UniEvo-VL: An On-policy Self-Distillation Training Recipe for Multimodal Model Self-improvement
Paper • 2609.38721 • Published • 275
정주원
daeguyoon
AI & ML interests
None yet
Recent Activity
updated a model 3 days ago
daeguyoon/efficientformer-multitask-dev published a model 3 days ago
daeguyoon/efficientformer-multitask-devOrganizations
None yet
upvoted 4
papers 3 days ago
The Teacher Is a Direction, Not a Destination: Extrapolating RL-Induced Representation Residuals in On-Policy Distillation
Paper • 2609.36484 • Published • 465
False Frontiers: Diagnosing and Mitigating Co-Cheating in Self-Evolving Search Agents
Paper • 2609.39102 • Published • 392
MaLiang-Harness: A Programmable Path to Image and Video Generation
Paper • 2609.34309 • Published • 409