Your Language Model is Its Own Critic: Reinforcement Learning with Value Estimation from Actor's Internal States
Paper • 2605.07579 • Published • 12
Hyeongjin Kim
madokalif
AI & ML interests
None yet
Recent Activity
upvoted a paper 1 day ago
KL for a KL: On-Policy Distillation with Control Variate Baseline updated a dataset 20 days ago
madokalif/pluralistic-value-conflict-benchmarkOrganizations
None yet
upvoted 2
papers 1 day ago