MM-Zero: Self-Evolving Multi-Model Vision Language Models From Zero Data
Paper • 2603.09206 • Published • 53
Hongyang Du
Hongyang-Du
AI & ML interests
Representation Learning, Explicit/Implicit World Model, Self-supervised Learning
Recent Activity
upvoted a paper 1 day ago
VideoGPA: Distilling Geometry Priors for 3D-Consistent Video Generation upvoted a paper about 1 month ago
Graph of Skills: Dependency-Aware Structural Retrieval for Massive Agent Skills published a model about 1 month ago
Hongyang-Du/wan-dpo-loraOrganizations
None yet
authored a
paper 2 months ago