Where Should Diffusion Enter a Language Model? Geometry-Guided Hidden-State Replacement Paper • 2605.14368 • Published 8 days ago • 13
Your Language Model is Its Own Critic: Reinforcement Learning with Value Estimation from Actor's Internal States Paper • 2605.07579 • Published 14 days ago • 16
KL for a KL: On-Policy Distillation with Control Variate Baseline Paper • 2605.07865 • Published 14 days ago • 19
ThinkBrake: Efficient Reasoning via Log-Probability Margin Guided Decoding Paper • 2510.00546 • Published Apr 20 • 14
