Home
News
Members
Interns
Publications
NVIDIA Research
Light
Dark
Automatic
Flex-Forcing: Towards a Unified Autoregressive and Bidirectional Video Diffusion Model
Xinyin Ma
,
Julius Berner
,
Chao Liu
,
Arash Vahdat
,
Weili Nie
,
Xinchao Wang
July 2026
Cite
arXiv
Website
Type
Conference paper
Publication
International Conference on Machine Learning (ICML)
Spotlight
Julius Berner
Chao Liu
Arash Vahdat
Team Lead
Related
Mode Seeking meets Mean Seeking for Long Video Generation
Transition Matching Distillation for Fast Video Generation
Cite
×