UniEvo-VL: An On-policy Self-Distillation Training Recipe for Multimodal Model Self-improvement
Paper • 2609.38721 • Published • 134
Li Erran Li
erranli
·
AI & ML interests
None yet
Recent Activity
upvoted a paper about 1 month ago
UniEvo-VL: An On-policy Self-Distillation Training Recipe for Multimodal Model Self-improvement updated a model 10 months ago
thinking-bio-lab/new_unimomo published a model 10 months ago
thinking-bio-lab/new_unimomoOrganizations
upvoted a paper about 1 month ago