/aaai/ChenLMT0Z025","title":"EvHDR-GS: Event-guided HDR Video Reconstruction with 3D Gaussian Splatting.","year":2025,"yearOfEvent":2025,"venue":"AAAI","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1609/AAAI.V39I3.32237"],"source":"https://dblp.org/rec/conf/aaai/ChenLMT0Z025","documentPage":"https://doi.org/10.1609/AAAI.V39I3.32237","type":"Inproceedings","doi":"https://doi.org/10.1609/AAAI.V39I3.32237","authorSignatures":[{}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/aaai/ChenLMT0Z025","documentUrl":"https://doi.org/10.1609/AAAI.V39I3.32237"},{"key":"conf/eccv/LiHZJ24","title":"Connecting Consistency Distillation to Score Distillation for Text-to-3D Generation.","year":2025,"yearOfEvent":2024,"venue":"ECCV (43)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1007/978-3-031-72775-7_16"],"source":"https://dblp.org/rec/conf/eccv/LiHZJ24","documentPage":"https://doi.org/10.1007/978-3-031-72775-7_16","type":"Inproceedings","doi":"https://doi.org/10.1007/978-3-031-72775-7_16","authorSignatures":[{"orcid":"https://orcid.org/0000-0003-3968-3622","inst":"https://dblp.org/inst/1/584","instLabel":"Zhejiang University (ZJU)"}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/eccv/LiHZJ24","documentUrl":"https://doi.org/10.1007/978-3-031-72775-7_16"},{"key":"conf/iccv/ShouWSZPC25","title":"Unsupervised Rgb-D Point Cloud Registration for Scenes With Low Overlap and Photometric Inconsistency.","year":2025,"yearOfEvent":2025,"venue":"ICCV","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/ICCV51701.2025.02306"],"source":"https://dblp.org/rec/conf/iccv/ShouWSZPC25","documentPage":"https://doi.org/10.1109/ICCV51701.2025.02306","type":"Inproceedings","doi":"https://doi.org/10.1109/ICCV51701.2025.02306","authorSignatures":[{"inst":"https://dblp.org/inst/1/584","instLabel":"Zhejiang University (ZJU)"},{"inst":"https://dblp.org/inst/7/744","instLabel":"Zhejiang University of Science and Technology (ZUST)"}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/ShouWSZPC25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.02306"},{"key":"conf/iclr/DaiC0Z025","title":"Mitigating Reward Over-Optimization in RLHF via Behavior-Supported Regularization.","year":2025,"yearOfEvent":2025,"venue":"ICLR","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/iclr/DaiC0Z025","documentPage":"https://openreview.net/forum?id=PNMv4r7s1i","type":"Inproceedings","doi":null,"authorSignatures":[{}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iclr/DaiC0Z025","documentUrl":"https://openreview.net/forum?id=PNMv4r7s1i"},{"key":"conf/icmcs/WangYZLYZM25","title":"Pixel-wise Single Image Reflection Removal Method Based on Reinforcement Learning.","year":2025,"yearOfEvent":2025,"venue":"ICME","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/ICME59968.2025.11210152"],"source":"https://dblp.org/rec/conf/icmcs/WangYZLYZM25","documentPage":"https://doi.org/10.1109/ICME59968.2025.11210152","type":"Inproceedings","doi":"https://doi.org/10.1109/ICME59968.2025.11210152","authorSignatures":[{"inst":"https://dblp.org/inst/1/584","instLabel":"Zhejiang University (ZJU)"}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/icmcs/WangYZLYZM25","documentUrl":"https://doi.org/10.1109/ICME59968.2025.11210152"},{"key":"conf/ijcai/LuCLMTZ025","title":"EDyGS: Event Enhanced Dynamic 3D Radiance Fields from Blurry Monocular Video.","year":2025,"yearOfEvent":2025,"venue":"IJCAI","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.24963/IJCAI.2025/188"],"source":"https://dblp.org/rec/conf/ijcai/LuCLMTZ025","documentPage":"https://doi.org/10.24963/IJCAI.2025/188","type":"Inproceedings","doi":"https://doi.org/10.24963/IJCAI.2025/188","authorSignatures":[{"inst":"https://dblp.org/inst/1/584","instLabel":"Zhejiang University (ZJU)"}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/ijcai/LuCLMTZ025","documentUrl":"https://doi.org/10.24963/IJCAI.2025/188"},{"key":"conf/iscas/LiGYZJLK25","title":"HRHuman: Tuning-Free Higher-Resolution Human Image Generation via Template Knowledge.","year":2025,"yearOfEvent":2025,"venue":"ISCAS","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/ISCAS56072.2025.11043860"],"source":"https://dblp.org/rec/conf/iscas/LiGYZJLK25","documentPage":"https://doi.org/10.1109/ISCAS56072.2025.11043860","type":"Inproceedings","doi":"https://doi.org/10.1109/ISCAS56072.2025.11043860","authorSignatures":[{"inst":"https://dblp.org/inst/1/584","instLabel":"Zhejiang University (ZJU)"},{"inst":"https://dblp.org/inst/7/744","instLabel":"Zhejiang University of Science and Technology (ZUST)"}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iscas/LiGYZJLK25","documentUrl":"https://doi.org/10.1109/ISCAS56072.2025.11043860"},{"key":"conf/nips/ZhouXPZYLYPCWWZ25","title":"Neural-Driven Image Editing.","year":2025,"yearOfEvent":2025,"venue":"NeurIPS","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/nips/ZhouXPZYLYPCWWZ25","documentPage":"http://papers.nips.cc/paper_files/paper/2025/hash/9138f908b3cfe807ee3288dbfd1156d3-Abstract-Conference.html","type":"Inproceedings","doi":null,"authorSignatures":[{}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/nips/ZhouXPZYLYPCWWZ25","documentUrl":"http://papers.nips.cc/paper_files/paper/2025/hash/9138f908b3cfe807ee3288dbfd1156d3-Abstract-Conference.html"},{"key":"journals/cbm/ChenLZ25","title":"A dataset of microscopic spirometra mansoni for medical image segmentation.","year":2025,"yearOfEvent":null,"venue":"Comput. Biol. Medicine","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1016/J.COMPBIOMED.2025.110661"],"source":"https://dblp.org/rec/journals/cbm/ChenLZ25","documentPage":"https://doi.org/10.1016/J.COMPBIOMED.2025.110661","type":"Article","doi":"https://doi.org/10.1016/J.COMPBIOMED.2025.110661","authorSignatures":[{}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/cbm/ChenLZ25","documentUrl":"https://doi.org/10.1016/J.COMPBIOMED.2025.110661"},{"key":"journals/corr/abs-2503-18130","title":"Mitigating Reward Over-Optimization in RLHF via Behavior-Supported Regularization.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2503.18130"],"source":"https://dblp.org/rec/journals/corr/abs-2503-18130","documentPage":"https://doi.org/10.48550/ARXIV.2503.18130","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2503.18130","authorSignatures":[{}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-18130","documentUrl":"https://doi.org/10.48550/ARXIV.2503.18130"},{"key":"journals/corr/abs-2505-05530","title":"Low-bit Model Quantization for Deep Neural Networks: A Survey.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2505.05530"],"source":"https://dblp.org/rec/journals/corr/abs-2505-05530","documentPage":"https://doi.org/10.48550/ARXIV.2505.05530","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2505.05530","authorSignatures":[{}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-05530","documentUrl":"https://doi.org/10.48550/ARXIV.2505.05530"},{"key":"journals/corr/abs-2505-13300","title":"DD-Ranking: Rethinking the Evaluation of Dataset Distillation.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2505.13300"],"source":"https://dblp.org/rec/journals/corr/abs-2505-13300","documentPage":"https://doi.org/10.48550/ARXIV.2505.13300","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2505.13300","authorSignatures":[{}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-13300","documentUrl":"https://doi.org/10.48550/ARXIV.2505.13300"},{"key":"journals/corr/abs-2507-05397","title":"Neural-Driven Image Editing.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2507.05397"],"source":"https://dblp.org/rec/journals/corr/abs-2507-05397","documentPage":"https://doi.org/10.48550/ARXIV.2507.05397","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2507.05397","authorSignatures":[{}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2507-05397","documentUrl":"https://doi.org/10.48550/ARXIV.2507.05397"},{"key":"journals/corr/abs-2509-16213","title":"DarwinWafer: A Wafer-Scale Neuromorphic Chip.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2509.16213"],"source":"https://dblp.org/rec/journals/corr/abs-2509-16213","documentPage":"https://doi.org/10.48550/ARXIV.2509.16213","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2509.16213","authorSignatures":[{}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-16213","documentUrl":"https://doi.org/10.48550/ARXIV.2509.16213"},{"key":"journals/fgcs/ZhengCWLPY25","title":"An accurate and efficient self-distillation method with channel-based feature enhancement via feature calibration and attention fusion for Internet of Things.","year":2025,"yearOfEvent":null,"venue":"Future Gener. Comput. Syst.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1016/J.FUTURE.2025.107816"],"source":"https://dblp.org/rec/journals/fgcs/ZhengCWLPY25","documentPage":"https://doi.org/10.1016/J.FUTURE.2025.107816","type":"Article","doi":"https://doi.org/10.1016/J.FUTURE.2025.107816","authorSignatures":[{"inst":"https://dblp.org/inst/3/487","instLabel":"Henan University"}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/fgcs/ZhengCWLPY25","documentUrl":"https://doi.org/10.1016/J.FUTURE.2025.107816"},{"key":"journals/ijmi/MoXJZZ25","title":"Predicting abnormal C-reactive protein level for improving utilization by deep neural network model.","year":2025,"yearOfEvent":null,"venue":"Int. J. Medical Informatics","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1016/J.IJMEDINF.2024.105726"],"source":"https://dblp.org/rec/journals/ijmi/MoXJZZ25","documentPage":"https://doi.org/10.1016/J.IJMEDINF.2024.105726","type":"Article","doi":"https://doi.org/10.1016/J.IJMEDINF.2024.105726","authorSignatures":[{"orcid":"https://orcid.org/0009-0003-7849-256X","inst":"https://dblp.org/inst/1/953","instLabel":"Sun Yat-sen University"}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/ijmi/MoXJZZ25","documentUrl":"https://doi.org/10.1016/J.IJMEDINF.2024.105726"},{"key":"journals/pami/WeiLDSJPCZ25","title":"Revisiting Supervised Learning-Based Photometric Stereo Networks.","year":2025,"yearOfEvent":null,"venue":"IEEE Trans. Pattern Anal. Mach. Intell.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1109/TPAMI.2025.3557498"],"source":"https://dblp.org/rec/journals/pami/WeiLDSJPCZ25","documentPage":"https://doi.org/10.1109/TPAMI.2025.3557498","type":"Article","doi":"https://doi.org/10.1109/TPAMI.2025.3557498","authorSignatures":[{"orcid":"https://orcid.org/0000-0003-3968-3622","inst":"https://dblp.org/inst/1/584","instLabel":"Zhejiang University (ZJU)"},{"orcid":"https://orcid.org/0000-0003-3968-3622","inst":"https://dblp.org/inst/7/744","instLabel":"Zhejiang University of Science and Technology (ZUST)"}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/pami/WeiLDSJPCZ25","documentUrl":"https://doi.org/10.1109/TPAMI.2025.3557498"},{"key":"journals/peerj-cs/ZhaoZZJ25","title":"A hybrid deep learning framework for skin disease localization and classification using wearable sensors.","year":2025,"yearOfEvent":null,"venue":"PeerJ Comput. Sci.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.7717/PEERJ-CS.3002"],"source":"https://dblp.org/rec/journals/peerj-cs/ZhaoZZJ25","documentPage":"https://doi.org/10.7717/PEERJ-CS.3002","type":"Article","doi":"https://doi.org/10.7717/PEERJ-CS.3002","authorSignatures":[{}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/peerj-cs/ZhaoZZJ25","documentUrl":"https://doi.org/10.7717/PEERJ-CS.3002"},{"key":"journals/ral/ShouWWZLXPC25","title":"Point Cloud Registration Based on Adaptively Fused Multimodal Features.","year":2025,"yearOfEvent":null,"venue":"IEEE Robotics Autom. Lett.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1109/LRA.2025.3580326"],"source":"https://dblp.org/rec/journals/ral/ShouWWZLXPC25","documentPage":"https://doi.org/10.1109/LRA.2025.3580326","type":"Article","doi":"https://doi.org/10.1109/LRA.2025.3580326","authorSignatures":[{"orcid":"https://orcid.org/0000-0003-3968-3622","inst":"https://dblp.org/inst/1/584","instLabel":"Zhejiang University (ZJU)"},{"orcid":"https://orcid.org/0000-0003-3968-3622","inst":"https://dblp.org/inst/7/744","instLabel":"Zhejiang University of Science and Technology (ZUST)"}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/ral/ShouWWZLXPC25","documentUrl":"https://doi.org/10.1109/LRA.2025.3580326"},{"key":"journals/tbe/ZhengHLSLLJT25","title":"Quantitative Ultrasonic Backscatter Evaluation of Elastic and Mechanical Property in a Rabbit Tendinopathy Healing Model.","year":2025,"yearOfEvent":null,"venue":"IEEE Trans. Biomed. Eng.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1109/TBME.2025.3544327"],"source":"https://dblp.org/rec/journals/tbe/ZhengHLSLLJT25","documentPage":"https://doi.org/10.1109/TBME.2025.3544327","type":"Article","doi":"https://doi.org/10.1109/TBME.2025.3544327","authorSignatures":[{"orcid":"https://orcid.org/0000-0003-3701-2657","inst":"https://dblp.org/inst/1/156","instLabel":"Fudan University"}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/tbe/ZhengHLSLLJT25","documentUrl":"https://doi.org/10.1109/TBME.2025.3544327"},{"key":"journals/tcsv/MengHLYPZ25","title":"LAC-PS: A Light Direction Selection Policy Under the Accuracy Constraint for Photometric Stereo.","year":2025,"yearOfEvent":null,"venue":"IEEE Trans. Circuits Syst. Video Technol.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1109/TCSVT.2025.3579572"],"source":"https://dblp.org/rec/journals/tcsv/MengHLYPZ25","documentPage":"https://doi.org/10.1109/TCSVT.2025.3579572","type":"Article","doi":"https://doi.org/10.1109/TCSVT.2025.3579572","authorSignatures":[{"orcid":"https://orcid.org/0000-0003-3968-3622","inst":"https://dblp.org/inst/1/584","instLabel":"Zhejiang University (ZJU)"},{"orcid":"https://orcid.org/0000-0003-3968-3622","inst":"https://dblp.org/inst/7/744","instLabel":"Zhejiang University of Science and Technology (ZUST)"}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/tcsv/MengHLYPZ25","documentUrl":"https://doi.org/10.1109/TCSVT.2025.3579572"},{"key":"journals/tnn/MengZYYP25","title":"Off-OAB: Off-Policy Policy Gradient Method With Optimal Action-Dependent Baseline.","year":2025,"yearOfEvent":null,"venue":"IEEE Trans. Neural Networks Learn. Syst.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1109/TNNLS.2025.3588881"],"source":"https://dblp.org/rec/journals/tnn/MengZYYP25","documentPage":"https://doi.org/10.1109/TNNLS.2025.3588881","type":"Article","doi":"https://doi.org/10.1109/TNNLS.2025.3588881","authorSignatures":[{"orcid":"https://orcid.org/0000-0003-3968-3622","inst":"https://dblp.org/inst/1/584","instLabel":"Zhejiang University (ZJU)"}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/tnn/MengZYYP25","documentUrl":"https://doi.org/10.1109/TNNLS.2025.3588881"}],"retrievedAt":"2026-10-19","querySource":"https://sparql.dblp.org/","method":"DBLP yearOfPublication=2025; Article + Inproceedings; excludes Informal/CoRR and explicit editorial/correction/erratum/preface; unique DBLP record keys within person.","verifiedLowerBound2025":4,"conferenceLowerBound2025":4,"journalLowerBound2025":0,"labName":"脑机智能实验室","labUrl":null,"labEvidence":"浙江大学计算机学院官方科研团队介绍表明确将郑乾及其本人邮箱列入脑机智能实验室，由潘纲任团队负责人。仅以官方表的团队现称标记，不从旧NTU ROSE经历推定当前组。该PDF的搜索索引正文已缓存，直接打开出现502。","labSourceUrl":"https://www.cs.zju.edu.cn/_upload/article/files/d4/45/e46a2ca6469693738d84d1fffc3f/e3880619-c941-4906-a16a-a70e5a4ddc5e.pdf","affiliationZh":"浙江大学","sourceWarning":false,"knownPreprintMinimum2025":null,"excludedMisattributed":[],"knownMinimum2025":4,"displayNotes":"该 DBLP 档案混有其他同名作者，剩余候选尚未逐篇核完，全年总数暂不给出。目前已逐篇核实 4 条，只作下界参考，不进入合计、中位数或排序。","labDisplayNotes":"浙大计算机学院官方科研团队表将其姓名与本人邮箱列入脑机智能实验室，团队负责人为潘纲，据此归组。这是成员关系；论文数仍为空缺，不画柱。"},{"index":115,"name":"Weishi Zheng","nameZh":"郑伟诗","affiliation":"Sun Yat-sen University","source":"DBLP Knowledge Graph official SPARQL API","profileUrl":"https://dblp.org/pid/30/8399","identifier":"30/8399","identityEvidence":[{"url":"https://dblp.org/pid/30/8399","evidence":"DBLP curated profile affiliations: Queen Mary University of London, Department of Computer Science; Sun Yat-sen University, School of Information Science and Technology."},{"url":"https://dblp.org/pid/30/8399","evidence":"DBLP curated profile homepages: http://sist.sysu.edu.cn/~zhwshi/; http://www.eecs.qmul.ac.uk/~jason/."}],"count2025":66,"conference2025":46,"journal2025":20,"preprint2025":45,"status":"verified","notes":"Counts are DBLP indexed coauthored records, not first-author counts, laboratory totals, unique scientific discoveries, or quality assessments. DBLP yearOfPublication=2025; yearOfEvent retained and can differ. Conference workshops are included. Preprints are separate and may overlap formal versions.","papers":[{"key":"conf/aaai/GuQTW025","title":"MaintaAvatar: A Maintainable Avatar Based on Neural Radiance Fields by Continual Learning.","year":2025,"yearOfEvent":2025,"venue":"AAAI","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1609/AAAI.V39I3.32327"],"source":"https://dblp.org/rec/conf/aaai/GuQTW025","documentPage":"https://doi.org/10.1609/AAAI.V39I3.32327","type":"Inproceedings","doi":"https://doi.org/10.1609/AAAI.V39I3.32327","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/aaai/GuQTW025","documentUrl":"https://doi.org/10.1609/AAAI.V39I3.32327"},{"key":"conf/aaai/Huang0H025","title":"CLIP-RestoreX: Restore Image Structure and Perception in Exposure Correction.","year":2025,"yearOfEvent":2025,"venue":"AAAI","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1609/AAAI.V39I4.32392"],"source":"https://dblp.org/rec/conf/aaai/Huang0H025","documentPage":"https://doi.org/10.1609/AAAI.V39I4.32392","type":"Inproceedings","doi":"https://doi.org/10.1609/AAAI.V39I4.32392","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/aaai/Huang0H025","documentUrl":"https://doi.org/10.1609/AAAI.V39I4.32392"},{"key":"conf/aaai/WangSSLFTLTH025","title":"ParGo: Bridging Vision-Language with Partial and Global Views.","year":2025,"yearOfEvent":2025,"venue":"AAAI","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1609/AAAI.V39I7.32806"],"source":"https://dblp.org/rec/conf/aaai/WangSSLFTLTH025","documentPage":"https://doi.org/10.1609/AAAI.V39I7.32806","type":"Inproceedings","doi":"https://doi.org/10.1609/AAAI.V39I7.32806","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/aaai/WangSSLFTLTH025","documentUrl":"https://doi.org/10.1609/AAAI.V39I7.32806"},{"key":"conf/aaai/ZengHW025","title":"Light-T2M: A Lightweight and Fast Model for Text-to-motion Generation.","year":2025,"yearOfEvent":2025,"venue":"AAAI","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1609/AAAI.V39I9.33062"],"source":"https://dblp.org/rec/conf/aaai/ZengHW025","documentPage":"https://doi.org/10.1609/AAAI.V39I9.33062","type":"Inproceedings","doi":"https://doi.org/10.1609/AAAI.V39I9.33062","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/aaai/ZengHW025","documentUrl":"https://doi.org/10.1609/AAAI.V39I9.33062"},{"key":"conf/aaai/Zheng0N025","title":"When Shadow Removal Meets Intrinsic Image Decomposition: A Joint Learning Framework Using Unpaired Data.","year":2025,"yearOfEvent":2025,"venue":"AAAI","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1609/AAAI.V39I10.33151"],"source":"https://dblp.org/rec/conf/aaai/Zheng0N025","documentPage":"https://doi.org/10.1609/AAAI.V39I10.33151","type":"Inproceedings","doi":"https://doi.org/10.1609/AAAI.V39I10.33151","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/aaai/Zheng0N025","documentUrl":"https://doi.org/10.1609/AAAI.V39I10.33151"},{"key":"conf/acl/LiuWWCL025","title":"Chain of Methodologies: Scaling Test Time Computation without Training.","year":2025,"yearOfEvent":2025,"venue":"ACL (Findings)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.18653/V1/2025.FINDINGS-ACL.276"],"source":"https://dblp.org/rec/conf/acl/LiuWWCL025","documentPage":"https://doi.org/10.18653/V1/2025.FINDINGS-ACL.276","type":"Inproceedings","doi":"https://doi.org/10.18653/V1/2025.FINDINGS-ACL.276","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/acl/LiuWWCL025","documentUrl":"https://doi.org/10.18653/V1/2025.FINDINGS-ACL.276"},{"key":"conf/bibm/ZhouYZZW25","title":"Textual Prototype-Guided Continual Learning for Medical Image Classification.","year":2025,"yearOfEvent":2025,"venue":"BIBM","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/BIBM66473.2025.11356104"],"source":"https://dblp.org/rec/conf/bibm/ZhouYZZW25","documentPage":"https://doi.org/10.1109/BIBM66473.2025.11356104","type":"Inproceedings","doi":"https://doi.org/10.1109/BIBM66473.2025.11356104","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/bibm/ZhouYZZW25","documentUrl":"https://doi.org/10.1109/BIBM66473.2025.11356104"},{"key":"conf/cvpr/FuYMYWMX025","title":"LLMDet: Learning Strong Open-Vocabulary Object Detectors under the Supervision of Large Language Models.","year":2025,"yearOfEvent":2025,"venue":"CVPR","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/CVPR52734.2025.01396"],"source":"https://dblp.org/rec/conf/cvpr/FuYMYWMX025","documentPage":"https://openaccess.thecvf.com/content/CVPR2025/html/Fu_LLMDet_Learning_Strong_Open-Vocabulary_Object_Detectors_under_the_Supervision_of_CVPR_2025_paper.html","type":"Inproceedings","doi":"https://doi.org/10.1109/CVPR52734.2025.01396","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/FuYMYWMX025","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Fu_LLMDet_Learning_Strong_Open-Vocabulary_Object_Detectors_under_the_Supervision_of_CVPR_2025_paper.html"},{"key":"conf/cvpr/HuangLXTLH025","title":"Modeling Multiple Normal Action Representations for Error Detection in Procedural Tasks.","year":2025,"yearOfEvent":2025,"venue":"CVPR","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/CVPR52734.2025.02588"],"source":"https://dblp.org/rec/conf/cvpr/HuangLXTLH025","documentPage":"https://openaccess.thecvf.com/content/CVPR2025/html/Huang_Modeling_Multiple_Normal_Action_Representations_for_Error_Detection_in_Procedural_CVPR_2025_paper.html","type":"Inproceedings","doi":"https://doi.org/10.1109/CVPR52734.2025.02588","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/HuangLXTLH025","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Huang_Modeling_Multiple_Normal_Action_Representations_for_Error_Detection_in_Procedural_CVPR_2025_paper.html"},{"key":"conf/cvpr/PengTLYMW025","title":"Person De-reidentification: A Variation-guided Identity Shift Modeling.","year":2025,"yearOfEvent":2025,"venue":"CVPR","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/CVPR52734.2025.02731"],"source":"https://dblp.org/rec/conf/cvpr/PengTLYMW025","documentPage":"https://openaccess.thecvf.com/content/CVPR2025/html/Peng_Person_De-reidentification_A_Variation-guided_Identity_Shift_Modeling_CVPR_2025_paper.html","type":"Inproceedings","doi":"https://doi.org/10.1109/CVPR52734.2025.02731","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/PengTLYMW025","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Peng_Person_De-reidentification_A_Variation-guided_Identity_Shift_Modeling_CVPR_2025_paper.html"},{"key":"conf/cvpr/Xiao0N0025","title":"RoGSplat: Learning Robust Generalizable Human Gaussian Splatting from Sparse Multi-View Images.","year":2025,"yearOfEvent":2025,"venue":"CVPR","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/CVPR52734.2025.00561"],"source":"https://dblp.org/rec/conf/cvpr/Xiao0N0025","documentPage":"https://openaccess.thecvf.com/content/CVPR2025/html/Xiao_RoGSplat_Learning_Robust_Generalizable_Human_Gaussian_Splatting_from_Sparse_Multi-View_CVPR_2025_paper.html","type":"Inproceedings","doi":"https://doi.org/10.1109/CVPR52734.2025.00561","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/Xiao0N0025","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Xiao_RoGSplat_Learning_Robust_Generalizable_Human_Gaussian_Splatting_from_Sparse_Multi-View_CVPR_2025_paper.html"},{"key":"conf/cvpr/Xie0025","title":"Diffusion-based Event Generation for High-Quality Image Deblurring.","year":2025,"yearOfEvent":2025,"venue":"CVPR","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/CVPR52734.2025.00210"],"source":"https://dblp.org/rec/conf/cvpr/Xie0025","documentPage":"https://openaccess.thecvf.com/content/CVPR2025/html/Xie_Diffusion-based_Event_Generation_for_High-Quality_Image_Deblurring_CVPR_2025_paper.html","type":"Inproceedings","doi":"https://doi.org/10.1109/CVPR52734.2025.00210","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/Xie0025","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Xie_Diffusion-based_Event_Generation_for_High-Quality_Image_Deblurring_CVPR_2025_paper.html"},{"key":"conf/cvpr/ZengHWGTM025","title":"ChainHOI: Joint-based Kinematic Chain Modeling for Human-Object Interaction Generation.","year":2025,"yearOfEvent":2025,"venue":"CVPR","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/CVPR52734.2025.01153"],"source":"https://dblp.org/rec/conf/cvpr/ZengHWGTM025","documentPage":"https://openaccess.thecvf.com/content/CVPR2025/html/Zeng_ChainHOI_Joint-based_Kinematic_Chain_Modeling_for_Human-Object_Interaction_Generation_CVPR_2025_paper.html","type":"Inproceedings","doi":"https://doi.org/10.1109/CVPR52734.2025.01153","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/ZengHWGTM025","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Zeng_ChainHOI_Joint-based_Kinematic_Chain_Modeling_for_Human-Object_Interaction_Generation_CVPR_2025_paper.html"},{"key":"conf/cvpr/ZhengZ0LLH025","title":"Panorama Generation From NFoV Image Done Right.","year":2025,"yearOfEvent":2025,"venue":"CVPR","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/CVPR52734.2025.02013"],"source":"https://dblp.org/rec/conf/cvpr/ZhengZ0LLH025","documentPage":"https://openaccess.thecvf.com/content/CVPR2025/html/Zheng_Panorama_Generation_From_NFoV_Image_Done_Right_CVPR_2025_paper.html","type":"Inproceedings","doi":"https://doi.org/10.1109/CVPR52734.2025.02013","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/ZhengZ0LLH025","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Zheng_Panorama_Generation_From_NFoV_Image_Done_Right_CVPR_2025_paper.html"},{"key":"conf/cvpr/ZhouZMLL025","title":"Decoupled Distillation to Erase: A General Unlearning Method for Any Class-centric Tasks.","year":2025,"yearOfEvent":2025,"venue":"CVPR","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/CVPR52734.2025.01895"],"source":"https://dblp.org/rec/conf/cvpr/ZhouZMLL025","documentPage":"https://openaccess.thecvf.com/content/CVPR2025/html/Zhou_Decoupled_Distillation_to_Erase_A_General_Unlearning_Method_for_Any_CVPR_2025_paper.html","type":"Inproceedings","doi":"https://doi.org/10.1109/CVPR52734.2025.01895","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/ZhouZMLL025","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Zhou_Decoupled_Distillation_to_Erase_A_General_Unlearning_Method_for_Any_CVPR_2025_paper.html"},{"key":"conf/cvpr/ZhuZWN025","title":"EntityErasure: Erasing Entity Cleanly via Amodal Entity Segmentation and Completion.","year":2025,"yearOfEvent":2025,"venue":"CVPR","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/CVPR52734.2025.02633"],"source":"https://dblp.org/rec/conf/cvpr/ZhuZWN025","documentPage":"https://openaccess.thecvf.com/content/CVPR2025/html/Zhu_EntityErasure_Erasing_Entity_Cleanly_via_Amodal_Entity_Segmentation_and_Completion_CVPR_2025_paper.html","type":"Inproceedings","doi":"https://doi.org/10.1109/CVPR52734.2025.02633","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/ZhuZWN025","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Zhu_EntityErasure_Erasing_Entity_Cleanly_via_Amodal_Entity_Segmentation_and_Completion_CVPR_2025_paper.html"},{"key":"conf/eccv/LiHWZMZ24","title":"EgoExo-Fitness: Towards Egocentric and Exocentric Full-Body Action Understanding.","year":2025,"yearOfEvent":2024,"venue":"ECCV (20)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1007/978-3-031-72661-3_21"],"source":"https://dblp.org/rec/conf/eccv/LiHWZMZ24","documentPage":"https://doi.org/10.1007/978-3-031-72661-3_21","type":"Inproceedings","doi":"https://doi.org/10.1007/978-3-031-72661-3_21","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/eccv/LiHWZMZ24","documentUrl":"https://doi.org/10.1007/978-3-031-72661-3_21"},{"key":"conf/eccv/LuMZ24","title":"PRET: Planning with Directed Fidelity Trajectory for Vision and Language Navigation.","year":2025,"yearOfEvent":2024,"venue":"ECCV (66)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1007/978-3-031-72848-8_5"],"source":"https://dblp.org/rec/conf/eccv/LuMZ24","documentPage":"https://doi.org/10.1007/978-3-031-72848-8_5","type":"Inproceedings","doi":"https://doi.org/10.1007/978-3-031-72848-8_5","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/eccv/LuMZ24","documentUrl":"https://doi.org/10.1007/978-3-031-72848-8_5"},{"key":"conf/eccv/MoGFYWZ24","title":"Bridge Past and Future: Overcoming Information Asymmetry in Incremental Object Detection.","year":2025,"yearOfEvent":2024,"venue":"ECCV (16)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1007/978-3-031-72640-8_26"],"source":"https://dblp.org/rec/conf/eccv/MoGFYWZ24","documentPage":"https://doi.org/10.1007/978-3-031-72640-8_26","type":"Inproceedings","doi":"https://doi.org/10.1007/978-3-031-72640-8_26","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/eccv/MoGFYWZ24","documentUrl":"https://doi.org/10.1007/978-3-031-72640-8_26"},{"key":"conf/eccv/TangPMZ24","title":"Rethinking Few-Shot Class-Incremental Learning: Learning from Yourself.","year":2025,"yearOfEvent":2024,"venue":"ECCV (61)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1007/978-3-031-73030-6_7"],"source":"https://dblp.org/rec/conf/eccv/TangPMZ24","documentPage":"https://doi.org/10.1007/978-3-031-73030-6_7","type":"Inproceedings","doi":"https://doi.org/10.1007/978-3-031-73030-6_7","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/eccv/TangPMZ24","documentUrl":"https://doi.org/10.1007/978-3-031-73030-6_7"},{"key":"conf/eccv/WuCJZWZ24","title":"An Economic Framework for 6-DoF Grasp Detection.","year":2025,"yearOfEvent":2024,"venue":"ECCV (27)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1007/978-3-031-73383-3_21"],"source":"https://dblp.org/rec/conf/eccv/WuCJZWZ24","documentPage":"https://doi.org/10.1007/978-3-031-73383-3_21","type":"Inproceedings","doi":"https://doi.org/10.1007/978-3-031-73383-3_21","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/eccv/WuCJZWZ24","documentUrl":"https://doi.org/10.1007/978-3-031-73383-3_21"},{"key":"conf/eccv/YanGYWXWZ24","title":"DreamView: Injecting View-Specific Text Guidance Into Text-to-3D Generation.","year":2025,"yearOfEvent":2024,"venue":"ECCV (25)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1007/978-3-031-72698-9_21"],"source":"https://dblp.org/rec/conf/eccv/YanGYWXWZ24","documentPage":"https://doi.org/10.1007/978-3-031-72698-9_21","type":"Inproceedings","doi":"https://doi.org/10.1007/978-3-031-72698-9_21","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/eccv/YanGYWXWZ24","documentUrl":"https://doi.org/10.1007/978-3-031-72698-9_21"},{"key":"conf/iccv/FuYLPLWHXZ25","title":"ViSpeak: Visual Instruction Feedback in Streaming Videos.","year":2025,"yearOfEvent":2025,"venue":"ICCV","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/ICCV51701.2025.02022"],"source":"https://dblp.org/rec/conf/iccv/FuYLPLWHXZ25","documentPage":"https://doi.org/10.1109/ICCV51701.2025.02022","type":"Inproceedings","doi":"https://doi.org/10.1109/ICCV51701.2025.02022","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/FuYLPLWHXZ25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.02022"},{"key":"conf/iccv/JiangWHZWZZ25","title":"Rethinking Bimanual Robotic Manipulation: Learning with Decoupled Interaction Framework.","year":2025,"yearOfEvent":2025,"venue":"ICCV","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/ICCV51701.2025.01155"],"source":"https://dblp.org/rec/conf/iccv/JiangWHZWZZ25","documentPage":"https://doi.org/10.1109/ICCV51701.2025.01155","type":"Inproceedings","doi":"https://doi.org/10.1109/ICCV51701.2025.01155","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/JiangWHZWZZ25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.01155"},{"key":"conf/iccv/LiangLTZZH25","title":"ReferDINO: Referring Video Object Segmentation with Visual Grounding Foundations.","year":2025,"yearOfEvent":2025,"venue":"ICCV","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/ICCV51701.2025.01861"],"source":"https://dblp.org/rec/conf/iccv/LiangLTZZH25","documentPage":"https://doi.org/10.1109/ICCV51701.2025.01861","type":"Inproceedings","doi":"https://doi.org/10.1109/ICCV51701.2025.01861","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/LiangLTZZH25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.01861"},{"key":"conf/iccv/LuLWCZW25","title":"FA: Forced Prompt Learning of Vision-Language Models for Out-of-Distribution Detection.","year":2025,"yearOfEvent":2025,"venue":"ICCV","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/ICCV51701.2025.00115"],"source":"https://dblp.org/rec/conf/iccv/LuLWCZW25","documentPage":"https://doi.org/10.1109/ICCV51701.2025.00115","type":"Inproceedings","doi":"https://doi.org/10.1109/ICCV51701.2025.00115","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/LuLWCZW25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.00115"},{"key":"conf/iccv/LuZCMZ25","title":"monoVLN: Bridging the Observation Gap between Monocular and Panoramic Vision and Language Navigation.","year":2025,"yearOfEvent":2025,"venue":"ICCV","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/ICCV51701.2025.00884"],"source":"https://dblp.org/rec/conf/iccv/LuZCMZ25","documentPage":"https://doi.org/10.1109/ICCV51701.2025.00884","type":"Inproceedings","doi":"https://doi.org/10.1109/ICCV51701.2025.00884","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/LuZCMZ25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.00884"},{"key":"conf/iccv/WeiLLJWZZ25","title":"AffordDexGrasp: Open-Set Language-Guided Dexterous Grasp With Generalizable-Instructive Affordance.","year":2025,"yearOfEvent":2025,"venue":"ICCV","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/ICCV51701.2025.01099"],"source":"https://dblp.org/rec/conf/iccv/WeiLLJWZZ25","documentPage":"https://doi.org/10.1109/ICCV51701.2025.01099","type":"Inproceedings","doi":"https://doi.org/10.1109/ICCV51701.2025.01099","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/WeiLLJWZZ25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.01099"},{"key":"conf/iccv/XiaLLHTZ25","title":"Less Static, More Private: Towards Transferable Privacy-Preserving Action Recognition by Generative Decoupled Learning.","year":2025,"yearOfEvent":2025,"venue":"ICCV","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/ICCV51701.2025.01198"],"source":"https://dblp.org/rec/conf/iccv/XiaLLHTZ25","documentPage":"https://doi.org/10.1109/ICCV51701.2025.01198","type":"Inproceedings","doi":"https://doi.org/10.1109/ICCV51701.2025.01198","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/XiaLLHTZ25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.01198"},{"key":"conf/iccv/YuZZZ25","title":"Structure-Guided Diffusion Models for High-Fidelity Portrait Shadow Removal.","year":2025,"yearOfEvent":2025,"venue":"ICCV","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/ICCV51701.2025.01086"],"source":"https://dblp.org/rec/conf/iccv/YuZZZ25","documentPage":"https://doi.org/10.1109/ICCV51701.2025.01086","type":"Inproceedings","doi":"https://doi.org/10.1109/ICCV51701.2025.01086","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/YuZZZ25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.01086"},{"key":"conf/iccv/ZhangHSLZXZ25","title":"Learning Implicit Features with Flow-Infused Transformations for Realistic Virtual Try-On.","year":2025,"yearOfEvent":2025,"venue":"ICCV","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/ICCV51701.2025.01741"],"source":"https://dblp.org/rec/conf/iccv/ZhangHSLZXZ25","documentPage":"https://doi.org/10.1109/ICCV51701.2025.01741","type":"Inproceedings","doi":"https://doi.org/10.1109/ICCV51701.2025.01741","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/ZhangHSLZXZ25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.01741"},{"key":"conf/iccv/ZhangZPOMZ25","title":"Viperson: Flexibly Generating Virtual Identity for Person Re-Identification.","year":2025,"yearOfEvent":2025,"venue":"ICCV","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/ICCV51701.2025.02170"],"source":"https://dblp.org/rec/conf/iccv/ZhangZPOMZ25","documentPage":"https://doi.org/10.1109/ICCV51701.2025.02170","type":"Inproceedings","doi":"https://doi.org/10.1109/ICCV51701.2025.02170","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/ZhangZPOMZ25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.02170"},{"key":"conf/iccv/ZhengCWWTWZ25","title":"iManip: Skill-Incremental Learning for Robotic Manipulation.","year":2025,"yearOfEvent":2025,"venue":"ICCV","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/ICCV51701.2025.01289"],"source":"https://dblp.org/rec/conf/iccv/ZhengCWWTWZ25","documentPage":"https://doi.org/10.1109/ICCV51701.2025.01289","type":"Inproceedings","doi":"https://doi.org/10.1109/ICCV51701.2025.01289","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/ZhengCWWTWZ25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.01289"},{"key":"conf/iccv/ZhengZLZ25","title":"DNF-Intrinsic: Deterministic Noise-Free Diffusion for Indoor Inverse Rendering.","year":2025,"yearOfEvent":2025,"venue":"ICCV","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/ICCV51701.2025.00963"],"source":"https://dblp.org/rec/conf/iccv/ZhengZLZ25","documentPage":"https://doi.org/10.1109/ICCV51701.2025.00963","type":"Inproceedings","doi":"https://doi.org/10.1109/ICCV51701.2025.00963","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/ZhengZLZ25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.00963"},{"key":"conf/icmcs/HuangZZGZ25","title":"Efficient Explicit Joint-level Interaction Modeling with Mamba for Text-guided HOI Generation.","year":2025,"yearOfEvent":2025,"venue":"ICME","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/ICME59968.2025.11209856"],"source":"https://dblp.org/rec/conf/icmcs/HuangZZGZ25","documentPage":"https://doi.org/10.1109/ICME59968.2025.11209856","type":"Inproceedings","doi":"https://doi.org/10.1109/ICME59968.2025.11209856","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/icmcs/HuangZZGZ25","documentUrl":"https://doi.org/10.1109/ICME59968.2025.11209856"},{"key":"conf/icmcs/LiWHZ25","title":"CosGaussian: Towards Text-to-3D Semantically Controllable 3D Object Style Transfer with Gaussian Splatting.","year":2025,"yearOfEvent":2025,"venue":"ICME","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/ICME59968.2025.11209494"],"source":"https://dblp.org/rec/conf/icmcs/LiWHZ25","documentPage":"https://doi.org/10.1109/ICME59968.2025.11209494","type":"Inproceedings","doi":"https://doi.org/10.1109/ICME59968.2025.11209494","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/icmcs/LiWHZ25","documentUrl":"https://doi.org/10.1109/ICME59968.2025.11209494"},{"key":"conf/icmcs/LiWZLPZZ25","title":"Supplementary Material for \"NoiseActor: A Noise-Action Collaborative Framework for Privacy-Preserving Action Recognition without Privacy Labels\".","year":2025,"yearOfEvent":2025,"venue":"ICME","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/ICME59968.2025.11209811"],"source":"https://dblp.org/rec/conf/icmcs/LiWZLPZZ25","documentPage":"https://doi.org/10.1109/ICME59968.2025.11209811","type":"Inproceedings","doi":"https://doi.org/10.1109/ICME59968.2025.11209811","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/icmcs/LiWZLPZZ25","documentUrl":"https://doi.org/10.1109/ICME59968.2025.11209811"},{"key":"conf/icpr/DuLMZ24","title":"Towards Completeness: A Generalizable Action Proposal Generator for Zero-Shot Temporal Action Localization.","year":2025,"yearOfEvent":2024,"venue":"ICPR (16)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1007/978-3-031-78444-6_17"],"source":"https://dblp.org/rec/conf/icpr/DuLMZ24","documentPage":"https://doi.org/10.1007/978-3-031-78444-6_17","type":"Inproceedings","doi":"https://doi.org/10.1007/978-3-031-78444-6_17","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/icpr/DuLMZ24","documentUrl":"https://doi.org/10.1007/978-3-031-78444-6_17"},{"key":"conf/icpr/JiangWCWZ24","title":"iGrasp: An Interactive 2D-3D Framework for 6-DoF Grasp Detection.","year":2025,"yearOfEvent":2024,"venue":"ICPR (30)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1007/978-3-031-78113-1_22"],"source":"https://dblp.org/rec/conf/icpr/JiangWCWZ24","documentPage":"https://doi.org/10.1007/978-3-031-78113-1_22","type":"Inproceedings","doi":"https://doi.org/10.1007/978-3-031-78113-1_22","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/icpr/JiangWCWZ24","documentUrl":"https://doi.org/10.1007/978-3-031-78113-1_22"},{"key":"conf/icpr/LiZ24","title":"Text-Guided Zero-Shot 3D Style Transfer of Neural Radiance Fields.","year":2025,"yearOfEvent":2024,"venue":"ICPR (8)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1007/978-3-031-78186-5_9"],"source":"https://dblp.org/rec/conf/icpr/LiZ24","documentPage":"https://doi.org/10.1007/978-3-031-78186-5_9","type":"Inproceedings","doi":"https://doi.org/10.1007/978-3-031-78186-5_9","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/icpr/LiZ24","documentUrl":"https://doi.org/10.1007/978-3-031-78186-5_9"},{"key":"conf/icpr/XieFCLZ24","title":"Depth-Enhanced Alignment for Label-Free 3D Semantic Segmentation.","year":2025,"yearOfEvent":2024,"venue":"ICPR (18)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1007/978-3-031-78456-9_1"],"source":"https://dblp.org/rec/conf/icpr/XieFCLZ24","documentPage":"https://doi.org/10.1007/978-3-031-78456-9_1","type":"Inproceedings","doi":"https://doi.org/10.1007/978-3-031-78456-9_1","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/icpr/XieFCLZ24","documentUrl":"https://doi.org/10.1007/978-3-031-78456-9_1"},{"key":"conf/icpr/ZhangPWZ24","title":"Privacy-Preserving Face Recognition with Adaptive Generative Perturbations.","year":2025,"yearOfEvent":2024,"venue":"ICPR (14)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1007/978-3-031-78341-8_14"],"source":"https://dblp.org/rec/conf/icpr/ZhangPWZ24","documentPage":"https://doi.org/10.1007/978-3-031-78341-8_14","type":"Inproceedings","doi":"https://doi.org/10.1007/978-3-031-78341-8_14","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/icpr/ZhangPWZ24","documentUrl":"https://doi.org/10.1007/978-3-031-78341-8_14"},{"key":"conf/icra/WangCLLZ25","title":"Task-Oriented 6-DoF Grasp Pose Detection in Clutters.","year":2025,"yearOfEvent":2025,"venue":"ICRA","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/ICRA55743.2025.11128749"],"source":"https://dblp.org/rec/conf/icra/WangCLLZ25","documentPage":"https://doi.org/10.1109/ICRA55743.2025.11128749","type":"Inproceedings","doi":"https://doi.org/10.1109/ICRA55743.2025.11128749","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/icra/WangCLLZ25","documentUrl":"https://doi.org/10.1109/ICRA55743.2025.11128749"},{"key":"conf/iros/XingLWRTLSZC25","title":"TacCap: A Wearable FBG-Based Tactile Sensor for Efficient Human-to-Robot Skill Transfer.","year":2025,"yearOfEvent":2025,"venue":"IROS","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/IROS60139.2025.11246050"],"source":"https://dblp.org/rec/conf/iros/XingLWRTLSZC25","documentPage":"https://doi.org/10.1109/IROS60139.2025.11246050","type":"Inproceedings","doi":"https://doi.org/10.1109/IROS60139.2025.11246050","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iros/XingLWRTLSZC25","documentUrl":"https://doi.org/10.1109/IROS60139.2025.11246050"},{"key":"conf/nips/LiLZMZ25","title":"Distilling LLM Prior to Flow Model for Generalizable Agent's Imagination in Object Goal Navigation.","year":2025,"yearOfEvent":2025,"venue":"NeurIPS","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/nips/LiLZMZ25","documentPage":"http://papers.nips.cc/paper_files/paper/2025/hash/c129741a2451e5fefe447591e39de30e-Abstract-Conference.html","type":"Inproceedings","doi":null,"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/nips/LiLZMZ25","documentUrl":"http://papers.nips.cc/paper_files/paper/2025/hash/c129741a2451e5fefe447591e39de30e-Abstract-Conference.html"},{"key":"conf/prcv/LiQPZZ24","title":"Privacy-Preserving Action Recognition: A Survey.","year":2025,"yearOfEvent":2024,"venue":"PRCV (7)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1007/978-981-97-8511-7_32"],"source":"https://dblp.org/rec/conf/prcv/LiQPZZ24","documentPage":"https://doi.org/10.1007/978-981-97-8511-7_32","type":"Inproceedings","doi":"https://doi.org/10.1007/978-981-97-8511-7_32","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/prcv/LiQPZZ24","documentUrl":"https://doi.org/10.1007/978-981-97-8511-7_32"},{"key":"journals/ijcv/YeCLZCD25","title":"Transformer for Object Re-identification: A Survey.","year":2025,"yearOfEvent":null,"venue":"Int. J. Comput. Vis.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1007/S11263-024-02284-4"],"source":"https://dblp.org/rec/journals/ijcv/YeCLZCD25","documentPage":"https://doi.org/10.1007/S11263-024-02284-4","type":"Article","doi":"https://doi.org/10.1007/S11263-024-02284-4","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/ijcv/YeCLZCD25","documentUrl":"https://doi.org/10.1007/S11263-024-02284-4"},{"key":"journals/ijcv/ZhengWLMZ25","title":"DiffuVolume: Diffusion Model for Volume based Stereo Matching.","year":2025,"yearOfEvent":null,"venue":"Int. J. Comput. Vis.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1007/S11263-025-02362-1"],"source":"https://dblp.org/rec/journals/ijcv/ZhengWLMZ25","documentPage":"https://doi.org/10.1007/S11263-025-02362-1","type":"Article","doi":"https://doi.org/10.1007/S11263-025-02362-1","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/ijcv/ZhengWLMZ25","documentUrl":"https://doi.org/10.1007/S11263-025-02362-1"},{"key":"journals/npjdm/ChenLLCLZLLCWZLCHZJLLLY25","title":"Digitalization of surgical features improves surgical accuracy via surgeon guidance and robotization.","year":2025,"yearOfEvent":null,"venue":"npj Digit. Medicine","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1038/S41746-025-01887-6"],"source":"https://dblp.org/rec/journals/npjdm/ChenLLCLZLLCWZLCHZJLLLY25","documentPage":"https://doi.org/10.1038/S41746-025-01887-6","type":"Article","doi":"https://doi.org/10.1038/S41746-025-01887-6","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/npjdm/ChenLLCLZLLCWZLCHZJLLLY25","documentUrl":"https://doi.org/10.1038/S41746-025-01887-6"},{"key":"journals/pami/LinZZ25","title":"Human-Centric Transformer for Domain Adaptive Action Recognition.","year":2025,"yearOfEvent":null,"venue":"IEEE Trans. Pattern Anal. Mach. Intell.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1109/TPAMI.2024.3429387"],"source":"https://dblp.org/rec/journals/pami/LinZZ25","documentPage":"https://doi.org/10.1109/TPAMI.2024.3429387","type":"Article","doi":"https://doi.org/10.1109/TPAMI.2024.3429387","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/pami/LinZZ25","documentUrl":"https://doi.org/10.1109/TPAMI.2024.3429387"},{"key":"journals/pami/LiPZ25","title":"Protecting Feature Privacy in Person Re-Identification.","year":2025,"yearOfEvent":null,"venue":"IEEE Trans. Pattern Anal. Mach. Intell.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1109/TPAMI.2025.3590979"],"source":"https://dblp.org/rec/journals/pami/LiPZ25","documentPage":"https://doi.org/10.1109/TPAMI.2025.3590979","type":"Article","doi":"https://doi.org/10.1109/TPAMI.2025.3590979","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/pami/LiPZ25","documentUrl":"https://doi.org/10.1109/TPAMI.2025.3590979"},{"key":"journals/pami/ZhaoCZLZ25","title":"Distilling the Unknown to Unveil Certainty.","year":2025,"yearOfEvent":null,"venue":"IEEE Trans. Pattern Anal. Mach. Intell.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1109/TPAMI.2025.3584386"],"source":"https://dblp.org/rec/journals/pami/ZhaoCZLZ25","documentPage":"https://doi.org/10.1109/TPAMI.2025.3584386","type":"Article","doi":"https://doi.org/10.1109/TPAMI.2025.3584386","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/pami/ZhaoCZLZ25","documentUrl":"https://doi.org/10.1109/TPAMI.2025.3584386"},{"key":"journals/pami/ZhengYP25","title":"A Versatile Framework for Multi-Scene Person Re-Identification.","year":2025,"yearOfEvent":null,"venue":"IEEE Trans. Pattern Anal. Mach. Intell.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1109/TPAMI.2024.3381184"],"source":"https://dblp.org/rec/journals/pami/ZhengYP25","documentPage":"https://doi.org/10.1109/TPAMI.2024.3381184","type":"Article","doi":"https://doi.org/10.1109/TPAMI.2024.3381184","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/pami/ZhengYP25","documentUrl":"https://doi.org/10.1109/TPAMI.2024.3381184"},{"key":"journals/pr/HouYZG25","title":"MultiSpectral Transformer Fusion via exploiting similarity and complementarity for robust pedestrian detection.","year":2025,"yearOfEvent":null,"venue":"Pattern Recognit.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1016/J.PATCOG.2025.111383"],"source":"https://dblp.org/rec/journals/pr/HouYZG25","documentPage":"https://doi.org/10.1016/J.PATCOG.2025.111383","type":"Article","doi":"https://doi.org/10.1016/J.PATCOG.2025.111383","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/pr/HouYZG25","documentUrl":"https://doi.org/10.1016/J.PATCOG.2025.111383"},{"key":"journals/pr/XianPSZ25","title":"Distilling consistent relations for multi-source domain adaptive person re-identification.","year":2025,"yearOfEvent":null,"venue":"Pattern Recognit.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1016/J.PATCOG.2024.110821"],"source":"https://dblp.org/rec/journals/pr/XianPSZ25","documentPage":"https://doi.org/10.1016/J.PATCOG.2024.110821","type":"Article","doi":"https://doi.org/10.1016/J.PATCOG.2024.110821","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/pr/XianPSZ25","documentUrl":"https://doi.org/10.1016/J.PATCOG.2024.110821"},{"key":"journals/ral/ChenWXJCZ25","title":"MotionGrasp: Long-Term Grasp Motion Tracking for Dynamic Grasping.","year":2025,"yearOfEvent":null,"venue":"IEEE Robotics Autom. Lett.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1109/LRA.2024.3504792"],"source":"https://dblp.org/rec/journals/ral/ChenWXJCZ25","documentPage":"https://doi.org/10.1109/LRA.2024.3504792","type":"Article","doi":"https://doi.org/10.1109/LRA.2024.3504792","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/ral/ChenWXJCZ25","documentUrl":"https://doi.org/10.1109/LRA.2024.3504792"},{"key":"journals/sigpro/ZhangSZL25","title":"Iterative UKF under generalized maximum correntropy criterion for intermittent observation systems with complex non-Gaussian noise.","year":2025,"yearOfEvent":null,"venue":"Signal Process.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1016/J.SIGPRO.2024.109701"],"source":"https://dblp.org/rec/journals/sigpro/ZhangSZL25","documentPage":"https://doi.org/10.1016/J.SIGPRO.2024.109701","type":"Article","doi":"https://doi.org/10.1016/J.SIGPRO.2024.109701","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/sigpro/ZhangSZL25","documentUrl":"https://doi.org/10.1016/J.SIGPRO.2024.109701"},{"key":"journals/tcsv/ChenWLCZZW25","title":"DAT: Dual-Branch Adapter-Tuning for Few-Shot Recognition.","year":2025,"yearOfEvent":null,"venue":"IEEE Trans. Circuits Syst. Video Technol.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1109/TCSVT.2025.3541960"],"source":"https://dblp.org/rec/journals/tcsv/ChenWLCZZW25","documentPage":"https://doi.org/10.1109/TCSVT.2025.3541960","type":"Article","doi":"https://doi.org/10.1109/TCSVT.2025.3541960","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/tcsv/ChenWLCZZW25","documentUrl":"https://doi.org/10.1109/TCSVT.2025.3541960"},{"key":"journals/tcsv/DuFLHQSHZ25","title":"Weakly-Supervised Temporal Action Localization by Progressive Complementary Learning.","year":2025,"yearOfEvent":null,"venue":"IEEE Trans. Circuits Syst. Video Technol.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1109/TCSVT.2024.3456795"],"source":"https://dblp.org/rec/journals/tcsv/DuFLHQSHZ25","documentPage":"https://doi.org/10.1109/TCSVT.2024.3456795","type":"Article","doi":"https://doi.org/10.1109/TCSVT.2024.3456795","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/tcsv/DuFLHQSHZ25","documentUrl":"https://doi.org/10.1109/TCSVT.2024.3456795"},{"key":"journals/tcsv/ZengWWHZ25","title":"Progressive Human Motion Generation Based on Text and Few Motion Frames.","year":2025,"yearOfEvent":null,"venue":"IEEE Trans. Circuits Syst. Video Technol.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1109/TCSVT.2025.3556868"],"source":"https://dblp.org/rec/journals/tcsv/ZengWWHZ25","documentPage":"https://doi.org/10.1109/TCSVT.2025.3556868","type":"Article","doi":"https://doi.org/10.1109/TCSVT.2025.3556868","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/tcsv/ZengWWHZ25","documentUrl":"https://doi.org/10.1109/TCSVT.2025.3556868"},{"key":"journals/tifs/LinYZLH25","title":"A Semantically Guided and Focused Network for Occluded Person Re-Identification.","year":2025,"yearOfEvent":null,"venue":"IEEE Trans. Inf. Forensics Secur.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1109/TIFS.2025.3608672"],"source":"https://dblp.org/rec/journals/tifs/LinYZLH25","documentPage":"https://doi.org/10.1109/TIFS.2025.3608672","type":"Article","doi":"https://doi.org/10.1109/TIFS.2025.3608672","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/tifs/LinYZLH25","documentUrl":"https://doi.org/10.1109/TIFS.2025.3608672"},{"key":"journals/tmm/FuYYWXZ25","title":"A Hierarchical Semantic Distillation Framework for Open-Vocabulary Object Detection.","year":2025,"yearOfEvent":null,"venue":"IEEE Trans. Multim.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1109/TMM.2025.3607729"],"source":"https://dblp.org/rec/journals/tmm/FuYYWXZ25","documentPage":"https://doi.org/10.1109/TMM.2025.3607729","type":"Article","doi":"https://doi.org/10.1109/TMM.2025.3607729","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/tmm/FuYYWXZ25","documentUrl":"https://doi.org/10.1109/TMM.2025.3607729"},{"key":"journals/tmm/LiangLHYZL25","title":"Rethinking Temporal Context in Video-QA: A Comprehensive Study of Single-Frame Static Bias.","year":2025,"yearOfEvent":null,"venue":"IEEE Trans. Multim.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1109/TMM.2025.3543031"],"source":"https://dblp.org/rec/journals/tmm/LiangLHYZL25","documentPage":"https://doi.org/10.1109/TMM.2025.3543031","type":"Article","doi":"https://doi.org/10.1109/TMM.2025.3543031","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/tmm/LiangLHYZL25","documentUrl":"https://doi.org/10.1109/TMM.2025.3543031"},{"key":"journals/tmm/ZhangYWXTZY25","title":"Visual Class Incremental Learning With Textual Priors Guidance Based on an Adapted Vision-Language Model.","year":2025,"yearOfEvent":null,"venue":"IEEE Trans. Multim.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1109/TMM.2025.3543109"],"source":"https://dblp.org/rec/journals/tmm/ZhangYWXTZY25","documentPage":"https://doi.org/10.1109/TMM.2025.3543109","type":"Article","doi":"https://doi.org/10.1109/TMM.2025.3543109","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/tmm/ZhangYWXTZY25","documentUrl":"https://doi.org/10.1109/TMM.2025.3543109"},{"key":"journals/tog/JiangZNXZZ25","title":"Self-supervised Texture Filtering.","year":2025,"yearOfEvent":null,"venue":"ACM Trans. Graph.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1145/3744899"],"source":"https://dblp.org/rec/journals/tog/JiangZNXZZ25","documentPage":"https://doi.org/10.1145/3744899","type":"Article","doi":"https://doi.org/10.1145/3744899","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/tog/JiangZNXZZ25","documentUrl":"https://doi.org/10.1145/3744899"},{"key":"journals/tvcg/WangZNZ25","title":"Towards Photorealistic Portrait Style Transfer in Unconstrained Conditions.","year":2025,"yearOfEvent":null,"venue":"IEEE Trans. Vis. Comput. Graph.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1109/TVCG.2025.3529751"],"source":"https://dblp.org/rec/journals/tvcg/WangZNZ25","documentPage":"https://doi.org/10.1109/TVCG.2025.3529751","type":"Article","doi":"https://doi.org/10.1109/TVCG.2025.3529751","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/tvcg/WangZNZ25","documentUrl":"https://doi.org/10.1109/TVCG.2025.3529751"}],"preprints":[{"key":"journals/corr/abs-2501-14607","title":"ReferDINO: Referring Video Object Segmentation with Visual Grounding Foundations.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2501.14607"],"source":"https://dblp.org/rec/journals/corr/abs-2501-14607","documentPage":"https://doi.org/10.48550/ARXIV.2501.14607","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2501.14607","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2501-14607","documentUrl":"https://doi.org/10.48550/ARXIV.2501.14607","arxivId":"2501.14607","arxivUrl":"https://arxiv.org/abs/2501.14607"},{"key":"journals/corr/abs-2501-18954","title":"LLMDet: Learning Strong Open-Vocabulary Object Detectors under the Supervision of Large Language Models.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2501.18954"],"source":"https://dblp.org/rec/journals/corr/abs-2501-18954","documentPage":"https://doi.org/10.48550/ARXIV.2501.18954","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2501.18954","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2501-18954","documentUrl":"https://doi.org/10.48550/ARXIV.2501.18954","arxivId":"2501.18954","arxivUrl":"https://arxiv.org/abs/2501.18954"},{"key":"journals/corr/abs-2502-02372","title":"MaintaAvatar: A Maintainable Avatar Based on Neural Radiance Fields by Continual Learning.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2502.02372"],"source":"https://dblp.org/rec/journals/corr/abs-2502-02372","documentPage":"https://doi.org/10.48550/ARXIV.2502.02372","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2502.02372","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2502-02372","documentUrl":"https://doi.org/10.48550/ARXIV.2502.02372","arxivId":"2502.02372","arxivUrl":"https://arxiv.org/abs/2502.02372"},{"key":"journals/corr/abs-2502-16976","title":"Task-Oriented 6-DoF Grasp Pose Detection in Clutters.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2502.16976"],"source":"https://dblp.org/rec/journals/corr/abs-2502-16976","documentPage":"https://doi.org/10.48550/ARXIV.2502.16976","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2502.16976","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2502-16976","documentUrl":"https://doi.org/10.48550/ARXIV.2502.16976","arxivId":"2502.16976","arxivUrl":"https://arxiv.org/abs/2502.16976"},{"key":"journals/corr/abs-2503-01789","title":"TacCap: A Wearable FBG-Based Tactile Sensor for Seamless Human-to-Robot Skill Transfer.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2503.01789"],"source":"https://dblp.org/rec/journals/corr/abs-2503-01789","documentPage":"https://doi.org/10.48550/ARXIV.2503.01789","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2503.01789","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-01789","documentUrl":"https://doi.org/10.48550/ARXIV.2503.01789","arxivId":"2503.01789","arxivUrl":"https://arxiv.org/abs/2503.01789"},{"key":"journals/corr/abs-2503-07087","title":"iManip: Skill-Incremental Learning for Robotic Manipulation.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2503.07087"],"source":"https://dblp.org/rec/journals/corr/abs-2503-07087","documentPage":"https://doi.org/10.48550/ARXIV.2503.07087","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2503.07087","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-07087","documentUrl":"https://doi.org/10.48550/ARXIV.2503.07087","arxivId":"2503.07087","arxivUrl":"https://arxiv.org/abs/2503.07087"},{"key":"journals/corr/abs-2503-07360","title":"AffordDexGrasp: Open-set Language-guided Dexterous Grasp with Generalizable-Instructive Affordance.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2503.07360"],"source":"https://dblp.org/rec/journals/corr/abs-2503-07360","documentPage":"https://doi.org/10.48550/ARXIV.2503.07360","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2503.07360","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-07360","documentUrl":"https://doi.org/10.48550/ARXIV.2503.07360","arxivId":"2503.07360","arxivUrl":"https://arxiv.org/abs/2503.07360"},{"key":"journals/corr/abs-2503-09186","title":"Rethinking Bimanual Robotic Manipulation: Learning with Decoupled Interaction Framework.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2503.09186"],"source":"https://dblp.org/rec/journals/corr/abs-2503-09186","documentPage":"https://doi.org/10.48550/ARXIV.2503.09186","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2503.09186","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-09186","documentUrl":"https://doi.org/10.48550/ARXIV.2503.09186","arxivId":"2503.09186","arxivUrl":"https://arxiv.org/abs/2503.09186"},{"key":"journals/corr/abs-2503-10152","title":"A Hierarchical Semantic Distillation Framework for Open-Vocabulary Object Detection.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2503.10152"],"source":"https://dblp.org/rec/journals/corr/abs-2503-10152","documentPage":"https://doi.org/10.48550/ARXIV.2503.10152","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2503.10152","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-10152","documentUrl":"https://doi.org/10.48550/ARXIV.2503.10152","arxivId":"2503.10152","arxivUrl":"https://arxiv.org/abs/2503.10152"},{"key":"journals/corr/abs-2503-12769","title":"ViSpeak: Visual Instruction Feedback in Streaming Videos.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2503.12769"],"source":"https://dblp.org/rec/journals/corr/abs-2503-12769","documentPage":"https://doi.org/10.48550/ARXIV.2503.12769","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2503.12769","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-12769","documentUrl":"https://doi.org/10.48550/ARXIV.2503.12769","arxivId":"2503.12769","arxivUrl":"https://arxiv.org/abs/2503.12769"},{"key":"journals/corr/abs-2503-13130","title":"ChainHOI: Joint-based Kinematic Chain Modeling for Human-Object Interaction Generation.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2503.13130"],"source":"https://dblp.org/rec/journals/corr/abs-2503-13130","documentPage":"https://doi.org/10.48550/ARXIV.2503.13130","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2503.13130","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-13130","documentUrl":"https://doi.org/10.48550/ARXIV.2503.13130","arxivId":"2503.13130","arxivUrl":"https://arxiv.org/abs/2503.13130"},{"key":"journals/corr/abs-2503-13300","title":"Progressive Human Motion Generation Based on Text and Few Motion Frames.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2503.13300"],"source":"https://dblp.org/rec/journals/corr/abs-2503-13300","documentPage":"https://doi.org/10.48550/ARXIV.2503.13300","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2503.13300","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-13300","documentUrl":"https://doi.org/10.48550/ARXIV.2503.13300","arxivId":"2503.13300","arxivUrl":"https://arxiv.org/abs/2503.13300"},{"key":"journals/corr/abs-2503-14198","title":"RoGSplat: Learning Robust Generalizable Human Gaussian Splatting from Sparse Multi-View Images.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2503.14198"],"source":"https://dblp.org/rec/journals/corr/abs-2503-14198","documentPage":"https://doi.org/10.48550/ARXIV.2503.14198","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2503.14198","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-14198","documentUrl":"https://doi.org/10.48550/ARXIV.2503.14198","arxivId":"2503.14198","arxivUrl":"https://arxiv.org/abs/2503.14198"},{"key":"journals/corr/abs-2503-18420","title":"Panorama Generation From NFoV Image Done Right.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2503.18420"],"source":"https://dblp.org/rec/journals/corr/abs-2503-18420","documentPage":"https://doi.org/10.48550/ARXIV.2503.18420","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2503.18420","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-18420","documentUrl":"https://doi.org/10.48550/ARXIV.2503.18420","arxivId":"2503.18420","arxivUrl":"https://arxiv.org/abs/2503.18420"},{"key":"journals/corr/abs-2503-21755","title":"VBench-2.0: Advancing Video Generation Benchmark Suite for Intrinsic Faithfulness.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2503.21755"],"source":"https://dblp.org/rec/journals/corr/abs-2503-21755","documentPage":"https://doi.org/10.48550/ARXIV.2503.21755","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2503.21755","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-21755","documentUrl":"https://doi.org/10.48550/ARXIV.2503.21755","arxivId":"2503.21755","arxivUrl":"https://arxiv.org/abs/2503.21755"},{"key":"journals/corr/abs-2503-22405","title":"Modeling Multiple Normal Action Representations for Error Detection in Procedural Tasks.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2503.22405"],"source":"https://dblp.org/rec/journals/corr/abs-2503-22405","documentPage":"https://doi.org/10.48550/ARXIV.2503.22405","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2503.22405","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-22405","documentUrl":"https://doi.org/10.48550/ARXIV.2503.22405","arxivId":"2503.22405","arxivUrl":"https://arxiv.org/abs/2503.22405"},{"key":"journals/corr/abs-2503-23121","title":"Efficient Explicit Joint-level Interaction Modeling with Mamba for Text-guided HOI Generation.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2503.23121"],"source":"https://dblp.org/rec/journals/corr/abs-2503-23121","documentPage":"https://doi.org/10.48550/ARXIV.2503.23121","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2503.23121","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-23121","documentUrl":"https://doi.org/10.48550/ARXIV.2503.23121","arxivId":"2503.23121","arxivUrl":"https://arxiv.org/abs/2503.23121"},{"key":"journals/corr/abs-2503-23509","title":"ReferDINO-Plus: 2nd Solution for 4th PVUW MeViS Challenge at CVPR 2025.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2503.23509"],"source":"https://dblp.org/rec/journals/corr/abs-2503-23509","documentPage":"https://doi.org/10.48550/ARXIV.2503.23509","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2503.23509","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-23509","documentUrl":"https://doi.org/10.48550/ARXIV.2503.23509","arxivId":"2503.23509","arxivUrl":"https://arxiv.org/abs/2503.23509"},{"key":"journals/corr/abs-2503-23751","title":"Decoupled Distillation to Erase: A General Unlearning Method for Any Class-centric Tasks.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2503.23751"],"source":"https://dblp.org/rec/journals/corr/abs-2503-23751","documentPage":"https://doi.org/10.48550/ARXIV.2503.23751","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2503.23751","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-23751","documentUrl":"https://doi.org/10.48550/ARXIV.2503.23751","arxivId":"2503.23751","arxivUrl":"https://arxiv.org/abs/2503.23751"},{"key":"journals/corr/abs-2504-11326","title":"PVUW 2025 Challenge Report: Advances in Pixel-level Understanding of Complex Videos in the Wild.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2504.11326"],"source":"https://dblp.org/rec/journals/corr/abs-2504-11326","documentPage":"https://doi.org/10.48550/ARXIV.2504.11326","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2504.11326","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2504-11326","documentUrl":"https://doi.org/10.48550/ARXIV.2504.11326","arxivId":"2504.11326","arxivUrl":"https://arxiv.org/abs/2504.11326"},{"key":"journals/corr/abs-2504-18152","title":"ActionArt: Advancing Multimodal Large Models for Fine-Grained Human-Centric Video Understanding.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2504.18152"],"source":"https://dblp.org/rec/journals/corr/abs-2504-18152","documentPage":"https://doi.org/10.48550/ARXIV.2504.18152","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2504.18152","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2504-18152","documentUrl":"https://doi.org/10.48550/ARXIV.2504.18152","arxivId":"2504.18152","arxivUrl":"https://arxiv.org/abs/2504.18152"},{"key":"journals/corr/abs-2505-12702","title":"Long-RVOS: A Comprehensive Benchmark for Long-term Referring Video Object Segmentation.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2505.12702"],"source":"https://dblp.org/rec/journals/corr/abs-2505-12702","documentPage":"https://doi.org/10.48550/ARXIV.2505.12702","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2505.12702","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-12702","documentUrl":"https://doi.org/10.48550/ARXIV.2505.12702","arxivId":"2505.12702","arxivUrl":"https://arxiv.org/abs/2505.12702"},{"key":"journals/corr/abs-2505-24718","title":"Reinforcing Video Reasoning with Focused Thinking.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2505.24718"],"source":"https://dblp.org/rec/journals/corr/abs-2505-24718","documentPage":"https://doi.org/10.48550/ARXIV.2505.24718","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2505.24718","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-24718","documentUrl":"https://doi.org/10.48550/ARXIV.2505.24718","arxivId":"2505.24718","arxivUrl":"https://arxiv.org/abs/2505.24718"},{"key":"journals/corr/abs-2506-06982","title":"Chain of Methodologies: Scaling Test Time Computation without Training.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2506.06982"],"source":"https://dblp.org/rec/journals/corr/abs-2506-06982","documentPage":"https://doi.org/10.48550/ARXIV.2506.06982","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2506.06982","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-06982","documentUrl":"https://doi.org/10.48550/ARXIV.2506.06982","arxivId":"2506.06982","arxivUrl":"https://arxiv.org/abs/2506.06982"},{"key":"journals/corr/abs-2507-01857","title":"TypeTele: Releasing Dexterity in Teleoperation by Dexterous Manipulation Types.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2507.01857"],"source":"https://dblp.org/rec/journals/corr/abs-2507-01857","documentPage":"https://doi.org/10.48550/ARXIV.2507.01857","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2507.01857","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2507-01857","documentUrl":"https://doi.org/10.48550/ARXIV.2507.01857","arxivId":"2507.01857","arxivUrl":"https://arxiv.org/abs/2507.01857"},{"key":"journals/corr/abs-2507-03924","title":"DNF-Intrinsic: Deterministic Noise-Free Diffusion for Indoor Inverse Rendering.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2507.03924"],"source":"https://dblp.org/rec/journals/corr/abs-2507-03924","documentPage":"https://doi.org/10.48550/ARXIV.2507.03924","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2507.03924","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2507-03924","documentUrl":"https://doi.org/10.48550/ARXIV.2507.03924","arxivId":"2507.03924","arxivUrl":"https://arxiv.org/abs/2507.03924"},{"key":"journals/corr/abs-2507-04060","title":"Temporal Continual Learning with Prior Compensation for Human Motion Prediction.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2507.04060"],"source":"https://dblp.org/rec/journals/corr/abs-2507-04060","documentPage":"https://doi.org/10.48550/ARXIV.2507.04060","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2507.04060","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2507-04060","documentUrl":"https://doi.org/10.48550/ARXIV.2507.04060","arxivId":"2507.04060","arxivUrl":"https://arxiv.org/abs/2507.04060"},{"key":"journals/corr/abs-2507-04243","title":"Domain Generalizable Portrait Style Transfer.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2507.04243"],"source":"https://dblp.org/rec/journals/corr/abs-2507-04243","documentPage":"https://doi.org/10.48550/ARXIV.2507.04243","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2507.04243","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2507-04243","documentUrl":"https://doi.org/10.48550/ARXIV.2507.04243","arxivId":"2507.04243","arxivUrl":"https://arxiv.org/abs/2507.04243"},{"key":"journals/corr/abs-2507-04511","title":"FA: Forced Prompt Learning of Vision-Language Models for Out-of-Distribution Detection.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2507.04511"],"source":"https://dblp.org/rec/journals/corr/abs-2507-04511","documentPage":"https://doi.org/10.48550/ARXIV.2507.04511","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2507.04511","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2507-04511","documentUrl":"https://doi.org/10.48550/ARXIV.2507.04511","arxivId":"2507.04511","arxivUrl":"https://arxiv.org/abs/2507.04511"},{"key":"journals/corr/abs-2507-04692","title":"Structure-Guided Diffusion Models for High-Fidelity Portrait Shadow Removal.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2507.04692"],"source":"https://dblp.org/rec/journals/corr/abs-2507-04692","documentPage":"https://doi.org/10.48550/ARXIV.2507.04692","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2507.04692","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2507-04692","documentUrl":"https://doi.org/10.48550/ARXIV.2507.04692","arxivId":"2507.04692","arxivUrl":"https://arxiv.org/abs/2507.04692"},{"key":"journals/corr/abs-2508-07162","title":"CoopDiff: Anticipating 3D Human-object Interactions via Contact-consistent Decoupled Diffusion.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2508.07162"],"source":"https://dblp.org/rec/journals/corr/abs-2508-07162","documentPage":"https://doi.org/10.48550/ARXIV.2508.07162","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2508.07162","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-07162","documentUrl":"https://doi.org/10.48550/ARXIV.2508.07162","arxivId":"2508.07162","arxivUrl":"https://arxiv.org/abs/2508.07162"},{"key":"journals/corr/abs-2508-09423","title":"Distilling LLM Prior to Flow Model for Generalizable Agent's Imagination in Object Goal Navigation.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2508.09423"],"source":"https://dblp.org/rec/journals/corr/abs-2508-09423","documentPage":"https://doi.org/10.48550/ARXIV.2508.09423","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2508.09423","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-09423","documentUrl":"https://doi.org/10.48550/ARXIV.2508.09423","arxivId":"2508.09423","arxivUrl":"https://arxiv.org/abs/2508.09423"},{"key":"journals/corr/abs-2508-17667","title":"Hierarchical Vision-Language Learning for Medical Out-of-Distribution Detection.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2508.17667"],"source":"https://dblp.org/rec/journals/corr/abs-2508-17667","documentPage":"https://doi.org/10.48550/ARXIV.2508.17667","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2508.17667","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-17667","documentUrl":"https://doi.org/10.48550/ARXIV.2508.17667","arxivId":"2508.17667","arxivUrl":"https://arxiv.org/abs/2508.17667"},{"key":"journals/corr/abs-2509-23915","title":"Revisit the Imbalance Optimization in Multi-task Learning: An Experimental Analysis.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2509.23915"],"source":"https://dblp.org/rec/journals/corr/abs-2509-23915","documentPage":"https://doi.org/10.48550/ARXIV.2509.23915","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2509.23915","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-23915","documentUrl":"https://doi.org/10.48550/ARXIV.2509.23915","arxivId":"2509.23915","arxivUrl":"https://arxiv.org/abs/2509.23915"},{"key":"journals/corr/abs-2509-24786","title":"LOVE-R1: Advancing Long Video Understanding with an Adaptive Zoom-in Mechanism via Multi-Step Reasoning.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2509.24786"],"source":"https://dblp.org/rec/journals/corr/abs-2509-24786","documentPage":"https://doi.org/10.48550/ARXIV.2509.24786","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2509.24786","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-24786","documentUrl":"https://doi.org/10.48550/ARXIV.2509.24786","arxivId":"2509.24786","arxivUrl":"https://arxiv.org/abs/2509.24786"},{"key":"journals/corr/abs-2509-24948","title":"World-Env: Leveraging World Model as a Virtual Environment for VLA Post-Training.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2509.24948"],"source":"https://dblp.org/rec/journals/corr/abs-2509-24948","documentPage":"https://doi.org/10.48550/ARXIV.2509.24948","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2509.24948","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-24948","documentUrl":"https://doi.org/10.48550/ARXIV.2509.24948","arxivId":"2509.24948","arxivUrl":"https://arxiv.org/abs/2509.24948"},{"key":"journals/corr/abs-2510-10671","title":"Image-to-Video Transfer Learning based on Image-Language Foundation Models: A Comprehensive Survey.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2510.10671"],"source":"https://dblp.org/rec/journals/corr/abs-2510-10671","documentPage":"https://doi.org/10.48550/ARXIV.2510.10671","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2510.10671","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-10671","documentUrl":"https://doi.org/10.48550/ARXIV.2510.10671","arxivId":"2510.10671","arxivUrl":"https://arxiv.org/abs/2510.10671"},{"key":"journals/corr/abs-2510-23119","title":"OmniDexGrasp: Generalizable Dexterous Grasping via Foundation Model and Force Feedback.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2510.23119"],"source":"https://dblp.org/rec/journals/corr/abs-2510-23119","documentPage":"https://doi.org/10.48550/ARXIV.2510.23119","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2510.23119","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-23119","documentUrl":"https://doi.org/10.48550/ARXIV.2510.23119","arxivId":"2510.23119","arxivUrl":"https://arxiv.org/abs/2510.23119"},{"key":"journals/corr/abs-2511-05129","title":"Decomposed Object Manipulation via Dual-Actor Policy.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2511.05129"],"source":"https://dblp.org/rec/journals/corr/abs-2511-05129","documentPage":"https://doi.org/10.48550/ARXIV.2511.05129","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2511.05129","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2511-05129","documentUrl":"https://doi.org/10.48550/ARXIV.2511.05129","arxivId":"2511.05129","arxivUrl":"https://arxiv.org/abs/2511.05129"},{"key":"journals/corr/abs-2511-13327","title":"ZeroDexGrasp: Zero-Shot Task-Oriented Dexterous Grasp Synthesis with Prompt-Based Multi-Stage Semantic Reasoning.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2511.13327"],"source":"https://dblp.org/rec/journals/corr/abs-2511-13327","documentPage":"https://doi.org/10.48550/ARXIV.2511.13327","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2511.13327","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2511-13327","documentUrl":"https://doi.org/10.48550/ARXIV.2511.13327","arxivId":"2511.13327","arxivUrl":"https://arxiv.org/abs/2511.13327"},{"key":"journals/corr/abs-2511-18695","title":"Exploring Surround-View Fisheye Camera 3D Object Detection.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2511.18695"],"source":"https://dblp.org/rec/journals/corr/abs-2511-18695","documentPage":"https://doi.org/10.48550/ARXIV.2511.18695","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2511.18695","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2511-18695","documentUrl":"https://doi.org/10.48550/ARXIV.2511.18695","arxivId":"2511.18695","arxivUrl":"https://arxiv.org/abs/2511.18695"},{"key":"journals/corr/abs-2512-01022","title":"CycleManip: Enabling Cyclic Task Manipulation via Effective Historical Perception and Understanding.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2512.01022"],"source":"https://dblp.org/rec/journals/corr/abs-2512-01022","documentPage":"https://doi.org/10.48550/ARXIV.2512.01022","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2512.01022","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-01022","documentUrl":"https://doi.org/10.48550/ARXIV.2512.01022","arxivId":"2512.01022","arxivUrl":"https://arxiv.org/abs/2512.01022"},{"key":"journals/corr/abs-2512-10730","title":"IRG-MotionLLM: Interleaving Motion Generation, Assessment and Refinement for Text-to-Motion Generation.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2512.10730"],"source":"https://dblp.org/rec/journals/corr/abs-2512-10730","documentPage":"https://doi.org/10.48550/ARXIV.2512.10730","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2512.10730","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-10730","documentUrl":"https://doi.org/10.48550/ARXIV.2512.10730","arxivId":"2512.10730","arxivUrl":"https://arxiv.org/abs/2512.10730"},{"key":"journals/corr/abs-2512-12309","title":"WeDetect: Fast Open-Vocabulary Object Detection as Retrieval.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2512.12309"],"source":"https://dblp.org/rec/journals/corr/abs-2512-12309","documentPage":"https://doi.org/10.48550/ARXIV.2512.12309","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2512.12309","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-12309","documentUrl":"https://doi.org/10.48550/ARXIV.2512.12309","arxivId":"2512.12309","arxivUrl":"https://arxiv.org/abs/2512.12309"},{"key":"journals/corr/abs-2512-22118","title":"ProEdit: Inversion-based Editing From Prompts Done Right.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2512.22118"],"source":"https://dblp.org/rec/journals/corr/abs-2512-22118","documentPage":"https://doi.org/10.48550/ARXIV.2512.22118","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2512.22118","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-22118","documentUrl":"https://doi.org/10.48550/ARXIV.2512.22118","arxivId":"2512.22118","arxivUrl":"https://arxiv.org/abs/2512.22118"}],"excludedFormal":[],"excludedOther":[],"excludedHomonyms":[],"unassignedCandidates":[],"retrievedAt":"2026-10-19","querySource":"https://sparql.dblp.org/","method":"DBLP yearOfPublication=2025; Article + Inproceedings; excludes Informal/CoRR and explicit editorial/correction/erratum/preface; unique DBLP record keys within person.","labName":"机器智能与先进计算教育部重点实验室","labUrl":null,"labEvidence":"深圳河套学院当前官方教师介绍明确称郑伟诗现任该重点实验室主任。没有将同校HCP实验室错误归给他。","labSourceUrl":"https://www.slai.edu.cn/zh-hans/teacher/209","affiliationZh":"中山大学","sourceWarning":false,"knownPreprintMinimum2025":null,"excludedMisattributed":[],"displayNotes":"身份已经个人或机构主页核对。2025 年正式记录 66 条（会议 46、期刊 20），所有作者位置均计入，不表示主导或贡献份额；预印本 45 条单列，不加总。","labDisplayNotes":"深圳河套学院官方教师页写明其现任机器智能与先进计算教育部重点实验室主任，据此归组。这是部级重点实验室，分组只含本人的记录；同校的 HCP 实验室是另一个团队，不归给他。"},{"index":116,"name":"Boyu Zhou","nameZh":"周博宇","affiliation":"Southern University of Science and Technology","source":"DBLP Knowledge Graph official SPARQL API","profileUrl":"https://dblp.org/pid/231/1114","identifier":"231/1114","identityEvidence":[{"url":"https://sustech.edu.cn/en/faculties/boyuzhou.html","evidence":"School profile identifies 周博宇 at SUSTech since January 2025, previously SYSU; DBLP papers mostly use ORCID 0000-0002-4125-7481 and these affiliations."},{"url":"https://link.springer.com/chapter/10.1007/978-981-97-8490-5_35","evidence":"Publisher assigns the PRCV emotional-support LLM author Boyu Zhou to Mind with Heart Robotics Co. Ltd. This does not establish whether it is the SUSTech faculty member, so the record remains unassigned and the annual total is withheld."}],"count2025":null,"conference2025":null,"journal2025":null,"preprint2025":null,"status":"partial_identity_review","notes":"Counts are DBLP indexed coauthored records, not first-author counts, laboratory totals, unique scientific discoveries, or quality assessments. DBLP yearOfPublication=2025; yearOfEvent retained and can differ. Conference workshops are included. Preprints are separate and may overlap formal versions. Mixed / unassigned DBLP profile. Main counts withheld pending review of every remaining candidate; retained papers establish a verified lower bound only. Do not present this lower bound as an exact annual total.","papers":[{"key":"conf/iros/LiangZXZ25","title":"DynamicPose: Real-time and Robust 6D Object Pose Tracking for Fast-Moving Cameras and Objects.","year":2025,"yearOfEvent":2025,"venue":"IROS","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/IROS60139.2025.11247403"],"source":"https://dblp.org/rec/conf/iros/LiangZXZ25","documentPage":"https://doi.org/10.1109/IROS60139.2025.11247403","type":"Inproceedings","doi":"https://doi.org/10.1109/IROS60139.2025.11247403","authorSignatures":[{"inst":"https://dblp.org/inst/9/310","instLabel":"Southern University of Science and Technology (SUSTC)"}],"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iros/LiangZXZ25","documentUrl":"https://doi.org/10.1109/IROS60139.2025.11247403"},{"key":"conf/iros/XieGMZ25","title":"AKF-LIO: LiDAR-Inertial Odometry with Gaussian Map by Adaptive Kalman Filter.","year":2025,"yearOfEvent":2025,"venue":"IROS","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/IROS60139.2025.11246097"],"source":"https://dblp.org/rec/conf/iros/XieGMZ25","documentPage":"https://doi.org/10.1109/IROS60139.2025.11246097","type":"Inproceedings","doi":"https://doi.org/10.1109/IROS60139.2025.11246097","authorSignatures":[{"inst":"https://dblp.org/inst/9/310","instLabel":"Southern University of Science and Technology (SUSTC)"}],"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iros/XieGMZ25","documentUrl":"https://doi.org/10.1109/IROS60139.2025.11246097"},{"key":"conf/iros/YuLMZ25","title":"Perception-aware Planning for Quadrotor Flight in Unknown and Feature-limited Environments.","year":2025,"yearOfEvent":2025,"venue":"IROS","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/IROS60139.2025.11246321"],"source":"https://dblp.org/rec/conf/iros/YuLMZ25","documentPage":"https://doi.org/10.1109/IROS60139.2025.11246321","type":"Inproceedings","doi":"https://doi.org/10.1109/IROS60139.2025.11246321","authorSignatures":[{"inst":"https://dblp.org/inst/9/310","instLabel":"Southern University of Science and Technology (SUSTC)"}],"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iros/YuLMZ25","documentUrl":"https://doi.org/10.1109/IROS60139.2025.11246321"},{"key":"journals/ral/GengNZZ25","title":"EPIC: A Lightweight LiDAR-Based AAV Exploration Framework for Large-Scale Scenarios.","year":2025,"yearOfEvent":null,"venue":"IEEE Robotics Autom. Lett.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1109/LRA.2025.3555878"],"source":"https://dblp.org/rec/journals/ral/GengNZZ25","documentPage":"https://doi.org/10.1109/LRA.2025.3555878","type":"Article","doi":"https://doi.org/10.1109/LRA.2025.3555878","authorSignatures":[{"orcid":"https://orcid.org/0000-0002-4125-7481","inst":"https://dblp.org/inst/1/953","instLabel":"Sun Yat-sen University"},{"orcid":"https://orcid.org/0000-0002-4125-7481","inst":"https://dblp.org/inst/9/310","instLabel":"Southern University of Science and Technology (SUSTC)"}],"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/ral/GengNZZ25","documentUrl":"https://doi.org/10.1109/LRA.2025.3555878"},{"key":"journals/ral/ZhangDWZQMZ25","title":"ApexNAV: An Adaptive Exploration Strategy for Zero-Shot Object Navigation With Target-Centric Semantic Fusion.","year":2025,"yearOfEvent":null,"venue":"IEEE Robotics Autom. Lett.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1109/LRA.2025.3606388"],"source":"https://dblp.org/rec/journals/ral/ZhangDWZQMZ25","documentPage":"https://doi.org/10.1109/LRA.2025.3606388","type":"Article","doi":"https://doi.org/10.1109/LRA.2025.3606388","authorSignatures":[{"orcid":"https://orcid.org/0000-0002-4125-7481","inst":"https://dblp.org/inst/9/310","instLabel":"Southern University of Science and Technology (SUSTC)"}],"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/ral/ZhangDWZQMZ25","documentUrl":"https://doi.org/10.1109/LRA.2025.3606388"},{"key":"journals/ral/ZhengLSBZZM25","title":"Local Reactive Control for Mobile Manipulators With Whole-Body Safety in Complex Environments.","year":2025,"yearOfEvent":null,"venue":"IEEE Robotics Autom. Lett.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1109/LRA.2025.3550733"],"source":"https://dblp.org/rec/journals/ral/ZhengLSBZZM25","documentPage":"https://doi.org/10.1109/LRA.2025.3550733","type":"Article","doi":"https://doi.org/10.1109/LRA.2025.3550733","authorSignatures":[{"orcid":"https://orcid.org/0000-0002-4125-7481","inst":"https://dblp.org/inst/9/310","instLabel":"Southern University of Science and Technology (SUSTC)"}],"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/ral/ZhengLSBZZM25","documentUrl":"https://doi.org/10.1109/LRA.2025.3550733"},{"key":"journals/tase/ZhuFXLMZ25","title":"FLARE: Fast Autonomous Aerial Exploration in Large-Scale 3D Scenarios Using Actively Rotated LiDAR.","year":2025,"yearOfEvent":null,"venue":"IEEE Trans Autom. Sci. Eng.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1109/TASE.2025.3631098"],"source":"https://dblp.org/rec/journals/tase/ZhuFXLMZ25","documentPage":"https://doi.org/10.1109/TASE.2025.3631098","type":"Article","doi":"https://doi.org/10.1109/TASE.2025.3631098","authorSignatures":[{"orcid":"https://orcid.org/0000-0002-4125-7481","inst":"https://dblp.org/inst/9/310","instLabel":"Southern University of Science and Technology (SUSTC)"}],"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/tase/ZhuFXLMZ25","documentUrl":"https://doi.org/10.1109/TASE.2025.3631098"},{"key":"journals/trob/ZhangCFZS25","title":"FALCON: Fast Autonomous Aerial Exploration Using Coverage Path Guidance.","year":2025,"yearOfEvent":null,"venue":"IEEE Trans. Robotics","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1109/TRO.2024.3522148"],"source":"https://dblp.org/rec/journals/trob/ZhangCFZS25","documentPage":"https://doi.org/10.1109/TRO.2024.3522148","type":"Article","doi":"https://doi.org/10.1109/TRO.2024.3522148","authorSignatures":[{"orcid":"https://orcid.org/0000-0002-4125-7481","inst":"https://dblp.org/inst/1/953","instLabel":"Sun Yat-sen University"},{"orcid":"https://orcid.org/0000-0002-4125-7481","inst":"https://dblp.org/inst/9/310","instLabel":"Southern University of Science and Technology (SUSTC)"}],"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/trob/ZhangCFZS25","documentUrl":"https://doi.org/10.1109/TRO.2024.3522148"}],"preprints":[{"key":"journals/corr/abs-2501-02815","title":"Local Reactive Control for Mobile Manipulators with Whole-Body Safety in Complex Environments.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2501.02815"],"source":"https://dblp.org/rec/journals/corr/abs-2501-02815","documentPage":"https://doi.org/10.48550/ARXIV.2501.02815","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2501.02815","authorSignatures":[{}],"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2501-02815","documentUrl":"https://doi.org/10.48550/ARXIV.2501.02815","arxivId":"2501.02815","arxivUrl":"https://arxiv.org/abs/2501.02815"},{"key":"journals/corr/abs-2501-06566","title":"Cooperative Aerial Robot Inspection Challenge: A Benchmark for Heterogeneous Multi-UAV Planning and Lessons Learned.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2501.06566"],"source":"https://dblp.org/rec/journals/corr/abs-2501-06566","documentPage":"https://doi.org/10.48550/ARXIV.2501.06566","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2501.06566","authorSignatures":[{}],"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2501-06566","documentUrl":"https://doi.org/10.48550/ARXIV.2501.06566","arxivId":"2501.06566","arxivUrl":"https://arxiv.org/abs/2501.06566"},{"key":"journals/corr/abs-2503-06891","title":"AKF-LIO: LiDAR-Inertial Odometry with Gaussian Map by Adaptive Kalman Filter.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2503.06891"],"source":"https://dblp.org/rec/journals/corr/abs-2503-06891","documentPage":"https://doi.org/10.48550/ARXIV.2503.06891","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2503.06891","authorSignatures":[{}],"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-06891","documentUrl":"https://doi.org/10.48550/ARXIV.2503.06891","arxivId":"2503.06891","arxivUrl":"https://arxiv.org/abs/2503.06891"},{"key":"journals/corr/abs-2503-07278","title":"Multi-Robot System for Cooperative Exploration in Unknown Environments: A Survey.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2503.07278"],"source":"https://dblp.org/rec/journals/corr/abs-2503-07278","documentPage":"https://doi.org/10.48550/ARXIV.2503.07278","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2503.07278","authorSignatures":[{}],"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-07278","documentUrl":"https://doi.org/10.48550/ARXIV.2503.07278","arxivId":"2503.07278","arxivUrl":"https://arxiv.org/abs/2503.07278"},{"key":"journals/corr/abs-2503-15273","title":"Perception-aware Planning for Quadrotor Flight in Unknown and Feature-limited Environments.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2503.15273"],"source":"https://dblp.org/rec/journals/corr/abs-2503-15273","documentPage":"https://doi.org/10.48550/ARXIV.2503.15273","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2503.15273","authorSignatures":[{}],"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-15273","documentUrl":"https://doi.org/10.48550/ARXIV.2503.15273","arxivId":"2503.15273","arxivUrl":"https://arxiv.org/abs/2503.15273"},{"key":"journals/corr/abs-2504-14478","title":"ApexNav: An Adaptive Exploration Strategy for Zero-Shot Object Navigation with Target-centric Semantic Fusion.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2504.14478"],"source":"https://dblp.org/rec/journals/corr/abs-2504-14478","documentPage":"https://doi.org/10.48550/ARXIV.2504.14478","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2504.14478","authorSignatures":[{}],"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2504-14478","documentUrl":"https://doi.org/10.48550/ARXIV.2504.14478","arxivId":"2504.14478","arxivUrl":"https://arxiv.org/abs/2504.14478"},{"key":"journals/corr/abs-2504-14862","title":"FERMI: Flexible Radio Mapping with a Hybrid Propagation Model and Scalable Autonomous Data Collection.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2504.14862"],"source":"https://dblp.org/rec/journals/corr/abs-2504-14862","documentPage":"https://doi.org/10.48550/ARXIV.2504.14862","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2504.14862","authorSignatures":[{}],"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2504-14862","documentUrl":"https://doi.org/10.48550/ARXIV.2504.14862","arxivId":"2504.14862","arxivUrl":"https://arxiv.org/abs/2504.14862"},{"key":"journals/corr/abs-2508-11950","title":"DynamicPose: Real-time and Robust 6D Object Pose Tracking for Fast-Moving Cameras and Objects.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2508.11950"],"source":"https://dblp.org/rec/journals/corr/abs-2508-11950","documentPage":"https://doi.org/10.48550/ARXIV.2508.11950","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2508.11950","authorSignatures":[{}],"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-11950","documentUrl":"https://doi.org/10.48550/ARXIV.2508.11950","arxivId":"2508.11950","arxivUrl":"https://arxiv.org/abs/2508.11950"},{"key":"journals/corr/abs-2509-19916","title":"GUIDE: A Diffusion-Based Autonomous Robot Exploration Framework Using Global Graph Inference.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2509.19916"],"source":"https://dblp.org/rec/journals/corr/abs-2509-19916","documentPage":"https://doi.org/10.48550/ARXIV.2509.19916","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2509.19916","authorSignatures":[{}],"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-19916","documentUrl":"https://doi.org/10.48550/ARXIV.2509.19916","arxivId":"2509.19916","arxivUrl":"https://arxiv.org/abs/2509.19916"},{"key":"journals/corr/abs-2511-12528","title":"D2-VPR: A Parameter-efficient Visual-foundation-model-based Visual Place Recognition Method via Knowledge Distillation and Deformable Aggregation.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2511.12528"],"source":"https://dblp.org/rec/journals/corr/abs-2511-12528","documentPage":"https://doi.org/10.48550/ARXIV.2511.12528","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2511.12528","authorSignatures":[{}],"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2511-12528","documentUrl":"https://doi.org/10.48550/ARXIV.2511.12528","arxivId":"2511.12528","arxivUrl":"https://arxiv.org/abs/2511.12528"}],"excludedFormal":[{"key":"journals/ral/GengNZZ25a","title":"Corrections to \"EPIC: A Lightweight LiDAR-Based AAV Exploration Framework for Large-Scale Scenarios\".","year":2025,"yearOfEvent":null,"venue":"IEEE Robotics Autom. Lett.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1109/LRA.2025.3592745"],"source":"https://dblp.org/rec/journals/ral/GengNZZ25a","documentPage":"https://doi.org/10.1109/LRA.2025.3592745","type":"Article","doi":"https://doi.org/10.1109/LRA.2025.3592745","authorSignatures":[{"orcid":"https://orcid.org/0000-0002-4125-7481","inst":"https://dblp.org/inst/9/310","instLabel":"Southern University of Science and Technology (SUSTC)"}],"exclusionReason":"Explicit editorial, correction, erratum or preface; excluded from research-paper count.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/ral/GengNZZ25a","documentUrl":"https://doi.org/10.1109/LRA.2025.3592745"}],"excludedOther":[],"excludedHomonyms":[],"unassignedCandidates":[{"key":"conf/prcv/ZhuJZSZL24","title":"Empathizing Before Generation: A Double-Layered Framework for Emotional Support LLM.","year":2025,"yearOfEvent":2024,"venue":"PRCV (2)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1007/978-981-97-8490-5_35"],"source":"https://dblp.org/rec/conf/prcv/ZhuJZSZL24","documentPage":"https://doi.org/10.1007/978-981-97-8490-5_35","type":"Inproceedings","doi":"https://doi.org/10.1007/978-981-97-8490-5_35","authorSignatures":[{}],"reviewStatus":"Identity unresolved; not included in the verified lower bound.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/prcv/ZhuJZSZL24","documentUrl":"https://doi.org/10.1007/978-981-97-8490-5_35"}],"retrievedAt":"2026-10-19","querySource":"https://sparql.dblp.org/","method":"DBLP yearOfPublication=2025; Article + Inproceedings; excludes Informal/CoRR and explicit editorial/correction/erratum/preface; unique DBLP record keys within person.","verifiedLowerBound2025":8,"conferenceLowerBound2025":3,"journalLowerBound2025":5,"labName":"Smart Autonomous Robotics（STAR）Group","labUrl":"https://robotics-star.com/","labEvidence":"南科大官方教师介绍明确称其任 STAR group 主任；课题组自己的 People 页面也明确写出同一关系。","labSourceUrl":"https://sustech.edu.cn/en/faculties/boyuzhou.html","affiliationZh":"南方科技大学","sourceWarning":false,"knownPreprintMinimum2025":10,"excludedMisattributed":[],"knownMinimum2025":8,"displayNotes":"该 DBLP 档案混有其他同名作者，全年总数暂不给出。目前已逐篇核实 8 条，只作下界参考，不进入合计、中位数或排序。唯一尚未确定的正式候选是一篇 PRCV 会议论文，出版社将作者 Boyu Zhou 列于一家机器人公司；企业与大学身份可能并存，现有证据既不能确认，也不能排除。","labDisplayNotes":"南科大官方教师页写明其任 STAR Group 主任，课题组的 People 页面也写明同一关系，据此命名；论文数仍为空缺。"},{"index":117,"name":"Shaohua Zhou","nameZh":"周少华","affiliation":"University of Science and Technology of China","source":"DBLP Knowledge Graph official SPARQL API","profileUrl":"https://dblp.org/pid/57/98","identifier":"57/98","identityEvidence":[{"url":"https://dblp.org/pid/57/98","evidence":"DBLP curated profile affiliations: Chinese Academy of Sciences (CAS), Institute of Computing Technology, Beijing, China; Siemens Corporate Technology, Imaging and Computer Vision."},{"url":"https://dblp.org/pid/57/98","evidence":"DBLP curated profile homepages: https://sites.google.com/site/skevinzhou/home."},{"url":"https://enbiomed.ustc.edu.cn/2024/1217/c38056a665761/page.htm","evidence":"USTC school profile identifies 周少华, S. Kevin Zhou, medical-imaging professor and former Siemens scientist. DBLP Shaohua Kevin Zhou 57/98 matches this biography; unnumbered Shaohua Zhou 196/8001 is not used."}],"count2025":43,"conference2025":27,"journal2025":16,"preprint2025":44,"status":"verified","notes":"Counts are DBLP indexed coauthored records, not first-author counts, laboratory totals, unique scientific discoveries, or quality assessments. DBLP yearOfPublication=2025; yearOfEvent retained and can differ. Conference workshops are included. Preprints are separate and may overlap formal versions.","papers":[{"key":"conf/acl/CaoHGDXZ25","title":"GraphInsight: Unlocking Insights in Large Language Models for Graph Structure Understanding.","year":2025,"yearOfEvent":2025,"venue":"ACL (1)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.18653/V1/2025.ACL-LONG.591"],"source":"https://dblp.org/rec/conf/acl/CaoHGDXZ25","documentPage":"https://doi.org/10.18653/V1/2025.ACL-LONG.591","type":"Inproceedings","doi":"https://doi.org/10.18653/V1/2025.ACL-LONG.591","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/acl/CaoHGDXZ25","documentUrl":"https://doi.org/10.18653/V1/2025.ACL-LONG.591"},{"key":"conf/acl/GaoCWKFZX25","title":"FRAG: A Flexible Modular Framework for Retrieval-Augmented Generation based on Knowledge Graphs.","year":2025,"yearOfEvent":2025,"venue":"ACL (Findings)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.18653/V1/2025.FINDINGS-ACL.321"],"source":"https://dblp.org/rec/conf/acl/GaoCWKFZX25","documentPage":"https://doi.org/10.18653/V1/2025.FINDINGS-ACL.321","type":"Inproceedings","doi":"https://doi.org/10.18653/V1/2025.FINDINGS-ACL.321","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/acl/GaoCWKFZX25","documentUrl":"https://doi.org/10.18653/V1/2025.FINDINGS-ACL.321"},{"key":"conf/acl/ZhangZMWWLZ25","title":"A General Knowledge Injection Framework for ICD Coding.","year":2025,"yearOfEvent":2025,"venue":"ACL (Findings)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.18653/V1/2025.FINDINGS-ACL.374"],"source":"https://dblp.org/rec/conf/acl/ZhangZMWWLZ25","documentPage":"https://doi.org/10.18653/V1/2025.FINDINGS-ACL.374","type":"Inproceedings","doi":"https://doi.org/10.18653/V1/2025.FINDINGS-ACL.374","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/acl/ZhangZMWWLZ25","documentUrl":"https://doi.org/10.18653/V1/2025.FINDINGS-ACL.374"},{"key":"conf/bibm/LiYZ25","title":"Distilling Dataset Summarization via Constrained Diffusion Model for Shareable Synthetic Histopathology Images.","year":2025,"yearOfEvent":2025,"venue":"BIBM","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/BIBM66473.2025.11355978"],"source":"https://dblp.org/rec/conf/bibm/LiYZ25","documentPage":"https://doi.org/10.1109/BIBM66473.2025.11355978","type":"Inproceedings","doi":"https://doi.org/10.1109/BIBM66473.2025.11355978","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/bibm/LiYZ25","documentUrl":"https://doi.org/10.1109/BIBM66473.2025.11355978"},{"key":"conf/bibm/WangYZJHTZ25","title":"KANTrust: A Multi-Omics Framework for Uncertainty-Aware Disease Subtyping.","year":2025,"yearOfEvent":2025,"venue":"BIBM","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/BIBM66473.2025.11357201"],"source":"https://dblp.org/rec/conf/bibm/WangYZJHTZ25","documentPage":"https://doi.org/10.1109/BIBM66473.2025.11357201","type":"Inproceedings","doi":"https://doi.org/10.1109/BIBM66473.2025.11357201","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/bibm/WangYZJHTZ25","documentUrl":"https://doi.org/10.1109/BIBM66473.2025.11357201"},{"key":"conf/cvpr/LuoFJZ25","title":"ICP: Immediate Compensation Pruning for Mid-to-high Sparsity.","year":2025,"yearOfEvent":2025,"venue":"CVPR","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/CVPR52734.2025.00886"],"source":"https://dblp.org/rec/conf/cvpr/LuoFJZ25","documentPage":"https://openaccess.thecvf.com/content/CVPR2025/html/Luo_ICP_Immediate_Compensation_Pruning_for_Mid-to-high_Sparsity_CVPR_2025_paper.html","type":"Inproceedings","doi":"https://doi.org/10.1109/CVPR52734.2025.00886","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/LuoFJZ25","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Luo_ICP_Immediate_Compensation_Pruning_for_Mid-to-high_Sparsity_CVPR_2025_paper.html"},{"key":"conf/cvpr/MaZYTWL0JZ25","title":"AA-CLIP: Enhancing Zero-Shot Anomaly Detection via Anomaly-Aware CLIP.","year":2025,"yearOfEvent":2025,"venue":"CVPR","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/CVPR52734.2025.00447"],"source":"https://dblp.org/rec/conf/cvpr/MaZYTWL0JZ25","documentPage":"https://openaccess.thecvf.com/content/CVPR2025/html/Ma_AA-CLIP_Enhancing_Zero-Shot_Anomaly_Detection_via_Anomaly-Aware_CLIP_CVPR_2025_paper.html","type":"Inproceedings","doi":"https://doi.org/10.1109/CVPR52734.2025.00447","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/MaZYTWL0JZ25","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Ma_AA-CLIP_Enhancing_Zero-Shot_Anomaly_Detection_via_Anomaly-Aware_CLIP_CVPR_2025_paper.html"},{"key":"conf/cvpr/ZhangLLZ25","title":"DH-Set: Improving Vision-Language Alignment with Diverse and Hybrid Set-Embeddings Learning.","year":2025,"yearOfEvent":2025,"venue":"CVPR","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/CVPR52734.2025.02327"],"source":"https://dblp.org/rec/conf/cvpr/ZhangLLZ25","documentPage":"https://openaccess.thecvf.com/content/CVPR2025/html/Zhang_DH-Set_Improving_Vision-Language_Alignment_with_Diverse_and_Hybrid_Set-Embeddings_Learning_CVPR_2025_paper.html","type":"Inproceedings","doi":"https://doi.org/10.1109/CVPR52734.2025.02327","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/ZhangLLZ25","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Zhang_DH-Set_Improving_Vision-Language_Alignment_with_Diverse_and_Hybrid_Set-Embeddings_Learning_CVPR_2025_paper.html"},{"key":"conf/ecai/DongTMGZ25","title":"Thinning a Medical Image Segmentation Model via Dual-Level Multiscale Fusion.","year":2025,"yearOfEvent":2025,"venue":"ECAI","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.3233/FAIA250874"],"source":"https://dblp.org/rec/conf/ecai/DongTMGZ25","documentPage":"https://doi.org/10.3233/FAIA250874","type":"Inproceedings","doi":"https://doi.org/10.3233/FAIA250874","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/ecai/DongTMGZ25","documentUrl":"https://doi.org/10.3233/FAIA250874"},{"key":"conf/emnlp/WangFCXZ25","title":"SkewRoute: Training-Free LLM Routing for Knowledge Graph Retrieval-Augmented Generation via Score Skewness of Retrieved Context.","year":2025,"yearOfEvent":2025,"venue":"EMNLP (Findings)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.18653/V1/2025.FINDINGS-EMNLP.606"],"source":"https://dblp.org/rec/conf/emnlp/WangFCXZ25","documentPage":"https://doi.org/10.18653/V1/2025.FINDINGS-EMNLP.606","type":"Inproceedings","doi":"https://doi.org/10.18653/V1/2025.FINDINGS-EMNLP.606","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/emnlp/WangFCXZ25","documentUrl":"https://doi.org/10.18653/V1/2025.FINDINGS-EMNLP.606"},{"key":"conf/icic/ChenHZZ25","title":"A Unified Framework for Few-Shot Medical Image Classification via Multi-agent Description Generation and Refined Contrastive Learning.","year":2025,"yearOfEvent":2025,"venue":"ICIC (28)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1007/978-981-95-0036-9_40"],"source":"https://dblp.org/rec/conf/icic/ChenHZZ25","documentPage":"https://doi.org/10.1007/978-981-95-0036-9_40","type":"Inproceedings","doi":"https://doi.org/10.1007/978-981-95-0036-9_40","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/icic/ChenHZZ25","documentUrl":"https://doi.org/10.1007/978-981-95-0036-9_40"},{"key":"conf/icic/HeHZZ25","title":"Eliminating Ambiguities in One-Shot Medical Landmark Detection via Mask Drawing.","year":2025,"yearOfEvent":2025,"venue":"ICIC (5)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1007/978-981-96-9794-6_9"],"source":"https://dblp.org/rec/conf/icic/HeHZZ25","documentPage":"https://doi.org/10.1007/978-981-96-9794-6_9","type":"Inproceedings","doi":"https://doi.org/10.1007/978-981-96-9794-6_9","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/icic/HeHZZ25","documentUrl":"https://doi.org/10.1007/978-981-96-9794-6_9"},{"key":"conf/iclr/WuKJZ25","title":"Self-Supervised Diffusion MRI Denoising via Iterative and Stable Refinement.","year":2025,"yearOfEvent":2025,"venue":"ICLR","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/iclr/WuKJZ25","documentPage":"https://openreview.net/forum?id=wxPnuFp8fZ","type":"Inproceedings","doi":null,"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iclr/WuKJZ25","documentUrl":"https://openreview.net/forum?id=wxPnuFp8fZ"},{"key":"conf/icml/FengC0XZ25","title":"Lego Sketch: A Scalable Memory-augmented Neural Network for Sketching Data Streams.","year":2025,"yearOfEvent":2025,"venue":"ICML","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/icml/FengC0XZ25","documentPage":"https://proceedings.mlr.press/v267/feng25a.html","type":"Inproceedings","doi":null,"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/icml/FengC0XZ25","documentUrl":"https://proceedings.mlr.press/v267/feng25a.html"},{"key":"conf/ijcai/KeCFCXZF25","title":"Prototype-based Optimal Transport for Out-of-Distribution Detection.","year":2025,"yearOfEvent":2025,"venue":"IJCAI","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.24963/IJCAI.2025/336"],"source":"https://dblp.org/rec/conf/ijcai/KeCFCXZF25","documentPage":"https://doi.org/10.24963/IJCAI.2025/336","type":"Inproceedings","doi":"https://doi.org/10.24963/IJCAI.2025/336","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/ijcai/KeCFCXZF25","documentUrl":"https://doi.org/10.24963/IJCAI.2025/336"},{"key":"conf/ijcai/Wang0LHTZ25","title":"MVP-CBM: Multi-layer Visual Preference-enhanced Concept Bottleneck Model for Explainable Medical Image Classification.","year":2025,"yearOfEvent":2025,"venue":"IJCAI","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.24963/IJCAI.2025/60"],"source":"https://dblp.org/rec/conf/ijcai/Wang0LHTZ25","documentPage":"https://doi.org/10.24963/IJCAI.2025/60","type":"Inproceedings","doi":"https://doi.org/10.24963/IJCAI.2025/60","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/ijcai/Wang0LHTZ25","documentUrl":"https://doi.org/10.24963/IJCAI.2025/60"},{"key":"conf/ijcnn/ShiLZ25","title":"Slide-CLIP: A Simple and Effective Pruning Method for CLIP.","year":2025,"yearOfEvent":2025,"venue":"IJCNN","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/IJCNN64981.2025.11229356"],"source":"https://dblp.org/rec/conf/ijcnn/ShiLZ25","documentPage":"https://doi.org/10.1109/IJCNN64981.2025.11229356","type":"Inproceedings","doi":"https://doi.org/10.1109/IJCNN64981.2025.11229356","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/ijcnn/ShiLZ25","documentUrl":"https://doi.org/10.1109/IJCNN64981.2025.11229356"},{"key":"conf/iros/WangLZlZ25","title":"Label-supervised surgical instrument segmentation using temporal equivariance and semantic continuity.","year":2025,"yearOfEvent":2025,"venue":"IROS","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/IROS60139.2025.11247143"],"source":"https://dblp.org/rec/conf/iros/WangLZlZ25","documentPage":"https://doi.org/10.1109/IROS60139.2025.11247143","type":"Inproceedings","doi":"https://doi.org/10.1109/IROS60139.2025.11247143","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iros/WangLZlZ25","documentUrl":"https://doi.org/10.1109/IROS60139.2025.11247143"},{"key":"conf/isbi/YangZ25","title":"EDA: Enhanced Domain-Adversarial Training for Anatomical Landmark Detection.","year":2025,"yearOfEvent":2025,"venue":"ISBI","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/ISBI60581.2025.10980903"],"source":"https://dblp.org/rec/conf/isbi/YangZ25","documentPage":"https://doi.org/10.1109/ISBI60581.2025.10980903","type":"Inproceedings","doi":"https://doi.org/10.1109/ISBI60581.2025.10980903","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/isbi/YangZ25","documentUrl":"https://doi.org/10.1109/ISBI60581.2025.10980903"},{"key":"conf/isbi/ZhaoQZ25","title":"ExpTopo: Explicit Topological Modeling for Bronchus Segmentation.","year":2025,"yearOfEvent":2025,"venue":"ISBI","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/ISBI60581.2025.10980891"],"source":"https://dblp.org/rec/conf/isbi/ZhaoQZ25","documentPage":"https://doi.org/10.1109/ISBI60581.2025.10980891","type":"Inproceedings","doi":"https://doi.org/10.1109/ISBI60581.2025.10980891","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/isbi/ZhaoQZ25","documentUrl":"https://doi.org/10.1109/ISBI60581.2025.10980891"},{"key":"conf/mm/TangNDMQD00Z25","title":"Mobile U-ViT: Revisiting large kernel and U-shaped ViT for efficient medical image segmentation.","year":2025,"yearOfEvent":2025,"venue":"ACM Multimedia","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1145/3746027.3755076"],"source":"https://dblp.org/rec/conf/mm/TangNDMQD00Z25","documentPage":"https://doi.org/10.1145/3746027.3755076","type":"Inproceedings","doi":"https://doi.org/10.1145/3746027.3755076","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/mm/TangNDMQD00Z25","documentUrl":"https://doi.org/10.1145/3746027.3755076"},{"key":"conf/mm/ZhaoLJZ25","title":"LoCo: Training-Free Layout-to-Image Synthesis with Localized Constraints.","year":2025,"yearOfEvent":2025,"venue":"ACM Multimedia","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1145/3746027.3754905"],"source":"https://dblp.org/rec/conf/mm/ZhaoLJZ25","documentPage":"https://doi.org/10.1145/3746027.3754905","type":"Inproceedings","doi":"https://doi.org/10.1145/3746027.3754905","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/mm/ZhaoLJZ25","documentUrl":"https://doi.org/10.1145/3746027.3754905"},{"key":"conf/nips/FengLCXZ25","title":"Ada-KV: Optimizing KV Cache Eviction by Adaptive Budget Allocation for Efficient LLM Inference.","year":2025,"yearOfEvent":2025,"venue":"NeurIPS","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/nips/FengLCXZ25","documentPage":"http://papers.nips.cc/paper_files/paper/2025/hash/a40ff56daab9f4808b1e18350c8a11ce-Abstract-Conference.html","type":"Inproceedings","doi":null,"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/nips/FengLCXZ25","documentUrl":"http://papers.nips.cc/paper_files/paper/2025/hash/a40ff56daab9f4808b1e18350c8a11ce-Abstract-Conference.html"},{"key":"conf/robosoft/ZhouHSHM25","title":"Improving Swimming Performance in Soft Robotic Fish with Distributed Muscles and Embedded Kinematic Sensing.","year":2025,"yearOfEvent":2025,"venue":"RoboSoft","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/ROBOSOFT63089.2025.11020876"],"source":"https://dblp.org/rec/conf/robosoft/ZhouHSHM25","documentPage":"https://doi.org/10.1109/ROBOSOFT63089.2025.11020876","type":"Inproceedings","doi":"https://doi.org/10.1109/ROBOSOFT63089.2025.11020876","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/robosoft/ZhouHSHM25","documentUrl":"https://doi.org/10.1109/ROBOSOFT63089.2025.11020876"},{"key":"conf/wacv/GaoYLXZ25","title":"MS-Glance: Bio-Inspired Non-Semantic Context Vectors and Their Applications in Supervising Image Reconstruction.","year":2025,"yearOfEvent":2025,"venue":"WACV","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/WACV61041.2025.00305"],"source":"https://dblp.org/rec/conf/wacv/GaoYLXZ25","documentPage":"https://doi.org/10.1109/WACV61041.2025.00305","type":"Inproceedings","doi":"https://doi.org/10.1109/WACV61041.2025.00305","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/wacv/GaoYLXZ25","documentUrl":"https://doi.org/10.1109/WACV61041.2025.00305"},{"key":"conf/wacv/MaYZHJZ25","title":"Towards Accurate Unified Anomaly Segmentation.","year":2025,"yearOfEvent":2025,"venue":"WACV","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/WACV61041.2025.00138"],"source":"https://dblp.org/rec/conf/wacv/MaYZHJZ25","documentPage":"https://doi.org/10.1109/WACV61041.2025.00138","type":"Inproceedings","doi":"https://doi.org/10.1109/WACV61041.2025.00138","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/wacv/MaYZHJZ25","documentUrl":"https://doi.org/10.1109/WACV61041.2025.00138"},{"key":"conf/wacv/YangJ0Z25","title":"PostoMETRO: Pose Token Enhanced Mesh Transformer for Robust 3D Human Mesh Recovery.","year":2025,"yearOfEvent":2025,"venue":"WACV","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/WACV61041.2025.00465"],"source":"https://dblp.org/rec/conf/wacv/YangJ0Z25","documentPage":"https://doi.org/10.1109/WACV61041.2025.00465","type":"Inproceedings","doi":"https://doi.org/10.1109/WACV61041.2025.00465","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/wacv/YangJ0Z25","documentUrl":"https://doi.org/10.1109/WACV61041.2025.00465"},{"key":"journals/bmcmi/ZhaoHLWZX25","title":"Zero-echo time magnetic resonance imaging for visualizing pulmonary neoplasms.","year":2025,"yearOfEvent":null,"venue":"BMC Medical Imaging","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1186/S12880-025-01666-5"],"source":"https://dblp.org/rec/journals/bmcmi/ZhaoHLWZX25","documentPage":"https://doi.org/10.1186/S12880-025-01666-5","type":"Article","doi":"https://doi.org/10.1186/S12880-025-01666-5","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/bmcmi/ZhaoHLWZX25","documentUrl":"https://doi.org/10.1186/S12880-025-01666-5"},{"key":"journals/memetic/HuZLLLZY25","title":"A Multi-start Algorithm with Iterated Decremental Local Search for Minimum Capacitated Dominating Set Problem in Large Graphs.","year":2025,"yearOfEvent":null,"venue":"Memetic Comput.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1007/S12293-025-00470-6"],"source":"https://dblp.org/rec/journals/memetic/HuZLLLZY25","documentPage":"https://doi.org/10.1007/S12293-025-00470-6","type":"Article","doi":"https://doi.org/10.1007/S12293-025-00470-6","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/memetic/HuZLLLZY25","documentUrl":"https://doi.org/10.1007/S12293-025-00470-6"},{"key":"journals/mia/LiFLZJZ25","title":"3DGR-CT: Sparse-view CT reconstruction with a 3D Gaussian representation.","year":2025,"yearOfEvent":null,"venue":"Medical Image Anal.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1016/J.MEDIA.2025.103585"],"source":"https://dblp.org/rec/journals/mia/LiFLZJZ25","documentPage":"https://doi.org/10.1016/J.MEDIA.2025.103585","type":"Article","doi":"https://doi.org/10.1016/J.MEDIA.2025.103585","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/mia/LiFLZJZ25","documentUrl":"https://doi.org/10.1016/J.MEDIA.2025.103585"},{"key":"journals/mia/LiYLLZCWZXWMZCZ25","title":"O-PRESS: Boosting OCT axial resolution with Prior guidance, Recurrence, and Equivariant Self-Supervision.","year":2025,"yearOfEvent":null,"venue":"Medical Image Anal.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1016/J.MEDIA.2024.103319"],"source":"https://dblp.org/rec/journals/mia/LiYLLZCWZXWMZCZ25","documentPage":"https://doi.org/10.1016/J.MEDIA.2024.103319","type":"Article","doi":"https://doi.org/10.1016/J.MEDIA.2024.103319","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/mia/LiYLLZCWZXWMZCZ25","documentUrl":"https://doi.org/10.1016/J.MEDIA.2024.103319"},{"key":"journals/mia/TangNLJYLZ25","title":"MambaMIM: Pre-training Mamba with state space token interpolation and its application to medical image segmentation.","year":2025,"yearOfEvent":null,"venue":"Medical Image Anal.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1016/J.MEDIA.2025.103606"],"source":"https://dblp.org/rec/journals/mia/TangNLJYLZ25","documentPage":"https://doi.org/10.1016/J.MEDIA.2025.103606","type":"Article","doi":"https://doi.org/10.1016/J.MEDIA.2025.103606","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/mia/TangNLJYLZ25","documentUrl":"https://doi.org/10.1016/J.MEDIA.2025.103606"},{"key":"journals/mia/WangYJLHTZ25","title":"ECAMP: Entity-centered Context-aware Medical Vision Language Pre-training.","year":2025,"yearOfEvent":null,"venue":"Medical Image Anal.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1016/J.MEDIA.2025.103690"],"source":"https://dblp.org/rec/journals/mia/WangYJLHTZ25","documentPage":"https://doi.org/10.1016/J.MEDIA.2025.103690","type":"Article","doi":"https://doi.org/10.1016/J.MEDIA.2025.103690","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/mia/WangYJLHTZ25","documentUrl":"https://doi.org/10.1016/J.MEDIA.2025.103690"},{"key":"journals/mia/WangZXZ25","title":"LACOSTE: Exploiting stereo and temporal contexts for surgical instrument segmentation.","year":2025,"yearOfEvent":null,"venue":"Medical Image Anal.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1016/J.MEDIA.2024.103387"],"source":"https://dblp.org/rec/journals/mia/WangZXZ25","documentPage":"https://doi.org/10.1016/J.MEDIA.2024.103387","type":"Article","doi":"https://doi.org/10.1016/J.MEDIA.2024.103387","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/mia/WangZXZ25","documentUrl":"https://doi.org/10.1016/J.MEDIA.2024.103387"},{"key":"journals/mia/ZhaoLZZZFQLZ25","title":"Skeleton2Mask: Skeleton-supervised airway segmentation.","year":2025,"yearOfEvent":null,"venue":"Medical Image Anal.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1016/J.MEDIA.2025.103693"],"source":"https://dblp.org/rec/journals/mia/ZhaoLZZZFQLZ25","documentPage":"https://doi.org/10.1016/J.MEDIA.2025.103693","type":"Article","doi":"https://doi.org/10.1016/J.MEDIA.2025.103693","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/mia/ZhaoLZZZFQLZ25","documentUrl":"https://doi.org/10.1016/J.MEDIA.2025.103693"},{"key":"journals/npjdm/JiangFRWZHLSTDWXDGWZCL25","title":"From pretraining to privacy: federated ultrasound foundation model with self-supervised learning.","year":2025,"yearOfEvent":null,"venue":"npj Digit. Medicine","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1038/S41746-025-02085-0"],"source":"https://dblp.org/rec/journals/npjdm/JiangFRWZHLSTDWXDGWZCL25","documentPage":"https://doi.org/10.1038/S41746-025-02085-0","type":"Article","doi":"https://doi.org/10.1038/S41746-025-02085-0","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/npjdm/JiangFRWZHLSTDWXDGWZCL25","documentUrl":"https://doi.org/10.1038/S41746-025-02085-0"},{"key":"journals/npjdm/XuTQYKDNZ25","title":"Fair ultrasound diagnosis via adversarial protected attribute aware perturbations on latent embeddings.","year":2025,"yearOfEvent":null,"venue":"npj Digit. Medicine","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1038/S41746-025-01641-Y"],"source":"https://dblp.org/rec/journals/npjdm/XuTQYKDNZ25","documentPage":"https://doi.org/10.1038/S41746-025-01641-Y","type":"Article","doi":"https://doi.org/10.1038/S41746-025-01641-Y","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/npjdm/XuTQYKDNZ25","documentUrl":"https://doi.org/10.1038/S41746-025-01641-Y"},{"key":"journals/pacmmod/XiangDGWXZ25","title":"Capsule: An Out-of-Core Training Mechanism for Colossal GNNs.","year":2025,"yearOfEvent":null,"venue":"Proc. ACM Manag. Data","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1145/3709669"],"source":"https://dblp.org/rec/journals/pacmmod/XiangDGWXZ25","documentPage":"https://doi.org/10.1145/3709669","type":"Article","doi":"https://doi.org/10.1145/3709669","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/pacmmod/XiangDGWXZ25","documentUrl":"https://doi.org/10.1145/3709669"},{"key":"journals/pvldb/CaoGLXZX25","title":"LEGO-GraphRAG: Modularizing Graph-based Retrieval-Augmented Generation for Design Space Exploration.","year":2025,"yearOfEvent":null,"venue":"Proc. VLDB Endow.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.14778/3748191.3748194"],"source":"https://dblp.org/rec/journals/pvldb/CaoGLXZX25","documentPage":"https://www.vldb.org/pvldb/vol18/p3269-cao.pdf","type":"Article","doi":"https://doi.org/10.14778/3748191.3748194","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/pvldb/CaoGLXZX25","documentUrl":"https://www.vldb.org/pvldb/vol18/p3269-cao.pdf"},{"key":"journals/tim/DengJWZ25","title":"CCA-Net: Zero-Shot SSVEP Classification via an Integration of Canonical Correlation Analysis and Deep Neural Network.","year":2025,"yearOfEvent":null,"venue":"IEEE Trans. Instrum. Meas.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1109/TIM.2025.3571139"],"source":"https://dblp.org/rec/journals/tim/DengJWZ25","documentPage":"https://doi.org/10.1109/TIM.2025.3571139","type":"Article","doi":"https://doi.org/10.1109/TIM.2025.3571139","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/tim/DengJWZ25","documentUrl":"https://doi.org/10.1109/TIM.2025.3571139"},{"key":"journals/tip/NianTDYZZL25","title":"SRS: Siamese Reconstruction-Segmentation Network Based on Dynamic-Parameter Convolution.","year":2025,"yearOfEvent":null,"venue":"IEEE Trans. Image Process.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1109/TIP.2025.3607624"],"source":"https://dblp.org/rec/journals/tip/NianTDYZZL25","documentPage":"https://doi.org/10.1109/TIP.2025.3607624","type":"Article","doi":"https://doi.org/10.1109/TIP.2025.3607624","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/tip/NianTDYZZL25","documentUrl":"https://doi.org/10.1109/TIP.2025.3607624"},{"key":"journals/tmi/QuanYZZ25","title":"IGU-Aug: Information-Guided Unsupervised Augmentation and Pixel-Wise Contrastive Learning for Medical Image Analysis.","year":2025,"yearOfEvent":null,"venue":"IEEE Trans. Medical Imaging","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1109/TMI.2024.3436713"],"source":"https://dblp.org/rec/journals/tmi/QuanYZZ25","documentPage":"https://doi.org/10.1109/TMI.2024.3436713","type":"Article","doi":"https://doi.org/10.1109/TMI.2024.3436713","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/tmi/QuanYZZ25","documentUrl":"https://doi.org/10.1109/TMI.2024.3436713"},{"key":"journals/tmi/ZhangPWSLZ25","title":"Unified Multi-Modal Image Synthesis for Missing Modality Imputation.","year":2025,"yearOfEvent":null,"venue":"IEEE Trans. Medical Imaging","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1109/TMI.2024.3424785"],"source":"https://dblp.org/rec/journals/tmi/ZhangPWSLZ25","documentPage":"https://doi.org/10.1109/TMI.2024.3424785","type":"Article","doi":"https://doi.org/10.1109/TMI.2024.3424785","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/tmi/ZhangPWSLZ25","documentUrl":"https://doi.org/10.1109/TMI.2024.3424785"}],"preprints":[{"key":"journals/corr/abs-2501-03565","title":"Bridged Semantic Alignment for Zero-shot 3D Medical Image Diagnosis.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2501.03565"],"source":"https://dblp.org/rec/journals/corr/abs-2501-03565","documentPage":"https://doi.org/10.48550/ARXIV.2501.03565","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2501.03565","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2501-03565","documentUrl":"https://doi.org/10.48550/ARXIV.2501.03565","arxivId":"2501.03565","arxivUrl":"https://arxiv.org/abs/2501.03565"},{"key":"journals/corr/abs-2501-09957","title":"FRAG: A Flexible Modular Framework for Retrieval-Augmented Generation based on Knowledge Graphs.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2501.09957"],"source":"https://dblp.org/rec/journals/corr/abs-2501-09957","documentPage":"https://doi.org/10.48550/ARXIV.2501.09957","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2501.09957","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2501-09957","documentUrl":"https://doi.org/10.48550/ARXIV.2501.09957","arxivId":"2501.09957","arxivUrl":"https://arxiv.org/abs/2501.09957"},{"key":"journals/corr/abs-2501-12295","title":"Towards Accurate Unified Anomaly Segmentation.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2501.12295"],"source":"https://dblp.org/rec/journals/corr/abs-2501-12295","documentPage":"https://doi.org/10.48550/ARXIV.2501.12295","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2501.12295","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2501-12295","documentUrl":"https://doi.org/10.48550/ARXIV.2501.12295","arxivId":"2501.12295","arxivUrl":"https://arxiv.org/abs/2501.12295"},{"key":"journals/corr/abs-2501-13514","title":"Self-Supervised Diffusion MRI Denoising via Iterative and Stable Refinement.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2501.13514"],"source":"https://dblp.org/rec/journals/corr/abs-2501-13514","documentPage":"https://doi.org/10.48550/ARXIV.2501.13514","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2501.13514","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2501-13514","documentUrl":"https://doi.org/10.48550/ARXIV.2501.13514","arxivId":"2501.13514","arxivUrl":"https://arxiv.org/abs/2501.13514"},{"key":"journals/corr/abs-2502-03805","title":"Identify Critical KV Cache in LLM Inference from an Output Perturbation Perspective.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2502.03805"],"source":"https://dblp.org/rec/journals/corr/abs-2502-03805","documentPage":"https://doi.org/10.48550/ARXIV.2502.03805","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2502.03805","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2502-03805","documentUrl":"https://doi.org/10.48550/ARXIV.2502.03805","arxivId":"2502.03805","arxivUrl":"https://arxiv.org/abs/2502.03805"},{"key":"journals/corr/abs-2502-08347","title":"Hi-End-MAE: Hierarchical encoder-driven masked autoencoders are stronger vision learners for medical image segmentation.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2502.08347"],"source":"https://dblp.org/rec/journals/corr/abs-2502-08347","documentPage":"https://doi.org/10.48550/ARXIV.2502.08347","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2502.08347","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2502-08347","documentUrl":"https://doi.org/10.48550/ARXIV.2502.08347","arxivId":"2502.08347","arxivUrl":"https://arxiv.org/abs/2502.08347"},{"key":"journals/corr/abs-2503-05203","title":"Path Pooling: Train-Free Structure Enhancement for Efficient Knowledge Graph Retrieval-Augmented Generation.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2503.05203"],"source":"https://dblp.org/rec/journals/corr/abs-2503-05203","documentPage":"https://doi.org/10.48550/ARXIV.2503.05203","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2503.05203","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-05203","documentUrl":"https://doi.org/10.48550/ARXIV.2503.05203","arxivId":"2503.05203","arxivUrl":"https://arxiv.org/abs/2503.05203"},{"key":"journals/corr/abs-2503-06661","title":"AA-CLIP: Enhancing Zero-shot Anomaly Detection via Anomaly-Aware CLIP.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2503.06661"],"source":"https://dblp.org/rec/journals/corr/abs-2503-06661","documentPage":"https://doi.org/10.48550/ARXIV.2503.06661","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2503.06661","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-06661","documentUrl":"https://doi.org/10.48550/ARXIV.2503.06661","arxivId":"2503.06661","arxivUrl":"https://arxiv.org/abs/2503.06661"},{"key":"journals/corr/abs-2503-09332","title":"SDD-4DGS: Static-Dynamic Aware Decoupling in Gaussian Splatting for 4D Scene Reconstruction.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2503.09332"],"source":"https://dblp.org/rec/journals/corr/abs-2503-09332","documentPage":"https://doi.org/10.48550/ARXIV.2503.09332","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2503.09332","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-09332","documentUrl":"https://doi.org/10.48550/ARXIV.2503.09332","arxivId":"2503.09332","arxivUrl":"https://arxiv.org/abs/2503.09332"},{"key":"journals/corr/abs-2503-16058","title":"Landmarks Are Alike Yet Distinct: Harnessing Similarity and Individuality for One-Shot Medical Landmark Detection.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2503.16058"],"source":"https://dblp.org/rec/journals/corr/abs-2503-16058","documentPage":"https://doi.org/10.48550/ARXIV.2503.16058","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2503.16058","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-16058","documentUrl":"https://doi.org/10.48550/ARXIV.2503.16058","arxivId":"2503.16058","arxivUrl":"https://arxiv.org/abs/2503.16058"},{"key":"journals/corr/abs-2503-17983","title":"Histomorphology-driven multi-instance learning for breast cancer WSI classification.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2503.17983"],"source":"https://dblp.org/rec/journals/corr/abs-2503-17983","documentPage":"https://doi.org/10.48550/ARXIV.2503.17983","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2503.17983","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-17983","documentUrl":"https://doi.org/10.48550/ARXIV.2503.17983","arxivId":"2503.17983","arxivUrl":"https://arxiv.org/abs/2503.17983"},{"key":"journals/corr/abs-2504-02382","title":"Benchmark of Segmentation Techniques for Pelvic Fracture in CT and X-ray: Summary of the PENGWIN 2024 Challenge.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2504.02382"],"source":"https://dblp.org/rec/journals/corr/abs-2504-02382","documentPage":"https://doi.org/10.48550/ARXIV.2504.02382","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2504.02382","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2504-02382","documentUrl":"https://doi.org/10.48550/ARXIV.2504.02382","arxivId":"2504.02382","arxivUrl":"https://arxiv.org/abs/2504.02382"},{"key":"journals/corr/abs-2504-11377","title":"Improving Swimming Performance in Soft Robotic Fish with Distributed Muscles and Embedded Kinematic Sensing.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2504.11377"],"source":"https://dblp.org/rec/journals/corr/abs-2504-11377","documentPage":"https://doi.org/10.48550/ARXIV.2504.11377","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2504.11377","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2504-11377","documentUrl":"https://doi.org/10.48550/ARXIV.2504.11377","arxivId":"2504.11377","arxivUrl":"https://arxiv.org/abs/2504.11377"},{"key":"journals/corr/abs-2505-08123","title":"JSover: Joint Spectrum Estimation and Multi-Material Decomposition from Single-Energy CT Projections.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2505.08123"],"source":"https://dblp.org/rec/journals/corr/abs-2505-08123","documentPage":"https://doi.org/10.48550/ARXIV.2505.08123","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2505.08123","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-08123","documentUrl":"https://doi.org/10.48550/ARXIV.2505.08123","arxivId":"2505.08123","arxivUrl":"https://arxiv.org/abs/2505.08123"},{"key":"journals/corr/abs-2505-18708","title":"A General Knowledge Injection Framework for ICD Coding.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2505.18708"],"source":"https://dblp.org/rec/journals/corr/abs-2505-18708","documentPage":"https://doi.org/10.48550/ARXIV.2505.18708","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2505.18708","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-18708","documentUrl":"https://doi.org/10.48550/ARXIV.2505.18708","arxivId":"2505.18708","arxivUrl":"https://arxiv.org/abs/2505.18708"},{"key":"journals/corr/abs-2505-18741","title":"MoMBS: Mixed-order minibatch sampling enhances model training from diverse-quality images.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2505.18741"],"source":"https://dblp.org/rec/journals/corr/abs-2505-18741","documentPage":"https://doi.org/10.48550/ARXIV.2505.18741","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2505.18741","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-18741","documentUrl":"https://doi.org/10.48550/ARXIV.2505.18741","arxivId":"2505.18741","arxivUrl":"https://arxiv.org/abs/2505.18741"},{"key":"journals/corr/abs-2505-19049","title":"Disentangled Human Body Representation Based on Unsupervised Semantic-Aware Learning.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2505.19049"],"source":"https://dblp.org/rec/journals/corr/abs-2505-19049","documentPage":"https://doi.org/10.48550/ARXIV.2505.19049","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2505.19049","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-19049","documentUrl":"https://doi.org/10.48550/ARXIV.2505.19049","arxivId":"2505.19049","arxivUrl":"https://arxiv.org/abs/2505.19049"},{"key":"journals/corr/abs-2505-19561","title":"Lego Sketch: A Scalable Memory-augmented Neural Network for Sketching Data Streams.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2505.19561"],"source":"https://dblp.org/rec/journals/corr/abs-2505-19561","documentPage":"https://doi.org/10.48550/ARXIV.2505.19561","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2505.19561","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-19561","documentUrl":"https://doi.org/10.48550/ARXIV.2505.19561","arxivId":"2505.19561","arxivUrl":"https://arxiv.org/abs/2505.19561"},{"key":"journals/corr/abs-2505-22126","title":"SridBench: Benchmark of Scientific Research Illustration Drawing of Image Generation Model.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2505.22126"],"source":"https://dblp.org/rec/journals/corr/abs-2505-22126","documentPage":"https://doi.org/10.48550/ARXIV.2505.22126","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2505.22126","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-22126","documentUrl":"https://doi.org/10.48550/ARXIV.2505.22126","arxivId":"2505.22126","arxivUrl":"https://arxiv.org/abs/2505.22126"},{"key":"journals/corr/abs-2505-23841","title":"SkewRoute: Training-Free LLM Routing for Knowledge Graph Retrieval-Augmented Generation via Score Skewness of Retrieved Context.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2505.23841"],"source":"https://dblp.org/rec/journals/corr/abs-2505-23841","documentPage":"https://doi.org/10.48550/ARXIV.2505.23841","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2505.23841","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-23841","documentUrl":"https://doi.org/10.48550/ARXIV.2505.23841","arxivId":"2505.23841","arxivUrl":"https://arxiv.org/abs/2505.23841"},{"key":"journals/corr/abs-2506-08967","title":"Step-Audio-AQAA: a Fully End-to-End Expressive Large Audio Language Model.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2506.08967"],"source":"https://dblp.org/rec/journals/corr/abs-2506-08967","documentPage":"https://doi.org/10.48550/ARXIV.2506.08967","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2506.08967","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-08967","documentUrl":"https://doi.org/10.48550/ARXIV.2506.08967","arxivId":"2506.08967","arxivUrl":"https://arxiv.org/abs/2506.08967"},{"key":"journals/corr/abs-2506-09427","title":"A High-Quality Dataset and Reliable Evaluation for Interleaved Image-Text Generation.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2506.09427"],"source":"https://dblp.org/rec/journals/corr/abs-2506-09427","documentPage":"https://doi.org/10.48550/ARXIV.2506.09427","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2506.09427","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-09427","documentUrl":"https://doi.org/10.48550/ARXIV.2506.09427","arxivId":"2506.09427","arxivUrl":"https://arxiv.org/abs/2506.09427"},{"key":"journals/corr/abs-2506-12568","title":"MVP-CBM:Multi-layer Visual Preference-enhanced Concept Bottleneck Model for Explainable Medical Image Classification.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2506.12568"],"source":"https://dblp.org/rec/journals/corr/abs-2506-12568","documentPage":"https://doi.org/10.48550/ARXIV.2506.12568","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2506.12568","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-12568","documentUrl":"https://doi.org/10.48550/ARXIV.2506.12568","arxivId":"2506.12568","arxivUrl":"https://arxiv.org/abs/2506.12568"},{"key":"journals/corr/abs-2506-12808","title":"Leveraging MIMIC Datasets for Better Digital Health: A Review on Open Problems, Progress Highlights, and Future Promises.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2506.12808"],"source":"https://dblp.org/rec/journals/corr/abs-2506-12808","documentPage":"https://doi.org/10.48550/ARXIV.2506.12808","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2506.12808","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-12808","documentUrl":"https://doi.org/10.48550/ARXIV.2506.12808","arxivId":"2506.12808","arxivUrl":"https://arxiv.org/abs/2506.12808"},{"key":"journals/corr/abs-2506-18034","title":"Pre-Trained LLM is a Semantic-Aware and Generalizable Segmentation Booster.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2506.18034"],"source":"https://dblp.org/rec/journals/corr/abs-2506-18034","documentPage":"https://doi.org/10.48550/ARXIV.2506.18034","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2506.18034","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-18034","documentUrl":"https://doi.org/10.48550/ARXIV.2506.18034","arxivId":"2506.18034","arxivUrl":"https://arxiv.org/abs/2506.18034"},{"key":"journals/corr/abs-2506-19742","title":"NeRF-based CBCT Reconstruction needs Normalization and Initialization.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2506.19742"],"source":"https://dblp.org/rec/journals/corr/abs-2506-19742","documentPage":"https://doi.org/10.48550/ARXIV.2506.19742","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2506.19742","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-19742","documentUrl":"https://doi.org/10.48550/ARXIV.2506.19742","arxivId":"2506.19742","arxivUrl":"https://arxiv.org/abs/2506.19742"},{"key":"journals/corr/abs-2506-21001","title":"Style-Aligned Image Composition for Robust Detection of Abnormal Cells in Cytopathology.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2506.21001"],"source":"https://dblp.org/rec/journals/corr/abs-2506-21001","documentPage":"https://doi.org/10.48550/ARXIV.2506.21001","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2506.21001","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-21001","documentUrl":"https://doi.org/10.48550/ARXIV.2506.21001","arxivId":"2506.21001","arxivUrl":"https://arxiv.org/abs/2506.21001"},{"key":"journals/corr/abs-2507-11415","title":"U-RWKV: Lightweight medical image segmentation with direction-adaptive RWKV.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2507.11415"],"source":"https://dblp.org/rec/journals/corr/abs-2507-11415","documentPage":"https://doi.org/10.48550/ARXIV.2507.11415","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2507.11415","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2507-11415","documentUrl":"https://doi.org/10.48550/ARXIV.2507.11415","arxivId":"2507.11415","arxivUrl":"https://arxiv.org/abs/2507.11415"},{"key":"journals/corr/abs-2507-16608","title":"Dyna3DGR: 4D Cardiac Motion Tracking with Dynamic 3D Gaussian Representation.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2507.16608"],"source":"https://dblp.org/rec/journals/corr/abs-2507-16608","documentPage":"https://doi.org/10.48550/ARXIV.2507.16608","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2507.16608","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2507-16608","documentUrl":"https://doi.org/10.48550/ARXIV.2507.16608","arxivId":"2507.16608","arxivUrl":"https://arxiv.org/abs/2507.16608"},{"key":"journals/corr/abs-2508-10947","title":"MedAtlas: Evaluating LLMs for Multi-Round, Multi-Task Medical Reasoning Across Diverse Imaging Modalities and Clinical Text.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2508.10947"],"source":"https://dblp.org/rec/journals/corr/abs-2508-10947","documentPage":"https://doi.org/10.48550/ARXIV.2508.10947","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2508.10947","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-10947","documentUrl":"https://doi.org/10.48550/ARXIV.2508.10947","arxivId":"2508.10947","arxivUrl":"https://arxiv.org/abs/2508.10947"},{"key":"journals/corr/abs-2508-15476","title":"LGMSNet: Thinning a medical image segmentation model via dual-level multiscale fusion.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2508.15476"],"source":"https://dblp.org/rec/journals/corr/abs-2508-15476","documentPage":"https://doi.org/10.48550/ARXIV.2508.15476","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2508.15476","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-15476","documentUrl":"https://doi.org/10.48550/ARXIV.2508.15476","arxivId":"2508.15476","arxivUrl":"https://arxiv.org/abs/2508.15476"},{"key":"journals/corr/abs-2508-21154","title":"RadGS-Reg: Registering Spine CT with Biplanar X-rays via Joint 3D Radiative Gaussians Reconstruction and 3D/3D Registration.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2508.21154"],"source":"https://dblp.org/rec/journals/corr/abs-2508-21154","documentPage":"https://doi.org/10.48550/ARXIV.2508.21154","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2508.21154","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-21154","documentUrl":"https://doi.org/10.48550/ARXIV.2508.21154","arxivId":"2508.21154","arxivUrl":"https://arxiv.org/abs/2508.21154"},{"key":"journals/corr/abs-2509-08311","title":"SimCroP: Radiograph Representation Learning with Similarity-driven Cross-granularity Pre-training.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2509.08311"],"source":"https://dblp.org/rec/journals/corr/abs-2509-08311","documentPage":"https://doi.org/10.48550/ARXIV.2509.08311","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2509.08311","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-08311","documentUrl":"https://doi.org/10.48550/ARXIV.2509.08311","arxivId":"2509.08311","arxivUrl":"https://arxiv.org/abs/2509.08311"},{"key":"journals/corr/abs-2509-13175","title":"More performant and scalable: Rethinking contrastive vision-language pre-training of radiology in the LLM era.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2509.13175"],"source":"https://dblp.org/rec/journals/corr/abs-2509-13175","documentPage":"https://doi.org/10.48550/ARXIV.2509.13175","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2509.13175","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-13175","documentUrl":"https://doi.org/10.48550/ARXIV.2509.13175","arxivId":"2509.13175","arxivUrl":"https://arxiv.org/abs/2509.13175"},{"key":"journals/corr/abs-2509-20067","title":"MACD: Multi-Agent Clinical Diagnosis with Self-Learned Knowledge for LLM.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2509.20067"],"source":"https://dblp.org/rec/journals/corr/abs-2509-20067","documentPage":"https://doi.org/10.48550/ARXIV.2509.20067","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2509.20067","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-20067","documentUrl":"https://doi.org/10.48550/ARXIV.2509.20067","arxivId":"2509.20067","arxivUrl":"https://arxiv.org/abs/2509.20067"},{"key":"journals/corr/abs-2509-26574","title":"Probing the Critical Point (CritPt) of AI Reasoning: a Frontier Physics Research Benchmark.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2509.26574"],"source":"https://dblp.org/rec/journals/corr/abs-2509-26574","documentPage":"https://doi.org/10.48550/ARXIV.2509.26574","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2509.26574","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-26574","documentUrl":"https://doi.org/10.48550/ARXIV.2509.26574","arxivId":"2509.26574","arxivUrl":"https://arxiv.org/abs/2509.26574"},{"key":"journals/corr/abs-2510-07041","title":"U-Bench: A Comprehensive Understanding of U-Net through 100-Variant Benchmarking.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2510.07041"],"source":"https://dblp.org/rec/journals/corr/abs-2510-07041","documentPage":"https://doi.org/10.48550/ARXIV.2510.07041","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2510.07041","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-07041","documentUrl":"https://doi.org/10.48550/ARXIV.2510.07041","arxivId":"2510.07041","arxivUrl":"https://arxiv.org/abs/2510.07041"},{"key":"journals/corr/abs-2510-09995","title":"FlareX: A Physics-Informed Dataset for Lens Flare Removal via 2D Synthesis and 3D Rendering.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2510.09995"],"source":"https://dblp.org/rec/journals/corr/abs-2510-09995","documentPage":"https://doi.org/10.48550/ARXIV.2510.09995","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2510.09995","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-09995","documentUrl":"https://doi.org/10.48550/ARXIV.2510.09995","arxivId":"2510.09995","arxivUrl":"https://arxiv.org/abs/2510.09995"},{"key":"journals/corr/abs-2510-13334","title":"Taming the Fragility of KV Cache Eviction in LLM Inference.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2510.13334"],"source":"https://dblp.org/rec/journals/corr/abs-2510-13334","documentPage":"https://doi.org/10.48550/ARXIV.2510.13334","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2510.13334","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-13334","documentUrl":"https://doi.org/10.48550/ARXIV.2510.13334","arxivId":"2510.13334","arxivUrl":"https://arxiv.org/abs/2510.13334"},{"key":"journals/corr/abs-2510-16769","title":"See or Say Graphs: Agent-Driven Scalable Graph Understanding with Vision-Language Models.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2510.16769"],"source":"https://dblp.org/rec/journals/corr/abs-2510-16769","documentPage":"https://doi.org/10.48550/ARXIV.2510.16769","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2510.16769","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-16769","documentUrl":"https://doi.org/10.48550/ARXIV.2510.16769","arxivId":"2510.16769","arxivUrl":"https://arxiv.org/abs/2510.16769"},{"key":"journals/corr/abs-2510-19626","title":"MedReason-R1: Learning to Reason for CT Diagnosis with Reinforcement Learning and Local Zoom.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2510.19626"],"source":"https://dblp.org/rec/journals/corr/abs-2510-19626","documentPage":"https://doi.org/10.48550/ARXIV.2510.19626","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2510.19626","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-19626","documentUrl":"https://doi.org/10.48550/ARXIV.2510.19626","arxivId":"2510.19626","arxivUrl":"https://arxiv.org/abs/2510.19626"},{"key":"journals/corr/abs-2510-27237","title":"Fusion of Heterogeneous Pathology Foundation Models for Whole Slide Image Analysis.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2510.27237"],"source":"https://dblp.org/rec/journals/corr/abs-2510-27237","documentPage":"https://doi.org/10.48550/ARXIV.2510.27237","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2510.27237","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-27237","documentUrl":"https://doi.org/10.48550/ARXIV.2510.27237","arxivId":"2510.27237","arxivUrl":"https://arxiv.org/abs/2510.27237"},{"key":"journals/corr/abs-2511-09965","title":"Equivariant Sampling for Improving Diffusion Model-based Image Restoration.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2511.09965"],"source":"https://dblp.org/rec/journals/corr/abs-2511-09965","documentPage":"https://doi.org/10.48550/ARXIV.2511.09965","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2511.09965","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2511-09965","documentUrl":"https://doi.org/10.48550/ARXIV.2511.09965","arxivId":"2511.09965","arxivUrl":"https://arxiv.org/abs/2511.09965"},{"key":"journals/corr/abs-2512-08980","title":"Training Multi-Image Vision Agents via End2End Reinforcement Learning.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2512.08980"],"source":"https://dblp.org/rec/journals/corr/abs-2512-08980","documentPage":"https://doi.org/10.48550/ARXIV.2512.08980","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2512.08980","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-08980","documentUrl":"https://doi.org/10.48550/ARXIV.2512.08980","arxivId":"2512.08980","arxivUrl":"https://arxiv.org/abs/2512.08980"}],"excludedFormal":[],"excludedOther":[{"key":"data/12/ZhangZYMZLZGXZL25","title":"Self-Supervised Anomaly Detection and Staging for CT Emphysema.","year":2025,"yearOfEvent":null,"venue":null,"types":["https://dblp.org/rdf/schema#Data"],"dois":["https://doi.org/10.5281/ZENODO.17271375"],"source":"https://dblp.org/rec/data/12/ZhangZYMZLZGXZL25","documentPage":"https://doi.org/10.5281/ZENODO.17271375","type":"other","doi":"https://doi.org/10.5281/ZENODO.17271375","exclusionReason":"Not DBLP Article, Inproceedings, or Informal; outside the requested publication types.","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/data/12/ZhangZYMZLZGXZL25","documentUrl":"https://doi.org/10.5281/ZENODO.17271375"}],"excludedHomonyms":[],"unassignedCandidates":[],"retrievedAt":"2026-10-19","querySource":"https://sparql.dblp.org/","method":"DBLP yearOfPublication=2025; Article + Inproceedings; excludes Informal/CoRR and explicit editorial/correction/erratum/preface; unique DBLP record keys within person.","labName":"医学影像、机器人与智能分析（MIRACLE）奇迹实验室","labUrl":"https://miracle.ustc.edu.cn/main.htm","labEvidence":"中科大苏州高研院官方人物报道明确把“奇迹”称为周少华团队实验室名字；当前官方实验室简介给出 MIRACLE 中文全名，并列其科研项目。","labSourceUrl":"https://miracle.ustc.edu.cn/2022/1121/c32999a585823/page.htm","affiliationZh":"中国科学技术大学","sourceWarning":false,"knownPreprintMinimum2025":null,"excludedMisattributed":[],"displayNotes":"身份已经个人或机构主页核对。2025 年正式记录 43 条（会议 27、期刊 16），所有作者位置均计入，不表示主导或贡献份额；预印本 44 条单列，不加总。","labDisplayNotes":"中国科大官方实验室介绍给出「医学影像、机器人与智能分析（MIRACLE）奇迹实验室」的全称，苏州高研院的报道称其为周少华团队的实验室，据此归组。"},{"index":118,"name":"Xiaowei Zhou","nameZh":"周晓巍","affiliation":"Zhejiang University","source":"DBLP Knowledge Graph official SPARQL API","profileUrl":"https://dblp.org/pid/30/1273-1","identifier":"30/1273-1","identityEvidence":[{"url":"https://dblp.org/pid/30/1273-1","evidence":"DBLP curated profile affiliations: Hong Kong University of Science and Technology, Tai Po Tsai, Hong Kong; University of Pennsylvania, Department of Computer and Information Science, Philadelphia, PA, USA; Zhejiang University, Hangzhou, China."},{"url":"https://dblp.org/pid/30/1273-1","evidence":"DBLP curated profile homepages: https://xzhou.me/."}],"count2025":31,"conference2025":28,"journal2025":3,"preprint2025":22,"status":"verified","notes":"Counts are DBLP indexed coauthored records, not first-author counts, laboratory totals, unique scientific discoveries, or quality assessments. DBLP yearOfPublication=2025; yearOfEvent retained and can differ. Conference workshops are included. Preprints are separate and may overlap formal versions.","papers":[{"key":"conf/cvpr/GuoZPLYXWZB25","title":"Multi-view Reconstruction via SfM-guided Monocular Depth Estimation.","year":2025,"yearOfEvent":2025,"venue":"CVPR","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/CVPR52734.2025.00497"],"source":"https://dblp.org/rec/conf/cvpr/GuoZPLYXWZB25","documentPage":"https://openaccess.thecvf.com/content/CVPR2025/html/Guo_Multi-view_Reconstruction_via_SfM-guided_Monocular_Depth_Estimation_CVPR_2025_paper.html","type":"Inproceedings","doi":"https://doi.org/10.1109/CVPR52734.2025.00497","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/GuoZPLYXWZB25","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Guo_Multi-view_Reconstruction_via_SfM-guided_Monocular_Depth_Estimation_CVPR_2025_paper.html"},{"key":"conf/cvpr/LinPCPSLBFZK25","title":"Prompting Depth Anything for 4K Resolution Accurate Metric Depth Estimation.","year":2025,"yearOfEvent":2025,"venue":"CVPR","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/CVPR52734.2025.01591"],"source":"https://dblp.org/rec/conf/cvpr/LinPCPSLBFZK25","documentPage":"https://openaccess.thecvf.com/content/CVPR2025/html/Lin_Prompting_Depth_Anything_for_4K_Resolution_Accurate_Metric_Depth_Estimation_CVPR_2025_paper.html","type":"Inproceedings","doi":"https://doi.org/10.1109/CVPR52734.2025.01591","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/LinPCPSLBFZK25","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Lin_Prompting_Depth_Anything_for_4K_Resolution_Accurate_Metric_Depth_Estimation_CVPR_2025_paper.html"},{"key":"conf/cvpr/WangYXSZCBPZ25","title":"FreeTimeGS: Free Gaussian Primitives at Anytime Anywhere for Dynamic Scene Reconstruction.","year":2025,"yearOfEvent":2025,"venue":"CVPR","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/CVPR52734.2025.02026"],"source":"https://dblp.org/rec/conf/cvpr/WangYXSZCBPZ25","documentPage":"https://openaccess.thecvf.com/content/CVPR2025/html/Wang_FreeTimeGS_Free_Gaussian_Primitives_at_Anytime_Anywhere_for_Dynamic_Scene_CVPR_2025_paper.html","type":"Inproceedings","doi":"https://doi.org/10.1109/CVPR52734.2025.02026","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/WangYXSZCBPZ25","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Wang_FreeTimeGS_Free_Gaussian_Primitives_at_Anytime_Anywhere_for_Dynamic_Scene_CVPR_2025_paper.html"},{"key":"conf/cvpr/Wu0H025","title":"Glossy Object Reconstruction with Cost-effective Polarized Acquisition.","year":2025,"yearOfEvent":2025,"venue":"CVPR","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/CVPR52734.2025.00048"],"source":"https://dblp.org/rec/conf/cvpr/Wu0H025","documentPage":"https://openaccess.thecvf.com/content/CVPR2025/html/Wu_Glossy_Object_Reconstruction_with_Cost-effective_Polarized_Acquisition_CVPR_2025_paper.html","type":"Inproceedings","doi":"https://doi.org/10.1109/CVPR52734.2025.00048","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/Wu0H025","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Wu_Glossy_Object_Reconstruction_with_Cost-effective_Polarized_Acquisition_CVPR_2025_paper.html"},{"key":"conf/cvpr/Xia0VHP25","title":"Reconstructing Humans with a Biomechanically Accurate Skeleton.","year":2025,"yearOfEvent":2025,"venue":"CVPR","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/CVPR52734.2025.00504"],"source":"https://dblp.org/rec/conf/cvpr/Xia0VHP25","documentPage":"https://openaccess.thecvf.com/content/CVPR2025/html/Xia_Reconstructing_Humans_with_a_Biomechanically_Accurate_Skeleton_CVPR_2025_paper.html","type":"Inproceedings","doi":"https://doi.org/10.1109/CVPR52734.2025.00504","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/Xia0VHP25","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Xia_Reconstructing_Humans_with_a_Biomechanically_Accurate_Skeleton_CVPR_2025_paper.html"},{"key":"conf/cvpr/XieCXXJSPBZ25","title":"EnvGS: Modeling View-Dependent Appearance with Environment Gaussian.","year":2025,"yearOfEvent":2025,"venue":"CVPR","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/CVPR52734.2025.00539"],"source":"https://dblp.org/rec/conf/cvpr/XieCXXJSPBZ25","documentPage":"https://openaccess.thecvf.com/content/CVPR2025/html/Xie_EnvGS_Modeling_View-Dependent_Appearance_with_Environment_Gaussian_CVPR_2025_paper.html","type":"Inproceedings","doi":"https://doi.org/10.1109/CVPR52734.2025.00539","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/XieCXXJSPBZ25","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Xie_EnvGS_Modeling_View-Dependent_Appearance_with_Environment_Gaussian_CVPR_2025_paper.html"},{"key":"conf/cvpr/Yan0LJGWZLB0P25","title":"StreetCrafter: Street View Synthesis with Controllable Video Diffusion Models.","year":2025,"yearOfEvent":2025,"venue":"CVPR","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/CVPR52734.2025.00085"],"source":"https://dblp.org/rec/conf/cvpr/Yan0LJGWZLB0P25","documentPage":"https://openaccess.thecvf.com/content/CVPR2025/html/Yan_StreetCrafter_Street_View_Synthesis_with_Controllable_Video_Diffusion_Models_CVPR_2025_paper.html","type":"Inproceedings","doi":"https://doi.org/10.1109/CVPR52734.2025.00085","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/Yan0LJGWZLB0P25","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Yan_StreetCrafter_Street_View_Synthesis_with_Controllable_Video_Diffusion_Models_CVPR_2025_paper.html"},{"key":"conf/cvpr/ZhangWX000SW25","title":"FLARE: Feed-forward Geometry, Appearance and Camera Estimation from Uncalibrated Sparse Views.","year":2025,"yearOfEvent":2025,"venue":"CVPR","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/CVPR52734.2025.02043"],"source":"https://dblp.org/rec/conf/cvpr/ZhangWX000SW25","documentPage":"https://openaccess.thecvf.com/content/CVPR2025/html/Zhang_FLARE_Feed-forward_Geometry_Appearance_and_Camera_Estimation_from_Uncalibrated_Sparse_CVPR_2025_paper.html","type":"Inproceedings","doi":"https://doi.org/10.1109/CVPR52734.2025.02043","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/ZhangWX000SW25","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Zhang_FLARE_Feed-forward_Geometry_Appearance_and_Camera_Estimation_from_Uncalibrated_Sparse_CVPR_2025_paper.html"},{"key":"conf/cvpr/ZhouFPYZCXZ25","title":"LiDAR-RT: Gaussian-based Ray Tracing for Dynamic LiDAR Re-simulation.","year":2025,"yearOfEvent":2025,"venue":"CVPR","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/CVPR52734.2025.00151"],"source":"https://dblp.org/rec/conf/cvpr/ZhouFPYZCXZ25","documentPage":"https://openaccess.thecvf.com/content/CVPR2025/html/Zhou_LiDAR-RT_Gaussian-based_Ray_Tracing_for_Dynamic_LiDAR_Re-simulation_CVPR_2025_paper.html","type":"Inproceedings","doi":"https://doi.org/10.1109/CVPR52734.2025.00151","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/ZhouFPYZCXZ25","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Zhou_LiDAR-RT_Gaussian-based_Ray_Tracing_for_Dynamic_LiDAR_Re-simulation_CVPR_2025_paper.html"},{"key":"conf/eccv/ChenPYLPLZ24","title":"IntrinsicAnything: Learning Diffusion Priors for Inverse Rendering Under Unknown Illumination.","year":2025,"yearOfEvent":2024,"venue":"ECCV (60)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1007/978-3-031-73027-6_26"],"source":"https://dblp.org/rec/conf/eccv/ChenPYLPLZ24","documentPage":"https://doi.org/10.1007/978-3-031-73027-6_26","type":"Inproceedings","doi":"https://doi.org/10.1007/978-3-031-73027-6_26","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/eccv/ChenPYLPLZ24","documentUrl":"https://doi.org/10.1007/978-3-031-73027-6_26"},{"key":"conf/eccv/GuoZPWSHZ24","title":"SAM-Guided Graph Cut for 3D Instance Segmentation.","year":2025,"yearOfEvent":2024,"venue":"ECCV (48)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1007/978-3-031-73195-2_14"],"source":"https://dblp.org/rec/conf/eccv/GuoZPWSHZ24","documentPage":"https://doi.org/10.1007/978-3-031-73195-2_14","type":"Inproceedings","doi":"https://doi.org/10.1007/978-3-031-73195-2_14","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/eccv/GuoZPWSHZ24","documentUrl":"https://doi.org/10.1007/978-3-031-73195-2_14"},{"key":"conf/eccv/HuZLLPZFY24","title":"CPT-VR: Improving Surface Rendering via Closest Point Transform with View-Reflection Appearance.","year":2025,"yearOfEvent":2024,"venue":"ECCV (73)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1007/978-3-031-73464-9_14"],"source":"https://dblp.org/rec/conf/eccv/HuZLLPZFY24","documentPage":"https://doi.org/10.1007/978-3-031-73464-9_14","type":"Inproceedings","doi":"https://doi.org/10.1007/978-3-031-73464-9_14","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/eccv/HuZLLPZFY24","documentUrl":"https://doi.org/10.1007/978-3-031-73464-9_14"},{"key":"conf/eccv/YanLZWSZLZP24","title":"Street Gaussians: Modeling Dynamic Urban Scenes with Gaussian Splatting.","year":2025,"yearOfEvent":2024,"venue":"ECCV (73)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1007/978-3-031-73464-9_10"],"source":"https://dblp.org/rec/conf/eccv/YanLZWSZLZP24","documentPage":"https://doi.org/10.1007/978-3-031-73464-9_10","type":"Inproceedings","doi":"https://doi.org/10.1007/978-3-031-73464-9_10","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/eccv/YanLZWSZLZP24","documentUrl":"https://doi.org/10.1007/978-3-031-73464-9_10"},{"key":"conf/iccv/CaoWFBZP25","title":"UniVerse: Unleashing the Scene Prior of Video Diffusion Models for Robust Radiance Field Reconstruction.","year":2025,"yearOfEvent":2025,"venue":"ICCV","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/ICCV51701.2025.02509"],"source":"https://dblp.org/rec/conf/iccv/CaoWFBZP25","documentPage":"https://doi.org/10.1109/ICCV51701.2025.02509","type":"Inproceedings","doi":"https://doi.org/10.1109/ICCV51701.2025.02509","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/CaoWFBZP25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.02509"},{"key":"conf/iccv/ChenWTMHOZBP25","title":"EgoAgent: A Joint Predictive Agent Model in Egocentric Worlds.","year":2025,"yearOfEvent":2025,"venue":"ICCV","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/ICCV51701.2025.00655"],"source":"https://dblp.org/rec/conf/iccv/ChenWTMHOZBP25","documentPage":"https://doi.org/10.1109/ICCV51701.2025.00655","type":"Inproceedings","doi":"https://doi.org/10.1109/ICCV51701.2025.00655","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/ChenWTMHOZBP25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.00655"},{"key":"conf/iccv/GuoPSSHWDHKPZ25","title":"Motion-2-To-3: Leveraging 2D Motion Data for 3D Motion Generations.","year":2025,"yearOfEvent":2025,"venue":"ICCV","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/ICCV51701.2025.01327"],"source":"https://dblp.org/rec/conf/iccv/GuoPSSHWDHKPZ25","documentPage":"https://doi.org/10.1109/ICCV51701.2025.01327","type":"Inproceedings","doi":"https://doi.org/10.1109/ICCV51701.2025.01327","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/GuoPSSHWDHKPZ25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.01327"},{"key":"conf/iccv/HeXXZP25","title":"ERNet: Efficient Non-Rigid Registration Network for Point Sequences.","year":2025,"yearOfEvent":2025,"venue":"ICCV","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/ICCV51701.2025.02521"],"source":"https://dblp.org/rec/conf/iccv/HeXXZP25","documentPage":"https://doi.org/10.1109/ICCV51701.2025.02521","type":"Inproceedings","doi":"https://doi.org/10.1109/ICCV51701.2025.02521","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/HeXXZP25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.02521"},{"key":"conf/iccv/JinPWXXYSBZ25","title":"Diffuman4D: 4D Consistent Human View Synthesis From Sparse-View Videos With Spatio-Temporal Diffusion Models.","year":2025,"yearOfEvent":2025,"venue":"ICCV","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/ICCV51701.2025.01028"],"source":"https://dblp.org/rec/conf/iccv/JinPWXXYSBZ25","documentPage":"https://doi.org/10.1109/ICCV51701.2025.01028","type":"Inproceedings","doi":"https://doi.org/10.1109/ICCV51701.2025.01028","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/JinPWXXYSBZ25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.01028"},{"key":"conf/iccv/SunYWXLWZBZP25","title":"Hierarchy UGP: Hierarchy Unified Gaussian Primitive for Large-Scale Dynamic Scene Reconstruction.","year":2025,"yearOfEvent":2025,"venue":"ICCV","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/ICCV51701.2025.02436"],"source":"https://dblp.org/rec/conf/iccv/SunYWXLWZBZP25","documentPage":"https://doi.org/10.1109/ICCV51701.2025.02436","type":"Inproceedings","doi":"https://doi.org/10.1109/ICCV51701.2025.02436","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/SunYWXLWZBZP25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.02436"},{"key":"conf/iccv/TanHPGZSHSBZ25","title":"ReTracker: Exploring Image Matching for Robust Online Any Point Tracking.","year":2025,"yearOfEvent":2025,"venue":"ICCV","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/ICCV51701.2025.00410"],"source":"https://dblp.org/rec/conf/iccv/TanHPGZSHSBZ25","documentPage":"https://doi.org/10.1109/ICCV51701.2025.00410","type":"Inproceedings","doi":"https://doi.org/10.1109/ICCV51701.2025.00410","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/TanHPGZSHSBZ25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.00410"},{"key":"conf/iccv/WangWGPQBZH25","title":"Precise Action-to-Video Generation Through Visual Action Prompts.","year":2025,"yearOfEvent":2025,"venue":"ICCV","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/ICCV51701.2025.01181"],"source":"https://dblp.org/rec/conf/iccv/WangWGPQBZH25","documentPage":"https://doi.org/10.1109/ICCV51701.2025.01181","type":"Inproceedings","doi":"https://doi.org/10.1109/ICCV51701.2025.01181","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/WangWGPQBZH25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.01181"},{"key":"conf/iccv/XiaoLPFPZFZPW25","title":"MotionStreamer: Streaming Motion Generation via Diffusion-Based Autoregressive Model in Causal Latent Space.","year":2025,"yearOfEvent":2025,"venue":"ICCV","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/ICCV51701.2025.00940"],"source":"https://dblp.org/rec/conf/iccv/XiaoLPFPZFZPW25","documentPage":"https://doi.org/10.1109/ICCV51701.2025.00940","type":"Inproceedings","doi":"https://doi.org/10.1109/ICCV51701.2025.00940","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/XiaoLPFPZFZPW25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.00940"},{"key":"conf/iccv/XiaoWXKMKZBSZ25","title":"SpatialTrackerV2: Advancing 3D Point Tracking with Explicit Camera Motion.","year":2025,"yearOfEvent":2025,"venue":"ICCV","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/ICCV51701.2025.00633"],"source":"https://dblp.org/rec/conf/iccv/XiaoWXKMKZBSZ25","documentPage":"https://doi.org/10.1109/ICCV51701.2025.00633","type":"Inproceedings","doi":"https://doi.org/10.1109/ICCV51701.2025.00633","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/XiaoWXKMKZBSZ25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.00633"},{"key":"conf/iccv/YuHZYYHSZZP25","title":"BoxDreamer: Dreaming Box Corners for Generalizable Object Pose Estimation.","year":2025,"yearOfEvent":2025,"venue":"ICCV","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/ICCV51701.2025.00875"],"source":"https://dblp.org/rec/conf/iccv/YuHZYYHSZZP25","documentPage":"https://doi.org/10.1109/ICCV51701.2025.00875","type":"Inproceedings","doi":"https://doi.org/10.1109/ICCV51701.2025.00875","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/YuHZYYHSZZP25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.00875"},{"key":"conf/iclr/CenPPSSB0H25","title":"Ready-to-React: Online Reaction Policy for Two-Character Interaction Generation.","year":2025,"yearOfEvent":2025,"venue":"ICLR","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/iclr/CenPPSSB0H25","documentPage":"https://openreview.net/forum?id=mm0cqJ2O3f","type":"Inproceedings","doi":null,"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iclr/CenPPSSB0H25","documentUrl":"https://openreview.net/forum?id=mm0cqJ2O3f"},{"key":"conf/iclr/WangZPHGSB025","title":"UniRestore3D: A Scalable Framework For General Shape Restoration.","year":2025,"yearOfEvent":2025,"venue":"ICLR","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/iclr/WangZPHGSB025","documentPage":"https://openreview.net/forum?id=xPO6fwvldG","type":"Inproceedings","doi":null,"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iclr/WangZPHGSB025","documentUrl":"https://openreview.net/forum?id=xPO6fwvldG"},{"key":"conf/siggraph/0006LB0025","title":"HumanRAM: Feed-forward Human Reconstruction and Animation Model using Transformers.","year":2025,"yearOfEvent":2025,"venue":"SIGGRAPH (Conference Paper Track)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1145/3721238.3730605"],"source":"https://dblp.org/rec/conf/siggraph/0006LB0025","documentPage":"https://doi.org/10.1145/3721238.3730605","type":"Inproceedings","doi":"https://doi.org/10.1145/3721238.3730605","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/siggraph/0006LB0025","documentUrl":"https://doi.org/10.1145/3721238.3730605"},{"key":"conf/siggraph/LiX0SZ0H25","title":"MASH: Masked Anchored SpHerical Distances for 3D Shape Representation and Generation.","year":2025,"yearOfEvent":2025,"venue":"SIGGRAPH (Conference Paper Track)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1145/3721238.3730610"],"source":"https://dblp.org/rec/conf/siggraph/LiX0SZ0H25","documentPage":"https://doi.org/10.1145/3721238.3730610","type":"Inproceedings","doi":"https://doi.org/10.1145/3721238.3730610","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/siggraph/LiX0SZ0H25","documentUrl":"https://doi.org/10.1145/3721238.3730610"},{"key":"journals/cg/ShenTuZXSCPZ25","title":"Dyn-E: Local appearance editing of dynamic neural radiance fields.","year":2025,"yearOfEvent":null,"venue":"Comput. Graph.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1016/J.CAG.2024.104140"],"source":"https://dblp.org/rec/journals/cg/ShenTuZXSCPZ25","documentPage":"https://doi.org/10.1016/J.CAG.2024.104140","type":"Article","doi":"https://doi.org/10.1016/J.CAG.2024.104140","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/cg/ShenTuZXSCPZ25","documentUrl":"https://doi.org/10.1016/J.CAG.2024.104140"},{"key":"journals/pami/FuZCLZGL25","title":"PanopticNeRF-360: Panoramic 3D-to-2D Label Transfer in Urban Scenes.","year":2025,"yearOfEvent":null,"venue":"IEEE Trans. Pattern Anal. Mach. Intell.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1109/TPAMI.2025.3581608"],"source":"https://dblp.org/rec/journals/pami/FuZCLZGL25","documentPage":"https://doi.org/10.1109/TPAMI.2025.3581608","type":"Article","doi":"https://doi.org/10.1109/TPAMI.2025.3581608","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/pami/FuZCLZGL25","documentUrl":"https://doi.org/10.1109/TPAMI.2025.3581608"},{"key":"journals/tog/HuYLWDDZJBZP25","title":"Split4D: Decomposed 4D Scene Reconstruction Without Video Segmentation.","year":2025,"yearOfEvent":null,"venue":"ACM Trans. Graph.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1145/3763343"],"source":"https://dblp.org/rec/journals/tog/HuYLWDDZJBZP25","documentPage":"https://doi.org/10.1145/3763343","type":"Article","doi":"https://doi.org/10.1145/3763343","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/tog/HuYLWDDZJBZP25","documentUrl":"https://doi.org/10.1145/3763343"}],"preprints":[{"key":"journals/corr/abs-2501-07556","title":"MatchAnything: Universal Cross-Modality Image Matching with Large-Scale Pre-Training.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2501.07556"],"source":"https://dblp.org/rec/journals/corr/abs-2501-07556","documentPage":"https://doi.org/10.48550/ARXIV.2501.07556","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2501.07556","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2501-07556","documentUrl":"https://doi.org/10.48550/ARXIV.2501.07556","arxivId":"2501.07556","arxivUrl":"https://arxiv.org/abs/2501.07556"},{"key":"journals/corr/abs-2502-05857","title":"Acquisition through My Eyes and Steps: A Joint Predictive Agent Model in Egocentric Worlds.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2502.05857"],"source":"https://dblp.org/rec/journals/corr/abs-2502-05857","documentPage":"https://doi.org/10.48550/ARXIV.2502.05857","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2502.05857","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2502-05857","documentUrl":"https://doi.org/10.48550/ARXIV.2502.05857","arxivId":"2502.05857","arxivUrl":"https://arxiv.org/abs/2502.05857"},{"key":"journals/corr/abs-2502-12138","title":"FLARE: Feed-forward Geometry, Appearance and Camera Estimation from Uncalibrated Sparse Views.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2502.12138"],"source":"https://dblp.org/rec/journals/corr/abs-2502-12138","documentPage":"https://doi.org/10.48550/ARXIV.2502.12138","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2502.12138","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2502-12138","documentUrl":"https://doi.org/10.48550/ARXIV.2502.12138","arxivId":"2502.12138","arxivUrl":"https://arxiv.org/abs/2502.12138"},{"key":"journals/corr/abs-2502-20370","title":"Ready-to-React: Online Reaction Policy for Two-Character Interaction Generation.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2502.20370"],"source":"https://dblp.org/rec/journals/corr/abs-2502-20370","documentPage":"https://doi.org/10.48550/ARXIV.2502.20370","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2502.20370","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2502-20370","documentUrl":"https://doi.org/10.48550/ARXIV.2502.20370","arxivId":"2502.20370","arxivUrl":"https://arxiv.org/abs/2502.20370"},{"key":"journals/corr/abs-2503-03222","title":"Mocap-2-to-3: Lifting 2D Diffusion-Based Pretrained Models for 3D Motion Capture.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2503.03222"],"source":"https://dblp.org/rec/journals/corr/abs-2503-03222","documentPage":"https://doi.org/10.48550/ARXIV.2503.03222","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2503.03222","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-03222","documentUrl":"https://doi.org/10.48550/ARXIV.2503.03222","arxivId":"2503.03222","arxivUrl":"https://arxiv.org/abs/2503.03222"},{"key":"journals/corr/abs-2503-14483","title":"Multi-view Reconstruction via SfM-guided Monocular Depth Estimation.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2503.14483"],"source":"https://dblp.org/rec/journals/corr/abs-2503-14483","documentPage":"https://doi.org/10.48550/ARXIV.2503.14483","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2503.14483","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-14483","documentUrl":"https://doi.org/10.48550/ARXIV.2503.14483","arxivId":"2503.14483","arxivUrl":"https://arxiv.org/abs/2503.14483"},{"key":"journals/corr/abs-2503-15451","title":"MotionStreamer: Streaming Motion Generation via Diffusion-based Autoregressive Model in Causal Latent Space.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2503.15451"],"source":"https://dblp.org/rec/journals/corr/abs-2503-15451","documentPage":"https://doi.org/10.48550/ARXIV.2503.15451","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2503.15451","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-15451","documentUrl":"https://doi.org/10.48550/ARXIV.2503.15451","arxivId":"2503.15451","arxivUrl":"https://arxiv.org/abs/2503.15451"},{"key":"journals/corr/abs-2503-21751","title":"Reconstructing Humans with a Biomechanically Accurate Skeleton.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2503.21751"],"source":"https://dblp.org/rec/journals/corr/abs-2503-21751","documentPage":"https://doi.org/10.48550/ARXIV.2503.21751","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2503.21751","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-21751","documentUrl":"https://doi.org/10.48550/ARXIV.2503.21751","arxivId":"2503.21751","arxivUrl":"https://arxiv.org/abs/2503.21751"},{"key":"journals/corr/abs-2504-07025","title":"Glossy Object Reconstruction with Cost-effective Polarized Acquisition.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2504.07025"],"source":"https://dblp.org/rec/journals/corr/abs-2504-07025","documentPage":"https://doi.org/10.48550/ARXIV.2504.07025","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2504.07025","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2504-07025","documentUrl":"https://doi.org/10.48550/ARXIV.2504.07025","arxivId":"2504.07025","arxivUrl":"https://arxiv.org/abs/2504.07025"},{"key":"journals/corr/abs-2504-07955","title":"BoxDreamer: Dreaming Box Corners for Generalizable Object Pose Estimation.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2504.07955"],"source":"https://dblp.org/rec/journals/corr/abs-2504-07955","documentPage":"https://doi.org/10.48550/ARXIV.2504.07955","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2504.07955","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2504-07955","documentUrl":"https://doi.org/10.48550/ARXIV.2504.07955","arxivId":"2504.07955","arxivUrl":"https://arxiv.org/abs/2504.07955"},{"key":"journals/corr/abs-2504-09149","title":"MASH: Masked Anchored SpHerical Distances for 3D Shape Representation and Generation.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2504.09149"],"source":"https://dblp.org/rec/journals/corr/abs-2504-09149","documentPage":"https://doi.org/10.48550/ARXIV.2504.09149","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2504.09149","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2504-09149","documentUrl":"https://doi.org/10.48550/ARXIV.2504.09149","arxivId":"2504.09149","arxivUrl":"https://arxiv.org/abs/2504.09149"},{"key":"journals/corr/abs-2506-03118","title":"HumanRAM: Feed-forward Human Reconstruction and Animation Model using Transformers.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2506.03118"],"source":"https://dblp.org/rec/journals/corr/abs-2506-03118","documentPage":"https://doi.org/10.48550/ARXIV.2506.03118","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2506.03118","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-03118","documentUrl":"https://doi.org/10.48550/ARXIV.2506.03118","arxivId":"2506.03118","arxivUrl":"https://arxiv.org/abs/2506.03118"},{"key":"journals/corr/abs-2506-05348","title":"FreeTimeGS: Free Gaussian Primitives at Anytime and Anywhere for Dynamic Scene Reconstruction.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2506.05348"],"source":"https://dblp.org/rec/journals/corr/abs-2506-05348","documentPage":"https://doi.org/10.48550/ARXIV.2506.05348","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2506.05348","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-05348","documentUrl":"https://doi.org/10.48550/ARXIV.2506.05348","arxivId":"2506.05348","arxivUrl":"https://arxiv.org/abs/2506.05348"},{"key":"journals/corr/abs-2507-11540","title":"Towards Depth Foundation Model: Recent Trends in Vision-Based Depth Estimation.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2507.11540"],"source":"https://dblp.org/rec/journals/corr/abs-2507-11540","documentPage":"https://doi.org/10.48550/ARXIV.2507.11540","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2507.11540","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2507-11540","documentUrl":"https://doi.org/10.48550/ARXIV.2507.11540","arxivId":"2507.11540","arxivUrl":"https://arxiv.org/abs/2507.11540"},{"key":"journals/corr/abs-2507-12462","title":"SpatialTrackerV2: 3D Point Tracking Made Easy.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2507.12462"],"source":"https://dblp.org/rec/journals/corr/abs-2507-12462","documentPage":"https://doi.org/10.48550/ARXIV.2507.12462","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2507.12462","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2507-12462","documentUrl":"https://doi.org/10.48550/ARXIV.2507.12462","arxivId":"2507.12462","arxivUrl":"https://arxiv.org/abs/2507.12462"},{"key":"journals/corr/abs-2507-13344","title":"Diffuman4D: 4D Consistent Human View Synthesis from Sparse-View Videos with Spatio-Temporal Diffusion Models.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2507.13344"],"source":"https://dblp.org/rec/journals/corr/abs-2507-13344","documentPage":"https://doi.org/10.48550/ARXIV.2507.13344","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2507.13344","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2507-13344","documentUrl":"https://doi.org/10.48550/ARXIV.2507.13344","arxivId":"2507.13344","arxivUrl":"https://arxiv.org/abs/2507.13344"},{"key":"journals/corr/abs-2508-13104","title":"Precise Action-to-Video Generation Through Visual Action Prompts.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2508.13104"],"source":"https://dblp.org/rec/journals/corr/abs-2508-13104","documentPage":"https://doi.org/10.48550/ARXIV.2508.13104","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2508.13104","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-13104","documentUrl":"https://doi.org/10.48550/ARXIV.2508.13104","arxivId":"2508.13104","arxivUrl":"https://arxiv.org/abs/2508.13104"},{"key":"journals/corr/abs-2510-01669","title":"UniVerse: Unleashing the Scene Prior of Video Diffusion Models for Robust Radiance Field Reconstruction.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2510.01669"],"source":"https://dblp.org/rec/journals/corr/abs-2510-01669","documentPage":"https://doi.org/10.48550/ARXIV.2510.01669","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2510.01669","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-01669","documentUrl":"https://doi.org/10.48550/ARXIV.2510.01669","arxivId":"2510.01669","arxivUrl":"https://arxiv.org/abs/2510.01669"},{"key":"journals/corr/abs-2510-15800","title":"ERNet: Efficient Non-Rigid Registration Network for Point Sequences.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2510.15800"],"source":"https://dblp.org/rec/journals/corr/abs-2510-15800","documentPage":"https://doi.org/10.48550/ARXIV.2510.15800","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2510.15800","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-15800","documentUrl":"https://doi.org/10.48550/ARXIV.2510.15800","arxivId":"2510.15800","arxivUrl":"https://arxiv.org/abs/2510.15800"},{"key":"journals/corr/abs-2511-14223","title":"StreamingTalker: Audio-driven 3D Facial Animation with Autoregressive Diffusion Model.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2511.14223"],"source":"https://dblp.org/rec/journals/corr/abs-2511-14223","documentPage":"https://doi.org/10.48550/ARXIV.2511.14223","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2511.14223","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2511-14223","documentUrl":"https://doi.org/10.48550/ARXIV.2511.14223","arxivId":"2511.14223","arxivUrl":"https://arxiv.org/abs/2511.14223"},{"key":"journals/corr/abs-2512-20617","title":"SpatialTree: How Spatial Abilities Branch Out in MLLMs.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2512.20617"],"source":"https://dblp.org/rec/journals/corr/abs-2512-20617","documentPage":"https://doi.org/10.48550/ARXIV.2512.20617","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2512.20617","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-20617","documentUrl":"https://doi.org/10.48550/ARXIV.2512.20617","arxivId":"2512.20617","arxivUrl":"https://arxiv.org/abs/2512.20617"},{"key":"journals/corr/abs-2512-22745","title":"Split4D: Decomposed 4D Scene Reconstruction Without Video Segmentation.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2512.22745"],"source":"https://dblp.org/rec/journals/corr/abs-2512-22745","documentPage":"https://doi.org/10.48550/ARXIV.2512.22745","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2512.22745","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-22745","documentUrl":"https://doi.org/10.48550/ARXIV.2512.22745","arxivId":"2512.22745","arxivUrl":"https://arxiv.org/abs/2512.22745"}],"excludedFormal":[],"excludedOther":[],"excludedHomonyms":[],"unassignedCandidates":[],"retrievedAt":"2026-10-19","querySource":"https://sparql.dblp.org/","method":"DBLP yearOfPublication=2025; Article + Inproceedings; excludes Informal/CoRR and explicit editorial/correction/erratum/preface; unique DBLP record keys within person.","labName":"State Key Laboratory of CAD&CG","labUrl":null,"labEvidence":"本人主页当前任职自述明确列浙江大学 State Key Laboratory of CAD&CG。独立 Group Page 没有可核验的新组名，因此不自行命名个人实验室。","labSourceUrl":"https://xzhou.me/","affiliationZh":"浙江大学","sourceWarning":false,"knownPreprintMinimum2025":null,"excludedMisattributed":[],"displayNotes":"身份已经个人或机构主页核对。2025 年正式记录 31 条（会议 28、期刊 3），所有作者位置均计入，不表示主导或贡献份额；预印本 22 条单列，不加总。","labDisplayNotes":"本人主页写明隶属 CAD&CG 全国重点实验室；其 Group Page 未写可核实的组名，不另行命名。与崔兆鹏、沈春华、章国锋按共同的上级实验室合为一组（112 条）。"},{"index":119,"name":"Wangmeng Zuo","nameZh":"左旺孟","affiliation":"Harbin Institute of Technology","source":"DBLP Knowledge Graph official SPARQL API","profileUrl":"https://dblp.org/pid/93/2671","identifier":"93/2671","identityEvidence":[{"url":"https://homepage.hit.edu.cn/wangmengzuo?lang=en","evidence":"HIT faculty site identifies 左旺孟, computer vision professor. DBLP author signatures link ORCID 0000-0002-3330-783X to Harbin Institute of Technology."},{"url":"https://dblp.org/rec/conf/cvpr/ZhuR0WZ25","evidence":"DBLP paper author signature connects this profile to Harbin Institute of Technology (HIT)."},{"url":"https://dblp.org/rec/conf/eccv/NiSZZ24","evidence":"DBLP paper author signature connects this profile to Peng Cheng Laboratory."},{"url":"https://dblp.org/rec/journals/pr/XuHQYGZ25","evidence":"DBLP paper author signature connects this profile to Harbin Institute of Technology (HIT) and https://orcid.org/0000-0002-3330-783X."}],"count2025":78,"conference2025":42,"journal2025":36,"preprint2025":50,"status":"verified","notes":"Counts are DBLP indexed coauthored records, not first-author counts, laboratory totals, unique scientific discoveries, or quality assessments. DBLP yearOfPublication=2025; yearOfEvent retained and can differ. Conference workshops are included. Preprints are separate and may overlap formal versions.","papers":[{"key":"conf/aaai/0001B00KZGL25","title":"VQA4CIR: Boosting Composed Image Retrieval with Visual Question Answering.","year":2025,"yearOfEvent":2025,"venue":"AAAI","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1609/AAAI.V39I3.32301"],"source":"https://dblp.org/rec/conf/aaai/0001B00KZGL25","documentPage":"https://doi.org/10.1609/AAAI.V39I3.32301","type":"Inproceedings","doi":"https://doi.org/10.1609/AAAI.V39I3.32301","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/aaai/0001B00KZGL25","documentUrl":"https://doi.org/10.1609/AAAI.V39I3.32301"},{"key":"conf/aaai/HuangZZZ0ZL25","title":"DreamPhysics: Learning Physics-Based 3D Dynamics with Video Diffusion Priors.","year":2025,"yearOfEvent":2025,"venue":"AAAI","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1609/AAAI.V39I4.32389"],"source":"https://dblp.org/rec/conf/aaai/HuangZZZ0ZL25","documentPage":"https://doi.org/10.1609/AAAI.V39I4.32389","type":"Inproceedings","doi":"https://doi.org/10.1609/AAAI.V39I4.32389","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/aaai/HuangZZZ0ZL25","documentUrl":"https://doi.org/10.1609/AAAI.V39I4.32389"},{"key":"conf/aaai/LiZZ25","title":"Rethinking Transformer-Based Blind-Spot Network for Self-Supervised Image Denoising.","year":2025,"yearOfEvent":2025,"venue":"AAAI","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1609/AAAI.V39I5.32506"],"source":"https://dblp.org/rec/conf/aaai/LiZZ25","documentPage":"https://doi.org/10.1609/AAAI.V39I5.32506","type":"Inproceedings","doi":"https://doi.org/10.1609/AAAI.V39I5.32506","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/aaai/LiZZ25","documentUrl":"https://doi.org/10.1609/AAAI.V39I5.32506"},{"key":"conf/aaai/WangZDZZ25","title":"MV-VTON: Multi-View Virtual Try-On with Diffusion Models.","year":2025,"yearOfEvent":2025,"venue":"AAAI","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1609/AAAI.V39I7.32827"],"source":"https://dblp.org/rec/conf/aaai/WangZDZZ25","documentPage":"https://doi.org/10.1609/AAAI.V39I7.32827","type":"Inproceedings","doi":"https://doi.org/10.1609/AAAI.V39I7.32827","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/aaai/WangZDZZ25","documentUrl":"https://doi.org/10.1609/AAAI.V39I7.32827"},{"key":"conf/aaai/Zhang0LHRXZ25","title":"VideoElevator: Elevating Video Generation Quality with Versatile Text-to-Image Diffusion Models.","year":2025,"yearOfEvent":2025,"venue":"AAAI","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1609/AAAI.V39I10.33114"],"source":"https://dblp.org/rec/conf/aaai/Zhang0LHRXZ25","documentPage":"https://doi.org/10.1609/AAAI.V39I10.33114","type":"Inproceedings","doi":"https://doi.org/10.1609/AAAI.V39I10.33114","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/aaai/Zhang0LHRXZ25","documentUrl":"https://doi.org/10.1609/AAAI.V39I10.33114"},{"key":"conf/cvpr/00140LG0WT0ZWWX25","title":"NTIRE 2025 Challenge on Real-World Face Restoration: Methods and Results.","year":2025,"yearOfEvent":2025,"venue":"CVPR Workshops","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/cvpr/00140LG0WT0ZWWX25","documentPage":"https://openaccess.thecvf.com/content/CVPR2025W/NTIRE/html/Chen_NTIRE_2025_Challenge_on_Real-World_Face_Restoration_Methods_and_Results_CVPRW_2025_paper.html","type":"Inproceedings","doi":null,"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/00140LG0WT0ZWWX25","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025W/NTIRE/html/Chen_NTIRE_2025_Challenge_on_Real-World_Face_Restoration_Methods_and_Results_CVPRW_2025_paper.html"},{"key":"conf/cvpr/JiangZFWLPLZ25","title":"MC^2: Multi-concept Guidance for Customized Multi-concept Generation.","year":2025,"yearOfEvent":2025,"venue":"CVPR","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/CVPR52734.2025.00267"],"source":"https://dblp.org/rec/conf/cvpr/JiangZFWLPLZ25","documentPage":"https://openaccess.thecvf.com/content/CVPR2025/html/Jiang_MC2_Multi-concept_Guidance_for_Customized__Multi-concept_Generation_CVPR_2025_paper.html","type":"Inproceedings","doi":"https://doi.org/10.1109/CVPR52734.2025.00267","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/JiangZFWLPLZ25","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Jiang_MC2_Multi-concept_Guidance_for_Customized__Multi-concept_Generation_CVPR_2025_paper.html"},{"key":"conf/cvpr/Wang0LP0Z25","title":"ACE: Anti-Editing Concept Erasure in Text-to-Image Models.","year":2025,"yearOfEvent":2025,"venue":"CVPR","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/CVPR52734.2025.02189"],"source":"https://dblp.org/rec/conf/cvpr/Wang0LP0Z25","documentPage":"https://openaccess.thecvf.com/content/CVPR2025/html/Wang_ACE_Anti-Editing_Concept_Erasure_in_Text-to-Image_Models_CVPR_2025_paper.html","type":"Inproceedings","doi":"https://doi.org/10.1109/CVPR52734.2025.02189","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/Wang0LP0Z25","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Wang_ACE_Anti-Editing_Concept_Erasure_in_Text-to-Image_Models_CVPR_2025_paper.html"},{"key":"conf/cvpr/WanQ0FZZ25","title":"CASP: Consistency-aware Audio-induced Saliency Prediction Model for Omnidirectional Video.","year":2025,"yearOfEvent":2025,"venue":"CVPR","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/CVPR52734.2025.01176"],"source":"https://dblp.org/rec/conf/cvpr/WanQ0FZZ25","documentPage":"https://openaccess.thecvf.com/content/CVPR2025/html/Wan_CASP_Consistency-aware_Audio-induced_Saliency_Prediction_Model_for_Omnidirectional_Video_CVPR_2025_paper.html","type":"Inproceedings","doi":"https://doi.org/10.1109/CVPR52734.2025.01176","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/WanQ0FZZ25","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Wan_CASP_Consistency-aware_Audio-induced_Saliency_Prediction_Model_for_Omnidirectional_Video_CVPR_2025_paper.html"},{"key":"conf/cvpr/WanSCZ25","title":"S2Gaussian: Sparse-View Super-Resolution 3D Gaussian Splatting.","year":2025,"yearOfEvent":2025,"venue":"CVPR","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/CVPR52734.2025.00075"],"source":"https://dblp.org/rec/conf/cvpr/WanSCZ25","documentPage":"https://openaccess.thecvf.com/content/CVPR2025/html/Wan_S2Gaussian_Sparse-View_Super-Resolution_3D_Gaussian_Splatting_CVPR_2025_paper.html","type":"Inproceedings","doi":"https://doi.org/10.1109/CVPR52734.2025.00075","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/WanSCZ25","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Wan_S2Gaussian_Sparse-View_Super-Resolution_3D_Gaussian_Splatting_CVPR_2025_paper.html"},{"key":"conf/cvpr/ZhuR0WZ25","title":"Generative Inbetweening through Frame-wise Conditions-Driven Video Generation.","year":2025,"yearOfEvent":2025,"venue":"CVPR","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/CVPR52734.2025.02604"],"source":"https://dblp.org/rec/conf/cvpr/ZhuR0WZ25","documentPage":"https://openaccess.thecvf.com/content/CVPR2025/html/Zhu_Generative_Inbetweening_through_Frame-wise_Conditions-Driven_Video_Generation_CVPR_2025_paper.html","type":"Inproceedings","doi":"https://doi.org/10.1109/CVPR52734.2025.02604","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/cvpr/ZhuR0WZ25","documentUrl":"https://openaccess.thecvf.com/content/CVPR2025/html/Zhu_Generative_Inbetweening_through_Frame-wise_Conditions-Driven_Video_Generation_CVPR_2025_paper.html"},{"key":"conf/eccv/LiCGXZ24","title":"ShoeModel: Learning to Wear on the User-Specified Shoes via Diffusion Model.","year":2025,"yearOfEvent":2024,"venue":"ECCV (69)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1007/978-3-031-72890-7_6"],"source":"https://dblp.org/rec/conf/eccv/LiCGXZ24","documentPage":"https://doi.org/10.1007/978-3-031-72890-7_6","type":"Inproceedings","doi":"https://doi.org/10.1007/978-3-031-72890-7_6","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/eccv/LiCGXZ24","documentUrl":"https://doi.org/10.1007/978-3-031-72890-7_6"},{"key":"conf/eccv/LiuWLLRXZ24","title":"SmartControl: Enhancing ControlNet for Handling Rough Visual Conditions.","year":2025,"yearOfEvent":2024,"venue":"ECCV (48)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1007/978-3-031-73195-2_1"],"source":"https://dblp.org/rec/conf/eccv/LiuWLLRXZ24","documentPage":"https://doi.org/10.1007/978-3-031-73195-2_1","type":"Inproceedings","doi":"https://doi.org/10.1007/978-3-031-73195-2_1","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/eccv/LiuWLLRXZ24","documentUrl":"https://doi.org/10.1007/978-3-031-73195-2_1"},{"key":"conf/eccv/MengHWSZ24","title":"Multi-modal Crowd Counting via a Broker Modality.","year":2025,"yearOfEvent":2024,"venue":"ECCV (74)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1007/978-3-031-72904-1_14"],"source":"https://dblp.org/rec/conf/eccv/MengHWSZ24","documentPage":"https://doi.org/10.1007/978-3-031-72904-1_14","type":"Inproceedings","doi":"https://doi.org/10.1007/978-3-031-72904-1_14","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/eccv/MengHWSZ24","documentUrl":"https://doi.org/10.1007/978-3-031-72904-1_14"},{"key":"conf/eccv/NiSZZ24","title":"Responsible Visual Editing.","year":2025,"yearOfEvent":2024,"venue":"ECCV (22)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1007/978-3-031-72670-5_18"],"source":"https://dblp.org/rec/conf/eccv/NiSZZ24","documentPage":"https://doi.org/10.1007/978-3-031-72670-5_18","type":"Inproceedings","doi":"https://doi.org/10.1007/978-3-031-72670-5_18","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/eccv/NiSZZ24","documentUrl":"https://doi.org/10.1007/978-3-031-72670-5_18"},{"key":"conf/eccv/ShangRZFZM24","title":"Arbitrary-Scale Video Super-Resolution with Structural and Textural Priors.","year":2025,"yearOfEvent":2024,"venue":"ECCV (57)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1007/978-3-031-72998-0_5"],"source":"https://dblp.org/rec/conf/eccv/ShangRZFZM24","documentPage":"https://doi.org/10.1007/978-3-031-72998-0_5","type":"Inproceedings","doi":"https://doi.org/10.1007/978-3-031-72998-0_5","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/eccv/ShangRZFZM24","documentUrl":"https://doi.org/10.1007/978-3-031-72998-0_5"},{"key":"conf/eccv/WeiJBZZZ24","title":"MasterWeaver: Taming Editability and Face Identity for Personalized Text-to-Image Generation.","year":2025,"yearOfEvent":2024,"venue":"ECCV (51)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1007/978-3-031-72983-6_15"],"source":"https://dblp.org/rec/conf/eccv/WeiJBZZZ24","documentPage":"https://doi.org/10.1007/978-3-031-72983-6_15","type":"Inproceedings","doi":"https://doi.org/10.1007/978-3-031-72983-6_15","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/eccv/WeiJBZZZ24","documentUrl":"https://doi.org/10.1007/978-3-031-72983-6_15"},{"key":"conf/eccv/WuZYZ24","title":"Dual-Camera Smooth Zoom on Mobile Phones.","year":2025,"yearOfEvent":2024,"venue":"ECCV (50)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1007/978-3-031-72973-7_15"],"source":"https://dblp.org/rec/conf/eccv/WuZYZ24","documentPage":"https://doi.org/10.1007/978-3-031-72973-7_15","type":"Inproceedings","doi":"https://doi.org/10.1007/978-3-031-72973-7_15","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/eccv/WuZYZ24","documentUrl":"https://doi.org/10.1007/978-3-031-72973-7_15"},{"key":"conf/eccv/WuZZGCZCZ24","title":"Self-Supervised Video Desmoking for Laparoscopic Surgery.","year":2025,"yearOfEvent":2024,"venue":"ECCV (72)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1007/978-3-031-73220-1_18"],"source":"https://dblp.org/rec/conf/eccv/WuZZGCZCZ24","documentPage":"https://doi.org/10.1007/978-3-031-73220-1_18","type":"Inproceedings","doi":"https://doi.org/10.1007/978-3-031-73220-1_18","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/eccv/WuZZGCZCZ24","documentUrl":"https://doi.org/10.1007/978-3-031-73220-1_18"},{"key":"conf/eccv/YaoCLYZ24","title":"Combining Generative and Geometry Priors for Wide-Angle Portrait Correction.","year":2025,"yearOfEvent":2024,"venue":"ECCV (29)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1007/978-3-031-73397-0_23"],"source":"https://dblp.org/rec/conf/eccv/YaoCLYZ24","documentPage":"https://doi.org/10.1007/978-3-031-73397-0_23","type":"Inproceedings","doi":"https://doi.org/10.1007/978-3-031-73397-0_23","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/eccv/YaoCLYZ24","documentUrl":"https://doi.org/10.1007/978-3-031-73397-0_23"},{"key":"conf/eccv/YaoLYYHZ24","title":"GLAD: Towards Better Reconstruction with Global and Local Adaptive Diffusion Models for Unsupervised Anomaly Detection.","year":2025,"yearOfEvent":2024,"venue":"ECCV (71)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1007/978-3-031-73209-6_1"],"source":"https://dblp.org/rec/conf/eccv/YaoLYYHZ24","documentPage":"https://doi.org/10.1007/978-3-031-73209-6_1","type":"Inproceedings","doi":"https://doi.org/10.1007/978-3-031-73209-6_1","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/eccv/YaoLYYHZ24","documentUrl":"https://doi.org/10.1007/978-3-031-73209-6_1"},{"key":"conf/eccv/ZouHYGLFZ24","title":"UniM2AE: Multi-modal Masked Autoencoders with Unified 3D Representation for 3D Perception in Autonomous Driving.","year":2025,"yearOfEvent":2024,"venue":"ECCV (22)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1007/978-3-031-72670-5_17"],"source":"https://dblp.org/rec/conf/eccv/ZouHYGLFZ24","documentPage":"https://doi.org/10.1007/978-3-031-72670-5_17","type":"Inproceedings","doi":"https://doi.org/10.1007/978-3-031-72670-5_17","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/eccv/ZouHYGLFZ24","documentUrl":"https://doi.org/10.1007/978-3-031-72670-5_17"},{"key":"conf/eccv/ZouYLFZ24","title":"ProGBA: Prompt Guided Bayesian Augmentation for Zero-Shot Domain Adaptation.","year":2025,"yearOfEvent":2024,"venue":"ECCV Workshops (7)","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1007/978-3-031-91767-7_17"],"source":"https://dblp.org/rec/conf/eccv/ZouYLFZ24","documentPage":"https://doi.org/10.1007/978-3-031-91767-7_17","type":"Inproceedings","doi":"https://doi.org/10.1007/978-3-031-91767-7_17","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/eccv/ZouYLFZ24","documentUrl":"https://doi.org/10.1007/978-3-031-91767-7_17"},{"key":"conf/icassp/Zhang0RZ25","title":"Flare-Aware RWKV for Flare Removal.","year":2025,"yearOfEvent":2025,"venue":"ICASSP","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/ICASSP49660.2025.10888487"],"source":"https://dblp.org/rec/conf/icassp/Zhang0RZ25","documentPage":"https://doi.org/10.1109/ICASSP49660.2025.10888487","type":"Inproceedings","doi":"https://doi.org/10.1109/ICASSP49660.2025.10888487","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/icassp/Zhang0RZ25","documentUrl":"https://doi.org/10.1109/ICASSP49660.2025.10888487"},{"key":"conf/iccv/GuoLWJBZZ25","title":"Integrating Visual Interpretation and Linguistic Reasoning for Geometric Problem Solving.","year":2025,"yearOfEvent":2025,"venue":"ICCV","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/ICCV51701.2025.00380"],"source":"https://dblp.org/rec/conf/iccv/GuoLWJBZZ25","documentPage":"https://doi.org/10.1109/ICCV51701.2025.00380","type":"Inproceedings","doi":"https://doi.org/10.1109/ICCV51701.2025.00380","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/GuoLWJBZZ25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.00380"},{"key":"conf/iccv/LiYWLLXSZ25","title":"Triad: Empowering LMM-Based Anomaly Detection with Expert-Guided Region-of-Interest Tokenizer and Manufacturing Process.","year":2025,"yearOfEvent":2025,"venue":"ICCV","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/ICCV51701.2025.02035"],"source":"https://dblp.org/rec/conf/iccv/LiYWLLXSZ25","documentPage":"https://doi.org/10.1109/ICCV51701.2025.02035","type":"Inproceedings","doi":"https://doi.org/10.1109/ICCV51701.2025.02035","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/LiYWLLXSZ25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.02035"},{"key":"conf/iccv/LvPSCZLW25","title":"Rethinking Cross-Modal Interaction in Multimodal Diffusion Transformers.","year":2025,"yearOfEvent":2025,"venue":"ICCV","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/ICCV51701.2025.00561"],"source":"https://dblp.org/rec/conf/iccv/LvPSCZLW25","documentPage":"https://doi.org/10.1109/ICCV51701.2025.00561","type":"Inproceedings","doi":"https://doi.org/10.1109/ICCV51701.2025.00561","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/LvPSCZLW25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.00561"},{"key":"conf/iccv/MaYZJZ25","title":"ReMP-AD: Retrieval-Enhanced Multi-Modal Prompt Fusion for Few-Shot Industrial Visual Anomaly Detection.","year":2025,"yearOfEvent":2025,"venue":"ICCV","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/ICCV51701.2025.01899"],"source":"https://dblp.org/rec/conf/iccv/MaYZJZ25","documentPage":"https://doi.org/10.1109/ICCV51701.2025.01899","type":"Inproceedings","doi":"https://doi.org/10.1109/ICCV51701.2025.01899","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/MaYZJZ25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.01899"},{"key":"conf/iccv/YangMDCLCXYZ25","title":"QR-LoRA: Efficient and Disentangled Fine-Tuning via QR Decomposition for Customized Generation.","year":2025,"yearOfEvent":2025,"venue":"ICCV","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/ICCV51701.2025.01634"],"source":"https://dblp.org/rec/conf/iccv/YangMDCLCXYZ25","documentPage":"https://doi.org/10.1109/ICCV51701.2025.01634","type":"Inproceedings","doi":"https://doi.org/10.1109/ICCV51701.2025.01634","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/YangMDCLCXYZ25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.01634"},{"key":"conf/iccv/ZhangZZXLZ25","title":"FramePainter: Endowing Interactive Image Editing with Video Diffusion Priors.","year":2025,"yearOfEvent":2025,"venue":"ICCV","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/ICCV51701.2025.01684"],"source":"https://dblp.org/rec/conf/iccv/ZhangZZXLZ25","documentPage":"https://doi.org/10.1109/ICCV51701.2025.01684","type":"Inproceedings","doi":"https://doi.org/10.1109/ICCV51701.2025.01684","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iccv/ZhangZZXLZ25","documentUrl":"https://doi.org/10.1109/ICCV51701.2025.01684"},{"key":"conf/iclr/NiF0Z25","title":"Visual-O1: Understanding Ambiguous Instructions via Multi-modal Multi-turn Chain-of-thoughts Reasoning.","year":2025,"yearOfEvent":2025,"venue":"ICLR","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/iclr/NiF0Z25","documentPage":"https://openreview.net/forum?id=v9CDpLpjiE","type":"Inproceedings","doi":null,"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iclr/NiF0Z25","documentUrl":"https://openreview.net/forum?id=v9CDpLpjiE"},{"key":"conf/iclr/Yan0Z0L025","title":"On the Importance of Language-driven Representation Learning for Heterogeneous Federated Learning.","year":2025,"yearOfEvent":2025,"venue":"ICLR","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/iclr/Yan0Z0L025","documentPage":"https://openreview.net/forum?id=7pDI74iOyu","type":"Inproceedings","doi":null,"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iclr/Yan0Z0L025","documentUrl":"https://openreview.net/forum?id=7pDI74iOyu"},{"key":"conf/iclr/Yan0ZG0025","title":"Federated Residual Low-Rank Adaptation of Large Language Models.","year":2025,"yearOfEvent":2025,"venue":"ICLR","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/iclr/Yan0ZG0025","documentPage":"https://openreview.net/forum?id=e0rQRMUhs7","type":"Inproceedings","doi":null,"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iclr/Yan0ZG0025","documentUrl":"https://openreview.net/forum?id=e0rQRMUhs7"},{"key":"conf/iclr/ZhangZWYZ25","title":"Exposure Bracketing Is All You Need For A High-Quality Image.","year":2025,"yearOfEvent":2025,"venue":"ICLR","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/iclr/ZhangZWYZ25","documentPage":"https://openreview.net/forum?id=rDIf6NA5mj","type":"Inproceedings","doi":null,"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/iclr/ZhangZWYZ25","documentUrl":"https://openreview.net/forum?id=rDIf6NA5mj"},{"key":"conf/icmcs/MeiZWZ25","title":"Image Demoiréing Using Dual Camera Fusion on Mobile Phones.","year":2025,"yearOfEvent":2025,"venue":"ICME","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1109/ICME59968.2025.11209149"],"source":"https://dblp.org/rec/conf/icmcs/MeiZWZ25","documentPage":"https://doi.org/10.1109/ICME59968.2025.11209149","type":"Inproceedings","doi":"https://doi.org/10.1109/ICME59968.2025.11209149","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/icmcs/MeiZWZ25","documentUrl":"https://doi.org/10.1109/ICME59968.2025.11209149"},{"key":"conf/mm/0001RZ0HZ25","title":"Motion-Aware Adaptive Pixel Pruning for Efficient Local Motion Deblurring.","year":2025,"yearOfEvent":2025,"venue":"ACM Multimedia","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1145/3746027.3755062"],"source":"https://dblp.org/rec/conf/mm/0001RZ0HZ25","documentPage":"https://doi.org/10.1145/3746027.3755062","type":"Inproceedings","doi":"https://doi.org/10.1145/3746027.3755062","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/mm/0001RZ0HZ25","documentUrl":"https://doi.org/10.1145/3746027.3755062"},{"key":"conf/mm/ZhengYH0HZ25","title":"Segmenting Objectiveness and Task-awareness Unknown Region for Autonomous Driving.","year":2025,"yearOfEvent":2025,"venue":"ACM Multimedia","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":["https://doi.org/10.1145/3746027.3755178"],"source":"https://dblp.org/rec/conf/mm/ZhengYH0HZ25","documentPage":"https://doi.org/10.1145/3746027.3755178","type":"Inproceedings","doi":"https://doi.org/10.1145/3746027.3755178","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/mm/ZhengYH0HZ25","documentUrl":"https://doi.org/10.1145/3746027.3755178"},{"key":"conf/nips/DongNHYZZ25","title":"MIRAGE: Assessing Hallucination in Multimodal Reasoning Chains of MLLM.","year":2025,"yearOfEvent":2025,"venue":"NeurIPS","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/nips/DongNHYZZ25","documentPage":"http://papers.nips.cc/paper_files/paper/2025/hash/b238324b309da12c7446d92c14db9f7e-Abstract-Conference.html","type":"Inproceedings","doi":null,"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/nips/DongNHYZZ25","documentUrl":"http://papers.nips.cc/paper_files/paper/2025/hash/b238324b309da12c7446d92c14db9f7e-Abstract-Conference.html"},{"key":"conf/nips/LiHQZYZHWWPOBZD25","title":"LabUtopia: High-Fidelity Simulation and Hierarchical Benchmark for Scientific Embodied Agents.","year":2025,"yearOfEvent":2025,"venue":"NeurIPS","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/nips/LiHQZYZHWWPOBZD25","documentPage":"http://papers.nips.cc/paper_files/paper/2025/hash/313d6659e6532e6ba192dfb910d4261e-Abstract-Datasets_and_Benchmarks_Track.html","type":"Inproceedings","doi":null,"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/nips/LiHQZYZHWWPOBZD25","documentUrl":"http://papers.nips.cc/paper_files/paper/2025/hash/313d6659e6532e6ba192dfb910d4261e-Abstract-Datasets_and_Benchmarks_Track.html"},{"key":"conf/nips/LinMWRZH25","title":"RoomEditor: High-Fidelity Furniture Synthesis with Parameter-Sharing U-Net.","year":2025,"yearOfEvent":2025,"venue":"NeurIPS","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/nips/LinMWRZH25","documentPage":"http://papers.nips.cc/paper_files/paper/2025/hash/2f46ef5725a8eca24f7f24a17955ad1a-Abstract-Conference.html","type":"Inproceedings","doi":null,"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/nips/LinMWRZH25","documentUrl":"http://papers.nips.cc/paper_files/paper/2025/hash/2f46ef5725a8eca24f7f24a17955ad1a-Abstract-Conference.html"},{"key":"conf/nips/NiYLLLZW25","title":"Point-RFT: Improving Multimodal Reasoning with Visually Grounded Reinforcement Finetuning.","year":2025,"yearOfEvent":2025,"venue":"NeurIPS","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/nips/NiYLLLZW25","documentPage":"http://papers.nips.cc/paper_files/paper/2025/hash/1d83ad88759cef8192451543e5d59bf6-Abstract-Conference.html","type":"Inproceedings","doi":null,"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/nips/NiYLLLZW25","documentUrl":"http://papers.nips.cc/paper_files/paper/2025/hash/1d83ad88759cef8192451543e5d59bf6-Abstract-Conference.html"},{"key":"conf/nips/XiLFGLFLDZYBJGZ25","title":"BMMR: A Large-Scale Bilingual Multimodal Multi-Discipline Reasoning Dataset.","year":2025,"yearOfEvent":2025,"venue":"NeurIPS","types":["https://dblp.org/rdf/schema#Inproceedings"],"dois":[],"source":"https://dblp.org/rec/conf/nips/XiLFGLFLDZYBJGZ25","documentPage":"http://papers.nips.cc/paper_files/paper/2025/hash/5acd3c628aa1819fbf07c39ef73e7285-Abstract-Datasets_and_Benchmarks_Track.html","type":"Inproceedings","doi":null,"yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/conf/nips/XiLFGLFLDZYBJGZ25","documentUrl":"http://papers.nips.cc/paper_files/paper/2025/hash/5acd3c628aa1819fbf07c39ef73e7285-Abstract-Datasets_and_Benchmarks_Track.html"},{"key":"journals/air/TianCPZTZWZ25","title":"A survey on deep learning fundamentals.","year":2025,"yearOfEvent":null,"venue":"Artif. Intell. Rev.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1007/S10462-025-11368-7"],"source":"https://dblp.org/rec/journals/air/TianCPZTZWZ25","documentPage":"https://doi.org/10.1007/S10462-025-11368-7","type":"Article","doi":"https://doi.org/10.1007/S10462-025-11368-7","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/air/TianCPZTZWZ25","documentUrl":"https://doi.org/10.1007/S10462-025-11368-7"},{"key":"journals/asc/QiaoSMZ25","title":"Physical-aware uncertainty prompt learning for real-world blind image restoration.","year":2025,"yearOfEvent":null,"venue":"Appl. Soft Comput.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1016/J.ASOC.2025.113173"],"source":"https://dblp.org/rec/journals/asc/QiaoSMZ25","documentPage":"https://doi.org/10.1016/J.ASOC.2025.113173","type":"Article","doi":"https://doi.org/10.1016/J.ASOC.2025.113173","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/asc/QiaoSMZ25","documentUrl":"https://doi.org/10.1016/J.ASOC.2025.113173"},{"key":"journals/cvm/WeiZZLJZZ25","title":"Personalized Image Generation with Deep Generative Models: A Decade Survey.","year":2025,"yearOfEvent":null,"venue":"Comput. Vis. Media","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.26599/CVM.2025.9450495"],"source":"https://dblp.org/rec/journals/cvm/WeiZZLJZZ25","documentPage":"https://doi.org/10.26599/CVM.2025.9450495","type":"Article","doi":"https://doi.org/10.26599/CVM.2025.9450495","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/cvm/WeiZZLJZZ25","documentUrl":"https://doi.org/10.26599/CVM.2025.9450495"},{"key":"journals/fcsc/LiuPYZZ25","title":"Adaptive network combination for single-image reflection removal: a domain generalization perspective.","year":2025,"yearOfEvent":null,"venue":"Frontiers Comput. Sci.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1007/S11704-024-3582-6"],"source":"https://dblp.org/rec/journals/fcsc/LiuPYZZ25","documentPage":"https://doi.org/10.1007/S11704-024-3582-6","type":"Article","doi":"https://doi.org/10.1007/S11704-024-3582-6","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/fcsc/LiuPYZZ25","documentUrl":"https://doi.org/10.1007/S11704-024-3582-6"},{"key":"journals/ijcv/FengHZKXLZGL25","title":"Diffusion-Enhanced Test-Time Adaptation with Text and Image Augmentation.","year":2025,"yearOfEvent":null,"venue":"Int. J. Comput. Vis.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1007/S11263-025-02412-8"],"source":"https://dblp.org/rec/journals/ijcv/FengHZKXLZGL25","documentPage":"https://doi.org/10.1007/S11263-025-02412-8","type":"Article","doi":"https://doi.org/10.1007/S11263-025-02412-8","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/ijcv/FengHZKXLZGL25","documentUrl":"https://doi.org/10.1007/S11263-025-02412-8"},{"key":"journals/ijcv/RenSLWLZ25","title":"Reblurring-Guided Single Image Defocus Deblurring: A Learning Framework with Misaligned Training Pairs.","year":2025,"yearOfEvent":null,"venue":"Int. J. Comput. Vis.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1007/S11263-025-02522-3"],"source":"https://dblp.org/rec/journals/ijcv/RenSLWLZ25","documentPage":"https://doi.org/10.1007/S11263-025-02522-3","type":"Article","doi":"https://doi.org/10.1007/S11263-025-02522-3","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/ijcv/RenSLWLZ25","documentUrl":"https://doi.org/10.1007/S11263-025-02522-3"},{"key":"journals/ijon/LiYSRLZ25","title":"Learning dual-pixel alignment for defocus deblurring.","year":2025,"yearOfEvent":null,"venue":"Neurocomputing","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1016/J.NEUCOM.2024.128880"],"source":"https://dblp.org/rec/journals/ijon/LiYSRLZ25","documentPage":"https://doi.org/10.1016/J.NEUCOM.2024.128880","type":"Article","doi":"https://doi.org/10.1016/J.NEUCOM.2024.128880","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/ijon/LiYSRLZ25","documentUrl":"https://doi.org/10.1016/J.NEUCOM.2024.128880"},{"key":"journals/ijon/WangGLYZ25","title":"DualAug: Exploiting additional heavy augmentation with OOD data rejection.","year":2025,"yearOfEvent":null,"venue":"Neurocomputing","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1016/J.NEUCOM.2025.131209"],"source":"https://dblp.org/rec/journals/ijon/WangGLYZ25","documentPage":"https://doi.org/10.1016/J.NEUCOM.2025.131209","type":"Article","doi":"https://doi.org/10.1016/J.NEUCOM.2025.131209","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/ijon/WangGLYZ25","documentUrl":"https://doi.org/10.1016/J.NEUCOM.2025.131209"},{"key":"journals/isci/ShangRYZ25","title":"Aggregating nearest sharp features via hybrid transformers for video deblurring.","year":2025,"yearOfEvent":null,"venue":"Inf. Sci.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1016/J.INS.2024.121689"],"source":"https://dblp.org/rec/journals/isci/ShangRYZ25","documentPage":"https://doi.org/10.1016/J.INS.2024.121689","type":"Article","doi":"https://doi.org/10.1016/J.INS.2024.121689","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/isci/ShangRYZ25","documentUrl":"https://doi.org/10.1016/J.INS.2024.121689"},{"key":"journals/jei/ZhangSRZ25","title":"Spatial restoration guided by amplitude-phase interaction for flare removal.","year":2025,"yearOfEvent":null,"venue":"J. Electronic Imaging","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1117/1.JEI.34.3.033053"],"source":"https://dblp.org/rec/journals/jei/ZhangSRZ25","documentPage":"https://doi.org/10.1117/1.JEI.34.3.033053","type":"Article","doi":"https://doi.org/10.1117/1.JEI.34.3.033053","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/jei/ZhangSRZ25","documentUrl":"https://doi.org/10.1117/1.JEI.34.3.033053"},{"key":"journals/nn/ChengSWQZM25","title":"Degradation-Guided cross-consistent deep unfolding network for video restoration under diverse weathers.","year":2025,"yearOfEvent":null,"venue":"Neural Networks","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1016/J.NEUNET.2025.107700"],"source":"https://dblp.org/rec/journals/nn/ChengSWQZM25","documentPage":"https://doi.org/10.1016/J.NEUNET.2025.107700","type":"Article","doi":"https://doi.org/10.1016/J.NEUNET.2025.107700","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/nn/ChengSWQZM25","documentUrl":"https://doi.org/10.1016/J.NEUNET.2025.107700"},{"key":"journals/nn/WuLWLYZP25","title":"Multi-stage network for single image deblurring based on dual-domain window mamba.","year":2025,"yearOfEvent":null,"venue":"Neural Networks","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1016/J.NEUNET.2025.107460"],"source":"https://dblp.org/rec/journals/nn/WuLWLYZP25","documentPage":"https://doi.org/10.1016/J.NEUNET.2025.107460","type":"Article","doi":"https://doi.org/10.1016/J.NEUNET.2025.107460","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/nn/WuLWLYZP25","documentUrl":"https://doi.org/10.1016/J.NEUNET.2025.107460"},{"key":"journals/pami/FengYXKGZL25","title":"Text to Image for Multi-Label Image Recognition With Joint Prompt-Adapter Learning.","year":2025,"yearOfEvent":null,"venue":"IEEE Trans. Pattern Anal. Mach. Intell.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1109/TPAMI.2025.3573852"],"source":"https://dblp.org/rec/journals/pami/FengYXKGZL25","documentPage":"https://doi.org/10.1109/TPAMI.2025.3573852","type":"Article","doi":"https://doi.org/10.1109/TPAMI.2025.3573852","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/pami/FengYXKGZL25","documentUrl":"https://doi.org/10.1109/TPAMI.2025.3573852"},{"key":"journals/pami/HeSFXTZZGL25","title":"Diffusion Models in Low-Level Vision: A Survey.","year":2025,"yearOfEvent":null,"venue":"IEEE Trans. Pattern Anal. Mach. Intell.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1109/TPAMI.2025.3545047"],"source":"https://dblp.org/rec/journals/pami/HeSFXTZZGL25","documentPage":"https://doi.org/10.1109/TPAMI.2025.3545047","type":"Article","doi":"https://doi.org/10.1109/TPAMI.2025.3545047","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/pami/HeSFXTZZGL25","documentUrl":"https://doi.org/10.1109/TPAMI.2025.3545047"},{"key":"journals/pami/LiGWHZP25","title":"Relationship Quantification of Image Degradations.","year":2025,"yearOfEvent":null,"venue":"IEEE Trans. Pattern Anal. Mach. Intell.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1109/TPAMI.2025.3568690"],"source":"https://dblp.org/rec/journals/pami/LiGWHZP25","documentPage":"https://doi.org/10.1109/TPAMI.2025.3568690","type":"Article","doi":"https://doi.org/10.1109/TPAMI.2025.3568690","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/pami/LiGWHZP25","documentUrl":"https://doi.org/10.1109/TPAMI.2025.3568690"},{"key":"journals/pami/LiZL25","title":"Enhanced Generative Structure Prior for Chinese Text Image Super-Resolution.","year":2025,"yearOfEvent":null,"venue":"IEEE Trans. Pattern Anal. Mach. Intell.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1109/TPAMI.2025.3596329"],"source":"https://dblp.org/rec/journals/pami/LiZL25","documentPage":"https://doi.org/10.1109/TPAMI.2025.3596329","type":"Article","doi":"https://doi.org/10.1109/TPAMI.2025.3596329","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/pami/LiZL25","documentUrl":"https://doi.org/10.1109/TPAMI.2025.3596329"},{"key":"journals/pami/ZhangWZZ25","title":"Self-Supervised Learning for Real-World Super-Resolution From Dual and Multiple Zoomed Observations.","year":2025,"yearOfEvent":null,"venue":"IEEE Trans. Pattern Anal. Mach. Intell.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1109/TPAMI.2024.3379736"],"source":"https://dblp.org/rec/journals/pami/ZhangWZZ25","documentPage":"https://doi.org/10.1109/TPAMI.2024.3379736","type":"Article","doi":"https://doi.org/10.1109/TPAMI.2024.3379736","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/pami/ZhangWZZ25","documentUrl":"https://doi.org/10.1109/TPAMI.2024.3379736"},{"key":"journals/pr/GongYZYYZ25","title":"Spatially adaptive pyramid feature fusion for scale-aware crowd counting.","year":2025,"yearOfEvent":null,"venue":"Pattern Recognit.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1016/J.PATCOG.2025.111832"],"source":"https://dblp.org/rec/journals/pr/GongYZYYZ25","documentPage":"https://doi.org/10.1016/J.PATCOG.2025.111832","type":"Article","doi":"https://doi.org/10.1016/J.PATCOG.2025.111832","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/pr/GongYZYYZ25","documentUrl":"https://doi.org/10.1016/J.PATCOG.2025.111832"},{"key":"journals/pr/HuangCDLZZ25","title":"IMWA: Iterative Model Weight Averaging benefits class-imbalanced learning.","year":2025,"yearOfEvent":null,"venue":"Pattern Recognit.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1016/J.PATCOG.2024.111293"],"source":"https://dblp.org/rec/journals/pr/HuangCDLZZ25","documentPage":"https://doi.org/10.1016/J.PATCOG.2024.111293","type":"Article","doi":"https://doi.org/10.1016/J.PATCOG.2024.111293","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/pr/HuangCDLZZ25","documentUrl":"https://doi.org/10.1016/J.PATCOG.2024.111293"},{"key":"journals/pr/QiaoSMZ25","title":"Learning physical-aware diffusion priors for zero-shot restoration of scattering-affected images.","year":2025,"yearOfEvent":null,"venue":"Pattern Recognit.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1016/J.PATCOG.2025.111473"],"source":"https://dblp.org/rec/journals/pr/QiaoSMZ25","documentPage":"https://doi.org/10.1016/J.PATCOG.2025.111473","type":"Article","doi":"https://doi.org/10.1016/J.PATCOG.2025.111473","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/pr/QiaoSMZ25","documentUrl":"https://doi.org/10.1016/J.PATCOG.2025.111473"},{"key":"journals/pr/XuHQYGZ25","title":"FILP-3D: Enhancing 3D few-shot class-incremental learning with pre-trained vision-language models.","year":2025,"yearOfEvent":null,"venue":"Pattern Recognit.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1016/J.PATCOG.2025.111558"],"source":"https://dblp.org/rec/journals/pr/XuHQYGZ25","documentPage":"https://doi.org/10.1016/J.PATCOG.2025.111558","type":"Article","doi":"https://doi.org/10.1016/J.PATCOG.2025.111558","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/pr/XuHQYGZ25","documentUrl":"https://doi.org/10.1016/J.PATCOG.2025.111558"},{"key":"journals/prl/LiGZ25","title":"Enhancing visual adversarial transferability via affine transformation of intermediate-level perturbations.","year":2025,"yearOfEvent":null,"venue":"Pattern Recognit. Lett.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1016/J.PATREC.2025.03.003"],"source":"https://dblp.org/rec/journals/prl/LiGZ25","documentPage":"https://doi.org/10.1016/J.PATREC.2025.03.003","type":"Article","doi":"https://doi.org/10.1016/J.PATREC.2025.03.003","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/prl/LiGZ25","documentUrl":"https://doi.org/10.1016/J.PATREC.2025.03.003"},{"key":"journals/ral/NiZCBCZZZ25","title":"Don't Let Your Robot Be Harmful: Responsible Robotic Manipulation via Safety-As-Policy.","year":2025,"yearOfEvent":null,"venue":"IEEE Robotics Autom. Lett.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1109/LRA.2025.3623027"],"source":"https://dblp.org/rec/journals/ral/NiZCBCZZZ25","documentPage":"https://doi.org/10.1109/LRA.2025.3623027","type":"Article","doi":"https://doi.org/10.1109/LRA.2025.3623027","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/ral/NiZCBCZZZ25","documentUrl":"https://doi.org/10.1109/LRA.2025.3623027"},{"key":"journals/spl/WanHFZZ25","title":"Enhancing No-Reference Audio-Visual Quality Assessment via Joint Cross-Attention Fusion.","year":2025,"yearOfEvent":null,"venue":"IEEE Signal Process. Lett.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1109/LSP.2024.3522855"],"source":"https://dblp.org/rec/journals/spl/WanHFZZ25","documentPage":"https://doi.org/10.1109/LSP.2024.3522855","type":"Article","doi":"https://doi.org/10.1109/LSP.2024.3522855","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/spl/WanHFZZ25","documentUrl":"https://doi.org/10.1109/LSP.2024.3522855"},{"key":"journals/tcsv/LiWWZFT25","title":"Multi-Timescale Motion-Decoupled Spiking Transformer for Audio-Visual Zero-Shot Learning.","year":2025,"yearOfEvent":null,"venue":"IEEE Trans. Circuits Syst. Video Technol.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1109/TCSVT.2025.3574499"],"source":"https://dblp.org/rec/journals/tcsv/LiWWZFT25","documentPage":"https://doi.org/10.1109/TCSVT.2025.3574499","type":"Article","doi":"https://doi.org/10.1109/TCSVT.2025.3574499","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/tcsv/LiWWZFT25","documentUrl":"https://doi.org/10.1109/TCSVT.2025.3574499"},{"key":"journals/tcsv/WangJWZ25","title":"Automatic Label Assignment for Object Detection.","year":2025,"yearOfEvent":null,"venue":"IEEE Trans. Circuits Syst. Video Technol.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1109/TCSVT.2025.3578021"],"source":"https://dblp.org/rec/journals/tcsv/WangJWZ25","documentPage":"https://doi.org/10.1109/TCSVT.2025.3578021","type":"Article","doi":"https://doi.org/10.1109/TCSVT.2025.3578021","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/tcsv/WangJWZ25","documentUrl":"https://doi.org/10.1109/TCSVT.2025.3578021"},{"key":"journals/tcsv/WanYLFZZ25","title":"No-Reference Stereoscopic Omnidirectional Image Quality Assessment via a Binocular Viewport Hypergraph Convolutional Network.","year":2025,"yearOfEvent":null,"venue":"IEEE Trans. Circuits Syst. Video Technol.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1109/TCSVT.2025.3538511"],"source":"https://dblp.org/rec/journals/tcsv/WanYLFZZ25","documentPage":"https://doi.org/10.1109/TCSVT.2025.3538511","type":"Article","doi":"https://doi.org/10.1109/TCSVT.2025.3538511","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/tcsv/WanYLFZZ25","documentUrl":"https://doi.org/10.1109/TCSVT.2025.3538511"},{"key":"journals/tip/MaoHFZ25","title":"A Swiss Army Knife for Tracking by Natural Language Specification.","year":2025,"yearOfEvent":null,"venue":"IEEE Trans. Image Process.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1109/TIP.2025.3553290"],"source":"https://dblp.org/rec/journals/tip/MaoHFZ25","documentPage":"https://doi.org/10.1109/TIP.2025.3553290","type":"Article","doi":"https://doi.org/10.1109/TIP.2025.3553290","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/tip/MaoHFZ25","documentUrl":"https://doi.org/10.1109/TIP.2025.3553290"},{"key":"journals/tip/TianXLZZZ25","title":"A Perception CNN for Facial Expression Recognition.","year":2025,"yearOfEvent":null,"venue":"IEEE Trans. Image Process.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1109/TIP.2025.3637715"],"source":"https://dblp.org/rec/journals/tip/TianXLZZZ25","documentPage":"https://doi.org/10.1109/TIP.2025.3637715","type":"Article","doi":"https://doi.org/10.1109/TIP.2025.3637715","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/tip/TianXLZZZ25","documentUrl":"https://doi.org/10.1109/TIP.2025.3637715"},{"key":"journals/tip/WangJWZ25","title":"WS-SAM: Generalizing SAM to Weakly Supervised Object Detection With Category Label.","year":2025,"yearOfEvent":null,"venue":"IEEE Trans. Image Process.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1109/TIP.2025.3581729"],"source":"https://dblp.org/rec/journals/tip/WangJWZ25","documentPage":"https://doi.org/10.1109/TIP.2025.3581729","type":"Article","doi":"https://doi.org/10.1109/TIP.2025.3581729","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/tip/WangJWZ25","documentUrl":"https://doi.org/10.1109/TIP.2025.3581729"},{"key":"journals/tmm/XuZWZ25","title":"NIR-Assisted Image Denoising: A Selective Fusion Approach and a Real-World Benchmark Dataset.","year":2025,"yearOfEvent":null,"venue":"IEEE Trans. Multim.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1109/TMM.2024.3521833"],"source":"https://dblp.org/rec/journals/tmm/XuZWZ25","documentPage":"https://doi.org/10.1109/TMM.2024.3521833","type":"Article","doi":"https://doi.org/10.1109/TMM.2024.3521833","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/tmm/XuZWZ25","documentUrl":"https://doi.org/10.1109/TMM.2024.3521833"},{"key":"journals/tmm/ZhuangDZLLWHLZ25","title":"Spatial-Temporal Saliency Guided Unbiased Contrastive Learning for Video Scene Graph Generation.","year":2025,"yearOfEvent":null,"venue":"IEEE Trans. Multim.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1109/TMM.2025.3557688"],"source":"https://dblp.org/rec/journals/tmm/ZhuangDZLLWHLZ25","documentPage":"https://doi.org/10.1109/TMM.2025.3557688","type":"Article","doi":"https://doi.org/10.1109/TMM.2025.3557688","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/tmm/ZhuangDZLLWHLZ25","documentUrl":"https://doi.org/10.1109/TMM.2025.3557688"},{"key":"journals/tnn/LiFWYZ25","title":"Unprejudiced Training Auxiliary Tasks Makes Primary Better: A Multitask Learning Perspective.","year":2025,"yearOfEvent":null,"venue":"IEEE Trans. Neural Networks Learn. Syst.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1109/TNNLS.2024.3462788"],"source":"https://dblp.org/rec/journals/tnn/LiFWYZ25","documentPage":"https://doi.org/10.1109/TNNLS.2024.3462788","type":"Article","doi":"https://doi.org/10.1109/TNNLS.2024.3462788","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/tnn/LiFWYZ25","documentUrl":"https://doi.org/10.1109/TNNLS.2024.3462788"},{"key":"journals/tnn/ShaoMQZZ25","title":"Latent Code Augmentation Based on Stable Diffusion for Data-Free Substitute Attacks.","year":2025,"yearOfEvent":null,"venue":"IEEE Trans. Neural Networks Learn. Syst.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1109/TNNLS.2025.3526338"],"source":"https://dblp.org/rec/journals/tnn/ShaoMQZZ25","documentPage":"https://doi.org/10.1109/TNNLS.2025.3526338","type":"Article","doi":"https://doi.org/10.1109/TNNLS.2025.3526338","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/tnn/ShaoMQZZ25","documentUrl":"https://doi.org/10.1109/TNNLS.2025.3526338"},{"key":"journals/tnn/ZhangZBZTZDZ25","title":"Revising Representation and Target Deviations for Accurate Human Pose Estimation.","year":2025,"yearOfEvent":null,"venue":"IEEE Trans. Neural Networks Learn. Syst.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1109/TNNLS.2025.3569464"],"source":"https://dblp.org/rec/journals/tnn/ZhangZBZTZDZ25","documentPage":"https://doi.org/10.1109/TNNLS.2025.3569464","type":"Article","doi":"https://doi.org/10.1109/TNNLS.2025.3569464","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/tnn/ZhangZBZTZDZ25","documentUrl":"https://doi.org/10.1109/TNNLS.2025.3569464"},{"key":"journals/tog/HuangZWLWWJLLZG25","title":"Voyager: Long-Range and World-Consistent Video Diffusion for Explorable 3D Scene Generation.","year":2025,"yearOfEvent":null,"venue":"ACM Trans. Graph.","types":["https://dblp.org/rdf/schema#Article"],"dois":["https://doi.org/10.1145/3763330"],"source":"https://dblp.org/rec/journals/tog/HuangZWLWWJLLZG25","documentPage":"https://doi.org/10.1145/3763330","type":"Article","doi":"https://doi.org/10.1145/3763330","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/tog/HuangZWLWWJLLZG25","documentUrl":"https://doi.org/10.1145/3763330"}],"preprints":[{"key":"journals/corr/abs-2501-01633","title":"ACE: Anti-Editing Concept Erasure in Text-to-Image Models.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2501.01633"],"source":"https://dblp.org/rec/journals/corr/abs-2501-01633","documentPage":"https://doi.org/10.48550/ARXIV.2501.01633","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2501.01633","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2501-01633","documentUrl":"https://doi.org/10.48550/ARXIV.2501.01633","arxivId":"2501.01633","arxivUrl":"https://arxiv.org/abs/2501.01633"},{"key":"journals/corr/abs-2501-08225","title":"FramePainter: Endowing Interactive Image Editing with Video Diffusion Priors.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2501.08225"],"source":"https://dblp.org/rec/journals/corr/abs-2501-08225","documentPage":"https://doi.org/10.48550/ARXIV.2501.08225","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2501.08225","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2501-08225","documentUrl":"https://doi.org/10.48550/ARXIV.2501.08225","arxivId":"2501.08225","arxivUrl":"https://arxiv.org/abs/2501.08225"},{"key":"journals/corr/abs-2502-13081","title":"Personalized Image Generation with Deep Generative Models: A Decade Survey.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2502.13081"],"source":"https://dblp.org/rec/journals/corr/abs-2502-13081","documentPage":"https://doi.org/10.48550/ARXIV.2502.13081","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2502.13081","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2502-13081","documentUrl":"https://doi.org/10.48550/ARXIV.2502.13081","arxivId":"2502.13081","arxivUrl":"https://arxiv.org/abs/2502.13081"},{"key":"journals/corr/abs-2503-04314","title":"S2Gaussian: Sparse-View Super-Resolution 3D Gaussian Splatting.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2503.04314"],"source":"https://dblp.org/rec/journals/corr/abs-2503-04314","documentPage":"https://doi.org/10.48550/ARXIV.2503.04314","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2503.04314","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-04314","documentUrl":"https://doi.org/10.48550/ARXIV.2503.04314","arxivId":"2503.04314","arxivUrl":"https://arxiv.org/abs/2503.04314"},{"key":"journals/corr/abs-2503-13184","title":"Triad: Empowering LMM-based Anomaly Detection with Vision Expert-guided Visual Tokenizer and Manufacturing Process.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2503.13184"],"source":"https://dblp.org/rec/journals/corr/abs-2503-13184","documentPage":"https://doi.org/10.48550/ARXIV.2503.13184","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2503.13184","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2503-13184","documentUrl":"https://doi.org/10.48550/ARXIV.2503.13184","arxivId":"2503.13184","arxivUrl":"https://arxiv.org/abs/2503.13184"},{"key":"journals/corr/abs-2504-02004","title":"Beyond Static Scenes: Camera-controllable Background Generation for Human Motion.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2504.02004"],"source":"https://dblp.org/rec/journals/corr/abs-2504-02004","documentPage":"https://doi.org/10.48550/ARXIV.2504.02004","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2504.02004","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2504-02004","documentUrl":"https://doi.org/10.48550/ARXIV.2504.02004","arxivId":"2504.02004","arxivUrl":"https://arxiv.org/abs/2504.02004"},{"key":"journals/corr/abs-2504-02304","title":"Measurement of LLM's Philosophies of Human Nature.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2504.02304"],"source":"https://dblp.org/rec/journals/corr/abs-2504-02304","documentPage":"https://doi.org/10.48550/ARXIV.2504.02304","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2504.02304","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2504-02304","documentUrl":"https://doi.org/10.48550/ARXIV.2504.02304","arxivId":"2504.02304","arxivUrl":"https://arxiv.org/abs/2504.02304"},{"key":"journals/corr/abs-2504-09949","title":"Pseudo-Label Guided Real-World Image De-weathering: A Learning Framework with Imperfect Supervision.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2504.09949"],"source":"https://dblp.org/rec/journals/corr/abs-2504-09949","documentPage":"https://doi.org/10.48550/ARXIV.2504.09949","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2504.09949","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2504-09949","documentUrl":"https://doi.org/10.48550/ARXIV.2504.09949","arxivId":"2504.09949","arxivUrl":"https://arxiv.org/abs/2504.09949"},{"key":"journals/corr/abs-2504-14553","title":"Grounding-MD: Grounded Video-language Pre-training for Open-World Moment Detection.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2504.14553"],"source":"https://dblp.org/rec/journals/corr/abs-2504-14553","documentPage":"https://doi.org/10.48550/ARXIV.2504.14553","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2504.14553","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2504-14553","documentUrl":"https://doi.org/10.48550/ARXIV.2504.14553","arxivId":"2504.14553","arxivUrl":"https://arxiv.org/abs/2504.14553"},{"key":"journals/corr/abs-2504-14600","title":"NTIRE 2025 Challenge on Real-World Face Restoration: Methods and Results.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2504.14600"],"source":"https://dblp.org/rec/journals/corr/abs-2504-14600","documentPage":"https://doi.org/10.48550/ARXIV.2504.14600","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2504.14600","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2504-14600","documentUrl":"https://doi.org/10.48550/ARXIV.2504.14600","arxivId":"2504.14600","arxivUrl":"https://arxiv.org/abs/2504.14600"},{"key":"journals/corr/abs-2504-19183","title":"Segmenting Objectiveness and Task-awareness Unknown Region for Autonomous Driving.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2504.19183"],"source":"https://dblp.org/rec/journals/corr/abs-2504-19183","documentPage":"https://doi.org/10.48550/ARXIV.2504.19183","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2504.19183","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2504-19183","documentUrl":"https://doi.org/10.48550/ARXIV.2504.19183","arxivId":"2504.19183","arxivUrl":"https://arxiv.org/abs/2504.19183"},{"key":"journals/corr/abs-2504-19432","title":"EarthMapper: Visual Autoregressive Models for Controllable Bidirectional Satellite-Map Translation.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2504.19432"],"source":"https://dblp.org/rec/journals/corr/abs-2504-19432","documentPage":"https://doi.org/10.48550/ARXIV.2504.19432","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2504.19432","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2504-19432","documentUrl":"https://doi.org/10.48550/ARXIV.2504.19432","arxivId":"2504.19432","arxivUrl":"https://arxiv.org/abs/2504.19432"},{"key":"journals/corr/abs-2504-19834","title":"AnimateAnywhere: Rouse the Background in Human Image Animation.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2504.19834"],"source":"https://dblp.org/rec/journals/corr/abs-2504-19834","documentPage":"https://doi.org/10.48550/ARXIV.2504.19834","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2504.19834","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2504-19834","documentUrl":"https://doi.org/10.48550/ARXIV.2504.19834","arxivId":"2504.19834","arxivUrl":"https://arxiv.org/abs/2504.19834"},{"key":"journals/corr/abs-2505-04262","title":"Bridging Geometry-Coherent Text-to-3D Generation with Multi-View Diffusion Priors and Gaussian Splatting.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2505.04262"],"source":"https://dblp.org/rec/journals/corr/abs-2505-04262","documentPage":"https://doi.org/10.48550/ARXIV.2505.04262","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2505.04262","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-04262","documentUrl":"https://doi.org/10.48550/ARXIV.2505.04262","arxivId":"2505.04262","arxivUrl":"https://arxiv.org/abs/2505.04262"},{"key":"journals/corr/abs-2505-06975","title":"High-Frequency Prior-Driven Adaptive Masking for Accelerating Image Super-Resolution.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2505.06975"],"source":"https://dblp.org/rec/journals/corr/abs-2505-06975","documentPage":"https://doi.org/10.48550/ARXIV.2505.06975","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2505.06975","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-06975","documentUrl":"https://doi.org/10.48550/ARXIV.2505.06975","arxivId":"2505.06975","arxivUrl":"https://arxiv.org/abs/2505.06975"},{"key":"journals/corr/abs-2505-11578","title":"Spatiotemporal Field Generation Based on Hybrid Mamba-Transformer with Physics-informed Fine-tuning.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2505.11578"],"source":"https://dblp.org/rec/journals/corr/abs-2505-11578","documentPage":"https://doi.org/10.48550/ARXIV.2505.11578","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2505.11578","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-11578","documentUrl":"https://doi.org/10.48550/ARXIV.2505.11578","arxivId":"2505.11578","arxivUrl":"https://arxiv.org/abs/2505.11578"},{"key":"journals/corr/abs-2505-17609","title":"Decoupled Visual Interpretation and Linguistic Reasoning for Math Problem Solving.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2505.17609"],"source":"https://dblp.org/rec/journals/corr/abs-2505-17609","documentPage":"https://doi.org/10.48550/ARXIV.2505.17609","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2505.17609","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-17609","documentUrl":"https://doi.org/10.48550/ARXIV.2505.17609","arxivId":"2505.17609","arxivUrl":"https://arxiv.org/abs/2505.17609"},{"key":"journals/corr/abs-2505-19702","title":"Point-RFT: Improving Multimodal Reasoning with Visually Grounded Reinforcement Finetuning.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2505.19702"],"source":"https://dblp.org/rec/journals/corr/abs-2505-19702","documentPage":"https://doi.org/10.48550/ARXIV.2505.19702","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2505.19702","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-19702","documentUrl":"https://doi.org/10.48550/ARXIV.2505.19702","arxivId":"2505.19702","arxivUrl":"https://arxiv.org/abs/2505.19702"},{"key":"journals/corr/abs-2505-19938","title":"Multi-Timescale Motion-Decoupled Spiking Transformer for Audio-Visual Zero-Shot Learning.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2505.19938"],"source":"https://dblp.org/rec/journals/corr/abs-2505-19938","documentPage":"https://doi.org/10.48550/ARXIV.2505.19938","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2505.19938","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-19938","documentUrl":"https://doi.org/10.48550/ARXIV.2505.19938","arxivId":"2505.19938","arxivUrl":"https://arxiv.org/abs/2505.19938"},{"key":"journals/corr/abs-2505-22634","title":"LabUtopia: High-Fidelity Simulation and Hierarchical Benchmark for Scientific Embodied Agents.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2505.22634"],"source":"https://dblp.org/rec/journals/corr/abs-2505-22634","documentPage":"https://doi.org/10.48550/ARXIV.2505.22634","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2505.22634","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-22634","documentUrl":"https://doi.org/10.48550/ARXIV.2505.22634","arxivId":"2505.22634","arxivUrl":"https://arxiv.org/abs/2505.22634"},{"key":"journals/corr/abs-2505-24238","title":"MIRAGE: Assessing Hallucination in Multimodal Reasoning Chains of MLLM.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2505.24238"],"source":"https://dblp.org/rec/journals/corr/abs-2505-24238","documentPage":"https://doi.org/10.48550/ARXIV.2505.24238","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2505.24238","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2505-24238","documentUrl":"https://doi.org/10.48550/ARXIV.2505.24238","arxivId":"2505.24238","arxivUrl":"https://arxiv.org/abs/2505.24238"},{"key":"journals/corr/abs-2506-02604","title":"Application of convolutional neural networks in image super-resolution.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2506.02604"],"source":"https://dblp.org/rec/journals/corr/abs-2506-02604","documentPage":"https://doi.org/10.48550/ARXIV.2506.02604","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2506.02604","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-02604","documentUrl":"https://doi.org/10.48550/ARXIV.2506.02604","arxivId":"2506.02604","arxivUrl":"https://arxiv.org/abs/2506.02604"},{"key":"journals/corr/abs-2506-04225","title":"Voyager: Long-Range and World-Consistent Video Diffusion for Explorable 3D Scene Generation.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2506.04225"],"source":"https://dblp.org/rec/journals/corr/abs-2506-04225","documentPage":"https://doi.org/10.48550/ARXIV.2506.04225","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2506.04225","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-04225","documentUrl":"https://doi.org/10.48550/ARXIV.2506.04225","arxivId":"2506.04225","arxivUrl":"https://arxiv.org/abs/2506.04225"},{"key":"journals/corr/abs-2506-07986","title":"Rethinking Cross-Modal Interaction in Multimodal Diffusion Transformers.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2506.07986"],"source":"https://dblp.org/rec/journals/corr/abs-2506-07986","documentPage":"https://doi.org/10.48550/ARXIV.2506.07986","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2506.07986","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-07986","documentUrl":"https://doi.org/10.48550/ARXIV.2506.07986","arxivId":"2506.07986","arxivUrl":"https://arxiv.org/abs/2506.07986"},{"key":"journals/corr/abs-2506-08361","title":"Image Demoiréing Using Dual Camera Fusion on Mobile Phones.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2506.08361"],"source":"https://dblp.org/rec/journals/corr/abs-2506-08361","documentPage":"https://doi.org/10.48550/ARXIV.2506.08361","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2506.08361","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-08361","documentUrl":"https://doi.org/10.48550/ARXIV.2506.08361","arxivId":"2506.08361","arxivUrl":"https://arxiv.org/abs/2506.08361"},{"key":"journals/corr/abs-2506-10575","title":"Text to Image for Multi-Label Image Recognition with Joint Prompt-Adapter Learning.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2506.10575"],"source":"https://dblp.org/rec/journals/corr/abs-2506-10575","documentPage":"https://doi.org/10.48550/ARXIV.2506.10575","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2506.10575","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-10575","documentUrl":"https://doi.org/10.48550/ARXIV.2506.10575","arxivId":"2506.10575","arxivUrl":"https://arxiv.org/abs/2506.10575"},{"key":"journals/corr/abs-2506-19613","title":"Position: Intelligent Science Laboratory Requires the Integration of Cognitive and Embodied AI.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2506.19613"],"source":"https://dblp.org/rec/journals/corr/abs-2506-19613","documentPage":"https://doi.org/10.48550/ARXIV.2506.19613","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2506.19613","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2506-19613","documentUrl":"https://doi.org/10.48550/ARXIV.2506.19613","arxivId":"2506.19613","arxivUrl":"https://arxiv.org/abs/2506.19613"},{"key":"journals/corr/abs-2507-03483","title":"BMMR: A Large-Scale Bilingual Multimodal Multi-Discipline Reasoning Dataset.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2507.03483"],"source":"https://dblp.org/rec/journals/corr/abs-2507-03483","documentPage":"https://doi.org/10.48550/ARXIV.2507.03483","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2507.03483","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2507-03483","documentUrl":"https://doi.org/10.48550/ARXIV.2507.03483","arxivId":"2507.03483","arxivUrl":"https://arxiv.org/abs/2507.03483"},{"key":"journals/corr/abs-2507-04599","title":"QR-LoRA: Efficient and Disentangled Fine-tuning via QR Decomposition for Customized Generation.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2507.04599"],"source":"https://dblp.org/rec/journals/corr/abs-2507-04599","documentPage":"https://doi.org/10.48550/ARXIV.2507.04599","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2507.04599","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2507-04599","documentUrl":"https://doi.org/10.48550/ARXIV.2507.04599","arxivId":"2507.04599","arxivUrl":"https://arxiv.org/abs/2507.04599"},{"key":"journals/corr/abs-2507-07708","title":"Motion-Aware Adaptive Pixel Pruning for Efficient Local Motion Deblurring.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2507.07708"],"source":"https://dblp.org/rec/journals/corr/abs-2507-07708","documentPage":"https://doi.org/10.48550/ARXIV.2507.07708","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2507.07708","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2507-07708","documentUrl":"https://doi.org/10.48550/ARXIV.2507.07708","arxivId":"2507.07708","arxivUrl":"https://arxiv.org/abs/2507.07708"},{"key":"journals/corr/abs-2507-10470","title":"RefSTAR: Blind Facial Image Restoration with Reference Selection, Transfer, and Reconstruction.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2507.10470"],"source":"https://dblp.org/rec/journals/corr/abs-2507-10470","documentPage":"https://doi.org/10.48550/ARXIV.2507.10470","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2507.10470","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2507-10470","documentUrl":"https://doi.org/10.48550/ARXIV.2507.10470","arxivId":"2507.10470","arxivUrl":"https://arxiv.org/abs/2507.10470"},{"key":"journals/corr/abs-2507-12952","title":"LoViC: Efficient Long Video Generation with Context Compression.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2507.12952"],"source":"https://dblp.org/rec/journals/corr/abs-2507-12952","documentPage":"https://doi.org/10.48550/ARXIV.2507.12952","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2507.12952","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2507-12952","documentUrl":"https://doi.org/10.48550/ARXIV.2507.12952","arxivId":"2507.12952","arxivUrl":"https://arxiv.org/abs/2507.12952"},{"key":"journals/corr/abs-2507-23141","title":"AI paradigm for solving differential equations: first-principles data generation and scale-dilation operator AI solver.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2507.23141"],"source":"https://dblp.org/rec/journals/corr/abs-2507-23141","documentPage":"https://doi.org/10.48550/ARXIV.2507.23141","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2507.23141","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2507-23141","documentUrl":"https://doi.org/10.48550/ARXIV.2507.23141","arxivId":"2507.23141","arxivUrl":"https://arxiv.org/abs/2507.23141"},{"key":"journals/corr/abs-2508-06924","title":"AR-GRPO: Training Autoregressive Image Generation Models via Reinforcement Learning.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2508.06924"],"source":"https://dblp.org/rec/journals/corr/abs-2508-06924","documentPage":"https://doi.org/10.48550/ARXIV.2508.06924","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2508.06924","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-06924","documentUrl":"https://doi.org/10.48550/ARXIV.2508.06924","arxivId":"2508.06924","arxivUrl":"https://arxiv.org/abs/2508.06924"},{"key":"journals/corr/abs-2508-07537","title":"Enhanced Generative Structure Prior for Chinese Text Image Super-resolution.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2508.07537"],"source":"https://dblp.org/rec/journals/corr/abs-2508-07537","documentPage":"https://doi.org/10.48550/ARXIV.2508.07537","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2508.07537","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-07537","documentUrl":"https://doi.org/10.48550/ARXIV.2508.07537","arxivId":"2508.07537","arxivUrl":"https://arxiv.org/abs/2508.07537"},{"key":"journals/corr/abs-2508-08605","title":"SelfHVD: Self-Supervised Handheld Video Deblurring for Mobile Phones.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2508.08605"],"source":"https://dblp.org/rec/journals/corr/abs-2508-08605","documentPage":"https://doi.org/10.48550/ARXIV.2508.08605","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2508.08605","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-08605","documentUrl":"https://doi.org/10.48550/ARXIV.2508.08605","arxivId":"2508.08605","arxivUrl":"https://arxiv.org/abs/2508.08605"},{"key":"journals/corr/abs-2508-16887","title":"MDIQA: Unified Image Quality Assessment for Multi-dimensional Evaluation and Restoration.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2508.16887"],"source":"https://dblp.org/rec/journals/corr/abs-2508-16887","documentPage":"https://doi.org/10.48550/ARXIV.2508.16887","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2508.16887","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-16887","documentUrl":"https://doi.org/10.48550/ARXIV.2508.16887","arxivId":"2508.16887","arxivUrl":"https://arxiv.org/abs/2508.16887"},{"key":"journals/corr/abs-2508-17404","title":"MoCo: Motion-Consistent Human Video Generation via Structure-Appearance Decoupling.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2508.17404"],"source":"https://dblp.org/rec/journals/corr/abs-2508-17404","documentPage":"https://doi.org/10.48550/ARXIV.2508.17404","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2508.17404","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2508-17404","documentUrl":"https://doi.org/10.48550/ARXIV.2508.17404","arxivId":"2508.17404","arxivUrl":"https://arxiv.org/abs/2508.17404"},{"key":"journals/corr/abs-2509-11360","title":"GLaVE-Cap: Global-Local Aligned Video Captioning with Vision Expert Integration.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2509.11360"],"source":"https://dblp.org/rec/journals/corr/abs-2509-11360","documentPage":"https://doi.org/10.48550/ARXIV.2509.11360","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2509.11360","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-11360","documentUrl":"https://doi.org/10.48550/ARXIV.2509.11360","arxivId":"2509.11360","arxivUrl":"https://arxiv.org/abs/2509.11360"},{"key":"journals/corr/abs-2509-12867","title":"Tool-R1: Sample-Efficient Reinforcement Learning for Agentic Tool Use.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2509.12867"],"source":"https://dblp.org/rec/journals/corr/abs-2509-12867","documentPage":"https://doi.org/10.48550/ARXIV.2509.12867","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2509.12867","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2509-12867","documentUrl":"https://doi.org/10.48550/ARXIV.2509.12867","arxivId":"2509.12867","arxivUrl":"https://arxiv.org/abs/2509.12867"},{"key":"journals/corr/abs-2510-10152","title":"Color3D: Controllable and Consistent 3D Colorization with Personalized Colorizer.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2510.10152"],"source":"https://dblp.org/rec/journals/corr/abs-2510-10152","documentPage":"https://doi.org/10.48550/ARXIV.2510.10152","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2510.10152","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-10152","documentUrl":"https://doi.org/10.48550/ARXIV.2510.10152","arxivId":"2510.10152","arxivUrl":"https://arxiv.org/abs/2510.10152"},{"key":"journals/corr/abs-2510-21447","title":"PhysWorld: From Real Videos to World Models of Deformable Objects via Physics-Aware Demonstration Synthesis.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2510.21447"],"source":"https://dblp.org/rec/journals/corr/abs-2510-21447","documentPage":"https://doi.org/10.48550/ARXIV.2510.21447","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2510.21447","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2510-21447","documentUrl":"https://doi.org/10.48550/ARXIV.2510.21447","arxivId":"2510.21447","arxivUrl":"https://arxiv.org/abs/2510.21447"},{"key":"journals/corr/abs-2511-00609","title":"PreferThinker: Reasoning-based Personalized Image Preference Assessment.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2511.00609"],"source":"https://dblp.org/rec/journals/corr/abs-2511-00609","documentPage":"https://doi.org/10.48550/ARXIV.2511.00609","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2511.00609","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2511-00609","documentUrl":"https://doi.org/10.48550/ARXIV.2511.00609","arxivId":"2511.00609","arxivUrl":"https://arxiv.org/abs/2511.00609"},{"key":"journals/corr/abs-2511-08032","title":"Perceptual Quality Assessment of 3D Gaussian Splatting: A Subjective Dataset and Prediction Metric.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2511.08032"],"source":"https://dblp.org/rec/journals/corr/abs-2511-08032","documentPage":"https://doi.org/10.48550/ARXIV.2511.08032","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2511.08032","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2511-08032","documentUrl":"https://doi.org/10.48550/ARXIV.2511.08032","arxivId":"2511.08032","arxivUrl":"https://arxiv.org/abs/2511.08032"},{"key":"journals/corr/abs-2511-10953","title":"Language-Guided Graph Representation Learning for Video Summarization.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2511.10953"],"source":"https://dblp.org/rec/journals/corr/abs-2511-10953","documentPage":"https://doi.org/10.48550/ARXIV.2511.10953","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2511.10953","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2511-10953","documentUrl":"https://doi.org/10.48550/ARXIV.2511.10953","arxivId":"2511.10953","arxivUrl":"https://arxiv.org/abs/2511.10953"},{"key":"journals/corr/abs-2511-20562","title":"PhysChoreo: Physics-Controllable Video Generation with Part-Aware Semantic Grounding.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2511.20562"],"source":"https://dblp.org/rec/journals/corr/abs-2511-20562","documentPage":"https://doi.org/10.48550/ARXIV.2511.20562","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2511.20562","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2511-20562","documentUrl":"https://doi.org/10.48550/ARXIV.2511.20562","arxivId":"2511.20562","arxivUrl":"https://arxiv.org/abs/2511.20562"},{"key":"journals/corr/abs-2512-00995","title":"S2AM3D: Scale-controllable Part Segmentation of 3D Point Cloud.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2512.00995"],"source":"https://dblp.org/rec/journals/corr/abs-2512-00995","documentPage":"https://doi.org/10.48550/ARXIV.2512.00995","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2512.00995","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-00995","documentUrl":"https://doi.org/10.48550/ARXIV.2512.00995","arxivId":"2512.00995","arxivUrl":"https://arxiv.org/abs/2512.00995"},{"key":"journals/corr/abs-2512-06422","title":"A Perception CNN for Facial Expression Recognition.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2512.06422"],"source":"https://dblp.org/rec/journals/corr/abs-2512-06422","documentPage":"https://doi.org/10.48550/ARXIV.2512.06422","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2512.06422","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-06422","documentUrl":"https://doi.org/10.48550/ARXIV.2512.06422","arxivId":"2512.06422","arxivUrl":"https://arxiv.org/abs/2512.06422"},{"key":"journals/corr/abs-2512-12220","title":"ProImage-Bench: Rubric-Based Evaluation for Professional Image Generation.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2512.12220"],"source":"https://dblp.org/rec/journals/corr/abs-2512-12220","documentPage":"https://doi.org/10.48550/ARXIV.2512.12220","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2512.12220","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-12220","documentUrl":"https://doi.org/10.48550/ARXIV.2512.12220","arxivId":"2512.12220","arxivUrl":"https://arxiv.org/abs/2512.12220"},{"key":"journals/corr/abs-2512-17573","title":"RoomEditor++: A Parameter-Sharing Diffusion Architecture for High-Fidelity Furniture Synthesis.","year":2025,"yearOfEvent":null,"venue":"CoRR","types":["https://dblp.org/rdf/schema#Informal"],"dois":["https://doi.org/10.48550/ARXIV.2512.17573"],"source":"https://dblp.org/rec/journals/corr/abs-2512-17573","documentPage":"https://doi.org/10.48550/ARXIV.2512.17573","type":"Informal","doi":"https://doi.org/10.48550/ARXIV.2512.17573","yearOfPublication":2025,"sourceUrl":"https://dblp.org/rec/journals/corr/abs-2512-17573","documentUrl":"https://doi.org/10.48550/ARXIV.2512.17573","arxivId":"2512.17573","arxivUrl":"https://arxiv.org/abs/2512.17573"}],"excludedFormal":[],"excludedOther":[],"excludedHomonyms":[],"unassignedCandidates":[],"retrievedAt":"2026-10-19","querySource":"https://sparql.dblp.org/","method":"DBLP yearOfPublication=2025; Article + Inproceedings; excludes Informal/CoRR and explicit editorial/correction/erratum/preface; unique DBLP record keys within person.","labName":null,"labUrl":null,"labEvidence":"本人哈工大教师页明确称机器学习研究中心教师，但未给出命名Lab；研究中心归属不自动改写成实验室名。","labSourceUrl":"https://homepage.hit.edu.cn/wangmengzuo","affiliationZh":"哈尔滨工业大学","sourceWarning":false,"knownPreprintMinimum2025":null,"excludedMisattributed":[],"displayNotes":"身份已经个人或机构主页核对。2025 年正式记录 78 条（会议 42、期刊 36），所有作者位置均计入，不表示主导或贡献份额；预印本 50 条单列，不加总。","labDisplayNotes":"哈工大本人页写明其属于机器学习研究中心，但未给出实验室名称；研究中心不自动改作实验室。图中以「姓名及合作者」单列。"}],"teams":[{"id":"team-0","labName":null,"labUrl":null,"memberIndices":[0],"label":"Jon Barron 及合作者","sharedLab":false,"count2025":10,"conference2025":8,"journal2025":2,"knownMinimum2025":null,"sourceWarning":false,"preprint2025":4,"knownPreprintMinimum2025":null,"arxivIds":["2502.10647","2503.14445","2510.08279","2512.04076"],"paperKeys":["conf/cvpr/AlzayerHBHSV25","conf/cvpr/TrevithickPHVWA25","conf/cvpr/WuGPTZBH25","conf/eccv/AttalVMHBOS24","conf/eccv/SrinivasanGVBM24","conf/iccv/MaiHKVFXKBZ25","conf/iccv/SzymanowiczZSGBHMBH25","conf/nips/NiemeyerMROTTBT25","journals/pami/HedmanSMRBD25","journals/pami/VerbinHMZBS25"]},{"id":"team-1","labName":"3D AI Lab","labUrl":"http://www.3dunderstanding.org/","memberIndices":[1],"label":"3D AI Lab","sharedLab":false,"count2025":14,"conference2025":13,"journal2025":1,"knownMinimum2025":null,"sourceWarning":false,"preprint2025":13,"knownPreprintMinimum2025":null,"arxivIds":["2502.05118","2503.01425","2503.15996","2503.17044","2503.17400","2503.23315","2504.15049","2504.16843","2505.05591","2505.07396","2506.07209","2507.23715","2511.07142"],"paperKeys":["conf/cvpr/BokhovkinMTD25","conf/cvpr/ErkocG0NDW0Z25","conf/cvpr/GaoSLD25","conf/cvpr/Meng0ND25","conf/cvpr/ZhangLD25","conf/humanoids/TaouilZDK25","conf/iccv/AnejaSKTDN25","conf/iccv/BoudjoghraLD25","conf/iccv/LiELSRDN25","conf/iccv/LiuHND25","conf/iccv/PiersonLDO25","conf/iccv/YeshwanthRD25","conf/iclr/BoudjoghraDLCA025","journals/ral/TaouilAKDBTS25"]},{"id":"team-2","labName":"Intelligent Dexterous Embodied AI Lab (IDEAL)","labUrl":"https://ideal.cs.unc.edu/","memberIndices":[2],"label":"Intelligent Dexterous Embodied AI Lab (IDEAL)","sharedLab":false,"count2025":20,"conference2025":14,"journal2025":6,"knownMinimum2025":null,"sourceWarning":true,"preprint2025":20,"knownPreprintMinimum2025":null,"arxivIds":["2501.09783","2502.01719","2502.13443","2502.15679","2503.14526","2503.22122","2504.13059","2505.02152","2505.12744","2506.17667","2508.03526","2508.17380","2510.04860","2510.05213","2510.20809","2511.12485","2511.19315","2511.19433","2511.19900","2512.18007"],"paperKeys":["conf/cvpr/GeXJPTLDJZ25","conf/cvpr/LiangMWCSZTLD25","conf/cvpr/MuCCPLGLYZXLXDL25","conf/iccv/ChenGTLGDSL25","conf/iclr/0002XPZHPDTZ25","conf/iclr/XiaHQZWZCCDLWY25","conf/icml/LiFGZLXYTZ0DZ25","conf/icra/JacobsonXDXTZW25","conf/icra/TangPZZYLTDF25","conf/icra/ZhangWCWLMTDZ25","conf/iros/FangYZZBSD25","conf/iros/GuoXZZTDZ25","conf/iros/SongCTZXD25","conf/nips/TongWCJQHGXZXDR25","journals/csur/SunZXLCQXDLGWWCYRFHYLLL25","journals/pami/ChenDYLDTTG25","journals/pami/LuXDZYTY25","journals/ral/LiuXHSDZT25","journals/ral/YangZDBS25","journals/tvt/FangLDCLHS25"]},{"id":"team-3","labName":"AI4CE Lab","labUrl":"https://ai4ce.github.io/","memberIndices":[3],"label":"AI4CE Lab","sharedLab":false,"count2025":11,"conference2025":10,"journal2025":1,"knownMinimum2025":null,"sourceWarning":true,"preprint2025":null,"knownPreprintMinimum2025":null,"arxivIds":[],"paperKeys":["conf/cvpr/0003LJSYZAZF25","conf/iccv/ChenDZSZHYZSF25","conf/iccv/ChenZSYJF25","conf/iccv/HanJLWIYLWPFL25","conf/iccv/LiJCXTWFZMIFZ25","conf/iccv/LiTCZFL25","conf/iccv/YangJHWRF25","conf/icra/FangSHTWZHYFZ25","conf/icra/PanHCLF25","conf/iros/WangZDFF25","journals/ral/ChenCLLDWF25"]},{"id":"team-4","labName":null,"labUrl":null,"memberIndices":[4],"label":"Jun Gao 及合作者","sharedLab":false,"count2025":5,"conference2025":5,"journal2025":0,"knownMinimum2025":null,"sourceWarning":false,"preprint2025":8,"knownPreprintMinimum2025":null,"arxivIds":["2501.18590","2503.01774","2503.03751","2504.11451","2506.09042","2508.10934","2509.19296","2510.04290"],"paperKeys":["conf/cvpr/LiangGLMHL00VFW25","conf/cvpr/RenSHLLN00F025","conf/cvpr/Wu0TR0SFGL25","conf/iccv/LiuUXSFSG25","conf/iccv/LuRYSWGWCCFH25"]},{"id":"team-5","labName":"Autonomous Vision Group (AVG)","labUrl":"https://uni-tuebingen.de/en/fakultaeten/mathematisch-naturwissenschaftliche-fakultaet/fachbereiche/informatik/lehrstuehle/autonomous-vision/home/","memberIndices":[5],"label":"Autonomous Vision Group (AVG)","sharedLab":false,"count2025":23,"conference2025":21,"journal2025":2,"knownMinimum2025":null,"sourceWarning":false,"preprint2025":23,"knownPreprintMinimum2025":null,"arxivIds":["2501.14726","2502.04318","2502.05151","2503.11650","2503.20168","2503.21219","2503.24391","2504.08385","2504.14032","2504.17838","2505.02075","2506.04218","2506.09981","2506.19117","2507.23597","2508.13148","2509.00269","2509.26645","2510.08575","2511.06810","2511.07292","2512.10719","2512.20563"],"paperKeys":["conf/3dim/LiCHPGP25","conf/acl/FlickeAIPSCKHSS25","conf/cvpr/EspositoCRBPSRZ25","conf/cvpr/LuCZZHY0L25","conf/cvpr/Miao0BYZ0L0L25","conf/cvpr/WuXH0C25","conf/cvpr/XuPWBB0P25","conf/cvpr/YangSLS0L25","conf/eccv/BaurMG24","conf/eccv/ChenXETG24","conf/eccv/ChenXZZPGCC24","conf/eccv/ChittaDG24","conf/eccv/MiaoHBQLGL24","conf/eccv/SimaRCCZXBLGL24","conf/iccv/ChenCXGC25","conf/iccv/DongDSBG25","conf/iccv/HavrylovHZG25","conf/iccv/HuangCHGZ25","conf/iclr/MiyatoL0W25","conf/nips/YangCGCSJLGYC25","conf/siggraph/0001SSBLAPYNGLW25","journals/pami/FuZCLZGL25","journals/ral/HanselmannDCLG25"]},{"id":"team-6","labName":"Vision Group at INSAIT","labUrl":"https://vision.insait.ai/","memberIndices":[6],"label":"Vision Group at INSAIT","sharedLab":true,"count2025":8,"conference2025":5,"journal2025":3,"knownMinimum2025":null,"sourceWarning":false,"preprint2025":11,"knownPreprintMinimum2025":null,"arxivIds":["2501.11561","2502.12600","2503.17221","2505.16007","2505.23130","2507.20590","2509.17677","2510.06036","2510.13029","2512.00993","2512.23165"],"paperKeys":["conf/cvpr/YouCGX025","conf/eccv/YouLGYXD24","conf/iclr/TaoG0WC25","conf/iclr/YuGHL025","conf/iclr/ZhuGY0025","journals/pami/HuGYYLYLD25","journals/tip/YouGCLZDX25","journals/tog/LinYHYSRGD25"]},{"id":"team-7","labName":"Machine Learning Laboratory","labUrl":"https://ml.utexas.edu/","memberIndices":[7],"label":"Machine Learning Laboratory","sharedLab":true,"count2025":23,"conference2025":18,"journal2025":5,"knownMinimum2025":null,"sourceWarning":true,"preprint2025":15,"knownPreprintMinimum2025":null,"arxivIds":["2503.00605","2503.00807","2503.05283","2503.12834","2503.21751","2504.04753","2504.10414","2505.00702","2505.12734","2510.20385","2512.03453","2512.04248","2512.07821","2512.17781","2512.19049"],"paperKeys":["conf/3dim/HeRH25","conf/cvpr/ChenWC0YZYFLHL25","conf/cvpr/HadgiMSGHRMO25","conf/cvpr/JiangXXCJLS0B0G25","conf/cvpr/Xia0VHP25","conf/cvpr/YangCKCHC25","conf/eccv/HeYZDBH24","conf/eccv/LuKLLYHH24","conf/eccv/YanBCZHL24","conf/eccv/ZhaoSGDZYBDH24","conf/iccv/BaiH25","conf/iccv/JiangHP25","conf/iccv/JiangTWJZBZLSHP25","conf/iccv/LeeJKHYK25","conf/iccv/LuHBHZ25","conf/iccv/LuHH25","conf/iclr/0005DJXPH25","conf/nips/BaiFYWH25","journals/cgf/FangYMH25","journals/cgf/HeYDLGH25","journals/cgf/LuLHHJLH25","journals/pami/ChiCHR25","journals/tog/YangYNHGH25"]},{"id":"team-8","labName":"Computer Science and Artificial Intelligence Laboratory (CSAIL)","labUrl":"https://www.csail.mit.edu/","memberIndices":[8],"label":"Computer Science and Artificial Intelligence Laboratory (CSAIL)","sharedLab":true,"count2025":7,"conference2025":7,"journal2025":0,"knownMinimum2025":null,"sourceWarning":false,"preprint2025":9,"knownPreprintMinimum2025":null,"arxivIds":["2503.00370","2506.02095","2507.07995","2507.12821","2507.13338","2508.11697","2508.12524","2510.02425","2510.08492"],"paperKeys":["conf/cvpr/TamirAIASFSID0F25","conf/iccv/BahngCDI25","conf/iclr/DuggalI0F25","conf/iclr/SundaramCTBI25","conf/icml/Rodriguez-Munoz25","conf/iros/PfaffFBIT25","conf/nips/DuggalBFTI25"]},{"id":"team-9","labName":"Artificial Intelligence & Visual Computing Laboratory (AIVC)","labUrl":"https://www.math.ucla.edu/aivc","memberIndices":[9],"label":"Artificial Intelligence & Visual Computing Laboratory (AIVC)","sharedLab":false,"count2025":20,"conference2025":16,"journal2025":4,"knownMinimum2025":null,"sourceWarning":false,"preprint2025":18,"knownPreprintMinimum2025":null,"arxivIds":["2501.13975","2501.16550","2502.03449","2502.03639","2503.00364","2503.05020","2503.05046","2504.01204","2504.12908","2505.12539","2506.06494","2507.09435","2508.11722","2509.15953","2511.13191","2512.01629","2512.12984","2512.14133"],"paperKeys":["conf/3dim/LiLJXGWYJ25","conf/cvpr/Feng0BS0W0J025","conf/cvpr/FengFSJ0ZSW0J025","conf/cvpr/LiMLCJ0X25","conf/cvpr/ShenS0J025","conf/cvpr/XieZJJ25","conf/icassp/GuoXHXJTJ025","conf/iclr/BansalLXZYBJSCG25","conf/iclr/CaoGWKHKJT025","conf/icra/DuYMJZYMCHJ25","conf/iros/MaDYJZXCYHJ25","conf/iros/YuDZCJH25","conf/nips/ChenCGKJRTK25","conf/nips/LiDYLZLJZH25","conf/siggraph/LanSL0J025","conf/siggraph/ShenS0JAZ025","journals/pacmcgit/LiuWJZ25","journals/tog/LanLYXSWJY25","journals/tog/LiYDJXCYJ25","journals/tog/LuLLWIJWY25"]},{"id":"team-10","labName":"Intelligent Medical Vision & Robotics Laboratory","labUrl":"https://yuemingjin.github.io/","memberIndices":[10],"label":"Intelligent Medical Vision & Robotics Laboratory","sharedLab":false,"count2025":16,"conference2025":9,"journal2025":7,"knownMinimum2025":null,"sourceWarning":false,"preprint2025":22,"knownPreprintMinimum2025":null,"arxivIds":["2503.04082","2503.10265","2503.18064","2503.18968","2503.20808","2504.09700","2505.08581","2505.21387","2506.02555","2506.02692","2506.15279","2506.23759","2507.18944","2508.08764","2509.16022","2509.17429","2509.21761","2510.18313","2510.22973","2511.16618","2512.14026","2512.23162"],"paperKeys":["conf/aaai/ZhuXJNAPLW25","conf/acl/WuZLXJ25","conf/acl/WuZQCXMJG25","conf/eccv/QiZWYJL24","conf/iccv/QinWSLZWHJ25","conf/iccv/YangWJWLJLZH25","conf/icml/Yang0WJL0Z0J25","conf/mm/NiuXW0JL25","conf/nips/ZengYMWJJ25","journals/mia/AliEJLGZZDCXWYZSLPFMBB25","journals/pami/WuZXJ25","journals/tbe/XuWYSJM25","journals/tmi/DuCZLIGJCH25","journals/tmi/PeiGZLJH25","journals/tmi/PeiZQWJH25","journals/tmi/ZhangPXJH25"]},{"id":"team-11","labName":"GraphViX Group (Graphics, Vision and X)","labUrl":"https://enigma-li.github.io/","memberIndices":[11],"label":"GraphViX Group (Graphics, Vision and X)","sharedLab":false,"count2025":11,"conference2025":8,"journal2025":3,"knownMinimum2025":null,"sourceWarning":false,"preprint2025":6,"knownPreprintMinimum2025":null,"arxivIds":["2503.16068","2504.19189","2506.16556","2508.10201","2511.18991","2512.13392"],"paperKeys":["conf/cvpr/BhuniaLB25","conf/cvpr/DanierALBA25","conf/cvpr/JiZWL25","conf/cvpr/WalkerERVOLA25","conf/cvpr/WeiF00Z025","conf/iccv/WangCL25","conf/iccv/WangLV25","conf/nips/BhuniaLB25","journals/mia/DouWLWYZSC25","journals/tmi/LiuFLWLSC25","journals/tog/ZhongGXWL25"]},{"id":"team-12","labName":"Deep Machine Vision (DMV)","labUrl":"https://web.engr.oregonstate.edu/~lif/#research","memberIndices":[12],"label":"Deep Machine Vision (DMV)","sharedLab":false,"count2025":4,"conference2025":4,"journal2025":0,"knownMinimum2025":null,"sourceWarning":false,"preprint2025":4,"knownPreprintMinimum2025":null,"arxivIds":["2503.13891","2504.05698","2506.06517","2512.10267"],"paperKeys":["conf/aaai/HopkinsWKLH25","conf/iccv/ChenTZBLHLX25","conf/iclr/KhademiL25","conf/nips/YangULLL25"]},{"id":"team-13","labName":"Simulation Intelligence Group (SIG)","labUrl":"https://www.cs.cmu.edu/~minchenl/#sec_group","memberIndices":[13],"label":"Simulation Intelligence Group (SIG)","sharedLab":false,"count2025":3,"conference2025":0,"journal2025":3,"knownMinimum2025":null,"sourceWarning":false,"preprint2025":6,"knownPreprintMinimum2025":null,"arxivIds":["2503.00868","2505.12539","2506.18867","2510.23880","2511.21978","2512.12151"],"paperKeys":["journals/tog/HuangLLKL25","journals/tog/LiuWL25","journals/tog/LuoCLCL25"]},{"id":"team-14","labName":"MAI Lab","labUrl":"http://mai-lab-2026.com/","memberIndices":[14],"label":"MAI Lab","sharedLab":false,"count2025":3,"conference2025":3,"journal2025":0,"knownMinimum2025":null,"sourceWarning":false,"preprint2025":3,"knownPreprintMinimum2025":null,"arxivIds":["2506.01430","2507.13353","2508.00873"],"paperKeys":["conf/iccv/LiXWZW25","conf/iclr/Xiao0ZM025","conf/nips/XieLLWYZ25"]},{"id":"team-15","labName":null,"labUrl":null,"memberIndices":[15],"label":"Ruoshi Liu 及合作者","sharedLab":false,"count2025":5,"conference2025":4,"journal2025":1,"knownMinimum2025":null,"sourceWarning":false,"preprint2025":2,"knownPreprintMinimum2025":null,"arxivIds":["2508.00795","2511.20544"],"paperKeys":["conf/eccv/CanberkBOLV24","conf/eccv/HoorickWOSLTDZV24","conf/eccv/SudhakarLHVZ24","conf/icra/LiuHHSV25","journals/iotj/LiuYHYGLYYZWRLLZ25"]},{"id":"team-16","labName":"Computer Vision Lab","labUrl":"https://www.cs.unc.edu/~liuxm/","memberIndices":[16],"label":"Computer Vision Lab","sharedLab":false,"count2025":17,"conference2025":15,"journal2025":2,"knownMinimum2025":null,"sourceWarning":false,"preprint2025":17,"knownPreprintMinimum2025":null,"arxivIds":["2503.20188","2503.21886","2504.04708","2504.09086","2504.10676","2505.04616","2505.13327","2505.18132","2505.24247","2506.22843","2508.00053","2508.05038","2508.11185","2508.21222","2511.16642","2511.17674","2511.18104"],"paperKeys":["conf/cvpr/GuoSZLL25","conf/cvpr/HuangLK25","conf/cvpr/KimYSLL25","conf/cvpr/Long00M25","conf/eccv/HouSZZHYL24","conf/eccv/SuKLJL24","conf/eccv/ZhuGKL24","conf/eccv/ZhuL24","conf/icb/NguyenFSNLLREDTVMFOGWLZ25","conf/iccv/AsnaniCLA25","conf/iccv/KumarGZHRL25","conf/iccv/MaLLSGMZZCHGDLWGCEELLGL25","conf/iccv/ZhuSKJL25","conf/nips/YeFHLLYL25","conf/wacv/YaoL00W0025","journals/ijcv/GuoLML25","journals/inffus/DeAndresTameTMVKRLGMFOZ25"]},{"id":"team-17","labName":"MMLab@NTU","labUrl":"https://www.mmlab-ntu.com/","memberIndices":[17,19],"label":"MMLab@NTU","sharedLab":true,"count2025":105,"conference2025":84,"journal2025":21,"knownMinimum2025":null,"sourceWarning":true,"preprint2025":null,"knownPreprintMinimum2025":15,"arxivIds":["2502.14316","2503.08434","2503.09419","2503.16153","2504.12369","2506.24113","2507.15728","2508.10893","2508.19188","2509.21263","2510.21432","2512.03040","2512.12425","2512.16615","2512.19539"],"paperKeys":["conf/3dim/RPET25","conf/accv/HuangCWL24","conf/acl/DingJ0JGWZW000T25","conf/acl/MiyaiYZMYILLLA25","conf/acl/TianZ0025","conf/acl/ZhangTH0025","conf/cvpr/0001HW0Z0L025","conf/cvpr/0001X0P25","conf/cvpr/0009KSP0025","conf/cvpr/0009TDCHL0XWSPL25","conf/cvpr/ChenLZ0P25","conf/cvpr/ChengMZCPZWF00P25","conf/cvpr/DongLSYHRL25","conf/cvpr/GuanWXYSHLCLFD025","conf/cvpr/HeW0P025","conf/cvpr/HongGKYNLM25","conf/cvpr/HuangWLW25","conf/cvpr/JiangXLZRGLCY025","conf/cvpr/KumbongLLLLLFRR25","conf/cvpr/LuoZLPL25","conf/cvpr/PangLC0Z025","conf/cvpr/Xie0H025","conf/cvpr/YangLGDZZWZXWOL25","conf/eccv/BahmaniLYSRLLPTWTL24","conf/eccv/ChenWWPJL24","conf/eccv/GuanXZWHZLFDLWZL24","conf/eccv/HuHL24","conf/eccv/JiangZLSYLL24","conf/eccv/LanHYZMDPL24","conf/eccv/LiuDZLZZYWHLCL24","conf/eccv/LiuWHSYZCLL24","conf/eccv/MaYHGJPPGBKBFLLENN24","conf/eccv/TangCCWZL24","conf/eccv/WuSJHL24","conf/eccv/XieZZLZHYL24","conf/eccv/XuKSZPCLL24","conf/eccv/YangDLLWTJKZZL24","conf/eccv/YangLY24","conf/eccv/YinCWWWMXYSYLY24","conf/eccv/ZhangJGHCHZGYHL24","conf/eccv/ZhangWWWLL24","conf/iccv/CaoSWL25","conf/iccv/LiuHCWHSCLL25","conf/iccv/LuLDZDLCYZWL25","conf/iccv/LvPSCZLW25","conf/iccv/LvSPCWQL25","conf/iccv/OuyangXYZYYSP25","conf/iccv/QiuZWCYWZL25","conf/iccv/RenZXPLWZL25","conf/iccv/WangLLWDY25","conf/iccv/WeiZCP25","conf/iccv/XieKDSZCLP25","conf/iccv/YangLCP25","conf/iccv/ZhangSLL25","conf/iccv/ZhangTHPGLHYZLCY25","conf/iccv/ZhangWTLWL25","conf/icip/ChenHTL25","conf/iclr/00030HH0L25","conf/iclr/BianKXP0025","conf/iclr/CaoP0W025","conf/iclr/LanZLH00PL25","conf/iclr/LiuD0HLR25","conf/iclr/LvSSY00W25","conf/iclr/XiaoO000SP25","conf/icml/WuL025","conf/mm/LiHSLLMGL025","conf/naacl/ZhangLZPCHLZYLL25","conf/nips/CaoCPL25","conf/nips/GaoLLLGYXWSLS25","conf/nips/LiDHLLLPKLL25","conf/nips/LiangRMTLGFOLGH25","conf/nips/LiuHJZDZHHCQOZL25","conf/nips/TanYWHGLL25","conf/nips/WangYHYZWLP25","conf/nips/WuYPXLLW25","conf/nips/XiaoLZOYZP25","conf/nips/ZhangZCWLPLL25","conf/nips/ZuoDKYJZSPLG25","conf/siggraph/GuYLLDS0L000025","conf/siggraph/Yang00WW0L25","conf/siggrapha/ChenLCP25","conf/siggrapha/FortesWZP25","conf/siggrapha/HeLLH0OL25","conf/wacv/Kong0CZPC025","journals/ijcv/HuHHPMXYL25","journals/ijcv/ShaoWL25","journals/ijcv/ShaoWNL25","journals/ijcv/TangWZCHHLLZW25","journals/ijcv/WangCMZHWYHYYGWSJCLDLQL25","journals/ijcv/XieLLLOL25","journals/ijcv/ZhangSZHYWSQSL25","journals/ijcv/ZhouCYZL25","journals/pami/CaoHWPL25","journals/pami/KongXRZPCOL25","journals/pami/LiLCLLL25","journals/pami/LiZCWPCYLL25","journals/pami/XieKZRPCL25","journals/pami/ZhangZL25","journals/pami/ZhouZWNYZL25","journals/pr/ZhangWYSL25","journals/tmlr/0080ZGZ00ZZL0L25","journals/tmlr/Ma0CJ0LC025","journals/tmlr/MiyaiYZMLYIJ0L025","journals/tmlr/ZhangWLLMLL25","journals/tmlr/ZhangZLZYZWTLL25"]},{"id":"team-18","labName":"Visual Intelligence & Social Multimedia Analytics (VIStA) Research Group","labUrl":"https://www.cs.rochester.edu/u/jluo/#People","memberIndices":[18],"label":"Visual Intelligence & Social Multimedia Analytics (VIStA) Research Group","sharedLab":false,"count2025":47,"conference2025":34,"journal2025":13,"knownMinimum2025":null,"sourceWarning":false,"preprint2025":50,"knownPreprintMinimum2025":null,"arxivIds":["2501.09019","2501.11241","2501.16329","2502.11767","2502.12073","2502.13127","2502.19411","2503.08677","2503.08689","2503.12605","2503.23377","2503.23715","2504.03151","2504.05541","2504.08591","2504.10157","2505.01490","2505.04620","2505.19415","2505.20292","2505.22645","2506.01327","2506.05332","2506.18999","2507.09961","2507.12851","2507.19929","2508.05006","2508.05008","2508.05205","2508.08179","2509.00357","2509.02172","2509.11752","2509.11866","2509.15216","2510.02750","2510.05034","2510.23925","2511.01775","2511.08521","2511.19261","2511.21087","2511.21120","2512.03247","2512.03804","2512.06921","2512.09907","2512.19512","2512.22029"],"paperKeys":["conf/3dim/LiuSZTHTLX25","conf/aaai/ChenL0QY0025","conf/aaai/Hua0X025","conf/acl/XiaMXW0ALBCDKY025","conf/aied/ZhouLSLSLDB25","conf/bigdataconf/ChatterjeeTNKHA25","conf/bigdataconf/ZhengL025","conf/coling/HuangPWL025","conf/cvpr/0016LLL00HL25","conf/cvpr/HuaLZSKZ00L025","conf/cvpr/YuanHHGSC0025","conf/eccv/HuaSKJZCCL24","conf/emnlp/LinWXHWHL25","conf/emnlp/YangLZSLCTQYLM25","conf/fat/Lyu0KK25","conf/iccv/ChenLQYZLM25","conf/iccv/LinLXL25","conf/iccv/WangHLYLZWLT25","conf/iccv/YuZZL25","conf/iccv/ZhouAL25","conf/icml/000100L0LWWZMSZ25","conf/icpr/HaoFLL24","conf/icpr/ZhangYLJYCL24","conf/mm/0018LHZW00C25","conf/mm/Pan0GZH025","conf/mm/ZhaoWL0Z00X25","conf/nips/AnWGLS25","conf/nips/HuaZSTHAXL25","conf/nips/LinWSWLSYCLLB25","conf/nips/LuoZLYLFHJCLJ25","conf/nips/SunHWLDRRT25","conf/nips/YuanHDYHLMLY25","conf/nips/ZhengYYZLL25","conf/www/QiL025","journals/ipm/ZhangJZZL25","journals/npjdm/LiuLYHLTBSYWZC25","journals/pami/LiuWHYBSCZLZC25","journals/pami/WangWYL25","journals/pami/YuanHSXZLCYL25","journals/pr/FengCSWJLLJL25","journals/spic/QiSHCSDLL25","journals/tcsv/BaoDHLLLGL25","journals/tcsv/LiWQDWCLLL25","journals/tist/LyuHZYMPYWL25","journals/tmlr/XiongLHWW0YSWHT25","journals/tmlr/ZangDLWLYLLL25","journals/tnn/HuaLDXL25"]},{"id":"team-20","labName":"SketchX Lab","labUrl":null,"memberIndices":[20],"label":"SketchX Lab","sharedLab":false,"count2025":17,"conference2025":13,"journal2025":4,"knownMinimum2025":null,"sourceWarning":false,"preprint2025":13,"knownPreprintMinimum2025":null,"arxivIds":["2501.04144","2501.16022","2503.14129","2505.21179","2505.23763","2507.07994","2507.20548","2508.07149","2508.20665","2509.13756","2509.21318","2510.25319","2511.20426"],"paperKeys":["conf/aaai/Chen0Q0P0S25","conf/cvpr/BandyopadhyayS25","conf/cvpr/ChenBZS25","conf/cvpr/KoleyDSCBS25","conf/cvpr/QuMZSDS25","conf/cvpr/SainMCKBS25","conf/eccv/BandyopadhyayCSKXBS24","conf/eccv/NgZSX24","conf/eccv/SainCKBS24","conf/iccv/MaityBKCSS25","conf/nips/ChenBZS25","conf/nips/ZuoWQS25","conf/vcip/ZhangYPZS25","journals/pami/GuoDSLDSM25","journals/pr/LiLCSLMXS25","journals/tcsv/YangCDSM25","journals/tip/TongCLWLHSM25"]},{"id":"team-21","labName":null,"labUrl":null,"memberIndices":[21],"label":"Qianqian Wang 及合作者","sharedLab":false,"count2025":6,"conference2025":6,"journal2025":0,"knownMinimum2025":null,"sourceWarning":false,"preprint2025":4,"knownPreprintMinimum2025":null,"arxivIds":["2501.12387","2503.22268","2504.13152","2512.10950"],"paperKeys":["conf/cvpr/HuangZXKZKW25","conf/cvpr/Li0C0JYKHS25","conf/cvpr/Qian0TKWX25","conf/cvpr/WangZHEK25","conf/iccv/FengZWYYBDK25","conf/iccv/WangYGZALK25"]},{"id":"team-22","labName":"Physical Superintelligence Lab","labUrl":"https://psi-lab.ai","memberIndices":[22],"label":"Physical Superintelligence Lab","sharedLab":false,"count2025":15,"conference2025":14,"journal2025":1,"knownMinimum2025":null,"sourceWarning":false,"preprint2025":20,"knownPreprintMinimum2025":null,"arxivIds":["2501.00601","2501.00602","2501.16411","2502.04329","2503.07739","2504.18904","2505.09698","2506.09366","2506.19201","2507.07978","2508.08254","2509.22970","2510.05070","2510.08807","2511.01163","2511.07416","2511.17441","2512.10947","2512.11797","2512.16881"],"paperKeys":["conf/cvpr/ShaoYZ0SGWPL25","conf/eccv/YangLLDGKWTW24","conf/humanoids/MaoZSHSYZGMGW25","conf/iccv/HanJLWIYLWPFL25","conf/iccv/LuRYSWGWCCFH25","conf/iclr/0002HI00LYSIKX025","conf/iclr/0004LD0G25","conf/iclr/ChenYHLEILGF0SW25","conf/iclr/ChoICS0WLYK0025","conf/iclr/ChowMLSG025","conf/iclr/LuYXLI0025","conf/icra/MaoLICWYXXPW25","conf/icra/YePZGHCWR25","conf/nips/LiFCLYFPYWWZPW25","journals/tmlr/SmithHSSGW25"]},{"id":"team-23","labName":"Vision, Ask, Answer and Act (V3A) Laboratory","labUrl":null,"memberIndices":[23],"label":"Vision, Ask, Answer and Act (V3A) Laboratory","sharedLab":false,"count2025":30,"conference2025":24,"journal2025":6,"knownMinimum2025":null,"sourceWarning":false,"preprint2025":28,"knownPreprintMinimum2025":null,"arxivIds":["2501.17403","2502.02024","2502.04400","2502.09152","2502.13345","2502.19024","2503.02358","2503.06847","2503.10069","2503.17109","2503.19308","2503.24065","2504.11774","2504.18579","2504.21044","2505.07500","2505.12443","2506.01031","2508.10315","2509.12129","2509.16673","2509.24910","2510.13080","2511.00933","2511.12201","2512.10322","2512.19021","2512.24851"],"paperKeys":["conf/aaai/GaiW0WZ025","conf/accv/ChenXWCATCW24","conf/cvpr/TangYGZ0G025","conf/cvpr/TangZQYG0LR0025","conf/dicta/ChenWX25","conf/dicta/ChenZW25","conf/dicta/WangCTKYXW25","conf/dicta/WangCXW25","conf/eccv/QiaoLLLW24","conf/eccv/ShiQWLD24","conf/eccv/ZhouHWWW24","conf/iccv/ZhangQWYWWL25","conf/iccv/ZhouHWZBW25","conf/iclr/0010Z025","conf/iclr/HongQWLW25","conf/icra/LiZHSLQW25","conf/icra/QiaoLWWLZTW25","conf/icra/ZhuQZHWL25","conf/ijcai/LeiG0Z025","conf/iros/ShiLLXDQW25","conf/mm/LiuZQ0025","conf/nips/QiaoHLAZXWW25","conf/wacv/LiuZQZLGWHWL25","conf/wasa/ZhuangYQTGXW25","journals/csr/ZhangCYGCCWXX25","journals/cvm/TianYW25","journals/ijautcomp/Tan0H0LZ25","journals/pami/LiCQZWSHY25","journals/tjs/LiangYDWG25","journals/tmm/WenTWWW25"]},{"id":"team-24","labName":"Machine Intelligence","labUrl":null,"memberIndices":[24],"label":"Machine Intelligence","sharedLab":true,"count2025":7,"conference2025":7,"journal2025":0,"knownMinimum2025":null,"sourceWarning":true,"preprint2025":null,"knownPreprintMinimum2025":null,"arxivIds":[],"paperKeys":["conf/cvpr/0001ZW025","conf/cvpr/He0W025","conf/cvpr/KayeJWRV25","conf/cvpr/ZhangLZW025","conf/eccv/SunLZLWW24","conf/nips/ZhaoWW25","conf/siggraph/DengZ0W025"]},{"id":"team-25","labName":"Vision · Learning · Assured Autonomy (VLAA) Lab","labUrl":"https://ucsc-vlaa.github.io/","memberIndices":[25],"label":"Vision · Learning · Assured Autonomy (VLAA) Lab","sharedLab":false,"count2025":24,"conference2025":17,"journal2025":7,"knownMinimum2025":null,"sourceWarning":false,"preprint2025":23,"knownPreprintMinimum2025":null,"arxivIds":["2501.09446","2501.16085","2502.03738","2502.05206","2503.20271","2504.01903","2504.11468","2504.13143","2505.04601","2505.14835","2505.16964","2506.02126","2507.21033","2508.21376","2509.01644","2510.00181","2510.04860","2510.10880","2510.18212","2511.02779","2511.07403","2511.20573","2511.22815"],"paperKeys":["conf/cvpr/LiWLWZX25","conf/cvpr/Wang0RWM0ZYX25","conf/cvpr/WangYYRWW0ZYX25","conf/cvpr/Yang0LKPRZLXZ25","conf/cvpr/YangWBBKCX25","conf/eccv/TuCWZZHZYX24","conf/eccv/XiaoZLLMYZYZX24","conf/eccv/XieXYM24","conf/emnlp/TuFCLTX25","conf/iccv/LiLTX25","conf/iccv/ShuZJX25","conf/iccv/WangSXLZ25","conf/iclr/HuiYZSWWXZ25","conf/iclr/RenLTWSZMYWWYX25","conf/iclr/XieZGWLZL00XZ25","conf/icml/0047Y0ZYX25","conf/icml/LiTH0ZXRM0ZZX25","journals/ftsec/MaGWWWSDXCZHLWZZBLWQZHL25","journals/tmlr/ChenTWLTDZX25","journals/tmlr/MeiCYX25","journals/tmlr/RenZ0LYX25","journals/tmlr/WangTMZ0X25","journals/tmlr/YangHBLQZBWYSTSRLWZCWZZ25","journals/tmlr/YangZX25"]},{"id":"team-26","labName":"Visual Computing Lab","labUrl":null,"memberIndices":[26],"label":"Visual Computing Lab","sharedLab":false,"count2025":30,"conference2025":15,"journal2025":15,"knownMinimum2025":null,"sourceWarning":true,"preprint2025":22,"knownPreprintMinimum2025":null,"arxivIds":["2501.04150","2502.04364","2503.06947","2503.23768","2506.00915","2506.09368","2506.23440","2507.11321","2507.20890","2507.22522","2508.08179","2508.14604","2509.01028","2509.18538","2509.21749","2509.24133","2510.12287","2510.25345","2511.20651","2512.01373","2512.01380","2512.16494"],"paperKeys":["conf/cvpr/XieLCYCXFSW025","conf/eccv/LuanGXSDPZLCYW24","conf/eccv/WangXMY24","conf/eccv/WuWYGLYW24","conf/eccv/ZhaiLLLWYDYLW24","conf/eccv/ZhuFCYQH24","conf/iccv/BhosaleWZTBXSYDG25","conf/iccv/LiWYLMYL25","conf/iccv/WangLLDWLYL25","conf/iccv/ZhaiLPDCYD25","conf/iccv/ZhuDRXKY25","conf/icmcs/AnandYBY25","conf/mm/ZhaoWL0Z00X25","conf/nips/ZhuLFWQY25","conf/www/XiMCDGS025","journals/air/ZhuZZDDXY25","journals/comsis/ZhangCLLCY25","journals/ijcv/LiLLZLY25","journals/mva/FengLCGLYQ25","journals/pami/LuanZMLCXY25","journals/tce/TangZLY25","journals/tifs/TuZGZYD25","journals/tip/FengLCQYYH25","journals/tip/LiaoYZLY25","journals/tip/LiuLZLY25","journals/tip/TuZGYD25","journals/tip/WenCSJYGYZ25","journals/titb/LaiLLLY25","journals/tmm/DingZYCXHY25","journals/tvcg/LiWTOY25"]},{"id":"team-27","labName":"Vision and Autonomy Intelligence Lab (VAIL)","labUrl":"https://vail-ucla.github.io/","memberIndices":[27],"label":"Vision and Autonomy Intelligence Lab (VAIL)","sharedLab":false,"count2025":20,"conference2025":19,"journal2025":1,"knownMinimum2025":null,"sourceWarning":false,"preprint2025":22,"knownPreprintMinimum2025":null,"arxivIds":["2501.02158","2501.06693","2501.09167","2502.03369","2503.04969","2504.20996","2505.00690","2506.08006","2506.09176","2506.09485","2506.13757","2506.23316","2507.22028","2508.04682","2508.04702","2508.04705","2509.03704","2510.01545","2510.15018","2512.10954","2512.14133","2512.24426"],"paperKeys":["conf/cvpr/WangDPLZ25","conf/cvpr/WuHZHZGLZ25","conf/cvpr/XieLPWZ25","conf/iccv/LengYYZ25","conf/iccv/MoNHILLTSSLZL25","conf/iccv/YangYHJPZC25","conf/iccv/ZhouXZZLZCLLBXHZM25","conf/iccv/ZhouZCHZM25","conf/iclr/LiuLWZ25","conf/iclr/WuHHWDLLZ25","conf/iclr/ZhangX00WZY25","conf/icml/CaiPZ25","conf/icml/LiFGZLXYTZ0DZ25","conf/icml/WangLLAZ025","conf/icra/PengLZ25","conf/iros/ZhaoXXXZM25","conf/nips/CaiPZ25","conf/nips/LiuPCZ25","conf/nips/ZhouCZZHZM25","journals/ral/LengYRZ25"]},{"id":"team-28","labName":"Generative Intelligence Lab","labUrl":"https://www.cs.cmu.edu/~generative-intelligence-lab/","memberIndices":[28],"label":"Generative Intelligence Lab","sharedLab":false,"count2025":14,"conference2025":13,"journal2025":1,"knownMinimum2025":null,"sourceWarning":false,"preprint2025":14,"knownPreprintMinimum2025":null,"arxivIds":["2501.01424","2501.06187","2502.01720","2504.02817","2505.05469","2507.18633","2508.15773","2508.21063","2510.02617","2510.14978","2511.01266","2511.10721","2511.21978","2512.10955"],"paperKeys":["conf/cvpr/ChenSMFLSAZ0T25","conf/cvpr/LiuKSZ25","conf/eccv/DengOWRZZA24","conf/eccv/KangZBPKPSZP24","conf/eccv/MahapatraMLCDWZCHX24","conf/iccv/DengLZSSBRZAZ25","conf/iccv/KumariYZMA25","conf/iccv/PunDLRLZ25","conf/iclr/Li0ZCLGXMZ025","conf/mm/PerezYZMTMSPKVW25","conf/nips/WangHEZZ25","conf/siggrapha/Lu00Z25","conf/siggrapha/ParmarPWONZCA25","journals/ijcv/GePZH25"]},{"id":"team-29","labName":"Language Agent Group","labUrl":"https://hit-scir-la.github.io/","memberIndices":[29],"label":"Language Agent Group","sharedLab":false,"count2025":33,"conference2025":22,"journal2025":11,"knownMinimum2025":null,"sourceWarning":false,"preprint2025":48,"knownPreprintMinimum2025":null,"arxivIds":["2501.06598","2502.03325","2502.12221","2502.17253","2503.06899","2503.09567","2503.17979","2504.03612","2504.09824","2505.11441","2505.13307","2505.14597","2505.15110","2505.15257","2505.15510","2505.18629","2505.20334","2505.24388","2506.04625","2506.11515","2506.15647","2506.23133","2506.23146","2506.23149","2507.01903","2507.05687","2507.09876","2507.23382","2508.00385","2508.02322","2508.11582","2508.16134","2509.10798","2509.21284","2509.24745","2509.26038","2510.08702","2510.08720","2510.09544","2510.09558","2510.14616","2510.14763","2510.15004","2510.21623","2511.09345","2512.01661","2512.01725","2512.20164"],"paperKeys":["conf/aaai/0001CZW0CL25","conf/aaai/ChengCZ0FCL025","conf/aaai/WangLYHLWCC25","conf/acl/XuWZZC25","conf/coling/LiGDFWXWCWXZ0ZZ25","conf/coling/ZhangWDZC25","conf/emnlp/ChenYMCLSLFHXLS25","conf/emnlp/NiuCWXYZWWC25","conf/emnlp/PengZCLCQC25","conf/emnlp/WangDZZC25","conf/emnlp/WangJLXXZC25","conf/emnlp/ZhangWXZC25","conf/emnlp/ZhangWXZC25a","conf/icassp/0001WCZHSLC25","conf/ijcai/WangLZC00LC025","conf/kdd/00060LHZC25","conf/mm/JiCCW0C25","conf/mm/ZhangLTC0C025","conf/naacl/MuHZFXQSLHSZC25","conf/naacl/ShiLLZLWLCW25","conf/nips/ChengCXWWFWWCCQ25","conf/nips/ZhaoGDWZHSZCQCL25","journals/chinaf/LiuWLNWC25","journals/chinaf/YangZWWZZMCWWQ25","journals/chinaf/YangZZWYCWWQ25","journals/fcsc/QinHCLCX25","journals/fcsc/ZhangWDZC25","journals/jair/LinMZWWWGZCBHL25","journals/mlc/LiDHFMWZSC25","journals/patterns/QinCZCLLLCY25","journals/tacl/XuJZC25","journals/tcsv/XuQCK25","journals/tois/LiuPZLCR25"]},{"id":"team-30","labName":"Inception3D Lab","labUrl":"http://www.inception3d.fun/","memberIndices":[30],"label":"Inception3D Lab","sharedLab":false,"count2025":10,"conference2025":10,"journal2025":0,"knownMinimum2025":null,"sourceWarning":false,"preprint2025":9,"knownPreprintMinimum2025":null,"arxivIds":["2503.21219","2503.24391","2504.14032","2506.23957","2507.14501","2507.20200","2509.26645","2510.06219","2511.06810"],"paperKeys":["conf/cvpr/ChenCCPX25","conf/cvpr/EspositoCRBPSRZ25","conf/cvpr/WuXH0C25","conf/cvpr/ZhangCWSYL025","conf/eccv/ChenXETG24","conf/iccv/ChenCXGC25","conf/iccv/HuangCHGZ25","conf/iccv/ZhangCXDSX25","conf/siggraph/0001GC0D25","conf/wacv/WeiXBCSX025"]},{"id":"team-31","labName":"Visual Intelligence Lab","labUrl":"https://ri.hkust.edu.hk/research/visual-intelligence","memberIndices":[31],"label":"Visual Intelligence Lab","sharedLab":false,"count2025":44,"conference2025":41,"journal2025":3,"knownMinimum2025":null,"sourceWarning":false,"preprint2025":39,"knownPreprintMinimum2025":null,"arxivIds":["2501.08332","2503.03464","2503.10270","2503.10522","2503.11731","2503.16948","2503.19906","2503.21172","2505.02094","2505.11818","2506.04213","2506.04216","2506.04590","2506.05207","2506.09373","2506.13846","2506.22800","2506.24123","2507.05601","2507.16869","2508.00782","2508.05580","2508.08134","2508.10858","2509.15221","2509.16630","2509.17042","2510.06231","2510.11072","2510.15742","2511.12304","2511.14719","2511.22847","2512.03046","2512.16924","2512.17532","2512.19583","2512.20615","2512.20618"],"paperKeys":["conf/3dim/ChengWSZXOCS25","conf/aaai/ChenMWYZTWMCL25","conf/aaai/FengMWQCC025","conf/aaai/MaHWWSQYC0SLC25","conf/cvm/ChenHHWZLX25","conf/cvpr/0001YZXSZCS25","conf/cvpr/Liu0WMCFSSC25","conf/cvpr/LiuCC0OZLSCL25","conf/cvpr/LiuWZWHPC25","conf/cvpr/LiuYOWCWLCS25","conf/cvpr/Tian0YPL0CXG25","conf/cvpr/WangOWWCCSW25","conf/cvpr/WangZ0TZLLY0C0Z25","conf/eccv/BaiSXOWYWWSC24","conf/eccv/ChenHLCCW24","conf/eccv/ChenXYQZYC24","conf/eccv/ChenYXCC24","conf/eccv/GuoHCXCWHZWCSW24","conf/eccv/HeXCCGXZWWSC24","conf/eccv/LiuKGCTP24","conf/eccv/LiuLGCLZLCQDW24","conf/eccv/QiTYDMCT24","conf/iccv/BaiOXWYCSC25","conf/iccv/ChenWZZLYC25","conf/iccv/ChenZHCDLCW25","conf/iccv/DuLCCMY25","conf/iccv/LiuCGZPCTKP25","conf/iccv/XingFHCXCC25","conf/iccv/YanMZCCZ25","conf/iccv/ZhouGCYCCQ25","conf/iclr/00070MTFCCL25","conf/icra/WenRXC25","conf/icra/ZhaoJLZYWC25","conf/iros/ZengDCLSGLXXCZCXZYL25","conf/mm/0001HX0025","conf/nips/ChenHCYL25","conf/siggraph/0003WZT00025","conf/siggrapha/XingQZ025","conf/vr/WangMCCLMC025","conf/wacv/MaCLXHQCC25","conf/wacv/RaoZLC25","journals/csur/WangCW25","journals/ijcv/WenRLSYLLC25","journals/trob/ZhaoJLYCY25"]},{"id":"team-32","labName":null,"labUrl":null,"memberIndices":[32],"label":"陈翔 及合作者","sharedLab":false,"count2025":12,"conference2025":9,"journal2025":3,"knownMinimum2025":null,"sourceWarning":false,"preprint2025":9,"knownPreprintMinimum2025":null,"arxivIds":["2504.12711","2505.19564","2509.06793","2509.11642","2509.12701","2509.21719","2510.17440","2511.06734","2512.09282"],"paperKeys":["conf/aaai/FanWYCGLY25","conf/aaai/LiuC0XL25","conf/cvpr/0082JJWLWYL0WTT25","conf/iccv/CiubotariuVZMTWSKYPDTCF25","conf/iccv/LiCDTP25","conf/ijcai/RenZCLL025","conf/mm/GuanYC0JJ25","conf/mm/JinYWCLC25","conf/nips/GuanCJJFSP25","journals/dsp/WuCCX25","journals/pami/ChenPDT25","journals/sivp/HuangZQWGC25"]},{"id":"team-33","labName":"EnVision-Research","labUrl":"http://envision-research.hkust-gz.edu.cn","memberIndices":[33],"label":"EnVision-Research","sharedLab":false,"count2025":39,"conference2025":33,"journal2025":6,"knownMinimum2025":null,"sourceWarning":true,"preprint2025":38,"knownPreprintMinimum2025":null,"arxivIds":["2501.03006","2502.06419","2503.01370","2503.02537","2503.06235","2503.10719","2503.14908","2503.20354","2504.17670","2505.06274","2505.10257","2505.17908","2505.21050","2505.21660","2506.02620","2507.04403","2507.19172","2507.22668","2509.15273","2509.20251","2509.22622","2509.24980","2509.26376","2509.26618","2510.09507","2510.13745","2510.13940","2510.14588","2511.08997","2511.13704","2511.15253","2511.16668","2511.23127","2512.01030","2512.09864","2512.14442","2512.16915","2512.21185"],"paperKeys":["conf/aaai/LuZWLDC25","conf/cvpr/0003X0R0LCZW25","conf/cvpr/ChenXGWYHWZZC25","conf/cvpr/Lin0CXYWXXZC25","conf/cvpr/Ma0000ZWFC0025","conf/cvpr/Wang0CWZZLC25","conf/eccv/LiLC24","conf/eccv/LinJCZLC24","conf/eccv/TangLXWHZCGCT24","conf/eccv/WangSGCLC24","conf/eccv/YangCCFLLC24","conf/emnlp/XuXCCZC25","conf/emnlp/ZhangXXZLC25","conf/iccv/FuWTNYXCZ25","conf/iccv/GeLSFHXC25","conf/iccv/HuaJCZ25","conf/iccv/LiWCLKCL25","conf/iccv/LuZTFGWWC25","conf/iccv/ShenWLGZTZWCLC25","conf/iccv/XuGLFXZZC25","conf/iccv/XuGQCYLZZZLC25","conf/iccv/YangGLCGSC25","conf/iclr/HeL0LLZZLC25","conf/iclr/HeLhSCQC25","conf/icml/LinJXCC25","conf/icra/XuLYCLC25","conf/mm/LinJXXLHC025","conf/nips/ChenZLJWC25","conf/nips/GuoXWLZZSC25","conf/nips/LuXZZZDTKC25","conf/nips/WangYHTLHWCW25","conf/pg/GeFSC25","conf/siggraph/WangMSL0000C25","journals/bioinformatics/0010SCCH25","journals/cgf/HeLWCXGWC25","journals/pami/LinJCLC25","journals/pami/WangLWYCHW25","journals/tim/WangLHCHW25","journals/tip/ZhangLLCW25"]},{"id":"team-34","labName":"计算机辅助设计与图形系统全国重点实验室（CAD&CG）","labUrl":null,"memberIndices":[34,77,109,118],"label":"计算机辅助设计与图形系统全国重点实验室（CAD&CG）","sharedLab":true,"count2025":112,"conference2025":88,"journal2025":24,"knownMinimum2025":null,"sourceWarning":false,"preprint2025":78,"knownPreprintMinimum2025":null,"arxivIds":["2501.05763","2501.07556","2501.08880","2501.09259","2502.01297","2502.05503","2502.05857","2502.12138","2502.17157","2502.18538","2502.20370","2503.03222","2503.06117","2503.06486","2503.08625","2503.14478","2503.14483","2503.15451","2503.16825","2503.18107","2503.18533","2503.18945","2503.19358","2503.21751","2503.24382","2504.05692","2504.07025","2504.07955","2504.08259","2504.09149","2504.13072","2504.19165","2505.20256","2505.21457","2506.03118","2506.05327","2506.05348","2506.14315","2506.19348","2507.08416","2507.11540","2507.12462","2507.13344","2507.13347","2507.15602","2508.01591","2508.04728","2508.07905","2508.08240","2508.08867","2508.09138","2508.13104","2508.14811","2509.05296","2509.12201","2509.19937","2509.23736","2509.23738","2510.01669","2510.02902","2510.03895","2510.03896","2510.05057","2510.07286","2510.10524","2510.11726","2510.15800","2510.24717","2510.25129","2511.12691","2511.14223","2511.17185","2511.17904","2512.00748","2512.01296","2512.07951","2512.20617","2512.22745"],"paperKeys":["conf/3dim/ChenLZ25","conf/aaai/ChenYWCHO00025","conf/aaai/YanLLCCLDYZS25","conf/aaai/YangZSAZBYC25","conf/chi/ZhangBP0I025","conf/cikm/GaoZPBZC25","conf/cvpr/0001LZXF0LSS25","conf/cvpr/Bao0YS0PC25","conf/cvpr/Guo00B025","conf/cvpr/GuoZPLYXWZB25","conf/cvpr/HuangYSY025","conf/cvpr/LiBTCF025","conf/cvpr/LinPCPSLBFZK25","conf/cvpr/SongJZLZ0Q25","conf/cvpr/WangYXSZCBPZ25","conf/cvpr/Wu0H025","conf/cvpr/Xia0VHP25","conf/cvpr/XieCXXJSPBZ25","conf/cvpr/Yan0LJGWZLB0P25","conf/cvpr/ZhaiLLPH025","conf/cvpr/ZhaiYLXHPXCWY0L25","conf/cvpr/ZhangWX000SW25","conf/cvpr/ZhouFPYZCXZ25","conf/cvpr/ZhuTCZGLYS25","conf/eccv/ChenPYLPLZ24","conf/eccv/ChenWYYCS24","conf/eccv/ChuSZS24","conf/eccv/GuoZPWSHZ24","conf/eccv/HuCFLYBZC24","conf/eccv/HuZLLPZFY24","conf/eccv/LiSHCBSWSBCZL24","conf/eccv/WangWZX24","conf/eccv/YanLZWSZLZP24","conf/iccv/CaoWFBZP25","conf/iccv/ChanLLLSZ25","conf/iccv/ChenWTMHOZBP25","conf/iccv/FangCLMDLZWZZDCL25","conf/iccv/GaoBLCS25","conf/iccv/GuoPSSHWDHKPZ25","conf/iccv/HeXXZP25","conf/iccv/JinPWXXYSBZ25","conf/iccv/LiuYJZCXFWLS25","conf/iccv/MaoSCZHBC25","conf/iccv/PanZZXJZ25","conf/iccv/ShenLCLHBCZ25","conf/iccv/SunYWXLWZBZP25","conf/iccv/TanHPGZSHSBZ25","conf/iccv/WangHBZBCZ25","conf/iccv/WangWGPQBZH25","conf/iccv/XiaoLPFPZFZPW25","conf/iccv/XiaoWXKMKZBSZ25","conf/iccv/YangYCMDCCB25","conf/iccv/YuHZYYHSZZP25","conf/iccv/ZengZHSDBC25","conf/iccv/ZhangGTXCLS25","conf/iccv/ZhangPXZZJZ25","conf/iccv/ZhuOSP25","conf/iccv/ZhuWZCZLCSPH25","conf/iclr/0015WZOCG0SS25","conf/iclr/BoMSB0MZ0S25","conf/iclr/CenPPSSB0H25","conf/iclr/ChenLJZRC0S25","conf/iclr/JiaoMJY0S25","conf/iclr/TangYWHB0025","conf/iclr/WangZPHGSB025","conf/iclr/XuGLFXZ0S25","conf/iclr/YangH0S00LO025","conf/iclr/ZhaoL0C000S25","conf/icml/00120S25","conf/icra/PanLFZBZ25","conf/icra/ZhaiZLPHCBZ25","conf/icxr/Chen0C024","conf/ijcai/JingLCXBGS25","conf/iros/ChenGPSZBC25","conf/iros/HuangPLZXZ25","conf/iros/NiSLZBZ25","conf/mir/Cui0DYBC25","conf/mm/DongYYL0BMC25","conf/mm/ZhanLHC0CDH025","conf/nips/LiXYLSWZHL25","conf/nips/ZhangBCZDBCZ25","conf/nips/ZhaoSLZZZCHS25","conf/nips/ZhongZDHZLWCS25","conf/siggraph/0006LB0025","conf/siggraph/GeXXKLHX0S25","conf/siggraph/LiX0SZ0H25","conf/siggrapha/ChenLDWLH0Y25","conf/siggrapha/PanLYZ025","journals/cg/ShenTuZXSCPZ25","journals/cmig/XuZXSSSWCW25","journals/cvm/DangDYYLMC25","journals/eaai/MingYWCFXZ25","journals/ijcv/LiuWZCHS25","journals/ijcv/LiuZCWFWLVS25","journals/ijcv/WangZCCZS25","journals/ijcv/WuLHSSCLGZ25","journals/mia/ZhengYCZAW25","journals/pami/BaoLYSBCZZ25","journals/pami/FuZCLZGL25","journals/pami/LiuHYDWLSJB25","journals/pami/WangLJWZS25","journals/pami/ZhuYWHZHZSQHO25","journals/ral/MingMDYFZK25","journals/tcsv/CuiYWZZHL25","journals/tcsv/PangZZWHZL25","journals/tcsv/RanLYHCBSC25","journals/tii/WangPYLZLTZ25","journals/tip/WangWYZ25","journals/tog/HuYLWDDZJBZP25","journals/tvcg/ChenLYWXZWLBZ25","journals/tvcg/XieCQYLCZWBZ25","journals/tvcg/ZhaiZZLHCBZ25"]},{"id":"team-35","labName":null,"labUrl":null,"memberIndices":[35],"label":"戴玉超 及合作者","sharedLab":false,"count2025":18,"conference2025":11,"journal2025":7,"knownMinimum2025":null,"sourceWarning":false,"preprint2025":10,"knownPreprintMinimum2025":null,"arxivIds":["2502.12975","2502.16488","2504.17732","2504.21302","2505.18129","2505.22499","2507.01652","2507.21960","2508.09525","2509.03872"],"paperKeys":["conf/aaai/DengSQZD25","conf/aaai/WangZHLD25","conf/apsipa/CaoHDH24","conf/apsipa/GaoLHD25","conf/apsipa/HeDHD25","conf/apsipa/HuangWLZHD24","conf/apsipa/LanHD25","conf/apsipa/Zhang0HD24","conf/iccv/LiuSDD25","conf/iccv/RenXZD25","conf/iccv/WanLDL25","journals/bigdatama/WangDMD25","journals/ijcv/WanFHDL25","journals/pr/ShenLWRLDZ25","journals/ral/WangDSXLLD25","journals/tcsv/FanGDXS25","journals/tcsv/MaoZWTLLD25","journals/tip/MaoZXLLZD25"]},{"id":"team-36","labName":"PKU-Agibot Lab","labUrl":null,"memberIndices":[36],"label":"PKU-Agibot Lab","sharedLab":false,"count2025":27,"conference2025":27,"journal2025":0,"knownMinimum2025":null,"sourceWarning":false,"preprint2025":32,"knownPreprintMinimum2025":null,"arxivIds":["2501.03841","2502.08449","2502.11124","2503.09243","2503.12779","2503.14051","2503.19913","2504.07596","2504.18904","2505.01809","2505.02166","2505.11032","2505.13982","2505.19487","2505.22503","2505.24305","2506.06221","2506.09343","2506.14317","2507.03930","2507.04452","2507.18276","2508.10416","2509.17125","2509.23829","2509.24494","2509.24797","2511.16651","2511.17441","2512.00287","2512.19390","2512.19402"],"paperKeys":["conf/cvpr/0009XZ00PXH0Z025","conf/cvpr/GaoPGZLDT0025","conf/cvpr/LongZPWKD25","conf/cvpr/PanZWZGD25","conf/cvpr/WuZWCW025","conf/cvpr/ZhouHCZX0LYL025","conf/eccv/MaDM24","conf/eccv/ZhangHPWHCZD24","conf/iccv/XueLLWDZHC25","conf/iccv/ZhangWWXLXDH25","conf/iclr/TianYZWL0P25","conf/iclr/TieCWDLG025","conf/iclr/WangZWLSWH0025","conf/icml/0035WKSL0FL025","conf/icra/CaiPYLYDZ25","conf/icra/LiLHHGDL25","conf/icra/WangZGFWSXZD25","conf/icra/WuLZWD25","conf/icra/WuZLHD25","conf/iros/HengLMLLWWJGZZD25","conf/iros/KimBLLPWD25","conf/iros/LiWZCJWSYD25","conf/iros/WuWWHFHGLYYCD25","conf/iros/ZhangLXZBSXD25","conf/nips/WangWCWLZGMAD25","conf/nips/ZhangMWCD25","conf/nips/ZhuBXCCLWDYFC25"]},{"id":"team-37","labName":null,"labUrl":null,"memberIndices":[37],"label":"窦琪 及合作者","sharedLab":false,"count2025":29,"conference2025":14,"journal2025":15,"knownMinimum2025":null,"sourceWarning":false,"preprint2025":25,"knownPreprintMinimum2025":null,"arxivIds":["2501.00525","2502.08189","2503.01252","2503.09160","2503.14925","2503.18296","2504.03198","2505.04954","2505.19031","2506.02555","2506.02557","2506.04716","2506.08048","2506.17337","2507.06647","2507.19165","2508.10881","2508.18886","2509.05657","2509.15103","2510.00037","2511.01276","2512.02485","2512.10206","2512.19387"],"paperKeys":["conf/acl/WuGG025","conf/cvpr/FuZC025","conf/eccv/MaCTWNKD24","conf/eccv/XuWYFDH24","conf/emnlp/HuLWZSZDLZL25","conf/emnlp/WuGGHLD25","conf/iccv/FanCYYQDYS25","conf/iclr/GongL0F25","conf/icml/Gong00F25","conf/iros/LiCQCD25","conf/iros/MaCXZXXD25","conf/isbi/ChenH025","conf/miccai/ZhangZCDW24","conf/nips/MaCZD25","journals/aisy/LiuNLHDXW25","journals/automatica/XinSDCS25","journals/mia/WangLCYSCYMD25","journals/mia/WangZLDCCDH25","journals/npjdm/ChenGFDCCQZNHDYL25","journals/scirobotics/LongLKZYSSFLWCCHYCKTLCW25","journals/tase/WeiLZMDLS25","journals/tcsv/ZhouCWZDQ25","journals/titb/ChenDZCCDCHC25","journals/titb/WangLZWZD25","journals/tmi/FuCDGHZLWG25","journals/tmi/GuoWWKDL25","journals/tmi/HanZPQFD25","journals/tmi/HuangZXWDZ25","journals/trob/ZhouHDAL25"]},{"id":"team-38","labName":null,"labUrl":null,"memberIndices":[38],"label":"杜冬 及合作者","sharedLab":false,"count2025":2,"conference2025":1,"journal2025":1,"knownMinimum2025":null,"sourceWarning":false,"preprint2025":1,"knownPreprintMinimum2025":null,"arxivIds":["2512.09435"],"paperKeys":["conf/cvpr/ZhangLDCSZDXZ025","journals/cmig/LiuDLTYHSL25"]},{"id":"team-39","labName":null,"labUrl":null,"memberIndices":[39],"label":"傅红波 及合作者","sharedLab":false,"count2025":20,"conference2025":7,"journal2025":13,"knownMinimum2025":null,"sourceWarning":false,"preprint2025":8,"knownPreprintMinimum2025":null,"arxivIds":["2502.04983","2503.22349","2503.23284","2504.20599","2508.13797","2509.06573","2509.21291","2510.26141"],"paperKeys":["conf/cvpr/Liang00K0L25","conf/cvpr/Liu0WY0Z025","conf/iccv/ChenZLJCHFH25","conf/icmcs/QiuLFZCLG25","conf/ismar/YangZXFH25","conf/siggraph/LiuLC0025","conf/siggrapha/0038ZL0L025","journals/cga/ZengFZC25","journals/pami/HuBSZDWSFT25","journals/pami/JiangCLFG25","journals/tcsv/WuXTSFJ25","journals/tog/ZhouQLF25","journals/tvcg/HuXZFH25","journals/tvcg/JiangLCWZLFG25","journals/tvcg/JiangXZFLW25","journals/tvcg/QuSLF25","journals/tvcg/QuSYHF25","journals/tvcg/SuWLHFL25","journals/tvcg/WangZSF25","journals/tvcg/ZouHCMSFZ25"]},{"id":"team-40","labName":null,"labUrl":null,"memberIndices":[40],"label":"付彦伟 及合作者","sharedLab":false,"count2025":44,"conference2025":39,"journal2025":5,"knownMinimum2025":null,"sourceWarning":false,"preprint2025":55,"knownPreprintMinimum2025":null,"arxivIds":["2501.03289","2501.09350","2501.11236","2502.05749","2502.07531","2502.11158","2502.14373","2502.16587","2503.01175","2503.01542","2503.06471","2503.06940","2503.09078","2503.15831","2503.16921","2503.23297","2504.00432","2504.10685","2504.11230","2504.14899","2504.18087","2505.19571","2505.21528","2506.05719","2506.05856","2506.05872","2506.18325","2506.18856","2506.23508","2507.01424","2507.06710","2507.06719","2507.10532","2507.11296","2508.01650","2508.03404","2508.03694","2508.06082","2508.11904","2509.24776","2509.25989","2510.03291","2510.04196","2510.11566","2510.11687","2510.13778","2510.20178","2510.21461","2511.13035","2511.17225","2511.18765","2511.20886","2512.02835","2512.13604","2512.21201"],"paperKeys":["conf/aaai/Zheng025","conf/cvpr/0002CYFX025","conf/cvpr/CaoYL0X025","conf/cvpr/ChengWSZ025","conf/cvpr/FuQR0TS0GZNDGZP25","conf/cvpr/HuangLW00025","conf/cvpr/KongW0HHP0LZW025","conf/cvpr/Liu0ZPL0025","conf/cvpr/ZhangCZL00W25","conf/cvpr/ZhangX0C25","conf/eccv/FuWPHQSLFGJ24","conf/eccv/GaoFWQFF24","conf/eccv/HuoWWQLFF24","conf/eccv/LiQWHXFM24","conf/eccv/RenCFX24","conf/icassp/WangQLC0025","conf/iccv/DongF25","conf/iccv/FuWRSGFPHG25","conf/iccv/LiuWWLXF25","conf/iccv/XuDXWCMFGXE25","conf/iclr/DingF00025","conf/iclr/Xu0Z0G25","conf/icmcs/WangJXZWZCCWWF25","conf/icml/Wu0W025","conf/icml/ZhuPM0YW025","conf/icra/HuangLWFJX25","conf/ijcai/0001LPHJ0JW025","conf/iros/GuLF25","conf/iros/HeSWGFFS25","conf/iros/WangFWFLJX25","conf/mm/LiHH0025","conf/mm/LiuZCZL0025","conf/mm/TanL0XHJZW025","conf/mm/ZhangL0FHZCW025","conf/nips/LiHHFJX25","conf/nips/LiQFCQZPFHGJ25","conf/nips/WangHDZFLW25","conf/nips/WuXXLSGSF25","conf/siggrapha/CaoZLLYW0F25","journals/ml/WanFSFLJZ25","journals/pami/GaoFFWQF25","journals/pami/QianWJXF25","journals/spl/WangZXCF25","journals/tip/WangQLFX25"]},{"id":"team-41","labName":"中山大学空间智能实验室（Spatial Artificial Intelligence Lab, SAIL）","labUrl":"https://sysu-sail.net/","memberIndices":[41],"label":"中山大学空间智能实验室（Spatial Artificial Intelligence Lab, SAIL）","sharedLab":false,"count2025":48,"conference2025":21,"journal2025":27,"knownMinimum2025":null,"sourceWarning":true,"preprint2025":18,"knownPreprintMinimum2025":null,"arxivIds":["2501.02519","2502.02163","2502.04628","2503.01309","2503.15934","2503.20368","2504.09491","2505.00259","2505.07622","2505.11868","2506.00835","2506.12766","2506.14769","2507.08400","2508.05884","2508.20466","2509.13662","2511.15288"],"paperKeys":["conf/aaai/JiangZWYG25","conf/accv/LiuWGZG24","conf/cvpr/LiuWZYG25","conf/cvpr/TangZLGD0X25","conf/cvpr/WangLZTW00TGJWY25","conf/cvpr/WangWMHXG25","conf/cvpr/WangZLLXWGW25","conf/cvpr/XuWCA0G25","conf/cvpr/ZhaoAZXG25","conf/eccv/FuWXWLGBB24","conf/eccv/MaLPG24","conf/eccv/WangLCWZXG24","conf/eccv/ZhangWLWG24","conf/globecom/YeDDG25","conf/iccv/ZhouGWX25","conf/icpr/YinGHZXZCWWCYLLHJDWLWTP24","conf/icra/LiuZZLG25","conf/icra/ZhangAZSHCG25","conf/icra/ZhangGLZCG25","conf/iros/ChenYHXZG25","conf/iros/ZhangLZSJZG25","journals/aeog/WangLFJDZCGW25","journals/cn/TengXGGXHC25","journals/pami/HuFOGGL25","journals/pami/WangGWDXYA25","journals/spl/WangXDGW25","journals/tcss/ZhangGHDLG25","journals/tcsv/YanFWGDWM25","journals/tgrs/YinALSLGW25","journals/tip/ChenLWYWZGLA25","journals/tip/FuGCHLBB25","journals/tip/FuZWXLGBB25","journals/tip/WangLWHWG25","journals/tmc/WangZLXWGW25","journals/tmc/XiangLZWZG25","journals/tmm/ChaoDGW25","journals/tmm/FengHZGYWM25","journals/tmm/GaoWAZG25","journals/tmm/LiGYYR25","journals/tmm/LiuHWXWG25","journals/tmm/LiuZLLPG25","journals/tmm/YuZLLG25","journals/tnn/DangZXWHG25","journals/tnn/LiAXLWLG25","journals/tnn/LiRGYY25","journals/tnn/WangLSGWY25","journals/tnn/WangLWYAG25","journals/vc/PeiLJZYLG25"]},{"id":"team-42","labName":"GAP Lab","labUrl":"https://gaplab.cuhk.edu.cn/","memberIndices":[42],"label":"GAP Lab","sharedLab":false,"count2025":20,"conference2025":15,"journal2025":5,"knownMinimum2025":null,"sourceWarning":false,"preprint2025":20,"knownPreprintMinimum2025":null,"arxivIds":["2501.05369","2501.16177","2503.11423","2503.21766","2503.22236","2505.01838","2506.13766","2507.23483","2509.00777","2509.16748","2509.21291","2509.23709","2510.07190","2510.23306","2511.06721","2511.18600","2511.19437","2512.07720","2512.08785","2512.09435"],"paperKeys":["conf/3dim/XuYQLTH25","conf/cvpr/GaoYG0Y025","conf/cvpr/LiuF0LL0QWD025","conf/cvpr/LiuZYLW025","conf/cvpr/ZhangLDCSZDXZ025","conf/cvpr/ZhaoLXH0025","conf/eccv/ChangXLCFH24","conf/eccv/LiCSQACH24","conf/eccv/YanZMWQYCCH24","conf/eccv/ZhangXWXZHBS24","conf/eccv/ZhouLLXCLHL24","conf/iccv/XuYLWCH25","conf/iccv/YeWLCGZZH25","conf/nips/LiLQZZDH25","conf/siggrapha/ZhiLLYSCCF025","journals/cmig/LiuDLTYHSL25","journals/tvcg/QuSYHF25","journals/tvcg/ShuSC0X25","journals/tvcg/ZhangXSZJXHW25","journals/tvcg/ZhiSCYFH25"]},{"id":"team-43","labName":null,"labUrl":null,"memberIndices":[43],"label":"侯军辉 及合作者","sharedLab":false,"count2025":49,"conference2025":21,"journal2025":28,"knownMinimum2025":null,"sourceWarning":false,"preprint2025":26,"knownPreprintMinimum2025":null,"arxivIds":["2501.00838","2501.07236","2501.10789","2501.15008","2503.09439","2503.14154","2503.15975","2503.16822","2504.19210","2505.17442","2506.02053","2506.09920","2506.15228","2508.17050","2508.17488","2509.00066","2509.04824","2509.18826","2509.19165","2509.23194","2510.03993","2510.12524","2511.12494","2511.20225","2511.21193","2512.00725"],"paperKeys":["conf/cvpr/HuLHHZWL025","conf/cvpr/LiuZ0H25","conf/cvpr/LiuZZZS0H25","conf/cvpr/WangLZTW00TGJWY25","conf/cvpr/YaoDH25","conf/eccv/YaoRHDZW24","conf/iccv/KristanMTLFZTVBNCFADFFG25","conf/iccv/QianHHSF25","conf/iccv/QianHWHF25","conf/iccv/RenHLW25","conf/iclr/JiaC0H25","conf/iclr/Liu00L0WH25","conf/iclr/LuZH25","conf/iclr/RenH25","conf/iclr/YouZ0H25","conf/icml/LiJ0H25","conf/icml/ZhangQL0HJ25","conf/kdd/YangC0DJH25","conf/nips/HouHJLH25","conf/nips/LiJLH25","conf/nips/QianHWHF25","journals/caaitrit/ChengWHHWX25","journals/cvm/DidykH25","journals/jstsp/LinHLZM25","journals/pami/FengWHGQHW25","journals/pami/RenHCXW25","journals/pami/TangZLH25","journals/pami/YangZWMHLW25","journals/pami/YaoDHZ25","journals/pami/ZhangHRWYS25","journals/pami/ZhuHLZH25","journals/tcsv/ChenLLSGHL25","journals/tcsv/HuoHWY25","journals/tcsv/JingWZYBZZH25","journals/tcsv/LiuZCDSH25","journals/tifs/ZhangHWSHF25","journals/tip/ChenWHZL25","journals/tip/ChengWWHWX25","journals/tip/HanJLH25","journals/tip/QiJLH25","journals/tmc/ZhuHLWH25","journals/tmm/ChenWRYYH25","journals/tmm/WuZHX25","journals/tmm/ZhangHQ25","journals/tvcg/GuoCYMHH25","journals/tvcg/LinYLZHJKKW25","journals/tvcg/WuCXZH25","journals/tvcg/WuHSX25","journals/tvcg/YouH25"]},{"id":"team-44","labName":"GeWu Lab","labUrl":"https://gewu-lab.github.io/","memberIndices":[44],"label":"GeWu Lab","sharedLab":false,"count2025":17,"conference2025":16,"journal2025":1,"knownMinimum2025":null,"sourceWarning":false,"preprint2025":14,"knownPreprintMinimum2025":null,"arxivIds":["2502.10816","2502.12191","2503.13068","2503.18595","2504.06666","2504.14588","2506.05191","2506.07127","2506.11465","2506.17248","2506.19613","2510.00050","2511.17441","2512.17229"],"paperKeys":["conf/acl/Chen0W00JMZDMLS25","conf/cvpr/DuLZZZ025","conf/cvpr/HuangWY025","conf/cvpr/PengHWWH25","conf/cvpr/XiaF0025","conf/eccv/MaSWH24","conf/eccv/WangSLZH24","conf/eccv/WangSZLZH24","conf/eccv/WeiLFH24","conf/iclr/FengHXGSSF025","conf/icml/NiWLCPL025","conf/icml/YangW025","conf/mir/HouY025","conf/nips/WeiMZH25","conf/nips/XiaYWMKH25","conf/sigir/Feng0PMZ0Z25","journals/pami/WeiHDW25"]},{"id":"team-45","labName":"可视计算研究中心","labUrl":null,"memberIndices":[45],"label":"可视计算研究中心","sharedLab":true,"count2025":18,"conference2025":16,"journal2025":2,"knownMinimum2025":null,"sourceWarning":false,"preprint2025":16,"knownPreprintMinimum2025":null,"arxivIds":["2502.05309","2502.20370","2503.08135","2503.19457","2504.04421","2504.07025","2504.07955","2504.09149","2504.16693","2505.11528","2506.24121","2507.11540","2508.13104","2511.13327","2512.03538","2512.04415"],"paperKeys":["conf/cvm/SuPKHH25","conf/cvpr/ChenMLCPCXH00025","conf/cvpr/GuoXL0LH25","conf/cvpr/Wu0H025","conf/eccv/DaiLSHMHXH24","conf/eccv/GuoZPWSHZ24","conf/eccv/SheZYHX24","conf/eccv/XuXHXHH24","conf/iccv/GuoPSSHWDHKPZ25","conf/iccv/JianLCLLH25","conf/iccv/TanHPGZSHSBZ25","conf/iccv/WangWGPQBZH25","conf/iccv/YuHZYYHSZZP25","conf/iclr/CenPPSSB0H25","conf/siggraph/LiX0SZ0H25","conf/siggrapha/ShenQLH025","journals/cg/ZhengMH25","journals/tog/ZhengYH25"]},{"id":"team-46","labName":"LEarning And Perception (LEAP) Lab","labUrl":"https://www.leaplab.ai","memberIndices":[46],"label":"LEarning And Perception (LEAP) Lab","sharedLab":false,"count2025":48,"conference2025":34,"journal2025":14,"knownMinimum2025":null,"sourceWarning":false,"preprint2025":35,"knownPreprintMinimum2025":null,"arxivIds":["2502.18364","2502.19247","2503.00345","2503.03595","2503.10437","2503.17760","2504.06803","2504.13065","2504.13820","2504.13837","2505.03335","2505.04965","2506.01939","2506.20601","2506.23280","2508.19236","2509.13832","2509.15333","2509.24804","2509.26231","2510.06809","2510.14381","2511.00833","2511.09555","2511.14329","2511.15550","2511.17441","2512.00493","2512.01643","2512.04813","2512.13006","2512.21542","2512.22288","2512.24330","2512.24603"],"paperKeys":["conf/aaai/ZhaoXLWLZ025","conf/cvpr/0001ZZSHQ0P25","conf/cvpr/GuoZDWGNSSH25","conf/cvpr/PengZ025","conf/cvpr/PuZTYYYCBZWLWLL25","conf/cvpr/TaoSZZ0LWL00D25","conf/cvpr/TianZ0XH025","conf/cvpr/YueWJLS025","conf/cvpr/YueWTLS025","conf/eccv/GuoXYCNGCLH24","conf/eccv/HanYHXPWSH24","conf/eccv/HuangPTTPSHE24","conf/eccv/LiuLLLLHY24","conf/eccv/NiWZLGHLYH24","conf/eccv/PuXGHLLYLHSHX24","conf/eccv/WangPHGWLH24","conf/eccv/YangZHCSHL24","conf/iccv/GuoYXWWHS25","conf/iccv/LiuNHDMZH25","conf/iclr/LuWLJ0W25","conf/iclr/WangS025","conf/iclr/Ye0XSZ0W25","conf/iclr/ZhaoHT0S0W025","conf/iclr/ZhengSPCHWS025","conf/icml/KangYL00W0F25","conf/iros/ChenYLHLL25","conf/miccai/JiangLSJSLSH24","conf/naacl/WangYLSZWSH25","conf/nips/ChenLZWYSH25","conf/nips/HuangZBPTGHE25","conf/nips/PuYLYHWWSHL25","conf/nips/WangYGZLLDCYZLY25","conf/nips/ZhangWXZSHCW25","conf/nips/ZhaoWWXYLWWZH25","journals/artmed/YangWLWSSFH25","journals/eaai/SunWLZHL25","journals/ijcv/WangNPZYSH25","journals/nn/LiCLXMH25","journals/nn/ZhaoZLLLH25","journals/nn/ZhaoZLLLH25a","journals/pami/WangZYSDFH25","journals/pr/JiangZHGNSH25","journals/tnn/GeHXLSLH25","journals/tnn/LiuDZLZWH25","journals/tnn/WangPSH25","journals/tnn/YueKMYHSY25","journals/tnn/ZhangWLHLLF25","journals/tnn/ZhuWPWZH25"]},{"id":"team-47","labName":null,"labUrl":null,"memberIndices":[47],"label":"黄海斌 及合作者","sharedLab":false,"count2025":null,"conference2025":null,"journal2025":null,"knownMinimum2025":null,"sourceWarning":false,"preprint2025":null,"knownPreprintMinimum2025":null,"arxivIds":[],"paperKeys":[]},{"id":"team-48","labName":null,"labUrl":null,"memberIndices":[48],"label":"贾旭 及合作者","sharedLab":false,"count2025":19,"conference2025":12,"journal2025":7,"knownMinimum2025":null,"sourceWarning":false,"preprint2025":14,"knownPreprintMinimum2025":null,"arxivIds":["2502.08639","2503.23368","2504.02402","2505.19797","2505.20469","2507.01735","2507.16534","2507.20745","2508.11538","2509.06442","2509.12046","2510.25772","2512.03041","2512.12324"],"paperKeys":["conf/cvpr/Li0IJC0LHLWB25","conf/eccv/DiaoWJZZLC24","conf/eccv/ZhangYWCLWLJ24","conf/iccv/TianLMYZHLLJ25","conf/iccv/YangLZYBMWCWLJ25","conf/iccv/YuFLTYTCJYYT25","conf/icra/XiaZHQHJ25","conf/mm/ZhuD000Z0000L25","conf/prcv/HuangJSZLWL24","conf/siggraph/WangLS0LX000G25","conf/wacv/0023LZLL0HTZLYL25","conf/wacv/LiCL0HYL025","journals/tcsv/LiWLGJHL25","journals/tcsv/LiuZCZJZY25","journals/tcsv/ZhangZCCZWLJY25","journals/tip/LiYYFJJRLZ25","journals/tip/WangLLCMLJ25","journals/tmm/WangJLLMZL25","journals/tnn/ZhangJHWZLWLJ25"]},{"id":"team-49","labName":null,"labUrl":null,"memberIndices":[49],"label":"蒋理 及合作者","sharedLab":false,"count2025":10,"conference2025":9,"journal2025":1,"knownMinimum2025":null,"sourceWarning":false,"preprint2025":9,"knownPreprintMinimum2025":null,"arxivIds":["2503.08422","2505.19239","2506.10507","2506.23120","2506.23729","2507.12455","2510.03198","2511.04595","2512.16811"],"paperKeys":["conf/aaai/XuLSLLGWJWSZJZC25","conf/cvpr/ChenS0SJL25","conf/eccv/DasHJS24","conf/eccv/WangTJSNLSW24","conf/iccv/HuangHSTJ25","conf/iccv/NingTSLHPJ25","conf/iccv/PengYJT25","conf/iccv/ShiSSZJ25","conf/siggrapha/ZhangSJXQS025","journals/pami/WuZHXWJLW25"]},{"id":"team-50","labName":null,"labUrl":null,"memberIndices":[50],"label":"靳潇杰 及合作者","sharedLab":false,"count2025":7,"conference2025":4,"journal2025":3,"knownMinimum2025":null,"sourceWarning":false,"preprint2025":9,"knownPreprintMinimum2025":null,"arxivIds":["2501.09781","2502.02589","2504.15415","2505.23155","2505.23922","2506.23825","2509.24997","2511.00962","2512.09363"],"paperKeys":["conf/cvpr/RenWG0KFJ25","conf/iccv/ZhangWTLFJ25","conf/nips/DengYYAYJSC25","conf/nips/LinQHJJW25","journals/pami/ZhangZJXYYW25","journals/tmm/HeCMHJLFYLF25","journals/tmm/WangZZJXW25"]},{"id":"team-51","labName":"Machine Learning Group (GSAI-ML)","labUrl":"https://github.com/ML-GSAI","memberIndices":[51],"label":"Machine Learning Group (GSAI-ML)","sharedLab":false,"count2025":20,"conference2025":17,"journal2025":3,"knownMinimum2025":null,"sourceWarning":false,"preprint2025":22,"knownPreprintMinimum2025":null,"arxivIds":["2502.09992","2502.14583","2502.15894","2503.07197","2503.13265","2503.14151","2505.15270","2505.16933","2505.19223","2505.21493","2507.06203","2509.13866","2509.22637","2509.24389","2510.10481","2511.06254","2511.10690","2511.20123","2512.03759","2512.04504","2512.13586","2512.15745"],"paperKeys":["conf/cvpr/WangSL0LW0XW25","conf/cvpr/You0G0L25","conf/eccv/WangWCXCYLSZ24","conf/eccv/ZhangLW24a","conf/eccv/ZhaoDYLDW24","conf/eccv/ZhongZYYZL24","conf/iccv/ZhongYTGL25","conf/iclr/LiuDP0LX25","conf/iclr/NieZDPLZLL25","conf/iclr/OuNXZSLL25","conf/icml/WangZZLW25","conf/icml/YouOZH0L25","conf/icml/ZhaoHCZLZ25","conf/nips/ChenNSFLWL25","conf/nips/ChenZZWZHSWL25","conf/nips/NieZYZOHZLWL25","conf/nips/ZhengZWHTHZL25","journals/chinaf/ZhaoWBLZ25","journals/ijautcomp/LuZBCLZ25","journals/tmlr/GuDPLL025"]},{"id":"team-52","labName":"HCP-I2 Lab: Human-Cyber-Physical Intelligence Integration","labUrl":"http://www.sysu-hcp.net","memberIndices":[52],"label":"HCP-I2 Lab: Human-Cyber-Physical Intelligence Integration","sharedLab":false,"count2025":48,"conference2025":32,"journal2025":16,"knownMinimum2025":null,"sourceWarning":true,"preprint2025":33,"knownPreprintMinimum2025":null,"arxivIds":["2501.01926","2503.03190","2503.11091","2503.11117","2503.11345","2503.12165","2503.12838","2503.23024","2504.04687","2504.08291","2504.11218","2505.12641","2505.18612","2506.17712","2507.04293","2507.07831","2507.23772","2508.02134","2508.03566","2508.04559","2508.05186","2508.08252","2508.13618","2509.23867","2510.10991","2510.25237","2511.06253","2511.06256","2511.06272","2511.12254","2511.17217","2512.08477","2512.14601"],"paperKeys":["conf/aaai/LengFCFLL25","conf/aaai/WuJLFQL25","conf/cvpr/HeNQWYLL25","conf/cvpr/LaiZQRWL25","conf/cvpr/LuoLCLWLL25","conf/cvpr/SongCL0LL25","conf/cvpr/YuanPRLH0ZLCL25","conf/cvpr/ZhuSWTW0LY25","conf/cvpr/ZhuangKBLL25","conf/eccv/HeCWLTL24","conf/eccv/WangCCZLZL24","conf/eccv/ZhangLZLWTLDWL24","conf/iccv/CaiLLCLXLL25","conf/iccv/HuangYCLWWWL25","conf/iccv/HuangYLWWWLL25","conf/iccv/JiangLCLCPLL25","conf/iccv/LiLCCLLL25","conf/iccv/LiYXBTSXJLZ25","conf/iccv/TangWZSLLY25","conf/iccv/WangZXZLLLZL25","conf/iccv/WangZZTLWL25","conf/iccv/YeGLCC25","conf/iccv/ZhangXZCTWL25","conf/iccv/ZhangZTYWLL25","conf/icmcs/TanML25","conf/icml/HeJ0ZHLD25","conf/ijcai/ChenLHL0CF25","conf/ijcai/FangMLC0L25","conf/isbi/CaiFGMSL25","conf/mm/MoCFL25","conf/mm/WeiL0CLLL25","conf/nips/LiLCML25","journals/kbs/JiLLLW25","journals/pami/ZhangLXGTSHL25","journals/pr/JiaLZLSLL25","journals/tip/ChenFLLL25","journals/tip/ChenLWZLLL25","journals/titb/DuJTLLLW25","journals/tkde/LiuCZCLL25","journals/tmi/HuangGZWWLLS25","journals/tmi/LouLLLXWW25","journals/tmm/HeCZWLLL25","journals/tmm/LiLGLL25","journals/tnn/LiCZHL25","journals/tnn/LiuLLWLL25","journals/tvcg/ZhangYZYWLWCL25","journals/vc/HuangLTCL25","journals/visintelligence/XieCZL25"]},{"id":"team-53","labName":"CUHK MMLab","labUrl":"https://mmlab.ie.cuhk.edu.hk/","memberIndices":[53,99,106],"label":"CUHK MMLab","sharedLab":true,"count2025":null,"conference2025":null,"journal2025":null,"knownMinimum2025":52,"sourceWarning":true,"preprint2025":null,"knownPreprintMinimum2025":75,"arxivIds":["2501.06533","2501.11515","2501.11561","2502.04719","2502.08639","2502.11382","2502.11555","2502.12600","2502.14744","2502.16707","2502.16779","2502.20037","2503.01291","2503.07300","2503.16302","2503.18055","2503.18422","2503.20268","2503.20748","2503.21776","2504.02402","2504.04126","2504.07667","2504.10443","2504.20830","2505.14502","2505.16938","2505.17018","2505.19761","2505.20294","2505.21327","2505.23764","2506.03131","2506.03140","2506.05280","2506.09981","2506.10082","2506.12430","2506.18898","2506.19257","2507.05163","2507.08772","2507.19478","2507.20331","2507.22827","2508.10881","2508.13503","2508.13628","2509.04394","2509.15221","2509.21320","2510.01546","2510.06308","2510.08555","2510.09606","2510.10518","2510.11369","2510.12747","2510.22213","2510.26140","2511.16317","2511.17731","2511.18780","2511.20646","2511.23476","2512.00993","2512.03043","2512.03052","2512.05511","2512.05530","2512.06802","2512.16279","2512.16295","2512.16918","2512.18772"],"paperKeys":["conf/aaai/LiuY00025","conf/acl/JiangGPTZ0025","conf/ccs/FanZ00000Z25","conf/cvpr/0002HLL025","conf/cvpr/CaiCLLZZSY25","conf/cvpr/ChenLDGX25","conf/cvpr/ChenWCY0ZGX25","conf/cvpr/CongWM025","conf/cvpr/LiZLX000GXS25","conf/cvpr/TangMSS0L0O025","conf/cvpr/YaoWTLXG25","conf/cvpr/YouCGX025","conf/eccv/ChenGYZGX24","conf/eccv/JiangZXG24","conf/eccv/LiWCZGX24","conf/eccv/MaGCXG24","conf/eccv/YouLGYXD24","conf/eccv/YuanZGYSQC24","conf/eccv/ZhangZDJY24","conf/iccv/ChenWLHPX25","conf/iccv/DongDCLWWWKGHWXX25","conf/iccv/GaoDHHWX25","conf/iccv/HeLXLKGXSSGY25","conf/iccv/JiangGXCMYL25","conf/iccv/JiangLZCY25","conf/iccv/LaiZZLWSYLHLJGY25","conf/iccv/LiFGY25","conf/iccv/LiZGYL25","conf/iccv/PengLYZXZBMWZSCZY25","conf/iccv/WangLZGLXD25","conf/iccv/WuWYMGZOT25","conf/iccv/XuZSXW25","conf/iccv/YuZLZDY25","conf/iccv/ZhangJLY25","conf/iccv/ZhangLLWCXG25","conf/iccv/ZhangLLY25","conf/iclr/HuangDWQY025","conf/icml/Hu0Q0CW025","conf/nips/ChenFLLYYW25","conf/nips/FengGLGWPWZWY25","conf/nips/HanCZWZYHYJ25","conf/nips/LiuY25","conf/nips/WangBYOZ25","conf/nips/WangXCXMLYZXYLC25","conf/nips/YangCGCSJLGYC25","conf/siggraph/WangLS0LX000G25","conf/siggrapha/ChenGYDYGX25","conf/siggrapha/LuoSBXXW0ZG25","journals/pami/ZhangDY25","journals/tip/LiYMYXG25","journals/tip/YouGCLZDX25","journals/tmc/DengXC25"]},{"id":"team-54","labName":null,"labUrl":null,"memberIndices":[54],"label":"李坤 及合作者","sharedLab":false,"count2025":8,"conference2025":2,"journal2025":6,"knownMinimum2025":null,"sourceWarning":false,"preprint2025":2,"knownPreprintMinimum2025":null,"arxivIds":["2507.20117","2508.12644"],"paperKeys":["conf/iccv/LiuZKMWHWLL25","conf/siggrapha/WangM0WLL25","journals/cvm/JingYHLL25","journals/displays/ShenYLY25","journals/tetci/LuoLLLY25","journals/tist/BiTXLY25","journals/tmm/YangXHYFL25","journals/tvcg/ZhangZZZLL25"]},{"id":"team-55","labName":"IMPlus@PCALab","labUrl":"https://github.com/IMPlus-PCALab","memberIndices":[55],"label":"IMPlus@PCALab","sharedLab":false,"count2025":27,"conference2025":17,"journal2025":10,"knownMinimum2025":null,"sourceWarning":false,"preprint2025":23,"knownPreprintMinimum2025":null,"arxivIds":["2501.03775","2501.04440","2501.13898","2504.18765","2505.04917","2505.10931","2505.15184","2505.19148","2505.20641","2506.01674","2506.02408","2507.01467","2508.01259","2508.09392","2509.02357","2509.17562","2509.20923","2509.25179","2509.25958","2509.26281","2511.02607","2511.16361","2511.21188"],"paperKeys":["conf/aaai/WangXLLGGC25","conf/aaai/ZhaoXD0TYC025","conf/acns/LiZLLZS25","conf/cvpr/FanNXZYFLYT25","conf/cvpr/PengWZLYDC025","conf/cvpr/ZhangYLYCL25","conf/eccv/LiWLLYDQZ24","conf/eccv/WuZLCLYL24","conf/iccv/HanYLZLYCD25","conf/iccv/LiSCLY25","conf/iclr/NanXZFYCL0T25","conf/icml/BiWL0Q0025","conf/icra/WuYWLHY25","conf/mm/XiongCZLT0025","conf/nips/TangQFZCLC25","conf/nips/WuYZLY25","conf/nips/WuZSGCWCGTYCL25","journals/ijcv/LiLDHLLCY25","journals/ijcv/YanLHZLY25","journals/ijcv/ZhangLYYLZJLCLYL25","journals/pami/ChenYWWLHC25","journals/pami/YanWLGLY25","journals/pami/YangLWWY25","journals/taes/DaiZLLNY25","journals/tcsv/FanLQLY25","journals/tgrs/DaiYDLLNXSY25","journals/tgrs/WangFLYL25"]},{"id":"team-56","labName":"Hong Kong Embodied AI Lab","labUrl":null,"memberIndices":[56],"label":"Hong Kong Embodied AI Lab","sharedLab":true,"count2025":5,"conference2025":4,"journal2025":1,"knownMinimum2025":null,"sourceWarning":false,"preprint2025":6,"knownPreprintMinimum2025":null,"arxivIds":["2503.18221","2504.17249","2504.21738","2505.13834","2510.10637","2510.11682"],"paperKeys":["conf/icra/LiaoZHHLS25","conf/icra/RyuLLDSM25","conf/iros/ChenHWLZLSWSGP25","conf/iros/OuyangLLLYSW25","journals/ijrr/LiPALBS25"]},{"id":"team-57","labName":"IGCL","labUrl":"http://igcl.pku.edu.cn/igcl/","memberIndices":[57],"label":"IGCL","sharedLab":false,"count2025":9,"conference2025":7,"journal2025":2,"knownMinimum2025":null,"sourceWarning":false,"preprint2025":7,"knownPreprintMinimum2025":null,"arxivIds":["2502.18364","2503.06472","2504.20403","2505.17778","2506.10963","2512.19024","2512.20479"],"paperKeys":["conf/cvpr/LiuML25","conf/cvpr/PuZTYYYCBZWLWLL25","conf/cvpr/XiongLHWWLZDL25","conf/eccv/ZhaoL24","conf/iccv/LuoTHHL25","conf/nips/LuoYCCYYDLL25","conf/siggrapha/ZhaoGLDLXL25","journals/cgf/XiongWZCLW25","journals/cvm/ZhaoGLGHFWZL25"]},{"id":"team-58","labName":"Precognition Lab（智能感知与预测实验室）","labUrl":"https://precognition.team/","memberIndices":[58],"label":"Precognition Lab（智能感知与预测实验室）","sharedLab":false,"count2025":9,"conference2025":9,"journal2025":0,"knownMinimum2025":null,"sourceWarning":false,"preprint2025":11,"knownPreprintMinimum2025":null,"arxivIds":["2505.11865","2505.15660","2505.18881","2505.19214","2505.22429","2505.23019","2508.07611","2509.22205","2510.00405","2511.01755","2512.16760"],"paperKeys":["conf/cvpr/LiLKY025","conf/cvpr/ZhouMLWQ025","conf/eccv/SunLZQL24","conf/eccv/ZhuZXZXLHLG24","conf/iccv/XuGQCYLZZZLC25","conf/icra/GongHQL25","conf/kdd/0047ZHC000Z0Y25","conf/nips/LiDHLLLPKLL25","conf/nips/ZhouYLMWQLZL25"]},{"id":"team-59","labName":null,"labUrl":null,"memberIndices":[59],"label":"廖菁 及合作者","sharedLab":false,"count2025":18,"conference2025":11,"journal2025":7,"knownMinimum2025":null,"sourceWarning":false,"preprint2025":13,"knownPreprintMinimum2025":null,"arxivIds":["2501.09921","2503.09733","2503.11412","2504.01014","2504.19478","2505.10558","2505.21374","2505.23740","2510.08527","2510.08530","2511.16669","2512.10894","2512.12534"],"paperKeys":["conf/ACMdis/MillerZ0L25","conf/cvpr/Feng00CZ25","conf/cvpr/WuS025","conf/cvpr/YeZ0LGZWL25","conf/eccv/WuWZLX24","conf/iccv/ChengGGLS25","conf/iccv/ZhangCL25","conf/iclr/SunGWYY00L25","conf/siggraph/0002Z025","conf/siggrapha/SunWSF025","conf/siggrapha/WuS025","journals/ijcv/WuSML25","journals/tbbis/Fu00H0L025","journals/tcsv/ZhangLZZCSL25","journals/titb/DuDXL25","journals/tvcg/SuWLHFL25","journals/tvcg/ZhuangCCJLLCLL25","journals/vi/ZhongWZL25"]},{"id":"team-60","labName":"X-Dimensional Representations Lab (X-D Lab)","labUrl":"https://yiyiliao.github.io/xdlab","memberIndices":[60],"label":"X-Dimensional Representations Lab (X-D Lab)","sharedLab":false,"count2025":15,"conference2025":12,"journal2025":3,"knownMinimum2025":null,"sourceWarning":false,"preprint2025":10,"knownPreprintMinimum2025":null,"arxivIds":["2501.01119","2503.20168","2504.00763","2504.11092","2505.07539","2506.01822","2506.08640","2506.19117","2507.11540","2507.17520"],"paperKeys":["conf/cvpr/LiLGBYL25","conf/cvpr/LuCZZHY0L25","conf/cvpr/Miao0BYZ0L0L25","conf/cvpr/ShaoYZ0SGWPL25","conf/cvpr/YangSLS0L25","conf/eccv/ChenGBZYWSL24","conf/eccv/JiLL24","conf/eccv/MiaoHBQLGL24","conf/iccv/HuangMYML25","conf/nips/LuTJZYOHYSL25","conf/rcar/HuangL25","conf/vcip/LiuZLLY25","journals/jzusc/ZhuGYL25","journals/pami/FuZCLZGL25","journals/ral/WuLJYWXL25"]},{"id":"team-61","labName":"Embodied Decision-Making (EDeM) Lab","labUrl":"https://guiliang.me/contents/group.html","memberIndices":[61],"label":"Embodied Decision-Making (EDeM) Lab","sharedLab":false,"count2025":11,"conference2025":9,"journal2025":2,"knownMinimum2025":null,"sourceWarning":false,"preprint2025":9,"knownPreprintMinimum2025":null,"arxivIds":["2501.14208","2503.00923","2503.06227","2503.11269","2505.11175","2505.24266","2510.03081","2510.22336","2512.01022"],"paperKeys":["conf/cvpr/RuanL0ZLLJ25","conf/eccv/QiaoQQL24","conf/iclr/XuYZL25","conf/iclr/YueWGLPL25","conf/iclr/ZhaoXYL25","conf/icml/LiuDZ0CCXTJ25","conf/icml/YueLL25","conf/iros/WangZYLJ25","conf/nips/MiaoXZCL25","journals/tmc/ZhangCZLWW25","journals/tmlr/LiuXLGSP25"]},{"id":"team-62","labName":"安徽省图形计算与感知交互重点实验室（GCL）","labUrl":null,"memberIndices":[62],"label":"安徽省图形计算与感知交互重点实验室（GCL）","sharedLab":true,"count2025":29,"conference2025":12,"journal2025":17,"knownMinimum2025":null,"sourceWarning":false,"preprint2025":16,"knownPreprintMinimum2025":null,"arxivIds":["2501.15279","2502.19800","2503.08135","2504.09149","2506.18910","2506.22319","2507.00690","2507.02419","2508.18733","2509.00840","2509.23718","2509.26055","2510.15564","2511.12474","2511.17322","2512.20904"],"paperKeys":["conf/aaai/TangDPWLLT25","conf/cvpr/GuoXL0LH25","conf/cvpr/Lin0FWL0LY25","conf/eccv/LinGWFCLY24","conf/eccv/TangHPLWMLT24","conf/mm/QinLHWFL25","conf/rt/LiLWSLW25","conf/rt/ZhuangLL25","conf/siggraph/00010LSWX0025","conf/siggraph/ChengF0025","conf/siggraph/LiX0SZ0H25","conf/siggrapha/00010025","journals/cagd/ZhuLXCL25","journals/cg/LiuLWCZZLXF25","journals/cg/ZhangLWZLWLF25","journals/cgf/ChengLF25","journals/cgf/ShiCWGFCLY25","journals/pami/ZhangNZLLC25","journals/tmm/ShuLXL25","journals/tog/LiuDLF25","journals/tog/LiuLF25","journals/tog/ZengLCL25","journals/tog/ZhangL25","journals/tog/ZhuHXDYGLZZLZ25","journals/tvcg/ChengFLF25","journals/tvcg/Du0G0025","journals/tvcg/ShuWLXL25","journals/tvcg/ShuYCXL25","journals/tvcg/ShuYCXL25a"]},{"id":"team-63","labName":"HKU-MMLab","labUrl":"https://mmlab.hk/about-us","memberIndices":[63,69],"label":"HKU-MMLab","sharedLab":true,"count2025":90,"conference2025":76,"journal2025":14,"knownMinimum2025":null,"sourceWarning":false,"preprint2025":97,"knownPreprintMinimum2025":null,"arxivIds":["2501.08325","2501.08332","2501.12612","2501.12976","2502.00359","2502.04896","2502.05179","2502.06756","2502.13092","2502.14814","2503.06669","2503.07365","2503.08422","2503.10639","2503.11650","2503.16408","2503.16430","2503.17359","2503.19462","2503.24376","2504.07943","2504.07963","2504.08736","2504.13059","2504.13162","2504.21853","2505.06111","2505.07818","2505.11777","2505.13427","2505.14030","2505.14302","2505.15929","2505.17022","2505.17099","2505.20147","2505.22618","2505.23885","2506.02648","2506.03126","2506.03141","2506.04217","2506.04421","2506.05240","2506.05985","2506.16141","2506.17206","2506.18088","2506.18899","2506.23351","2507.02299","2507.02713","2507.05240","2507.06165","2507.06219","2507.07984","2507.18537","2507.21610","2508.00350","2508.02518","2508.14036","2508.15720","2508.17472","2508.19699","2508.20018","2508.20072","2509.03903","2509.08736","2509.09680","2509.10463","2509.15185","2509.16063","2509.17398","2509.23922","2509.24695","2509.26328","2510.00050","2510.08994","2510.11718","2510.12784","2510.18002","2510.19871","2510.20774","2510.24711","2510.25602","2510.26800","2511.07934","2511.16901","2511.17373","2512.00975","2512.02014","2512.07503","2512.08186","2512.08765","2512.14099","2512.17909","2512.22342"],"paperKeys":["conf/aaai/LaiLCPHP025","conf/aaai/YangZ000025","conf/aaai/YuYZY00N25","conf/acl/ChenSXWGZ025","conf/acl/HuCC0S025","conf/acl/HuCZLCL00SL25","conf/acl/LvLSLLY25","conf/cvpr/ChenGZZZYHWLHLZ25","conf/cvpr/ChenMLCPCXH00025","conf/cvpr/ChenS0SJL25","conf/cvpr/GeXJPTLDJZ25","conf/cvpr/HuangGAY0ZLLCS25","conf/cvpr/KumbongLLLLLFRR25","conf/cvpr/LiHNLHJLYRDYY025","conf/cvpr/LiSHDQLSS25","conf/cvpr/LiangMWCSZTLD25","conf/cvpr/LiuCC0OZLSCL25","conf/cvpr/MuCCPLGLYZXLXDL25","conf/cvpr/Sun0X00QL025","conf/cvpr/SunHL0XLL25","conf/cvpr/WangR0HGYZFL25","conf/cvpr/WuCWMLPLXYR025","conf/cvpr/YangZ000025","conf/eccv/BahmaniLYSRLLPTWTL24","conf/eccv/ChenGXWYRWLLL24","conf/eccv/JinLLLQL24","conf/eccv/JinYXLQWL24","conf/eccv/LiSWXFZYXLL24","conf/eccv/MuCPCGZLXL24","conf/eccv/SimaRCCZXBLGL24","conf/eccv/WangLHHLOB24","conf/eccv/YaoJXZLQLW24","conf/eccv/ZhangSCXSZLCL24","conf/eccv/ZhangZJQLL24","conf/eccv/ZhuWZCL24","conf/iccv/ChenGTLGDSL25","conf/iccv/FangDWLHTZZDLL25","conf/iccv/GeCLZLDZ25","conf/iccv/HaoYZWWKYFYQMSCZZZSLN25","conf/iccv/HuangZWHL25","conf/iccv/JiZWZCGSCSXHL25","conf/iccv/LuSLDMLCHZL25","conf/iccv/LuWXJSZLL25","conf/iccv/QinKSYLLZB25","conf/iccv/WangKYCWZXLWLZZSLL25","conf/iccv/WangLTZRFL25","conf/iccv/XiongLHFL25","conf/iccv/YuQWWZL25","conf/iccv/ZhuWZPL25","conf/iclr/JiZWSC0YY025","conf/iclr/LinLSYZ00Z25","conf/iclr/MengW0L0YLZD00Z25","conf/iclr/TengSLND0LL25","conf/iclr/YangZZB00S25","conf/icml/GuoZYY0GS0L025","conf/icml/Liao0Z0Z25","conf/icml/MengLTLSZ0L025","conf/icml/QinSYWZLYLSS0Z25","conf/icra/LongRSWHLP25","conf/kdd/Hu0XSLLLR25","conf/mm/XuHS0WQYL25","conf/naacl/WuLGGLWSL25","conf/nips/ChenCCZWZL25","conf/nips/ChenLDWHMWDLSS25","conf/nips/ChenPZSLW25","conf/nips/ChuHCZXxWYLZLZY25","conf/nips/FangDWHLTYYZDLL25","conf/nips/HuZFNYXSJLZWYGL25","conf/nips/LinZXMLWP25","conf/nips/LiuDCWGHXCLY25","conf/nips/LvLTLYL25","conf/nips/TengWLCSWLLZL25","conf/nips/WangLLZSKWLL25","conf/nips/YueWWZLOBZ25","conf/siggrapha/YangZGZHLXLCL25","conf/siggrapha/YuBQL000L25","journals/chinaf/LiHWLWLWWQ25","journals/csur/SunZXLCQXDLGWWCYRFHYLLL25","journals/cvm/LiuLLLW25","journals/ijcv/WangWXQSWL25","journals/ijcv/XuHWL25","journals/pami/HuangDSXLL25","journals/pami/XuSZGLLMHQL25","journals/pami/YanCZYXYZCSSLQCY25","journals/spl/ZhangLQXZ25","journals/tbd/ShaoLHGXZMHLQL25","journals/tifs/ZhangSLMLQZZ25","journals/tmlr/XiongLHWW0YSWHT25","journals/tvcg/LiuLLWLLW25","journals/tvcg/XieZWWWLGLW25"]},{"id":"team-64","labName":null,"labUrl":null,"memberIndices":[64],"label":"刘烨斌 及合作者","sharedLab":false,"count2025":17,"conference2025":9,"journal2025":8,"knownMinimum2025":null,"sourceWarning":false,"preprint2025":18,"knownPreprintMinimum2025":null,"arxivIds":["2503.00382","2503.21847","2505.15800","2506.01579","2506.02444","2506.06645","2506.09565","2506.14135","2507.04258","2507.23143","2508.00298","2508.14036","2509.00403","2511.22704","2512.03034","2512.03918","2512.07381","2512.17717"],"paperKeys":["conf/cvpr/LyuZG0CL0025","conf/cvpr/PangSZT0Z0L25","conf/cvpr/TuLZZZZWL25","conf/eccv/ChenZLXL24","conf/eccv/XuWZSL24","conf/iccv/LiaoTPZZL25","conf/iccv/ZhangLZPWLL25","conf/iclr/ZhaoXSXZ0LSL25","conf/nips/DangSZMLW25","journals/pami/TangZLH25","journals/pami/WuZFLC25","journals/pami/ZhangZZZZSHL25","journals/tmm/LuoDYMXCGL25","journals/tog/ShaoXSYZCLW25","journals/tvcg/ZhangZZZLL25","journals/tvcg/ZhouLCCZYL25","journals/tvcg/ZhouYZWZJFL25"]},{"id":"team-65","labName":"Intelligent Graphics Lab","labUrl":"https://github.com/IGL-HKUST","memberIndices":[65],"label":"Intelligent Graphics Lab","sharedLab":false,"count2025":40,"conference2025":28,"journal2025":12,"knownMinimum2025":null,"sourceWarning":true,"preprint2025":28,"knownPreprintMinimum2025":null,"arxivIds":["2501.03847","2501.09978","2502.01045","2502.11697","2502.20732","2503.20644","2503.23162","2504.04294","2505.07003","2505.12703","2506.07020","2506.24113","2507.11949","2507.18939","2507.21045","2509.00066","2509.07552","2509.12721","2509.14981","2509.19995","2509.20358","2509.21965","2510.07723","2511.01767","2511.11175","2511.21978","2512.08358","2512.22808"],"paperKeys":["conf/3dim/LiuLLZLYT25","conf/cvm/SunSLMY25","conf/cvpr/LiLLLZWLWG25","conf/cvpr/LiZLY0QCXCXLG25","conf/cvpr/LiuLY0HTMW25","conf/cvpr/LuHLDLC0YWL25","conf/eccv/ChenPYLPLZ24","conf/eccv/LiuDZLZZYWHLCL24","conf/eccv/WangLDYLLXSLW24","conf/eccv/XuLZLCDY24","conf/eccv/YuDLLLLMKHTLW24","conf/eccv/ZhouDCLWWLKWL24","conf/iccv/RenZXPLWZL25","conf/iccv/WangLLWDY25","conf/iccv/ZhangTHPGLHYZLCY25","conf/iclr/Huang0Z0DY25","conf/iclr/Li0CLDMYLW0Y25","conf/iclr/Liu00L0WH25","conf/iclr/WuD0S0Y0LCKGTWL25","conf/nips/ChenLZZLZDWL25","conf/nips/LuXDLHDLYL25","conf/nips/WangCHDLGL25","conf/nips/XuDSPHWLLMWK25","conf/siggraph/GuYLLDS0L000025","conf/siggraph/LiMC000LS0G25","conf/siggraph/Wang000DLGK0025","conf/siggrapha/Zhang00WYSY0025","conf/wacv/0001S0MY25","journals/cvm/LiuLLLW25","journals/pami/YangZWMHLW25","journals/ral/LuZWRLDY25","journals/tmi/LiuFLWLSC25","journals/tog/DongWXLLXZLTKKSW25","journals/tog/DongXDXLCXTKW25","journals/tog/DouPLYFLWGLK25","journals/tvcg/0049GLLL25","journals/tvcg/LiLLLLLLWG25","journals/tvcg/LinYLZHJKKW25","journals/tvcg/LiuLLWLLW25","journals/tvcg/WangDL0DGZ00G25"]},{"id":"team-66","labName":"Generative Intelligence Lab (GenLab)","labUrl":"https://thegenlab.ai/","memberIndices":[66],"label":"Generative Intelligence Lab (GenLab)","sharedLab":false,"count2025":3,"conference2025":3,"journal2025":0,"knownMinimum2025":null,"sourceWarning":false,"preprint2025":1,"knownPreprintMinimum2025":null,"arxivIds":["2506.09998"],"paperKeys":["conf/cvpr/BianXX00LB025","conf/iclr/LiuXLBZ25","conf/iclr/QiuLF0XCTWBS25"]},{"id":"team-67","labName":"3D Vision Lab","labUrl":"https://www.xxlong.site/group.html","memberIndices":[67],"label":"3D Vision Lab","sharedLab":false,"count2025":21,"conference2025":16,"journal2025":5,"knownMinimum2025":null,"sourceWarning":false,"preprint2025":19,"knownPreprintMinimum2025":null,"arxivIds":["2502.20732","2503.05689","2503.23162","2505.18078","2506.21319","2506.24113","2507.00917","2507.07997","2507.14501","2507.18939","2509.03887","2509.09676","2510.07729","2511.01767","2511.02483","2511.05038","2511.20565","2512.04939","2512.22808"],"paperKeys":["conf/aaai/HanZLWX25","conf/cvpr/ChenZLLLLLLFT25","conf/cvpr/LiLLLZWLWG25","conf/cvpr/LiLYCLCTL25","conf/cvpr/LiuLY0HTMW25","conf/cvpr/Wang0LLHL25","conf/cvpr/XingZHJHZLY25","conf/eccv/FuYHWMTSLL24","conf/eccv/JinZLLZHLZYSZJLCZ24","conf/eccv/RenHYLSM24","conf/eccv/YuDLLLLMKHTLW24","conf/iccv/DengYGZHRLT25","conf/iccv/ZhangTHPGLHYZLCY25","conf/icra/WangYLZXGZ25","conf/iros/WangZXGGHSZLY25","conf/siggraph/Wang000DLGK0025","journals/cvm/LiuLLLW25","journals/tvcg/0049GLLL25","journals/tvcg/LaiHGCPLLLG25","journals/tvcg/LiLLLLLLWG25","journals/tvcg/LiuLLWLLW25"]},{"id":"team-68","labName":"Machine Vision and Intelligence Group (MVIG)","labUrl":"https://www.mvig.org/","memberIndices":[68],"label":"Machine Vision and Intelligence Group (MVIG)","sharedLab":false,"count2025":51,"conference2025":42,"journal2025":9,"knownMinimum2025":null,"sourceWarning":false,"preprint2025":32,"knownPreprintMinimum2025":null,"arxivIds":["2502.16420","2503.02881","2503.03081","2503.06677","2503.13217","2503.23348","2504.02312","2504.04170","2504.04573","2504.13175","2505.01396","2505.22159","2506.01551","2506.02860","2506.08334","2506.21057","2507.02600","2507.21545","2508.07770","2508.14441","2509.11839","2509.15953","2509.17141","2509.17450","2509.19292","2509.21242","2510.02298","2510.07975","2511.05996","2511.17059","2511.17898","2512.10946"],"paperKeys":["conf/aaai/0003LXWCL25","conf/aaai/LiuW0ZFLMC025","conf/cvpr/0002LZCL025","conf/cvpr/BianXX00LB025","conf/cvpr/ChenLLTGL025","conf/cvpr/ZhangXWYYLLWL25","conf/eccv/LiWYLD24","conf/eccv/LiYRZMLKI24","conf/eccv/LiuHYLL24","conf/eccv/LiuLZZYL24","conf/eccv/XuLCWLTT24","conf/eccv/XuLYLL24","conf/eccv/YouXYHZSFHGL24","conf/eccv/ZhangCLXLL24","conf/icassp/YuHYZ0HAL25","conf/iccv/SuZFXFLLY25","conf/iccv/SunLWXWZL25","conf/iccv/YuXXLAZL25","conf/iclr/0002LLH0L25","conf/iclr/0003LCL25","conf/iclr/LiLCZGL025","conf/icra/ChenFFL25","conf/icra/ChenXZFL25","conf/icra/LiuWWWL25","conf/icra/LuoPLHDLL25","conf/icra/XiaFLF25","conf/icra/YuHYJHLCWLLGL25","conf/iros/ChenSLHQZYOSQLS25","conf/iros/JinLJL25","conf/iros/JinLYFLL25","conf/iros/LiHYJHZLGL25","conf/iros/LiZXTL25","conf/iros/MiaoLFJL25","conf/iros/QianZWLL25","conf/iros/TangLXL25","conf/iros/YanFL25","conf/iros/YanWFYL25","conf/iros/YuYJCZHYCMLL25","conf/nips/TangHHXLC25","conf/nips/WuLLHSYWL25","conf/nips/YeXLC25","conf/nips/YuLYRHDHHSCZL25","journals/ijrr/FirooziTTMSLZSKHIDWLS25","journals/ijrr/LvFZZSL25","journals/pami/LiBXCYL25","journals/pami/PangWLL25","journals/pami/QuZRLCTJ25","journals/pami/YangZZZKXL25","journals/ral/HeFCFL25","journals/ral/SuZFLLY25","journals/ral/ZhangXYXTL25"]},{"id":"team-70","labName":"4DV Lab","labUrl":"https://yuexinma.me/team.html","memberIndices":[70],"label":"4DV Lab","sharedLab":false,"count2025":null,"conference2025":null,"journal2025":null,"knownMinimum2025":null,"sourceWarning":true,"preprint2025":null,"knownPreprintMinimum2025":null,"arxivIds":[],"paperKeys":[]},{"id":"team-71","labName":"ScaleLab","labUrl":"https://scalelab-sjtu.github.io/","memberIndices":[71],"label":"ScaleLab","sharedLab":false,"count2025":18,"conference2025":17,"journal2025":1,"knownMinimum2025":null,"sourceWarning":false,"preprint2025":27,"knownPreprintMinimum2025":null,"arxivIds":["2501.09218","2502.13092","2502.21257","2503.01439","2503.06669","2503.09366","2503.22942","2504.03515","2504.13059","2505.14030","2505.15679","2506.04217","2506.18088","2506.23351","2507.02600","2507.20622","2507.21610","2508.02629","2508.05976","2508.20072","2509.09674","2509.23823","2510.11027","2510.13778","2510.14300","2510.20774","2512.00975"],"paperKeys":["conf/acl/HuCC0S025","conf/acl/HuCZLCL00SL25","conf/cvpr/ChenC0YHL0PZJ0Y25","conf/cvpr/ChenMLCPCXH00025","conf/cvpr/DingJHZW0025","conf/cvpr/JiTSHZZWZ0AXSL025","conf/cvpr/LiangMWCSZTLD25","conf/cvpr/MuCCPLGLYZXLXDL25","conf/eccv/MuCPCGZLXL24","conf/iccv/HaoYZWWKYFYQMSCZZZSLN25","conf/iccv/ZhuZPJM25","conf/iclr/ChenYZX0HSW0025","conf/iclr/Wen00K25","conf/iros/XiongMLFHL25","conf/iros/YuYJCZHYCMLL25","conf/ivs/WangLCJML25","conf/nips/ChenLDWHMWDLSS25","journals/tmlr/XiongLHWW0YSWHT25"]},{"id":"team-72","labName":null,"labUrl":null,"memberIndices":[72],"label":"裴文杰 及合作者","sharedLab":false,"count2025":12,"conference2025":10,"journal2025":2,"knownMinimum2025":null,"sourceWarning":false,"preprint2025":7,"knownPreprintMinimum2025":null,"arxivIds":["2503.08387","2503.14824","2504.11879","2506.07358","2506.23120","2507.16310","2510.20217"],"paperKeys":["conf/cvpr/FangLWZYLP25","conf/cvpr/SunZJ0YLP25","conf/eccv/SunLTPC24","conf/eccv/WuFLZCLP24","conf/eccv/WuTLLP24","conf/iccv/LiuSXGCP25","conf/iccv/NingTSLHPJ25","conf/iccv/PeiTLTY25","conf/nips/WangCYLP25","conf/prcv/ChenPLL24","journals/tnn/XuPWPLX25","journals/tnn/ZhouMPWWH25"]},{"id":"team-73","labName":"Computational Imaging & Mixed Representation Laboratory (WeLight@HKU)","labUrl":"https://hku.welight.fun/","memberIndices":[73],"label":"Computational Imaging & Mixed Representation Laboratory (WeLight@HKU)","sharedLab":false,"count2025":11,"conference2025":6,"journal2025":5,"knownMinimum2025":null,"sourceWarning":false,"preprint2025":4,"knownPreprintMinimum2025":null,"arxivIds":["2504.07025","2507.22523","2507.23704","2508.18071"],"paperKeys":["conf/cvpr/LiuO0AH025","conf/cvpr/Wu0H025","conf/ismar/LiBZSXP25","conf/siggrapha/ShenQLH025","conf/siggrapha/ShengHZH0LZZ0W025","conf/siggrapha/ZhouML025","journals/tog/DaiZDXPDSYLLX25","journals/tog/LiuHPW25","journals/tog/WuYZYPPWH25","journals/tvcg/DaiTYPZQ25","journals/tvcg/XiaMTMZY025"]},{"id":"team-74","labName":null,"labUrl":null,"memberIndices":[74],"label":"彭思达 及合作者","sharedLab":false,"count2025":33,"conference2025":30,"journal2025":3,"knownMinimum2025":null,"sourceWarning":false,"preprint2025":21,"knownPreprintMinimum2025":null,"arxivIds":["2501.07556","2502.05857","2502.08556","2502.20370","2503.03222","2503.14483","2503.15451","2504.00437","2504.07955","2504.11443","2506.05348","2507.11540","2507.13344","2508.13104","2509.07978","2510.01669","2510.07316","2510.15800","2511.14223","2512.20617","2512.22745"],"paperKeys":["conf/cvm/SuPKHH25","conf/cvpr/GuoZPLYXWZB25","conf/cvpr/LinPCPSLBFZK25","conf/cvpr/WangYXSZCBPZ25","conf/cvpr/XieCXXJSPBZ25","conf/cvpr/Yan0LJGWZLB0P25","conf/cvpr/ZhouFPYZCXZ25","conf/eccv/ChenPYLPLZ24","conf/eccv/DongFHXWPD24","conf/eccv/GuoZPWSHZ24","conf/eccv/HeCPHLHYOH24","conf/eccv/HuZLLPZFY24","conf/eccv/LiuLLYPCQHLO24","conf/eccv/XuSWCYPSW24","conf/eccv/YanLZWSZLZP24","conf/iccv/CaoWFBZP25","conf/iccv/ChenWTMHOZBP25","conf/iccv/GuoPSSHWDHKPZ25","conf/iccv/HeXXZP25","conf/iccv/JinPWXXYSBZ25","conf/iccv/SunYWXLWZBZP25","conf/iccv/TanHPGZSHSBZ25","conf/iccv/WangWGPQBZH25","conf/iccv/XiaoLPFPZFZPW25","conf/iccv/YuHZYYHSZZP25","conf/iclr/CenPPSSB0H25","conf/iclr/FuLWPXSY0ZL25","conf/iclr/WangZPHGSB025","conf/ijcai/TangWCWPXO25","conf/nips/XuLLWYZPCSWCYPY25","journals/cg/ShenTuZXSCPZ25","journals/pami/GaoYKPLT25","journals/tog/HuYLWDDZJBZP25"]},{"id":"team-75","labName":"Computer Vision and Machine Intelligence Lab (CVMI Lab)","labUrl":"https://cvmi.hku.hk/","memberIndices":[75],"label":"Computer Vision and Machine Intelligence Lab (CVMI Lab)","sharedLab":false,"count2025":43,"conference2025":37,"journal2025":6,"knownMinimum2025":null,"sourceWarning":false,"preprint2025":39,"knownPreprintMinimum2025":null,"arxivIds":["2502.20321","2503.06960","2503.08037","2503.08038","2503.08685","2503.10604","2503.12015","2503.15208","2505.13031","2505.24521","2506.01701","2506.13151","2507.01027","2507.02358","2507.04285","2507.05819","2507.07966","2507.08441","2507.10548","2507.12384","2507.14503","2508.06350","2508.08048","2508.11256","2508.14395","2508.14648","2509.03516","2509.11287","2509.12812","2510.10584","2510.10962","2510.11696","2511.22609","2512.00771","2512.04519","2512.04786","2512.09364","2512.20557","2512.22374"],"paperKeys":["conf/cvpr/0004ZCP025","conf/cvpr/HanHSZSZZ0L025","conf/cvpr/HuangLSYLCQ25","conf/cvpr/LiGLZDCZTZW0Z0Z25","conf/cvpr/YuWK0CLL025","conf/cvpr/Zhao0LMY025","conf/dac/LiYFWDLSYWQZW25","conf/dac/LinLLYHLSCQW25","conf/eccv/LiuLLYPCQHLO24","conf/eccv/LiuWZCQ24","conf/eccv/MaJWYQ24","conf/eccv/MaZCQYLLLQSH24","conf/eccv/WuSCZWLQ24","conf/eccv/YangDBQX24","conf/emnlp/LuZYGZQLH25","conf/iccv/ChangLLLHTWZQ25","conf/iccv/ChenLFLCZFQW25","conf/iccv/GuoDCCLZLTQLZ25","conf/iccv/WenZEDQ25","conf/iccv/WuTCZLYQJ25","conf/iccv/XiePLHHQ25","conf/iccv/ZhaoLWTQ25","conf/iccv/ZhengWZDWZQ25","conf/iclr/0003TXFDF0025","conf/iclr/HuangLLHTZ00025","conf/iclr/TanWHZ025","conf/icml/0042QL0L0BMZ025","conf/iros/DingQZJYYQW25","conf/nips/ChenHSHYZLMKQLY25","conf/nips/MaJWYYYPQ25","conf/nips/TanWWZCSSQ25","conf/nips/WuTLZQYJ25","conf/nips/WuYLHWZWQ25","conf/nips/XiaoSCLCGHLQS25","conf/nips/ZhengWZMWYZQ25","conf/siggrapha/YuanYSGCLQ25","conf/uist/ZhaoJZCCDJQQN25","journals/access/WangWLQS25","journals/aisy/HuangFWWQZ25","journals/aisy/HuangPBCQZ25","journals/ncs/LinWLWSHZYZZWWCJZLXQWSL25","journals/ncs/XuWHLZYQWXSLML25","journals/tvcg/DaiTYPZQ25"]},{"id":"team-76","labName":"Visual Information Processing and Learning (VIPL)","labUrl":"https://vipl.ict.ac.cn/en/","memberIndices":[76],"label":"Visual Information Processing and Learning (VIPL)","sharedLab":true,"count2025":48,"conference2025":29,"journal2025":19,"knownMinimum2025":null,"sourceWarning":false,"preprint2025":33,"knownPreprintMinimum2025":null,"arxivIds":["2502.04684","2502.13433","2503.06236","2503.08977","2503.12955","2503.16566","2503.17724","2503.19369","2504.17253","2504.20518","2505.17659","2505.19084","2505.24517","2506.00925","2507.19024","2508.09584","2508.10268","2508.13692","2509.04823","2509.16031","2509.23635","2510.19484","2510.20134","2510.24717","2511.13420","2511.20223","2512.00343","2512.06885","2512.14320","2512.14333","2512.14341","2512.19022","2512.23953"],"paperKeys":["conf/cvpr/GuoLZZS25","conf/cvpr/LiH0S025","conf/eccv/HuLCMSC24","conf/eccv/PanTWS24","conf/eccv/WangZSC24","conf/eccv/ZhangKSC24","conf/emnlp/WangZYHSZ25","conf/fgr/HanH0S25","conf/fgr/LuoYS025","conf/iccv/CaiHWSC25","conf/iccv/LiuGCLSC25","conf/iccv/QiuKZS25","conf/iccv/WangYSC25","conf/iccv/XueKSC25","conf/iccv/YuanYSC25","conf/iccv/ZhaoHTCS25","conf/iclr/DengPDLCLSQW25","conf/iclr/XuHS025","conf/iclr/ZhangWL0YS025","conf/icml/0022H0S025","conf/icpr/XuKJBSC24","conf/iros/LiangKSC25","conf/mm/YanCM0WWS25","conf/nips/LiZCHSC25","conf/nips/LiangHHCSC25","conf/nips/LiuCGCTSC25","conf/nips/YangCHSC25","conf/repss/YangZYLGDSZHL25","conf/wacv/ZhangHKS25","journals/chinaf/PanTWLS25","journals/pami/LiCSC25","journals/pami/LiSCSS25","journals/pami/LongZS25","journals/pami/XieHSC25","journals/pami/ZhangYCZHSG25","journals/pr/ShiZJBS25","journals/pr/SunHSH25","journals/pr/YuanZS25","journals/prl/HuCSC25","journals/taffco/ChenLSWH25","journals/taffco/LiuWLCCTCS25","journals/taffco/ZengYQCSGHLZLSC25","journals/tase/KanZLZFLSC25","journals/tifs/LongZS25","journals/tifs/ZhangWHLWS25","journals/tip/LiLCDZZSG25","journals/tip/YuanZSC25","journals/tmm/ZhaoHCGMSC25"]},{"id":"team-78","labName":null,"labUrl":null,"memberIndices":[78],"label":"盛律 及合作者","sharedLab":false,"count2025":17,"conference2025":12,"journal2025":5,"knownMinimum2025":null,"sourceWarning":false,"preprint2025":17,"knownPreprintMinimum2025":null,"arxivIds":["2501.12612","2503.05127","2503.12590","2506.04308","2506.09740","2506.16402","2506.18315","2506.19851","2507.09955","2508.19247","2509.17757","2510.07181","2511.13488","2511.22659","2512.13660","2512.20936","2512.23573"],"paperKeys":["conf/cvpr/HuangGAY0ZLLCS25","conf/cvpr/LiSHDQLSS25","conf/cvpr/WenH0CS25","conf/cvpr/ZhouSC0W0S025","conf/iccv/HuangGWYMCS25","conf/icml/QinSYWZLYLSS0Z25","conf/iros/ChenSLHQZYOSQLS25","conf/iros/ZhouQYSHZSS25","conf/mm/Fan0CHWS25","conf/nips/HeCSYSS25","conf/nips/ZhouACHRZWWHSZ25","conf/siggrapha/HuangFSGCS25","journals/ieeejas/XiongWCSXLXCHT25","journals/ijcv/ZhangSZHYWSQSL25","journals/tip/FanHWCYS25","journals/tip/WangLZXZYSX25","journals/tnn/XuYZSRST25"]},{"id":"team-79","labName":"Camera Intelligence Lab","labUrl":"https://camera.pku.edu.cn/","memberIndices":[79],"label":"Camera Intelligence Lab","sharedLab":false,"count2025":43,"conference2025":32,"journal2025":11,"knownMinimum2025":null,"sourceWarning":false,"preprint2025":24,"knownPreprintMinimum2025":null,"arxivIds":["2502.19125","2504.07758","2504.12401","2505.16797","2505.18699","2505.22016","2505.22394","2506.08003","2506.18882","2507.05728","2507.11931","2507.17268","2507.18060","2507.21572","2508.10582","2508.13503","2509.19726","2510.16791","2511.18287","2512.03044","2512.10571","2512.11510","2512.12372","2512.17376"],"paperKeys":["conf/aaai/HuangLLQSX25","conf/aaai/XiaZZXS25","conf/aaai/ZhouXS25","conf/cvpr/0016ADSWSTPGLYL25","conf/cvpr/CaiWXS25","conf/cvpr/GaoDLTC0S25","conf/cvpr/TangF0TLCHCWS25","conf/cvpr/WengZZHJ0S25","conf/cvpr/Yu0SS25","conf/cvpr/YuLW0SSS25","conf/cvpr/ZhouZL0MSS25","conf/eccv/HongZWLS24","conf/eccv/LuoSLW24","conf/eccv/YangHCFYS24","conf/iccad/WeiTFSWL25","conf/iccv/HanTGLLSJM25","conf/iccv/LiangYYZRDS25","conf/iccv/TengLYZCRS25","conf/iccv/WangDSW25","conf/iccv/XuZSXW25","conf/iccv/YangLHXCYS25","conf/iccv/YangZZWZRS25","conf/iccv/ZhangLGLMS25","conf/iccv/ZhouDXXS25","conf/iccv/ZhouYLGSS25","conf/iccv/ZhuFZCZXS25","conf/mm/00010ZSS25","conf/nips/LiDHZXS25","conf/nips/LouLTWS25","conf/nips/WengZCLSW25","conf/nips/XiaWYLZTJJS25","conf/wacv/Yin000S25","journals/aisy/RenDDZGSZG25","journals/ijcv/LinWZSYHXY25","journals/ijcv/ZhouTZXSS25","journals/pami/DuanLYLTZMS25","journals/pami/JuSWLJK25","journals/pami/LuoRSGLW25","journals/pami/WeiLDSJPCZ25","journals/pami/WengGZWLS25","journals/tcsv/FanGDXS25","journals/tcsv/HuangLLSXC25","journals/tcsv/WuZWSL25"]},{"id":"team-80","labName":null,"labUrl":null,"memberIndices":[80],"label":"宋杰 及合作者","sharedLab":false,"count2025":11,"conference2025":10,"journal2025":1,"knownMinimum2025":null,"sourceWarning":false,"preprint2025":9,"knownPreprintMinimum2025":null,"arxivIds":["2501.02771","2501.10283","2501.12289","2504.01358","2504.05287","2504.13167","2506.01950","2507.23597","2508.05506"],"paperKeys":["conf/cvpr/ZhangKX0O25","conf/cvpr/ZhengXZ025","conf/eccv/GuoJKZVSH24","conf/eccv/JiangBMZEOPHKS24","conf/eccv/LuDSH24","conf/eccv/XueGZWJHKSH24","conf/eccv/ZhangCFHS24","conf/iccv/DongDSBG25","conf/iccv/WangHPGFS25","conf/siggrapha/JiangHK025","journals/ral/HuangZWCS25"]},{"id":"team-81","labName":"智能技术与系统实验室","labUrl":"https://ai.cs.tsinghua.edu.cn/","memberIndices":[81],"label":"智能技术与系统实验室","sharedLab":true,"count2025":30,"conference2025":15,"journal2025":15,"knownMinimum2025":null,"sourceWarning":false,"preprint2025":28,"knownPreprintMinimum2025":null,"arxivIds":["2501.15420","2501.19040","2502.07279","2502.09923","2502.19127","2503.16975","2505.04662","2505.17646","2506.01616","2506.12336","2506.12382","2506.13120","2506.23844","2507.12768","2507.12898","2507.18484","2507.22428","2507.22446","2507.23523","2508.15370","2508.17198","2509.01909","2509.16117","2509.24393","2511.07480","2512.00412","2512.13030","2512.17661"],"paperKeys":["conf/eccv/KangDWRCSW24","conf/eccv/KongCWSHYL24","conf/eccv/LiuCLZLRZYSZZGL24","conf/eccv/LiuZRLZYJLYSZZ24","conf/eccv/RuanDLHSW24","conf/eccv/WangWCXCYLSZ24","conf/emnlp/ZhangZDS25","conf/iccv/RuanLHWKSDW25","conf/iclr/ChenSSZ25","conf/iclr/LiuWLTCWX0025","conf/icml/ChenJZ00025","conf/icml/ChengLWHZH025","conf/icml/Zeng0WL25","conf/ijcai/ZhouY00025","conf/naacl/ChenYFTDYS25","journals/ijcv/LiuDXYSZCHXZ25","journals/ijcv/YangXPDWSZ25","journals/jvcir/LiuXHXZS25","journals/pami/WangXZSZ25","journals/pami/WeiKDWRCS25","journals/pami/WeiRDSC25","journals/pami/YangWWYSZ25","journals/prl/LiuXDZWDZS25","journals/prl/ZhuYSZ25","journals/tbd/ChenZYYHXQS25","journals/tbd/ZhuYSZZ25","journals/tdsc/YinZSPLL25","journals/tip/ZhouSWH25","journals/tits/QianHYCZSZ25","journals/tmm/WangHDZSH25"]},{"id":"team-82","labName":"STAIR Lab, Fudan University","labUrl":null,"memberIndices":[82],"label":"STAIR Lab, Fudan University","sharedLab":false,"count2025":24,"conference2025":17,"journal2025":7,"knownMinimum2025":null,"sourceWarning":true,"preprint2025":null,"knownPreprintMinimum2025":11,"arxivIds":["2502.12724","2503.01837","2503.11999","2503.20208","2505.05753","2509.05595","2509.11417","2510.25765","2511.01177","2511.11563","2511.16659"],"paperKeys":["conf/aaai/MuLSYYLS25","conf/acl/GaoPLCYHFSK0TLY25","conf/eccv/XuLCLSSL24","conf/eccv/ZhangWZGGJSG24","conf/iclr/0001VSL0025","conf/iclr/Liu0025a","conf/iclr/ShuklaTS25","conf/iclr/YuanMTFZ025","conf/iclr/ZhouGCXS25","conf/icml/Escoriza0TM025","conf/icml/LiH025a","conf/iros/ShiLZAHS25","conf/nips/WangTHLSHBHSPSP25","conf/siggrapha/0003LW0L25","conf/siggrapha/WangWSZ0L25","conf/siggrapha/YuanSWZSL25","conf/wacv/WeiXBCSX025","journals/cgf/OhYWSXLS25","journals/scirobotics/AiTSWPTCSWL25","journals/tmlr/ChenYM025","journals/tog/LanLYXSWJY25","journals/tog/LiuXYTXWSS25","journals/tog/YangDLZSCXS25","journals/tog/YuanXYS25"]},{"id":"team-83","labName":"Sun’s Lab","labUrl":"https://sites.google.com/site/sunkurt/","memberIndices":[83],"label":"Sun’s Lab","sharedLab":false,"count2025":12,"conference2025":6,"journal2025":6,"knownMinimum2025":null,"sourceWarning":false,"preprint2025":4,"knownPreprintMinimum2025":null,"arxivIds":["2504.09997","2509.02055","2509.24413","2512.03548"],"paperKeys":["conf/acl/YanLZ0G25","conf/iros/JiS25","conf/iros/WangQGJS25","conf/iros/XuSW25","conf/rcar/ChenQLJS25","conf/rcar/WeiWHWZSCJ25","journals/bib/XieGZLCHLTSLYC25","journals/jfr/WanZWWLCDHSZJ25","journals/tie/JiGXS25","journals/tnn/ZhuBYLSMC25","journals/trob/GaoJSXRS25","journals/tsmc/WangLSX25"]},{"id":"team-84","labName":null,"labUrl":null,"memberIndices":[84],"label":"谭平 及合作者","sharedLab":false,"count2025":16,"conference2025":12,"journal2025":4,"knownMinimum2025":null,"sourceWarning":false,"preprint2025":19,"knownPreprintMinimum2025":null,"arxivIds":["2501.02831","2501.09978","2503.18007","2505.02094","2505.07747","2505.22394","2505.23253","2506.01337","2506.07491","2506.21076","2507.07997","2508.13488","2508.17972","2509.06285","2509.14981","2510.04111","2511.20565","2512.10957","2512.19583"],"paperKeys":["conf/3dim/FangDLHST25","conf/3dim/LiuLLZLYT25","conf/aaai/QuML0MWZ0T25","conf/aaai/YanLLLT25","conf/cvpr/ChenZLLLLLLFT25","conf/cvpr/LiLYCLCTL25","conf/cvpr/WangZ0TZLLY0C0Z25","conf/eccv/ChenXLLLFTL24","conf/eccv/FuYHWMTSLL24","conf/iccv/DengYGZHRLT25","conf/nips/MaoZFZTZTZ25","conf/siggraph/0003WZT00025","journals/pami/LiuZLTZ25","journals/ral/HuWJYJJZHT25","journals/tim/HuWXZJQJTZ25","journals/tvcg/FengKPDYTZW25"]},{"id":"team-85","labName":"Freedom AI","labUrl":"https://freedomintelligence.github.io/","memberIndices":[85],"label":"Freedom AI","sharedLab":false,"count2025":37,"conference2025":34,"journal2025":3,"knownMinimum2025":null,"sourceWarning":false,"preprint2025":41,"knownPreprintMinimum2025":null,"arxivIds":["2501.00353","2501.05727","2501.14492","2502.00271","2502.01085","2502.01506","2502.11155","2502.11812","2502.12900","2502.13894","2503.02875","2503.05085","2503.08292","2503.21776","2505.07787","2505.11175","2505.15333","2505.18562","2505.24428","2506.01111","2506.09820","2506.09968","2506.12860","2506.18095","2507.05675","2508.05132","2508.13618","2508.14706","2508.18240","2508.21148","2509.09174","2509.09307","2510.00032","2510.03659","2510.04204","2510.11040","2510.20342","2510.20513","2510.22758","2511.14783","2512.11558"],"paperKeys":["conf/acl/CaiCWWDSCZW25","conf/acl/ChenCJWLWW25","conf/acl/ChenGGJWWW25","conf/acl/JiCGXWW25","conf/acl/ZhangLBZW025","conf/acl/ZhangMKLSWXH0Z25","conf/acl/ZhuHLLTAA0HWYCM25","conf/coling/SongWCWGW25","conf/emnlp/ChenGJHGYW25","conf/emnlp/DaiZWL25","conf/emnlp/LaiZCLYLHW25","conf/emnlp/LiuCJZCW25","conf/emnlp/SongLWCSW25","conf/emnlp/WangLWHZ25","conf/emnlp/WangSCCCZSW25","conf/iclr/Gao0YCMDLMCXTWZ25","conf/iclr/ZhengWL0ZW25","conf/icml/WangHDCWZ25","conf/icra/QinSHWZ25","conf/mm/XiaoLPZZHLCTW25","conf/naacl/ChenLW25","conf/naacl/ChenghaoZhuCGZTW25","conf/naacl/GanFZLJWCCXHW25","conf/naacl/GeCCCCCXYCLSWGZLWW25","conf/naacl/HuangSHGW25","conf/naacl/WangLCZWZXCFWGW25","conf/naacl/YangZHGGHLZWXHYW25","conf/nips/FengGLGWPWZWY25","conf/nips/JiXLLHLCCWTMY25","conf/nips/LiTLXBDSWWLL25","conf/nips/LiuXYLJCSWXW25","conf/nips/YangZWZZYHW25","conf/uai/LiuLLYW25","conf/www/ChengZJW025","journals/ior/HuangTHJZGWW25","journals/nn/ZhangWWTLWQ25","journals/tmlr/LiDTWZHHHHZGCWCDLSWLW25"]},{"id":"team-86","labName":"多模态人工智能系统全国重点实验室","labUrl":null,"memberIndices":[86],"label":"多模态人工智能系统全国重点实验室","sharedLab":true,"count2025":null,"conference2025":null,"journal2025":null,"knownMinimum2025":27,"sourceWarning":true,"preprint2025":null,"knownPreprintMinimum2025":null,"arxivIds":[],"paperKeys":["conf/cvpr/Yang0H0C0H25","conf/eccv/WangHHCLHZW24","conf/icb/MaZYLXCZWLWOLAWZXWWKGXB25","conf/iccv/ChenLHYCW25","conf/icmcs/ShiLLSHFZW25","conf/icpr/DuYWHW24","conf/itsc/LiZLLW25","conf/mm/00040YW0000025","conf/mm/Wang0LWHLW025","conf/mm/WuZCHZZ0025","journals/ijautcomp/Wu0SC0025","journals/ijcv/HuangHZWZW25","journals/pami/AnWWWHHW25","journals/pami/ChenAHXSLRW25","journals/pami/HuangWZHCW25","journals/ral/LiWHCWK25","journals/tbbis/Shen00H025","journals/tcsv/LiuZZLFW25","journals/tcsv/WangHGHHZW25","journals/tifs/HouWLWWH25","journals/tip/ZhengWWWC25","journals/titb/FanYHWYJ25","journals/tiv/ZhangCDW25","journals/tkde/HuSLWW25","journals/tkde/ZhangXZZWB25","journals/tmm/LiJZLMW25","journals/tnn/LuQLTW25"]},{"id":"team-87","labName":null,"labUrl":null,"memberIndices":[87],"label":"王立元 及合作者","sharedLab":false,"count2025":null,"conference2025":null,"journal2025":null,"knownMinimum2025":5,"sourceWarning":false,"preprint2025":null,"knownPreprintMinimum2025":5,"arxivIds":["2502.06192","2503.00677","2505.22306","2510.06842","2510.16914"],"paperKeys":["conf/eccv/ZhouWZSLLL24","conf/iclr/KangWZA25","conf/icml/SunYW0LZ25","journals/pami/WangXZSZ25","journals/tvcg/ZhouHWL25"]},{"id":"team-88","labName":"Spatial Intelligence Group（SIG）","labUrl":null,"memberIndices":[88],"label":"Spatial Intelligence Group（SIG）","sharedLab":false,"count2025":5,"conference2025":3,"journal2025":2,"knownMinimum2025":null,"sourceWarning":false,"preprint2025":3,"knownPreprintMinimum2025":null,"arxivIds":["2502.06093","2504.09975","2509.24150"],"paperKeys":["conf/siggraph/WeiWZCW25","conf/siggraph/ZhongWWLZ25","conf/siggrapha/WangTCW25","journals/cgf/XiongWZCLW25","journals/cvm/YangGXLPWTG25"]},{"id":"team-89","labName":"HUST Vision Lab","labUrl":"https://hustvl.github.io/","memberIndices":[89],"label":"HUST Vision Lab","sharedLab":false,"count2025":36,"conference2025":23,"journal2025":13,"knownMinimum2025":null,"sourceWarning":false,"preprint2025":39,"knownPreprintMinimum2025":null,"arxivIds":["2501.01423","2501.02962","2502.13144","2502.13145","2503.07608","2503.08686","2503.10322","2503.10596","2503.13440","2504.18318","2504.20438","2506.07497","2506.08052","2507.19493","2508.03643","2508.09136","2508.13515","2508.14153","2508.14814","2508.14892","2509.04406","2509.25079","2510.08562","2511.06245","2511.11077","2511.17300","2511.20410","2511.21475","2511.23386","2511.23469","2512.05060","2512.07745","2512.08829","2512.13687","2512.14480","2512.15713","2512.19331","2512.20344","2512.23421"],"paperKeys":["conf/aaai/LiaoWZZH25","conf/aaai/XuZ0W25","conf/cvpr/JiangLCWLS0W25","conf/cvpr/LiC00W25","conf/cvpr/LiaoCY0WYZLZZW25","conf/cvpr/YaoYW25","conf/cvpr/ZhuHLLYFW25","conf/eccv/ChenFHYZXWDXT24","conf/eccv/LiaoCJCZLHW24","conf/eccv/ShiCZLW24","conf/eccv/WangMZWFXX24","conf/eccv/WuHZW24","conf/eccv/XiongFWL24","conf/eccv/ZhuLGLWWHYY24","conf/iccv/HuZZCLLRCLW25","conf/iccv/LiLLW25","conf/iclr/LiCCSSR00W25","conf/iclr/ZhuWW25","conf/icmcs/DengXFWL25","conf/mm/ZhangWXW0025","conf/nips/GaoCJLSGPYLZZLZ25","conf/nips/GuoWXXZXXSWCYLW25","conf/nips/ZhaoHFW25","journals/ijcv/LiaoCZJZLHW25","journals/ijcv/ZhangCLWH25","journals/ijcv/ZhaoHZYDWWLF25","journals/ijcv/ZhuWFCLJZH25","journals/ijcv/ZouLZLW25","journals/ivc/ChenWCZHL25","journals/ivc/XiongFWWL25","journals/mva/ChengWLL25","journals/mva/HuWL25","journals/npjdm/YaoWSZMCLW25","journals/ral/ZhangYHWWZL25","journals/tcsv/LiuWWLB25","journals/titb/ZhangZZWZWL25"]},{"id":"team-90","labName":"龙岗区智能数字经济安全重点实验室（iDES）","labUrl":null,"memberIndices":[90],"label":"龙岗区智能数字经济安全重点实验室（iDES）","sharedLab":true,"count2025":18,"conference2025":12,"journal2025":6,"knownMinimum2025":null,"sourceWarning":false,"preprint2025":14,"knownPreprintMinimum2025":null,"arxivIds":["2501.06429","2502.05206","2502.12202","2502.18520","2504.16474","2504.16907","2505.08294","2505.11541","2505.12620","2506.22930","2508.04524","2509.24269","2510.22622","2512.05651"],"paperKeys":["conf/aaai/MaZZZWHHW25","conf/aaai/TanTLGWZW25","conf/acl/WangGWY25","conf/acl/WangWDY25","conf/cvpr/HuangHLH00W0C25","conf/icassp/ZengLLDWL25","conf/iccv/WangZOCTWW25","conf/iclr/YuanZWLW25","conf/icml/0002WJZLCYDW025","conf/mm/LiHWHLWC25","conf/nips/ChenYCZLW25","conf/wacv/LiLWWZD25","journals/ftsec/MaGWWWSDXCZHLWZZBLWQZHL25","journals/ijcv/WuCZZWYZWLS25","journals/pami/ZhengYZCW25","journals/tdsc/ZhuLWZWL25","journals/tfs/DaiZGWZ25","journals/tip/XiePLWZ25"]},{"id":"team-91","labName":null,"labUrl":null,"memberIndices":[91],"label":"吴桐 及合作者","sharedLab":false,"count2025":null,"conference2025":null,"journal2025":null,"knownMinimum2025":15,"sourceWarning":false,"preprint2025":null,"knownPreprintMinimum2025":12,"arxivIds":["2501.16330","2502.08590","2504.06232","2504.07083","2506.05210","2506.05284","2508.04700","2508.05609","2512.03036","2512.05076","2512.11799","2512.14284"],"paperKeys":["conf/cvpr/0009TDCHL0XWSPL25","conf/eccv/ChenWWPJL24","conf/eccv/ZhangWWWLL24","conf/iccv/SunWZZDXLW25","conf/iccv/ZhangWTLWL25","conf/iccv/ZhouBLZWHLDZCRWN25","conf/iclr/LiW000L25","conf/iclr/LingB0DZWC0025","conf/iclr/YeZHZBKHLWW0CLH25","conf/nips/BuLZZWDZCLW25","conf/nips/TanYWHGLL25","conf/nips/WuYPXLLW25","conf/nips/ZhangZCWLPLL25","conf/siggraph/Yang00WW0L25","journals/tog/LiZWTWL25"]},{"id":"team-92","labName":"AI for Multimodality and Science Lab（AIMS Lab）","labUrl":"https://junxia97.github.io/","memberIndices":[92],"label":"AI for Multimodality and Science Lab（AIMS Lab）","sharedLab":false,"count2025":12,"conference2025":9,"journal2025":3,"knownMinimum2025":null,"sourceWarning":false,"preprint2025":9,"knownPreprintMinimum2025":null,"arxivIds":["2501.18492","2503.03211","2504.00540","2505.03853","2505.09262","2506.21107","2509.11782","2510.07964","2511.13124"],"paperKeys":["conf/iclr/0012CGW000HL25","conf/iclr/Chen0ZZGH0DL25","conf/iclr/XiaLZCX00L25","conf/ijcai/Chi0ZC0L25","conf/ijcai/LiDXWWYW25","conf/ijcai/XiaZCLL25","conf/ijcai/XiangXJDZZ25","conf/nips/ChengCZXX25","conf/nips/XiangLLCYDXZJZ25","journals/bib/XuZHYTXL24","journals/bioinformatics/LiuLX0L25","journals/bioinformatics/XiangLHJWXDYFYZX25"]},{"id":"team-93","labName":"Endless AI Lab（远兮实验室）","labUrl":"https://endless.do","memberIndices":[93],"label":"Endless AI Lab（远兮实验室）","sharedLab":false,"count2025":5,"conference2025":5,"journal2025":0,"knownMinimum2025":null,"sourceWarning":false,"preprint2025":6,"knownPreprintMinimum2025":null,"arxivIds":["2503.10624","2503.24391","2505.05022","2509.24817","2509.26645","2510.06219"],"paperKeys":["conf/cvpr/BianXX00LB025","conf/cvpr/ChenCCPX25","conf/iccv/ChenCXGC25","conf/iccv/LiFCBX25","conf/siggraph/LiaoZXK00025"]},{"id":"team-94","labName":null,"labUrl":null,"memberIndices":[94],"label":"徐枫 及合作者","sharedLab":false,"count2025":18,"conference2025":9,"journal2025":9,"knownMinimum2025":null,"sourceWarning":false,"preprint2025":11,"knownPreprintMinimum2025":null,"arxivIds":["2505.05010","2505.05336","2506.03478","2506.10580","2506.22907","2508.03313","2508.06139","2509.12742","2510.17101","2511.20366","2512.11237"],"paperKeys":["conf/apsipa/ZhangHLLX24","conf/bibm/DongGLHYPLX25","conf/bibm/YeGLHLPX25","conf/eccv/MingLLZX24","conf/iccv/ShaoYYGYX25","conf/iccv/ZhengLWWX25","conf/mm/0001LLTPM0025","conf/siggraph/HuangLZ025","conf/uist/ZhangYX25","journals/cee/XuZBLGX25","journals/patterns/TangGLHLLX25","journals/tim/ZhuZHWQZYX25","journals/tog/HanLSQZXX25","journals/tog/YiPX25","journals/tog/YinSWYXG25","journals/tog/ZuoHJYSCYXGQ25","journals/tvcg/PanYZJZ0025","journals/tvcg/WangXLXPG25"]},{"id":"team-95","labName":"Tsinghua Embodied AI Lab（TEA Lab）","labUrl":null,"memberIndices":[95],"label":"Tsinghua Embodied AI Lab（TEA Lab）","sharedLab":false,"count2025":16,"conference2025":14,"journal2025":2,"knownMinimum2025":null,"sourceWarning":false,"preprint2025":20,"knownPreprintMinimum2025":null,"arxivIds":["2502.07730","2502.10956","2502.16932","2503.02881","2503.22444","2504.06961","2505.06883","2505.07819","2505.15692","2506.05064","2507.02712","2507.16645","2508.17230","2508.20085","2509.00576","2509.15273","2509.23721","2510.08549","2510.14830","2511.05007"],"paperKeys":["conf/cvpr/QiJWCWX25","conf/eccv/HuangJZX24","conf/eccv/JuHZZJX24","conf/iccv/HouZFGHYZX25","conf/iclr/HeCXP25","conf/iclr/HuRHLHX25","conf/iclr/JiangSH0LX25","conf/iclr/ZhuJZWYHX25","conf/icml/HuangZLXKL0XX25","conf/icml/KangHLYZX25","conf/icra/NaiYCCZXG25","conf/icra/ZhangLCZX25","conf/iros/XuWLZX25","conf/naacl/LiuHWLTLHX25","journals/ijairr/ZhangYPYMCXZZ25","journals/ral/PanBYJJLPLX25"]},{"id":"team-96","labName":"物理智能团队","labUrl":null,"memberIndices":[96],"label":"物理智能团队","sharedLab":false,"count2025":21,"conference2025":11,"journal2025":10,"knownMinimum2025":null,"sourceWarning":false,"preprint2025":18,"knownPreprintMinimum2025":null,"arxivIds":["2501.02519","2502.02163","2503.01309","2503.08135","2503.12758","2504.04421","2504.16693","2505.11528","2505.18994","2506.15610","2506.19455","2506.21401","2506.24121","2507.17594","2508.06625","2512.03538","2512.04415","2512.14095"],"paperKeys":["conf/cvpr/GuoXL0LH25","conf/cvpr/TangZLGD0X25","conf/cvpr/WangWMHXG25","conf/cvpr/WangY00025","conf/cvpr/ZhaoAZXG25","conf/eccv/DaiLSHMHXH24","conf/eccv/SheZYHX24","conf/iccv/CaoZYLQZDX25","conf/iccv/GaoYDZCZX25","conf/iccv/GaoYHCZX25","conf/prcv/LiuXHYZ24","journals/cgf/LanZGZCYWX25","journals/cvgip/ZhaoYHYZX25","journals/fcsc/WenZYWZX25","journals/pami/WanSCX25","journals/tcsv/GaoYZZCX25","journals/tcsv/ZhuYWZX25","journals/tmm/TianQYZX25","journals/tog/XiaoLZLX25","journals/tvcg/HuangZLX25","journals/vc/WangYWZXH25"]},{"id":"team-97","labName":"多学科人工现实工作室（MARS）","labUrl":null,"memberIndices":[97],"label":"多学科人工现实工作室（MARS）","sharedLab":false,"count2025":18,"conference2025":15,"journal2025":3,"knownMinimum2025":null,"sourceWarning":false,"preprint2025":18,"knownPreprintMinimum2025":null,"arxivIds":["2502.06392","2502.08297","2502.12894","2502.16175","2503.12242","2503.18349","2503.21268","2505.21041","2506.03478","2507.21493","2508.02106","2509.07653","2509.17506","2509.17513","2510.20155","2511.01294","2512.07410","2512.11237"],"paperKeys":["conf/3dim/ZhengWLZSCZLZZWX25","conf/aaai/LiuZRHYX25","conf/aaai/WangWZLPZZJZXWY25","conf/cvpr/JiangSGH0ZHX25","conf/cvpr/YanLLFDZZMXWS025","conf/iccv/JiSJCXMYW25","conf/iccv/YangLWLWYSX25","conf/icmcs/WuSHXYW25","conf/mm/HongWSGJZ00025","conf/mm/LongZOZ00025","conf/mmsp/ShenCLHWZZX25","conf/nips/WangHLZXYG25","conf/nips/ZhengWZTCXYZHZ25","conf/siggrapha/JiangGWHZSZJ00H25","conf/siggrapha/LiuZLCCZ00S0Z25","journals/tog/HanLSQZXX25","journals/tog/YaoZYZZXYGY25","journals/tog/ZhangZJBYXY25"]},{"id":"team-98","labName":null,"labUrl":null,"memberIndices":[98],"label":"徐梦迪 及合作者","sharedLab":false,"count2025":1,"conference2025":0,"journal2025":1,"knownMinimum2025":null,"sourceWarning":true,"preprint2025":2,"knownPreprintMinimum2025":null,"arxivIds":["2505.24871","2510.18316"],"paperKeys":["journals/ral/ZhangLHHLXZ25"]},{"id":"team-100","labName":"Shenzhen Key Laboratory for High-Performance Data Mining","labUrl":null,"memberIndices":[100],"label":"Shenzhen Key Laboratory for High-Performance Data Mining","sharedLab":true,"count2025":48,"conference2025":39,"journal2025":9,"knownMinimum2025":null,"sourceWarning":true,"preprint2025":34,"knownPreprintMinimum2025":null,"arxivIds":["2501.04561","2501.09426","2501.12619","2501.16727","2502.12566","2504.15524","2504.19627","2505.01696","2505.16281","2505.16673","2505.17654","2505.20277","2505.23923","2505.24196","2506.02347","2506.02504","2506.02973","2506.07691","2506.09003","2507.04781","2507.18929","2508.13152","2508.15361","2509.02522","2510.05134","2510.05969","2510.13721","2510.14000","2510.20780","2510.26167","2511.04328","2511.08317","2511.09146","2511.22619"],"paperKeys":["conf/aaai/NiKL000025","conf/aaai/WangDLB0WW025","conf/aaai/ZhangLLXYLWCLQY25","conf/acl/0004CLT0LLCLAA025","conf/acl/0005FBDHDHLWLQZ25","conf/acl/ChenFGXLLLQAN025","conf/acl/ChenSWWLLWAY25","conf/acl/LeeZALDHW0LA0LW25","conf/acl/LuoZCLLWYLWZGSL25","conf/acl/SunCABH0W0025","conf/acl/ZhangLLWLZQFYGS25","conf/acl/ZhuZJWFLGZGLWQY25","conf/bibm/ZhaoXTZAAY25","conf/coling/ZhaoZTYLD0YL0W25","conf/emnlp/ChenLFLNAAYL25","conf/emnlp/LiYHL25","conf/emnlp/WangLCYYW25","conf/emnlp/XiongSYTWLWZGYKW25","conf/emnlp/ZhangLWKYW25","conf/icassp/NiC025","conf/icassp/WangT0B0ZY025","conf/iccv/ZhangLYYLH25","conf/iclr/LuoLCHLLZSRXLH025","conf/icmcs/XiongTZWCLYYX25","conf/icml/0201Y00CZCHL25","conf/icpr/HuZYLLH24","conf/mm/Chen0L000H25","conf/naacl/BaiDLJZLFCZZMWYWLHZLFYN25","conf/naacl/YuGTCY25","conf/nips/ChenWYLY25","conf/nips/LuoLZWLLCLZXAHY25","conf/nips/LuoSCLWYX25","conf/nips/YaoYZYWWSSQTH25","conf/nips/ZhanHYCYW25","conf/sigir/WangBWLYZX25","conf/socrob/NiY24","conf/socrob/ZhuTYLA24","conf/www/LianGCZDLYLYHSH25","conf/www/YangZWTL025","journals/aiethics/WangCDNYZ25","journals/cogcom/SunBTLYX25","journals/ijon/WangLBYGX25","journals/ipm/WenWWGLCLYX25","journals/tacl/ChenWYZWLWYCW25","journals/tacl/YuLWYHL25","journals/taffco/TuJLYYQX25","journals/tcss/LuoLWLCZHYX25","journals/tnn/ZhaoYQX25"]},{"id":"team-101","labName":"Physical Intelligence Lab（NJU-PIL）","labUrl":"https://yoyo000.github.io/group.html","memberIndices":[101],"label":"Physical Intelligence Lab（NJU-PIL）","sharedLab":false,"count2025":14,"conference2025":14,"journal2025":0,"knownMinimum2025":null,"sourceWarning":true,"preprint2025":null,"knownPreprintMinimum2025":7,"arxivIds":["2502.07615","2502.07685","2505.17412","2509.09676","2510.07729","2512.02993","2512.04939"],"paperKeys":["conf/aaai/ChengLSWZT00Q25","conf/cvpr/Gao0ZZ0Z0SQ25","conf/cvpr/LuZFNTQC0025","conf/cvpr/ZhangW0GH0C025","conf/eccv/GaoGLLZCZY24","conf/eccv/HeJGLDHYZMXWZCZ24","conf/eccv/HeZWYZLZCZ24","conf/eccv/ZengJZLLZHCY24","conf/eccv/ZhuCDDXCYZZ24","conf/iclr/0003LYZSCZZ025","conf/iclr/ChenLL00C025","conf/nips/WuLZZYBQZCTY25","conf/siggrapha/0003CXSCSD00Z25","conf/sips/ZhangGZYZT25"]},{"id":"team-102","labName":"Multimedia Analysis and ReaSoning（MARS）Group","labUrl":"https://marswhu.github.io/","memberIndices":[102],"label":"Multimedia Analysis and ReaSoning（MARS）Group","sharedLab":false,"count2025":76,"conference2025":47,"journal2025":29,"knownMinimum2025":null,"sourceWarning":false,"preprint2025":26,"knownPreprintMinimum2025":null,"arxivIds":["2502.14881","2503.04229","2503.04543","2503.08175","2503.09206","2503.16843","2503.22171","2504.00540","2505.13408","2505.16916","2505.18640","2505.23024","2506.03750","2507.02409","2507.03402","2508.08789","2509.00540","2509.16635","2509.18849","2510.17685","2511.08369","2511.09141","2511.10945","2511.12982","2512.03745","2512.07216"],"paperKeys":["conf/aaai/0006HWY25","conf/aaai/WangLYYWX25","conf/aaai/WangZHZLY25","conf/aaai/ZhaoRLY25","conf/cvpr/0001HWYY25","conf/cvpr/BaiJCWY25","conf/cvpr/FangHWSY25","conf/cvpr/TanWHLZ0Y25","conf/cvpr/WuSWY25","conf/cvpr/YangL0Y25","conf/cvpr/YangSWY25","conf/eccv/HuangYSDT24","conf/eccv/LiCY24","conf/eccv/YangYT24","conf/icassp/ZhengYFYY25","conf/iccv/DongY25","conf/iccv/YaoYHDY25","conf/iclr/WanSHZTY25","conf/icmcs/WuCZCDY25","conf/icml/00030SZW00TY25","conf/icml/00030WZ0SY0T25","conf/icml/Fang000SY25","conf/icml/Fang0WYY25","conf/icml/He00LY25","conf/icml/Liao0W00Y25","conf/icml/QianW0ZW0Y25","conf/icml/Rong0HY25","conf/icml/ShiW0Z00Y25","conf/icml/Tan0W00Y25","conf/icml/YangHW0Y25","conf/ijcai/ChenHWSLDYDX25","conf/ijcai/LiLLLYG0YY25","conf/ijcai/LuSLY25","conf/ijcai/WangHCSWQYWLY25","conf/mm/Duan0Y25","conf/nips/FangY25","conf/nips/GuanHGYYY25","conf/nips/RongHLBXLDY25","conf/nips/ShenLCHY25","conf/nips/WanCLHSJZDY25","conf/nips/WanQHXGLZDY25","conf/nips/WanRZHRZWDY25","conf/nips/XiaoLLHXZYP25","conf/nips/YangLLY25","conf/nips/YuanHWGLY25","conf/nips/ZhouSXDWY25","conf/nips/ZhouYHCY25","journals/caaitrit/YeHSYD25","journals/chinaf/HuangYSLD25","journals/chinaf/YeHSLD25","journals/csur/YeSDSKY25","journals/ijcv/YeCLZCD25","journals/ijcv/ZhangZYYS25","journals/nn/MeiYYLYYMC25","journals/npjdm/LeiWLYSYLXGZYYDW25","journals/pami/FangYD25","journals/pami/OuyangDYDSS25","journals/pami/YeWD25","journals/pr/LiuJZJYY25","journals/taffco/RaoCY25","journals/tbbis/LiYSD25","journals/tcsv/SunWFYJLZHM25","journals/tifs/ChenYHD25","journals/tifs/FangCSLZHYX25","journals/tifs/HuangYSLD25","journals/tifs/YouCFLJY25","journals/tifs/ZhuZHWLY25","journals/tip/ChenYDD25","journals/tip/GaoBCDYZ25","journals/tip/ShiYHDZ25","journals/titb/HuYWSKY25","journals/tmc/FangY25","journals/tmc/ShenYYY25","journals/tmi/WenYLCX25","journals/tnn/PangWYCZHW25","journals/visintelligence/XuWGCYL25"]},{"id":"team-103","labName":null,"labUrl":null,"memberIndices":[103],"label":"弋力 及合作者","sharedLab":false,"count2025":16,"conference2025":15,"journal2025":1,"knownMinimum2025":null,"sourceWarning":false,"preprint2025":14,"knownPreprintMinimum2025":null,"arxivIds":["2501.04595","2501.09978","2502.09614","2502.13143","2503.07481","2503.12332","2503.19913","2503.20784","2505.10918","2506.03135","2507.02747","2507.04447","2509.13833","2509.17759"],"paperKeys":["conf/3dim/LiuLLZLYT25","conf/3dim/YiCY25","conf/cvpr/GaoPGZLDT0025","conf/cvpr/LiLLDCY25","conf/cvpr/Liu025","conf/cvpr/LiuZXTYY25","conf/cvpr/WangCC0YLLW025","conf/eccv/LiuLZDY24","conf/eccv/QiDZGHGYM24","conf/eccv/ZhangLHLY24","conf/iccv/HeLYQZCZZYW25","conf/iclr/LiuAHQ025","conf/iclr/WuZCTLFZXYY0025","conf/nips/QiZDDYLXLHFZHGJ25","conf/nips/ZhangLQWYZDHWZY25","journals/tvcg/ShiTYLYZ25"]},{"id":"team-104","labName":"LAMDA Group","labUrl":"https://www.lamda.nju.edu.cn/","memberIndices":[104],"label":"LAMDA Group","sharedLab":true,"count2025":29,"conference2025":16,"journal2025":13,"knownMinimum2025":null,"sourceWarning":false,"preprint2025":10,"knownPreprintMinimum2025":null,"arxivIds":["2502.04778","2503.04793","2503.19267","2503.21383","2505.10010","2505.13425","2506.08446","2506.23235","2509.22402","2511.10030"],"paperKeys":["conf/iclr/0001BLZG025","conf/iclr/0001Z00JZ0A25","conf/iclr/LinXSZ0JYZ025","conf/iclr/Liu00025","conf/iclr/LiuL0JWZ025","conf/iclr/PangTLTCZ0S025","conf/iclr/QianZSLWALZ0Y25","conf/icml/Gao0CX0Z25","conf/icml/JiaLW0HD025","conf/icml/Li0LJ025","conf/icml/Zhang0DCS025","conf/icml/ZhangYLBX000025","conf/nips/LiLJZWYZY25","conf/nips/LuoYY25","conf/nips/WangCXZY25","conf/nips/XueZLGYY25","journals/fcsc/GuanXFCZYQY25","journals/fcsc/ZhuTCZY25","journals/nn/GuanJLZYY25","journals/pami/LiCZZYY25","journals/tec/XueWGYFFQY25","journals/tmlr/0042CQG0Z025","journals/tmlr/PangFWXTYJXCHY25","journals/tnn/DingJZGCYY25","journals/tnn/GuanCYZY25","journals/tnn/PangXJLY25","journals/tnn/XiaoYLZLY25","journals/tnn/YuanLZZGY25","journals/tnn/ZhangLLZYY25"]},{"id":"team-105","labName":"PKU-YUAN-Lab（袁粒课题组）","labUrl":"https://github.com/PKU-YuanGroup","memberIndices":[105],"label":"PKU-YUAN-Lab（袁粒课题组）","sharedLab":false,"count2025":39,"conference2025":32,"journal2025":7,"knownMinimum2025":null,"sourceWarning":false,"preprint2025":31,"knownPreprintMinimum2025":null,"arxivIds":["2501.02807","2501.07641","2503.06687","2503.07265","2503.09154","2503.14941","2503.23162","2504.02782","2504.12314","2504.21650","2505.07889","2505.15233","2505.15287","2505.20275","2505.20292","2505.20354","2505.21205","2505.21318","2506.03147","2506.03827","2506.05260","2506.08473","2506.24113","2507.03019","2507.04451","2508.09912","2509.09666","2509.25187","2510.16888","2511.20561","2512.10369"],"paperKeys":["conf/aaai/0001YC0Z0025","conf/aaai/0004ZCY0PL025","conf/coling/YangNLYTS025","conf/cvpr/0001YCZGG0025","conf/cvpr/Li0YCCY025","conf/cvpr/YanZCGFYDWY25","conf/cvpr/YuanHHGSC0025","conf/cvpr/ZhangN00Y0YCSY25","conf/eccv/JinLCLYLJYC24","conf/eccv/LiFWSYJYC24","conf/eccv/LiJJCLSLY24","conf/eccv/YuYCGLHLST24","conf/eccv/ZhangTPCJWZNY24","conf/icassp/ZhouNZ0Z25","conf/iccv/PangZBZTLYY25","conf/iccv/XuJWLSSY25","conf/iccv/YuFLTYTCJYYT25","conf/iccv/ZhangTHPGLHYZLCY25","conf/iclr/0001Z0Y25","conf/iclr/NingYLYL0SY25","conf/icmcs/ChenLLZWYZCY25","conf/icmcs/WuNWZLY25","conf/icml/0001Z0Y25","conf/icml/0002WJZLCYDW025","conf/mm/0001TYPZZ0025","conf/mm/ZhouYGC0025","conf/nips/LiCFSTYTYL25","conf/nips/LiFTDYTY25","conf/nips/LiuNZYWYXSCWY25","conf/nips/YeHLLYYHY25","conf/nips/YuanHDYHLMLY25","conf/sigir/LiuYPF0JPLLS25","journals/chinaf/LinLLWLZCCYT25","journals/ijcv/WangYWF25","journals/ncs/LiLYWTWM25","journals/pami/JinLYYC25","journals/pami/YuanHSXZLCYL25","journals/tamd/ZhouCNYLYLZ25","journals/tcsv/WangCYYY25"]},{"id":"team-107","labName":null,"labUrl":null,"memberIndices":[107],"label":"张超 及合作者","sharedLab":false,"count2025":null,"conference2025":null,"journal2025":null,"knownMinimum2025":null,"sourceWarning":false,"preprint2025":null,"knownPreprintMinimum2025":null,"arxivIds":[],"paperKeys":[]},{"id":"team-108","labName":"AGI Lab, Westlake University","labUrl":"https://github.com/Westlake-AGI-Lab","memberIndices":[108],"label":"AGI Lab, Westlake University","sharedLab":false,"count2025":16,"conference2025":15,"journal2025":1,"knownMinimum2025":null,"sourceWarning":true,"preprint2025":null,"knownPreprintMinimum2025":21,"arxivIds":["2502.03207","2502.19204","2503.02268","2503.07076","2504.04753","2504.04907","2504.11301","2505.24862","2506.05046","2507.16010","2507.17745","2508.03334","2508.08789","2508.09702","2508.12918","2509.11062","2509.15130","2511.12578","2511.18919","2511.22533","2512.21894"],"paperKeys":["conf/chi/ZhangYLLHCHF025","conf/cvpr/ChenWC0YZYFLHL25","conf/cvpr/ChengMZCPZWF00P25","conf/cvpr/HanLCYWDLDFLZZL25","conf/eccv/JiangCZYLYF24","conf/eccv/LiCZCZYLYC24","conf/eccv/YangCCZXYLL24","conf/iccv/ChenWLWCZZL25","conf/iccv/LiaoZWYLZ25","conf/iclr/Chen0HYCTC0YL025","conf/icmcs/LiZJYFCCFCW25","conf/ijcnn/HanZCYYWYFZ25","conf/mm/SongWSZTF025","conf/mm/ZhuangJZYZZ25","conf/nips/WangZLYZ25","journals/tmm/YinCZJZLYC25"]},{"id":"team-110","labName":"Logos Robotics Group","labUrl":"https://github.com/logosroboticsgroup","memberIndices":[110],"label":"Logos Robotics Group","sharedLab":false,"count2025":26,"conference2025":21,"journal2025":5,"knownMinimum2025":null,"sourceWarning":false,"preprint2025":18,"knownPreprintMinimum2025":null,"arxivIds":["2501.02741","2501.13971","2502.03496","2503.14182","2503.18328","2503.22976","2505.16902","2506.22099","2506.22242","2507.17342","2508.11428","2508.11488","2508.11492","2508.11952","2508.12404","2510.11092","2510.13800","2512.23147"],"paperKeys":["conf/cvpr/000300V0ZZ25","conf/cvpr/GuW0Z25","conf/cvpr/GuWZY025","conf/cvpr/LiGLZDCZTZW0Z0Z25","conf/cvpr/ZhangSJZ25","conf/eccv/GaoGLLZCZY24","conf/eccv/LuHYZZ24","conf/eccv/NiePWCHXZ24","conf/icassp/YuanGWXZ25","conf/iccv/MaJCZ25","conf/iccv/YangPYZZ25","conf/iclr/0003GC025","conf/iclr/YangPGZ25","conf/iclr/YaoZGZ025","conf/iclr/YuanGWZXZ25","conf/mm/HuangXSFYSZ25","conf/nips/NieWHXZ25","conf/nips/SongJLZZ25","conf/nips/ZhangCXHMCZYCHQ25","conf/nips/ZhangCXHZYCHQXZ25","conf/nips/ZhangSLZDZ25","journals/ijcv/MaZFZ25","journals/ijcv/NieCXZ25","journals/ijcv/WanHLYZ25","journals/pami/ChenZXLZLZ25","journals/pami/YangSLZZT25"]},{"id":"team-111","labName":"生物启发的智能计算研究组（BRAVE GROUP）","labUrl":"https://zhaoxiangzhang.net/lab/","memberIndices":[111],"label":"生物启发的智能计算研究组（BRAVE GROUP）","sharedLab":false,"count2025":50,"conference2025":40,"journal2025":10,"knownMinimum2025":null,"sourceWarning":false,"preprint2025":62,"knownPreprintMinimum2025":null,"arxivIds":["2501.08295","2501.09368","2501.09705","2502.01977","2502.06635","2502.08234","2502.09963","2502.16614","2502.19361","2502.21093","2503.08638","2503.11028","2503.15990","2503.17407","2503.18511","2504.01901","2504.01941","2504.14545","2504.14727","2505.12808","2505.14552","2506.05453","2506.18904","2506.19850","2506.22291","2506.23090","2507.02747","2507.06181","2507.06203","2507.07999","2507.18311","2508.10881","2508.13186","2508.14507","2508.17832","2509.17328","2509.17940","2509.23852","2509.23967","2509.25191","2510.06207","2510.10689","2510.12679","2510.12796","2510.17095","2510.18250","2510.18726","2510.18876","2510.24106","2510.24717","2511.05459","2511.07250","2511.15122","2511.18538","2511.21161","2512.04501","2512.12730","2512.15649","2512.21094","2512.23300","2512.24157","2512.24867"],"paperKeys":["conf/aaai/ChenJTL0L025","conf/aaai/Zhou0HZLLP025","conf/acl/0016MF0025","conf/acl/HeLLWB0P0ZS025","conf/acl/HuangCLXHSXYLZC25","conf/acl/LiCSC0025","conf/acl/LiuDLYLZZCWK0WZ25","conf/cvpr/FanZWLZ25","conf/cvpr/ZhouFH000025","conf/eccv/ChenWLZC24","conf/eccv/LiFZ24","conf/eccv/LiuLFWPZ24","conf/eccv/WangHCZ24","conf/eccv/WangWLZLZ24","conf/eccv/YuWCZ24","conf/eccv/ZhanLLZC24","conf/eccv/ZhangFCZLZ24","conf/emnlp/WangZXZLZWSLLQZZZXFH25","conf/globecom/ZhaoZCHYZ25","conf/icb/MaZQCGQZL25","conf/iccv/ChenWZ25","conf/iccv/HeLYQZCZZYW25","conf/iccv/LiSCJCLZ25","conf/iccv/LiWLHFZ25","conf/iccv/LinCJYFZZZ25","conf/iccv/WangZWFZZ25","conf/iccv/YangFLWZ25","conf/iclr/0347LMP025","conf/iclr/ChaiL0YJLS0RGWW25","conf/iclr/LiF00C0T25","conf/iclr/WangFWC025","conf/iclr/WangWWLSPDZWPZG25","conf/iclr/WangZZWG0025","conf/icmcs/WangQAYLZ25","conf/ijcai/Zou00025","conf/nips/LiZMYZGLLWYWQSZ25","conf/nips/LiuLTLYNFPZ25","conf/nips/PengWZWWZYLWWLJ25","conf/nips/ShangCWLZ25","conf/nips/ShiYLBCZMWWHSZL25","journals/bib/ZhangSZZZZWW25","journals/chinaf/TangWZLZ25","journals/ijautcomp/GuanSZ25","journals/ijautcomp/ZhangWHWWZZLL25","journals/ijcv/WangSFLWWZ25","journals/ijcv/WangWSFWZ25","journals/pami/FanWWZ25","journals/pami/WangCZ25","journals/pami/WangFWSWZZ25","journals/tnn/HaoGZ25"]},{"id":"team-112","labName":"MARS Lab, Tsinghua University","labUrl":"https://group.iiis.tsinghua.edu.cn/~marslab/","memberIndices":[112],"label":"MARS Lab, Tsinghua University","sharedLab":false,"count2025":21,"conference2025":19,"journal2025":2,"knownMinimum2025":null,"sourceWarning":false,"preprint2025":29,"knownPreprintMinimum2025":null,"arxivIds":["2502.01465","2502.01481","2502.01536","2503.07485","2503.08471","2503.08564","2503.10434","2503.18738","2505.11123","2505.15880","2505.23115","2505.23757","2506.03079","2507.16331","2507.16645","2507.17617","2507.18255","2507.18473","2507.18498","2507.19451","2507.20879","2509.00576","2509.20109","2509.26219","2510.13375","2511.17441","2511.17914","2512.04552","2512.04952"],"paperKeys":["conf/eccv/YeJXLZ24","conf/iccv/ChenQYLZ25","conf/iccv/YeQZGZZZ25","conf/icra/ChenLYJLZ25","conf/icra/SunWZNWXZJLZ25","conf/icra/WangLYMLYZZ25","conf/icra/ZhangLZCLQWZWZZ25","conf/icra/ZhuHMZ25","conf/icra/ZhuLMLXZ25","conf/iros/DuanZZS25","conf/iros/HuangZDZ25","conf/iros/LiZQLLWLZGLCZZ25","conf/iros/XuZLYCGZSPMJSYZTLYZ25","conf/iros/YuanJZSZG25","conf/iros/ZhangQZZGCGWLLGLZZ25","conf/nips/ChiGLLLLYYWLWHS25","conf/nips/DongLLZH25","conf/nips/JiangZZLSWS25","conf/wacv/MaYC0XKWMCRLZZH25","journals/ijairr/ZhangYPYMCXZZ25","journals/ral/ZhuMLYHZ25"]},{"id":"team-113","labName":"Super Artificial Intelligence Lab（SAIL）","labUrl":"https://sail.ai.hku.hk","memberIndices":[113],"label":"Super Artificial Intelligence Lab（SAIL）","sharedLab":false,"count2025":49,"conference2025":43,"journal2025":6,"knownMinimum2025":null,"sourceWarning":false,"preprint2025":44,"knownPreprintMinimum2025":null,"arxivIds":["2501.01427","2501.01428","2501.02048","2501.12382","2501.14729","2503.03705","2503.08575","2503.14694","2503.16429","2503.23024","2504.01934","2505.10565","2505.24870","2506.04228","2506.09995","2506.14574","2506.14686","2506.17221","2506.22434","2507.02299","2507.02860","2507.02861","2507.10302","2507.13348","2508.00350","2508.09454","2508.11256","2508.14042","2508.18633","2509.07969","2509.26599","2510.05095","2510.06214","2510.13809","2510.23607","2511.01768","2511.05491","2511.12594","2512.08765","2512.12751","2512.12799","2512.14699","2512.15715","2512.16905"],"paperKeys":["conf/cvpr/0001ZHHYZCJ0Z025","conf/cvpr/0002DFSXYENZS25","conf/cvpr/CaoZ0ABZ025","conf/cvpr/ChenGHLTXWZZYWX25","conf/cvpr/ChenZZZKL00Z0D025","conf/cvpr/HuangDWHLZXHZL25","conf/cvpr/XuB0LXWWZ25","conf/cvpr/YuanPRLH0ZLCL25","conf/eccv/ChenLCFLSZ24","conf/eccv/HuangWCZZL24","conf/eccv/TangTLHZZLJ24","conf/eccv/WangLLZW24","conf/eccv/XuWZ24","conf/eccv/ZhangHLHZ24","conf/eccv/ZhuCWZJ24","conf/emnlp/ZhuCWYZJ25","conf/iccv/WangCXJLSZ25","conf/iccv/ZhangYYYGLZ25","conf/iccv/ZhaoZWWZ25","conf/iccv/ZhengQCWWZ25","conf/iccv/ZhouLTCDZTZB25","conf/iclr/0001ZHZL0CJ0Z025","conf/icml/0001ZPDZ025","conf/icml/00410XHGSZ25","conf/icml/Li00LZ25","conf/icml/LiRYZ00BZ25","conf/icml/Liao0Z0Z25","conf/icml/ZhuCW0ZJ25","conf/nips/ChenZLWXLBZ25","conf/nips/ChuHCZXxWYLZLZY25","conf/nips/HuangWZZNL25","conf/nips/MiaoFZGLYQCWZ25","conf/nips/TuLCBWZ25","conf/nips/WangXZPDZZ25","conf/nips/WangZXWPDZZ25","conf/nips/YangLLWLMYZJ25","conf/nips/ZhangWLWTWZ25","conf/nips/ZhengQCWWZ25","conf/siggraph/Ji00TWZ25","conf/siggraph/JiW000Z25","conf/siggraph/TuCLZ25","conf/siggraph/TuLCJBZ25","conf/siggrapha/WangC00Z25","journals/pami/ChenHLSZZ25","journals/pami/LiXLZ25","journals/pami/WangLCLTZW25","journals/pami/YangWYTCZT25","journals/pami/YangZZ25","journals/pami/ZhuYWHZHZSQHO25"]},{"id":"team-114","labName":"脑机智能实验室","labUrl":null,"memberIndices":[114],"label":"脑机智能实验室","sharedLab":true,"count2025":null,"conference2025":null,"journal2025":null,"knownMinimum2025":4,"sourceWarning":false,"preprint2025":null,"knownPreprintMinimum2025":null,"arxivIds":[],"paperKeys":["conf/aaai/ChenLMTZ025","conf/aaai/YanLCMTZ025","conf/iccv/LiuCYMTZP25","conf/icml/YanWMTZ025"]},{"id":"team-115","labName":"机器智能与先进计算教育部重点实验室","labUrl":null,"memberIndices":[115],"label":"机器智能与先进计算教育部重点实验室","sharedLab":true,"count2025":66,"conference2025":46,"journal2025":20,"knownMinimum2025":null,"sourceWarning":false,"preprint2025":45,"knownPreprintMinimum2025":null,"arxivIds":["2501.14607","2501.18954","2502.02372","2502.16976","2503.01789","2503.07087","2503.07360","2503.09186","2503.10152","2503.12769","2503.13130","2503.13300","2503.14198","2503.18420","2503.21755","2503.22405","2503.23121","2503.23509","2503.23751","2504.11326","2504.18152","2505.12702","2505.24718","2506.06982","2507.01857","2507.03924","2507.04060","2507.04243","2507.04511","2507.04692","2508.07162","2508.09423","2508.17667","2509.23915","2509.24786","2509.24948","2510.10671","2510.23119","2511.05129","2511.13327","2511.18695","2512.01022","2512.10730","2512.12309","2512.22118"],"paperKeys":["conf/aaai/GuQTW025","conf/aaai/Huang0H025","conf/aaai/WangSSLFTLTH025","conf/aaai/ZengHW025","conf/aaai/Zheng0N025","conf/acl/LiuWWCL025","conf/bibm/ZhouYZZW25","conf/cvpr/FuYMYWMX025","conf/cvpr/HuangLXTLH025","conf/cvpr/PengTLYMW025","conf/cvpr/Xiao0N0025","conf/cvpr/Xie0025","conf/cvpr/ZengHWGTM025","conf/cvpr/ZhengZ0LLH025","conf/cvpr/ZhouZMLL025","conf/cvpr/ZhuZWN025","conf/eccv/LiHWZMZ24","conf/eccv/LuMZ24","conf/eccv/MoGFYWZ24","conf/eccv/TangPMZ24","conf/eccv/WuCJZWZ24","conf/eccv/YanGYWXWZ24","conf/iccv/FuYLPLWHXZ25","conf/iccv/JiangWHZWZZ25","conf/iccv/LiangLTZZH25","conf/iccv/LuLWCZW25","conf/iccv/LuZCMZ25","conf/iccv/WeiLLJWZZ25","conf/iccv/XiaLLHTZ25","conf/iccv/YuZZZ25","conf/iccv/ZhangHSLZXZ25","conf/iccv/ZhangZPOMZ25","conf/iccv/ZhengCWWTWZ25","conf/iccv/ZhengZLZ25","conf/icmcs/HuangZZGZ25","conf/icmcs/LiWHZ25","conf/icmcs/LiWZLPZZ25","conf/icpr/DuLMZ24","conf/icpr/JiangWCWZ24","conf/icpr/LiZ24","conf/icpr/XieFCLZ24","conf/icpr/ZhangPWZ24","conf/icra/WangCLLZ25","conf/iros/XingLWRTLSZC25","conf/nips/LiLZMZ25","conf/prcv/LiQPZZ24","journals/ijcv/YeCLZCD25","journals/ijcv/ZhengWLMZ25","journals/npjdm/ChenLLCLZLLCWZLCHZJLLLY25","journals/pami/LiPZ25","journals/pami/LinZZ25","journals/pami/ZhaoCZLZ25","journals/pami/ZhengYP25","journals/pr/HouYZG25","journals/pr/XianPSZ25","journals/ral/ChenWXJCZ25","journals/sigpro/ZhangSZL25","journals/tcsv/ChenWLCZZW25","journals/tcsv/DuFLHQSHZ25","journals/tcsv/ZengWWHZ25","journals/tifs/LinYZLH25","journals/tmm/FuYYWXZ25","journals/tmm/LiangLHYZL25","journals/tmm/ZhangYWXTZY25","journals/tog/JiangZNXZZ25","journals/tvcg/WangZNZ25"]},{"id":"team-116","labName":"Smart Autonomous Robotics（STAR）Group","labUrl":"https://robotics-star.com/","memberIndices":[116],"label":"Smart Autonomous Robotics（STAR）Group","sharedLab":false,"count2025":null,"conference2025":null,"journal2025":null,"knownMinimum2025":8,"sourceWarning":false,"preprint2025":null,"knownPreprintMinimum2025":10,"arxivIds":["2501.02815","2501.06566","2503.06891","2503.07278","2503.15273","2504.14478","2504.14862","2508.11950","2509.19916","2511.12528"],"paperKeys":["conf/iros/LiangZXZ25","conf/iros/XieGMZ25","conf/iros/YuLMZ25","journals/ral/GengNZZ25","journals/ral/ZhangDWZQMZ25","journals/ral/ZhengLSBZZM25","journals/tase/ZhuFXLMZ25","journals/trob/ZhangCFZS25"]},{"id":"team-117","labName":"医学影像、机器人与智能分析（MIRACLE）奇迹实验室","labUrl":"https://miracle.ustc.edu.cn/main.htm","memberIndices":[117],"label":"医学影像、机器人与智能分析（MIRACLE）奇迹实验室","sharedLab":false,"count2025":43,"conference2025":27,"journal2025":16,"knownMinimum2025":null,"sourceWarning":false,"preprint2025":44,"knownPreprintMinimum2025":null,"arxivIds":["2501.03565","2501.09957","2501.12295","2501.13514","2502.03805","2502.08347","2503.05203","2503.06661","2503.09332","2503.16058","2503.17983","2504.02382","2504.11377","2505.08123","2505.18708","2505.18741","2505.19049","2505.19561","2505.22126","2505.23841","2506.08967","2506.09427","2506.12568","2506.12808","2506.18034","2506.19742","2506.21001","2507.11415","2507.16608","2508.10947","2508.15476","2508.21154","2509.08311","2509.13175","2509.20067","2509.26574","2510.07041","2510.09995","2510.13334","2510.16769","2510.19626","2510.27237","2511.09965","2512.08980"],"paperKeys":["conf/acl/CaoHGDXZ25","conf/acl/GaoCWKFZX25","conf/acl/ZhangZMWWLZ25","conf/bibm/LiYZ25","conf/bibm/WangYZJHTZ25","conf/cvpr/LuoFJZ25","conf/cvpr/MaZYTWL0JZ25","conf/cvpr/ZhangLLZ25","conf/ecai/DongTMGZ25","conf/emnlp/WangFCXZ25","conf/icic/ChenHZZ25","conf/icic/HeHZZ25","conf/iclr/WuKJZ25","conf/icml/FengC0XZ25","conf/ijcai/KeCFCXZF25","conf/ijcai/Wang0LHTZ25","conf/ijcnn/ShiLZ25","conf/iros/WangLZlZ25","conf/isbi/YangZ25","conf/isbi/ZhaoQZ25","conf/mm/TangNDMQD00Z25","conf/mm/ZhaoLJZ25","conf/nips/FengLCXZ25","conf/robosoft/ZhouHSHM25","conf/wacv/GaoYLXZ25","conf/wacv/MaYZHJZ25","conf/wacv/YangJ0Z25","journals/bmcmi/ZhaoHLWZX25","journals/memetic/HuZLLLZY25","journals/mia/LiFLZJZ25","journals/mia/LiYLLZCWZXWMZCZ25","journals/mia/TangNLJYLZ25","journals/mia/WangYJLHTZ25","journals/mia/WangZXZ25","journals/mia/ZhaoLZZZFQLZ25","journals/npjdm/JiangFRWZHLSTDWXDGWZCL25","journals/npjdm/XuTQYKDNZ25","journals/pacmmod/XiangDGWXZ25","journals/pvldb/CaoGLXZX25","journals/tim/DengJWZ25","journals/tip/NianTDYZZL25","journals/tmi/QuanYZZ25","journals/tmi/ZhangPWSLZ25"]},{"id":"team-119","labName":null,"labUrl":null,"memberIndices":[119],"label":"左旺孟 及合作者","sharedLab":false,"count2025":78,"conference2025":42,"journal2025":36,"knownMinimum2025":null,"sourceWarning":false,"preprint2025":50,"knownPreprintMinimum2025":null,"arxivIds":["2501.01633","2501.08225","2502.13081","2503.04314","2503.13184","2504.02004","2504.02304","2504.09949","2504.14553","2504.14600","2504.19183","2504.19432","2504.19834","2505.04262","2505.06975","2505.11578","2505.17609","2505.19702","2505.19938","2505.22634","2505.24238","2506.02604","2506.04225","2506.07986","2506.08361","2506.10575","2506.19613","2507.03483","2507.04599","2507.07708","2507.10470","2507.12952","2507.23141","2508.06924","2508.07537","2508.08605","2508.16887","2508.17404","2509.11360","2509.12867","2510.10152","2510.21447","2511.00609","2511.08032","2511.10953","2511.20562","2512.00995","2512.06422","2512.12220","2512.17573"],"paperKeys":["conf/aaai/0001B00KZGL25","conf/aaai/HuangZZZ0ZL25","conf/aaai/LiZZ25","conf/aaai/WangZDZZ25","conf/aaai/Zhang0LHRXZ25","conf/cvpr/00140LG0WT0ZWWX25","conf/cvpr/JiangZFWLPLZ25","conf/cvpr/WanQ0FZZ25","conf/cvpr/WanSCZ25","conf/cvpr/Wang0LP0Z25","conf/cvpr/ZhuR0WZ25","conf/eccv/LiCGXZ24","conf/eccv/LiuWLLRXZ24","conf/eccv/MengHWSZ24","conf/eccv/NiSZZ24","conf/eccv/ShangRZFZM24","conf/eccv/WeiJBZZZ24","conf/eccv/WuZYZ24","conf/eccv/WuZZGCZCZ24","conf/eccv/YaoCLYZ24","conf/eccv/YaoLYYHZ24","conf/eccv/ZouHYGLFZ24","conf/eccv/ZouYLFZ24","conf/icassp/Zhang0RZ25","conf/iccv/GuoLWJBZZ25","conf/iccv/LiYWLLXSZ25","conf/iccv/LvPSCZLW25","conf/iccv/MaYZJZ25","conf/iccv/YangMDCLCXYZ25","conf/iccv/ZhangZZXLZ25","conf/iclr/NiF0Z25","conf/iclr/Yan0Z0L025","conf/iclr/Yan0ZG0025","conf/iclr/ZhangZWYZ25","conf/icmcs/MeiZWZ25","conf/mm/0001RZ0HZ25","conf/mm/ZhengYH0HZ25","conf/nips/DongNHYZZ25","conf/nips/LiHQZYZHWWPOBZD25","conf/nips/LinMWRZH25","conf/nips/NiYLLLZW25","conf/nips/XiLFGLFLDZYBJGZ25","journals/air/TianCPZTZWZ25","journals/asc/QiaoSMZ25","journals/cvm/WeiZZLJZZ25","journals/fcsc/LiuPYZZ25","journals/ijcv/FengHZKXLZGL25","journals/ijcv/RenSLWLZ25","journals/ijon/LiYSRLZ25","journals/ijon/WangGLYZ25","journals/isci/ShangRYZ25","journals/jei/ZhangSRZ25","journals/nn/ChengSWQZM25","journals/nn/WuLWLYZP25","journals/pami/FengYXKGZL25","journals/pami/HeSFXTZZGL25","journals/pami/LiGWHZP25","journals/pami/LiZL25","journals/pami/ZhangWZZ25","journals/pr/GongYZYYZ25","journals/pr/HuangCDLZZ25","journals/pr/QiaoSMZ25","journals/pr/XuHQYGZ25","journals/prl/LiGZ25","journals/ral/NiZCBCZZZ25","journals/spl/WanHFZZ25","journals/tcsv/LiWWZFT25","journals/tcsv/WanYLFZZ25","journals/tcsv/WangJWZ25","journals/tip/MaoHFZ25","journals/tip/TianXLZZZ25","journals/tip/WangJWZ25","journals/tmm/XuZWZ25","journals/tmm/ZhuangDZLLWHLZ25","journals/tnn/LiFWYZ25","journals/tnn/ShaoMQZZ25","journals/tnn/ZhangZBZTZDZ25","journals/tog/HuangZWLWWJLLZG25"]}]}