一作NeurIPS 2026Spotlight
When Policy Entropy Constraint Fails: Preserving Diversity in Flow-based RLHF via Perceptual Entropy
Xiaofeng Tan · Jun Liu · Bin-Bin Gao · Yuanting Fan · Xi Jiang · Chengjie Wang · Hongsong Wang · Feng Zheng
对齐与偏好OpenReview
首次获取该候选人的完整档案及 StartLux 评估共 20 积分;每位用户单独解锁,之后查看免费。主动刷新 20 积分。
实时查找电子邮箱,费用不超过20积分;未找到邮箱不扣费。
Xiaofeng Tan · Jun Liu · Bin-Bin Gao · Yuanting Fan · Xi Jiang · Chengjie Wang · Hongsong Wang · Feng Zheng