Trainable Log-linear Sparse Attention for Efficient Diffusion Transformers
Paper
•
2512.16615
•
Published
•
4
Yifan Zhou
SingleZombie
AI & ML interests
Computer Vision, Image Generation
Recent Activity
authored
a paper
6 days ago
WORLDMEM: Long-term Consistent World Simulation with Memory
authored
a paper
6 days ago
TokensGen: Harnessing Condensed Tokens for Long Video Generation
upvoted
a
paper
11 days ago
Trainable Log-linear Sparse Attention for Efficient Diffusion Transformers
Organizations
None yet
upvoted
a
paper
11 days ago