When Numbers Speak: Aligning Textual Numerals and Visual Instances in Text-to-Video Diffusion Models
Paper • 2604.08546 • Published • 115
Xin Zhou
LMD0311
·
AI & ML interests
None yet
Recent Activity
liked a model 5 days ago
H-EmbodVis/HERMESV2 published a model 5 days ago
H-EmbodVis/HERMESV2 updated a model 6 days ago
H-EmbodVis/HERMESV2Organizations
authored a
paper 25 days ago
authored 4
papers about 1 month ago
Seeing the Future, Perceiving the Future: A Unified Driving World Model for Future Generation and Perception
Paper • 2503.13587 • Published
More Than Generation: Unifying Generation and Depth Estimation via Text-to-Image Diffusion Models
Paper • 2510.23574 • Published
Less is Enough: Training-Free Video Diffusion Acceleration via Runtime-Adaptive Caching
Paper • 2507.02860 • Published
Out of Sight but Not Out of Mind: Hybrid Memory for Dynamic Video World Models
Paper • 2603.25716 • Published • 156