Where Should Diffusion Enter a Language Model? Geometry-Guided Hidden-State Replacement Paper • 2605.14368 • Published 10 days ago • 14
KL for a KL: On-Policy Distillation with Control Variate Baseline Paper • 2605.07865 • Published 16 days ago • 19
Your Language Model is Its Own Critic: Reinforcement Learning with Value Estimation from Actor's Internal States Paper • 2605.07579 • Published 16 days ago • 16
Why Do Multilingual Reasoning Gaps Emerge in Reasoning Language Models? Paper • 2510.27269 • Published Oct 31, 2025 • 7