一作ICLR 2026Poster· Reinforcement Learning / OnlineHierarchy-of-Groups Policy Optimization for Long-Horizon Agentic TasksShuo He · Lang Feng · qi wei · Xin Cheng · Lei Feng · Bo An强化学习与后训练智能体与工具OpenReview
作者位次 #3/8CVPR 2026Poster· Computer Vision & Pattern RecognitionTest-Time Attention Purification for Backdoored Large Vision Language ModelsZhifang Zhang · Bojun Yang · Shuo He · Weitong Chen · Wei Emma Zhang · Olaf Maennel · Lei Feng · Miao Xu安全多模态OpenReview 项目页