Divot: Diffusion Powers Video Tokenizer for Comprehension and Generation
Paper
•
2412.04432
•
Published
•
13
qiulu
qiulu66
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
8 days ago
Divot: Diffusion Powers Video Tokenizer for Comprehension and Generation
upvoted
a
paper
9 days ago
Moto: Latent Motion Token as the Bridging Language for Robot
Manipulation
upvoted
a
paper
9 days ago
GenMAC: Compositional Text-to-Video Generation with Multi-Agent
Collaboration
Organizations
None yet
qiulu66's activity
upvoted
a
paper
8 days ago
upvoted
2
papers
9 days ago
liked
a
dataset
12 days ago
updated
a
dataset
about 1 month ago