UniEvo-VL: An On-policy Self-Distillation Training Recipe for Multimodal Model Self-improvement
Paper • 2609.38721 • Published • 295
Jacob Green
jacobgreenwo
·
AI & ML interests
Building AI tools for small businesses
Recent Activity
updated a model 8 days ago
jacobgreenwo/mobilevit-demo86 published a model 8 days ago
jacobgreenwo/mobilevit-demo86Organizations
None yet
upvoted 4
papers 8 days ago
The Teacher Is a Direction, Not a Destination: Extrapolating RL-Induced Representation Residuals in On-Policy Distillation
Paper • 2609.36484 • Published • 582
MaLiang-Harness: A Programmable Path to Image and Video Generation
Paper • 2609.34309 • Published • 413
False Frontiers: Diagnosing and Mitigating Co-Cheating in Self-Evolving Search Agents
Paper • 2609.39102 • Published • 677