Point-It-Out: Benchmarking Embodied Reasoning for Vision Language Models in Multi-Stage Visual Grounding
机构 * Georgia Tech(佐治亚理工学院) ; NVIDIA(英伟达)
高校专区
机构 * Georgia Tech(佐治亚理工学院) ; NVIDIA(英伟达)
机构 * Stanford University(斯坦福大学) ; Georgia Institute of Technology(佐治亚理工学院)
Comments ICCV Short Video Understanding Workshop Paper
机构 * School of Aerospace Engineering(航空航天工程学院) ; Institute for Robotics and Intelligent Machines(机器人与智能机械研究所) ; Georgia Institute of Technology(佐治亚理工学院)
机构 * EleutherAI ; Georgia Institute of Technology(佐治亚理工学院)
机构 * Georgia Institute of Technology(佐治亚理工学院) ; Nutanix(Nutanix公司)
Comments 24 pages, 4 figures
机构 * Department of Computer and Information Science, University of Pennsylvania(计算机与信息科学系,宾夕法尼亚大学) ; School of Mathematics, Georgia Institute of Technology(数学学院,佐治亚理工学院) ; Department of Bioengineering, University of Pennsylvania(生物工程系,宾夕法尼亚大学)
机构 * Georgia Tech-Europe - IRL2958 GT-CNRS, Metz, France(佐治亚理工学院-欧洲分校 - IRL2958 GT-CNRS,法国梅茨)
Comments Accepted to VCIP 2025
机构 * Georgia Institute of Technology(佐治亚理工学院) ; University of Waterloo(滑铁卢大学)
Comments 18 pages; Extended version of ASE'25 paper with extra appendices
机构 * Emory University(埃默里大学) ; Georgia Institute of Technology(佐治亚理工学院) ; Rutgers University(罗格斯大学) ; SUNY Albany(纽约州立大学阿尔巴尼分校) ; UT Southwestern Medical Center(德克萨斯西南医学中心)
Comments Accepted to NeurIPS 2025 (Spotlight)
机构 * Georgia Tech(佐治亚理工学院) ; University of Oxford(牛津大学)
Comments Our dataset and code can be found at: https://findingdory-benchmark.github.io/
机构 * Georgia Institute of Technology(佐治亚理工学院)
Comments Accepted to EMNLP 2025 main conference
机构 * School of Mathematics, Georgia Institute of Technology(佐治亚理工学院数学系)
机构 * Department of Industrial and Systems Engineering, Georgia Institute of Technology, Atlanta, Georgia, USA(工业与系统工程系,佐治亚理工学院,亚特兰大,佐治亚州,美国)
Comments 7 pages, 2 figures
机构 * School of Mathematics, Georgia Institute of Technology(数学学院,佐治亚理工学院)
机构 * Center for Excellence in Computational Cognition, Georgia Tech(计算认知卓越中心,佐治亚理工学院) ; School of Mathematics, Georgia Tech(数学学院,佐治亚理工学院) ; School of Psychology, Georgia Tech(心理学学院,佐治亚理工学院)
Comments 9 pages, 4 figures, preprint
机构 * Department of Electrical Engineering, Stanford University(斯坦福大学电气工程系) ; Industrial and Systems Engineering, Georgia Institute of Technology(佐治亚理工学院工业与系统工程系)
Comments To be presented at IEEE Conference on Decision and Control (CDC) 2025
机构 * Georgia Institute of Technology(佐治亚理工学院)
Comments 6 pages with 7 figures and 3 tables
机构 * Georgia Institute of Technology(佐治亚理工学院)
Comments Accepted as spotlight at NeurIPS 2025
机构 * Texas A&M University(德克萨斯A&M大学) ; Georgia Institute of Technology(佐治亚理工学院)
机构 * Google DeepMind(谷歌DeepMind) ; KAIST(韩国科学技术院) ; Google(谷歌) ; Google Research(谷歌研究) ; Georgia Institute of Technology(佐治亚理工学院)
Comments CVPR 2025, Project page: https://kyungmnlee.github.io/capo.github.io/
机构 * Georgia Institute of Technology(佐治亚理工学院) ; Tsinghua University(清华大学)
Comments 9 pages, 5 figures
机构 * Bose Corporation(博世公司) ; Georgia Institute of Technology(佐治亚理工学院)
Comments Accepted into WASPAA 2025 demo session
机构 * University of Toronto(多伦多大学) ; Vector Institute(向量研究所) ; Shanghai Jiao Tong University(上海交通大学) ; Wilfrid Laurier University(威尔弗里德·劳里埃大学) ; Acceleration Consortium(加速联盟) ; Georgia Institute of Technology(佐治亚理工学院)
Comments Accepted at CoRL 2025
机构 * Department of Management Science and Engineering, Stanford University(斯坦福大学管理科学与工程系) ; H. Milton Stewart School of Industrial and Systems Engineering, Georgia Institute of Technology(佐治亚理工学院H. Milton Stewart工业与系统工程学院)
Comments arXiv admin note: text overlap with arXiv:2302.03151
机构 * Department of Electrical and Computer Engineering(电气与计算机工程系) ; Georgia Institute of Technology(佐治亚理工学院) ; Department of Mathematics(数学系) ; Massachusetts Institute of Technology(麻省理工学院)
Comments NeurIPS 2024 Spotlight. Revise calculation errors
机构 * Georgia Institute of Technology(佐治亚理工学院) ; Nvidia(英伟达)
机构 * School of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, USA(电气与计算机工程学院,佐治亚理工学院,亚特兰大,美国) ; School of Computational Science and Engineering, Georgia Institute of Technology, Atlanta, USA(计算科学与工程学院,佐治亚理工学院,亚特兰大,美国) ; School of Public Health, UT Southwestern Medical Center, Dallas, USA(公共卫生学院,德克萨斯西南医学中心,达拉斯,美国) ; Wallace H. Coulter Department of Biomedical Engineering, Georgia Institute of Technology and Emory University, Atlanta, GA, USA(沃克·赫·库勒生物医学工程学院,佐治亚理工学院和埃默里大学,亚特兰大,佐治亚州,美国)
机构 * Georgia Institute of Technology(佐治亚理工学院)
Comments 10 pages, 12 figures
机构 * Georgia Institute of Technology(佐治亚理工学院)
Comments Accepted at 39th Conference on Neural Information Processing Systems (NeurIPS 2025) and Oral at Conference on Robot Learning (CoRL 2025)
机构 * FAIR at Meta(Meta 的 FAIR 研究中心) ; School of Chemical and Biomolecular Engineering, Georgia Institute of Technology(佐治亚理工学院化学与生物分子工程学院) ; University of Tennessee-Oak Ridge Innovation Institute, Oak Ridge National Laboratory(田纳西大学奥本海默创新研究所) ; Department of Chemical Engineering, Carnegie Mellon University(卡内基梅隆大学化学工程系)