AI Lab Tracker
Labs
Timeline
What's New
Collections
Sign in
Labs
Timeline
What's New
Divot
model
2024-12-05
Tencent
Your tags
+ Collections
Create
Your notes
Add note
Diffusion-powered video tokenizer for comprehension and generation, unifying video understanding and synthesis. Published at CVPR 2025.
Paper (arXiv)
GitHub
Model Details
Paper
Venue
CVPR 2025
arXiv
HTML
video
tokenizer
generation
research