作者位次 #6/7AAAI 2026Poster· Artificial Intelligence
Preference Optimization via Contrastive Divergence: Your Policy Is Secretly an NLL Estimator
Zhuotong Chen · Fang Liu · Xuan Zhu · Haozhu Wang · Jiayu Li · Yanjun Qi · Mohammad Ghavamzadeh
对齐与偏好OpenReview