SafetyPairs: Isolating Safety Critical Image Features with Counterfactual Image Generation
机构 * Georgia Tech(佐治亚理工学院) ; Apple(苹果公司)
高校专区
机构 * Georgia Tech(佐治亚理工学院) ; Apple(苹果公司)
机构 * Westlake University(西拉丘市大学) ; Zhejiang University(浙江大学) ; Hunan University(湖南大学) ; Wuhan University(武汉大学) ; Georgia Institute of Technology(佐治亚理工学院)
Comments The Thirty-Ninth Annual Conference on Neural Information Processing Systems(NeurIPS 2025)
机构 * Georgia Institute of Technology(佐治亚理工学院) ; Havard University School of Engineeering and Applied Sciences(哈佛大学工程与应用科学学院)
Comments 41 pages. Accepted at NeurIPS 2025
机构 * Design Intelligence Laboratory, Georgia Institute of Technology(设计智能实验室,佐治亚理工学院)
Comments 14 pages, 7 figures
机构 * University of Washington(华盛顿大学) ; University of Southern California(南加州大学) ; Microsoft(微软) ; University of California, Santa Cruz(加州大学圣克鲁兹分校) ; Georgia Institute of Technology(佐治亚理工学院)
Comments link: https://github.com/ypwang61/One-Shot-RLVR
机构 * Georgia Institute of Technology(佐治亚理工学院) ; Stanford University(斯坦福大学) ; Carnegie Mellon University(卡内基梅隆大学)
Comments 53 pages. AAAI 2025 MARW Best Paper Award. Accepted at NeurIPS 2025 (spotlight)
机构 * Georgia Institute of Technology(佐治亚理工学院) ; Amazon(亚马逊)
Comments Accepted by COLM 2025
机构 * Oak Ridge National Laboratory(橡树岭国家实验室) ; Argonne National Laboratory(阿贡国家实验室) ; York University(约克大学) ; University of Massachusetts Amherst(马萨诸塞大学阿默斯特分校) ; Georgia Institute of Technology(佐治亚理工学院)
Comments 13 pages, 9 figures, 2 tables
机构 * Neurosciences Graduate Program University of California San Diego(加州大学圣地亚哥分校神经科学研究生项目) ; School of Psychology Georgia Tech(佐治亚理工学院心理学系) ; Department of Psychology New York University(纽约大学心理学系) ; Department of Neurobiology University of California San Diego(加州大学圣地亚哥分校神经生物学系)
机构 * Georgia Institute of Technology(佐治亚理工学院) ; Georgia Tech Research Institute(佐治亚理工研究机构) ; The University of Texas at Austin(德克萨斯大学奥斯汀分校) ; Arizona State University(亚利桑那州立大学) ; International Institute of Information Technology Bangalore(班加罗尔国际信息科技研究所)
Comments MLCAD 2024 version of the paper. New case study with ML QoR prediction. Artifact evaluation details included
机构 * School of Electrical and Computer Engineering, Georgia Institute of Technology(电气与计算机工程学院,佐治亚理工学院) ; Georgia Tech Research Institute(佐治亚理工研究机构)
Comments 10 pages, 7 figures, 4 tables, 3 listings