Tuna-2: Pixel Embeddings Beat Vision Encoders for Multimodal Understanding and Generation
Paper • 2604.24763 • Published • 70
fangzixun
fangzx
·
AI & ML interests
None yet
Recent Activity
upvoted an article about 1 year ago
KV Caching Explained: Optimizing Transformer Inference Efficiency upvoted a paper over 1 year ago
DepthLab: From Partial to CompleteOrganizations
upvoted a paper 15 days ago
upvoted an article about 1 year ago
Article
KV Caching Explained: Optimizing Transformer Inference Efficiency
not-lain
• • 326 upvoted a paper over 1 year ago
updated a
model almost 2 years ago