The Teacher Is a Direction, Not a Destination: Extrapolating RL-Induced Representation Residuals in On-Policy Distillation Paper • 2609.36484 • Published 16 days ago • 562
Edge0/Audio8-ASR-Infinite Automatic Speech Recognition • 4B • Updated 21 days ago • 41.9k • 2.45k
False Frontiers: Diagnosing and Mitigating Co-Cheating in Self-Evolving Search Agents Paper • 2609.39102 • Published 15 days ago • 664