arxiv:2405.07990
WANG Jiahao
techmonsterwang
AI & ML interests
Scalable and efficient neural networks for vision and language
Recent Activity
upvoted a paper about 6 hours ago
Tuna-2: Pixel Embeddings Beat Vision Encoders for Multimodal Understanding and Generation published a model 3 days ago
techmonsterwang/LINA-c2i-d48w1536-marvae published a model 3 days ago
techmonsterwang/LINA-t2i-d48w1536-sdxl512Organizations
None yet