UniEvo-VL: An On-policy Self-Distillation Training Recipe for Multimodal Model Self-improvement
Paper • 2609.38721 • Published • 294
L. Mercier
mercier47
·
AI & ML interests
Pizza is my favorite algorithm
Recent Activity
updated a model 17 days ago
mercier47/experiment-classification published a model 17 days ago
mercier47/experiment-classificationOrganizations
None yet