Yuhong Yang
Con6924
AI & ML interests
Computer Vision, Diffusion Models
Recent Activity
upvoted a paper about 7 hours ago
Tuna-2: Pixel Embeddings Beat Vision Encoders for Multimodal Understanding and Generation upvoted a paper 13 days ago
Rethinking the Diffusion Model from a Langevin Perspective upvoted a paper about 1 month ago
Mixture-of-Depths AttentionOrganizations
None yet