Tuna-2: Pixel Embeddings Beat Vision Encoders for Multimodal Understanding and Generation
Paper • 2604.24763 • Published • 37
Wupingyu
wpy1999
AI & ML interests
None yet
Recent Activity
upvoted a paper about 8 hours ago
Tuna-2: Pixel Embeddings Beat Vision Encoders for Multimodal Understanding and Generation upvoted a paper 6 months ago
Routing Matters in MoE: Scaling Diffusion Transformers with Explicit
Routing Guidance authored a paper about 1 year ago
Wan: Open and Advanced Large-Scale Video Generative ModelsOrganizations
None yet