Your Language Model is Its Own Critic: Reinforcement Learning with Value Estimation from Actor's Internal States
Paper • 2605.07579 • Published • 15
pikachu
optimized-pikachu
AI & ML interests
None yet
Recent Activity
upvoted a paper 6 days ago
KL for a KL: On-Policy Distillation with Control Variate Baseline upvoted a paper 24 days ago
ThinkBrake: Efficient Reasoning via Log-Probability Margin Guided DecodingOrganizations
None yet