Yong (Norris) Zhang
Beijing, China
Representative works on AIGC image and video generation:
-- Foundation Video Models : VideoCrafter series, DynamiCrafter, LVDM, CV-VAE,
-- Human Video Models : LongCat-Video-Avatar, MeiGen-InfiniteTalk, MeiGen-MultiTalk,
-- Controllable Generation : AnchorCrafter, StereoCrafter, DepthCrafter, Make-Your-Video, Make-Your-Anchor, StyleCrafter, AnimateZero,
-- ID Consistency : VideoMaker, CustomCrafter, CustomTTT, OMG, CeleBias, TaleCrafter, Animate-a-story ,
-- Long Video Generation : DiTCtrl , FreeNoise ,
-- High-resolution : DAM-VSR , Noise Calibration , ScaleCrafter , Make-a-cheap-scaling ,
-- Interpolation : ZeroSmooth , ToonCrafter
-- Video Editing : FateZero , MOFA-Video ,
-- Benchmark : EvalCrafter ,
News
Two papers (Infinite-World and WildActor) accepted by ICML 2026.
MAViD conditionally accepted to SIGGRAPH 2026.
Two papers (UMind and ORCA) accepted by CVPR 2026.
MultiTalk has been accepted by NeurIPS 2025.
Two papers (DAM-VSR and Mobius) conditionally accepted to SIGGRAPH 2025.
Two papers accepted to CVPR 2025. Congratulations to the co-authors.
Two papers (CustomCrafter and CustomTTT) accepted to AAAI 2025. Congratulations to the co-authors.
Two papers accepted to NeurIPS 2024. Congratulations to Sijie and Liang Chen.
Two papers conditionally accepted to Siggraph Asia 2024. Congratulations to the co-authors.
Five papers accepted to ECCV 2024. Congratulations to the co-authors.
Congratulations to Ziyao! Our "face swapping" paper has been accepted to TOG
