All modalities are equal, but video is more equal: Closing the Cross-Attention Gap in Joint Video Generation
Paper • 2609.27901 • Published • 5
Sapir Yiflach
sapiry7
AI & ML interests
None yet
Recent Activity
upvoted a paper about 9 hours ago
All modalities are equal, but video is more equal: Closing the Cross-Attention Gap in Joint Video Generation liked a model almost 2 years ago
nvidia/NVLM-D-72B liked a model almost 2 years ago
meta-llama/Llama-3.2-11B-Vision-InstructOrganizations
None yet
upvoted a paper about 9 hours ago