Mitigating Forgetting Between Supervised and Reinforcement Learning Yields Stronger Reasoners
机构 * Georgia Institute of Technology(佐治亚理工学院) ; Adobe Research(Adobe研究) ; Rutgers University(罗格斯大学)
高校专区
机构 * Georgia Institute of Technology(佐治亚理工学院) ; Adobe Research(Adobe研究) ; Rutgers University(罗格斯大学)
机构 * The Hong Kong University of Science and Technology(香港科学与技术大学) ; Georgia Institute of Technology(佐治亚理工学院) ; University of Massachusetts Amherst(马萨诸塞大学阿默斯特分校) ; TwelveLabs
机构 * Georgia Institute of Technology(佐治亚理工学院) ; Rutgers University(罗格斯大学) ; University of Illinois Chicago(伊利诺伊大学香槟分校)
Comments 22 pages
机构 * Georgia Institute of Technology(佐治亚理工学院)
机构 * UC San Diego(加州大学圣地亚哥分校) ; Massachusetts Institute of Technology(麻省理工学院) ; Georgia Institute of Technology(佐治亚理工学院) ; Carnegie Mellon University(卡内基梅隆大学) ; Tongji University(同济大学) ; Tsinghua University(清华大学) ; University of Pennsylvania(宾夕法尼亚大学)
机构 * Georgia Institute of Technology(佐治亚理工学院) ; Cisco Systems(思科系统)
机构 * Georgia Institute of Technology, Atlanta, GA 30332 USA(佐治亚理工学院)
Comments Accepted to Twelfth Annual Conference on Advances in Cognitive Systems