I am currently a senior researcher at Alibaba DAMO Academy, focusing on AIGC, especially video generation. Prior to this, I worked as a research engineer at Tencent TEG, responsible for city generation.

I received my PhD from South China University of Technology (SCUT) under the supervision of Prof. Qiong Liu. During my PhD, I visited the University of California, Merced, where I studied dynamic neural networks under the guidance of Prof. Ming-Hsuan Yang and Dr. Varun Jampani. My academic journey began at SCUT, where I earned my B.Eng. in software engineering.

Beyond research, I actively engage with the academic community as a reviewer for top-tier conferences and enjoy playing computer games in my free time.

Research Interests: Video Generation, Image Generation

Selected Publications

[Google Scholar]

RealisDance-DiT: Simple yet strong baseline towards controllable character animation in the wild.
arXiv, 2025.
Jingkai Zhou*, Yifan Wu*, Shikai Li, Min Wei, Chao Fan, Weihua Chen, Wei Jiang, Fan Wang.
pdf / project page / code (github)

RealisHuman: A two-stage approach for refining malformed human parts in generated images.
AAAI, 2025.
Benzhi Wang, Jingkai Zhou, Jingqi Bai, Yang Yang, Weihua Chen, Fan Wang, Zhen Lei.
pdf / code (github)

RealisDance: Equip controllable character animation with realistic hands.
arXiv, 2024.
Jingkai Zhou, Benzhi Wang, Weihua Chen, Jingqi Bai, Dongyang Li, Aixi Zhang, Hao Xu, Mingyang Yang, Fan Wang.
pdf / code (github)

Adversarial Score Distillation: When score distillation meets GAN.
CVPR, 2024.
Min Wei*, Jingkai Zhou*, Junyao Sun, Xuesong Zhang.
pdf / project page / code (github)

What limits the performance of local self-attention?
IJCV, 2023.
Jingkai Zhou, Pichao Wang, Jiasheng Tang, Fan Wang, Qiong Liu*, Hao Li, Rong Jin.
pdf / code (github)

Decoupled dynamic filter networks.
CVPR, 2021.
Jingkai Zhou, Varun Jampani, Zhixiong Pi, Qiong Liu*, Ming-Hsuan Yang.
pdf / video / project page / code (github)