I am currently a Senior Staff Researcher at the Kling Team,
Kuaishou Technology. I lead a team spanning multimodal video generation
(Omni), reinforcement learning for video generation, video generative super-resolution,
and next-generation unified multimodal models. Recently, my research has focused on
next-state-prediction-style generative video pre-training, aiming to build native unified multimodal foundation models
as a step toward world models. Previously, I was a Senior Staff Researcher at
Tencent ARC Lab
and
Tencent AI Lab.
I received my Ph.D. from
Multimedia Lab (MMLab),
the Chinese University of Hong
Kong, advised by Prof.
Xiaoou Tang
and Prof.
Chen Change Loy. I obtained my
bachelor's degree from
Zhejiang University.
