The Teacher Is a Direction, Not a Destination: Extrapolating RL-Induced Representation Residuals in On-Policy Distillation Paper • 2609.36484 • Published 7 days ago • 577
False Frontiers: Diagnosing and Mitigating Co-Cheating in Self-Evolving Search Agents Paper • 2609.39102 • Published 6 days ago • 646
stabilityai/stable-video-diffusion-img2vid-xt Image-to-Video • 2B • Updated Jul 10, 2024 • 146k • 3.44k