Research Interest
I am interested in video generation.
Check my Google Scholar for the most updated list of publications. * denotes equal contribution.
AtlasVid: Efficient Ultra-High-Resolution Long Video Generation via Decoupled Global-Local Modeling
Ziyang Mai* ,
Yuyao Zhang*,
Yu-Wing Tai
NeurIPS 2026
Paper
/
Project Page
Your browser does not support the video tag.
ContextAnyone: Context-Aware Diffusion for Character-Consistent Text-to-Video Generation
Ziyang Mai ,
Yu-Wing Tai
arXiv Preprint, arXiv:2512.07328
Paper
Motion Inversion for Video Customization
Luozhou Wang*,
Ziyang Mai* ,
Guibao Shen,
Yixun Liang,
Xin Tao,
Pengfei Wan,
Di Zhang,
Yijun Li,
Yingcong Chen
SIGGRAPH 2O25 Conference Paper
Paper /
Project Page /
Code
Page Last Updated: September 2026