AI Papers Daily

#EM

1 篇

Learning from Language Feedback via Variational Policy Distillation

通过变分策略蒸馏从语言反馈中学习

🧭 LLM ★ 深度解读

Salesforce AI Research

将语言反馈学习形式化为变分EM，通过教师与学生的协进化蒸馏持续提升推理性能

LLM | 2026-05-14 | cs.LG | score 8/10

Variational Policy DistillationSelf-DistillationEMRLVRLanguage FeedbackTrust Region