The Teacher Is a Direction, Not a Destination: Extrapolating RL-Induced Representation Residuals in On-Policy Distillation
Paper • 2609.36484 • Published • 556
Jacob Lopez
Jacoblope
·
AI & ML interests
None yet
Recent Activity
updated a model 5 days ago
Jacoblope/thesis-knowledge-distillation29 published a model 5 days ago
Jacoblope/thesis-knowledge-distillation29 liked a model 5 days ago
autotrust/JEV-27B-VLOrganizations
None yet
upvoted 4
papers 11 days ago
MaLiang-Harness: A Programmable Path to Image and Video Generation
Paper • 2609.34309 • Published • 394
False Frontiers: Diagnosing and Mitigating Co-Cheating in Self-Evolving Search Agents
Paper • 2609.39102 • Published • 653
UniEvo-VL: An On-policy Self-Distillation Training Recipe for Multimodal Model Self-improvement
Paper • 2609.38721 • Published • 274