作者位次 #4/8NeurIPS 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