VSTAR: Generative Temporal Nursing for Longer Dynamic Video Synthesis
Paper • 2403.13501 • Published • 9 •
3
Yumeng Li
Yumeng
AI & ML interests
Generative Models, Vision-Language Models, Out-of-Distribution Generalization
Recent Activity
authored a paper 1 day ago
MosaicMem: Hybrid Spatial Memory for Controllable Video World Models upvoted a paper 1 day ago
MosaicMem: Hybrid Spatial Memory for Controllable Video World Models upvoted an article about 1 month ago
A Guide to Reinforcement Learning Post-Training for LLMs: PPO, DPO, GRPO, and BeyondOrganizations
None yet
commented a
paper over 1 year ago
commented a
paper almost 2 years ago
commented a
paper about 2 years ago