Xinyuan Chen

Research Scientist
Shanghai Artificial Intelligence Laboratory

Adjunct PhD Advisor
Shanghai Jiao Tong University

Research Interests:
Generative AI
Image and Video Generation
Diffusion Models

Email: chenxinyuan [at] pjlab.org.cn
Google Scholar

Dr. Xinyuan Chen is a Research Scientist at Shanghai Artificial Intelligence Laboratory, and adjunct PhD advisor at Shanghai Jiao Tong University. She obtained my dual PhD degree from Shanghai Jiao Tong University and University of Technology Sydney, advised by Prof.Xiaokang Yang and Prof. Dacheng Tao.

My research interests lies in the area of computer vision and generative model, including video generation, image generation, and world models.

I am happy to work with self-motivated research interns at Shanghai AI lab. Feel free to contact me if you are interested.

[2026/03] 2 papers (ShotDirector and VDOT) accepted at CVPR 2026.

[2026/01] CineTrans accepted at ICLR 2026.

[2025/05] Timestep Master accepted at ICML 2025.

[2025/02] 3 papers (Cinemo, RAPO and Ouroboros3D) accepted at CVPR 2025.

[2025/01] VBench++ accepted at TPAMI 2025.

[2024/09] 4Diffusion accepted at NeurIPS 2024.

[2024/02] VBench selected as CVPR 2024 Highlight.

[2024/01] SEINE accepted at ICLR 2024 as Spotlight.

ShotDirector: Directorially Controllable Multi-Shot Video Generation with Cinematographic Transitions
Xiaoxue Wu, Xinyuan Chen, Yaohui Wang, Yu Qiao
CVPR 2026
[Paper] [Project Page]

VDOT: Efficient Unified Video Creation via Optimal Transport Distillation
Yaohui Wang, Haiyu Zhang, Tianfan Xue, Yu Qiao, Yi Wang, Cunjian Chen, Xinyuan Chen
CVPR 2026
[Paper] [Project Page] [Code]

CineTrans: Learning to Generate Videos with Cinematic Transitions via Masked Diffusion Models
Xiaoxue Wu, Bingjie Gao, Yu Qiao, Yaohui Wang, Xinyuan Chen
ICLR 2026
[Paper] [Project Page] [Code]

SEINE: Short-to-Long Video Diffusion Model for Generative Transition and Prediction
Xinyuan Chen, Yaohui Wang, Lingjun Zhang, Shaobin Zhuang, Xin Ma, Jiashuo Yu, Yali Wang, Dahua Lin, Yu Qiao, Ziwei Liu
ICLR 2024 Spotlight
[Paper] [Project Page] [Code]

LaVie: High-Quality Video Generation with Cascaded Latent Diffusion Models
Yaohui Wang*, Xinyuan Chen*, Xin Ma*, Shangchen Zhou, Ziqi Huang, Yi Wang, Ceyuan Yang, Yinan He, Jiashuo Yu, Peiqing Yang, Yuwei Guo, Tianxing Wu, Chenyang Si, Yuming Jiang, Cunjian Chen, Chen Change Loy, Bo Dai, Dahua Lin, Yu Qiao, Ziwei Liu
IJCV 2024
[Paper] [Project Page] [Code]

Vchitect-2.0: Parallel Transformer for Scaling Up Video Diffusion Models
Weichen Fan, Chenyang Si, Junhao Song, Zhenyu Yang, Yinan He, Long Zhuo, Ziqi Huang, Ziyue Dong, Jingwen He, Dongwei Pan, Yi Wang, Yuming Jiang, Yaohui Wang, Peng Gao, Xinyuan Chen, Hengjie Li, Dahua Lin, Yu Qiao, Ziwei Liu
arXiv 2025
[Paper] [Code]

Latte: Latent Diffusion Transformer for Video Generation
Xin Ma, Yaohui Wang, Xinyuan Chen, Gengyun Jia, Ziwei Liu, Yuan-Fang Li, Cunjian Chen, Yu Qiao
TMLR 2025
[Paper] [Project Page] [Code]

VBench: Comprehensive Benchmark Suite for Video Generative Models
Ziqi Huang, Yinan He, Jiashuo Yu, Fan Zhang, Chenyang Si, Yuming Jiang, Yuanhan Zhang, Tianxing Wu, Qingyang Jin, Nattapol Chanpaisit, Yaohui Wang, Xinyuan Chen, Limin Wang, Dahua Lin, Yu Qiao, Ziwei Liu
CVPR 2024 Highlight
[Paper] [Project Page] [Code]

Vlogger: Make Your Dream A Vlog
Shaobin Zhuang, Kunchang Li, Xinyuan Chen*, Yaohui Wang*, Ziwei Liu, Yu Qiao, Yali Wang*
CVPR 2024
[Paper] [Project Page] [Code]

Cinemo: Consistent and Controllable Image Animation with Motion Diffusion Models
Xin Ma, Yaohui Wang, Gengyun Jia, Xinyuan Chen, Tien-Tsin Wong, Yuan-Fang Li, Cunjian Chen, Yu Qiao
CVPR 2025
[Paper] [Project Page] [Code]