The Teacher Is a Direction, Not a Destination: Extrapolating RL-Induced Representation Residuals in On-Policy Distillation Paper • 2609.36484 • Published 4 days ago • 338
False Frontiers: Diagnosing and Mitigating Co-Cheating in Self-Evolving Search Agents Paper • 2609.39102 • Published 3 days ago • 256
UniEvo-VL: An On-policy Self-Distillation Training Recipe for Multimodal Model Self-improvement Paper • 2609.38721 • Published 3 days ago • 272
Beyond Visual Similarity: Entity-Aligned Retrieval for Knowledge-Based Visual Question Answering Paper • 2608.21450 • Published Aug 19 • 25
Repo-To-Skill: Distilling GitHub Repositories Into AI4AI Skills Paper • 2609.02749 • Published about 1 month ago • 407