Rethinking UMM Visual Generation: Masked Modeling for Efficient Image-Only Pre-training
Paper • 2603.16139 • Published • 28
li
runanli5522
AI & ML interests
None yet
Recent Activity
upvoted a paper 3 days ago
AI Can Learn Scientific Taste upvoted a paper about 1 month ago
MOVA: Towards Scalable and Synchronized Video-Audio GenerationOrganizations
None yet