一作ICML 2026Poster· Reinforcement Learning / Deep RLHuman-in-the-Loop Policy Optimization for Preference-Based Multi-Objective Reinforcement LearningTianmeng Hu · Biao Luo · Ke Li强化学习与后训练对齐与偏好社会与人本OpenReview
一作ICML 2026Poster· Applications / Chemistry, Physics, and Earth SciencesCocoRNA: Collective RNA Design with Cooperative Multi-agent Reinforcement LearningTianmeng Hu · Biao Luo · Ke Li智能体与工具强化学习与后训练OpenReview