Open to collaboration & discussion

先为力胜

I am a research scientist at ByteDance Seed. My work sits at the intersection of graphics, vision and robotics, with a focus on video generation and embodied AI.

I received my Ph.D. in computer science from ShanghaiTech University, advised by Prof. Lan Xu and Prof. Jingyi Yu. My ultimate aspiration is to realise human-centered super agents that free people from tedious and heavy work.

  • World Models
  • Video Generation
  • Embodied AI
  • Digital Humans
Get in touch Conference timer

Latest news

  • One paper is accepted by SIGGRAPH Asia 2026.
  • One paper is accepted by IROS 2026.
  • Seedance 2.0 technical report is released.
  • Seedance 2.0 is released.
  • InterAgent is accepted by CVPR 2026.
  • OmniHuman 1.5 is accepted by ICLR 2026.Oral
  • One paper is accepted by AAAI 2025.
  • One paper is accepted by SIGGRAPH 2024.
  • OMG is accepted by CVPR 2024.
  • InterGen is accepted by IJCV 2024.
  • One paper is accepted by TVCG 2023.
  • One paper is accepted by AAAI 2023.Oral
  • One paper is accepted by CVPR 2021.Oral

Academic service

  • Conference reviewerICLR · AAAI · ICCV · CVPR · SIGGRAPH
  • Journal reviewerIJCV · TOG · TVCG · TMM
Research

Selected Publications

* Equal contribution + Corresponding author

Seedance 2.0: Advancing Video Generation for World Complexity

Seedance Team, ByteDance Seed

Seed · 2026
Project arXiv

Seedance 1.5 Pro: A Native Audio-Visual Joint Generation Foundation Model

Seedance Team, ByteDance Seed

Seed · 2025
Project arXiv

OmniHuman-1.5: Instilling an Active Mind in Avatars via Cognitive Simulation

OmniHuman Team, ByteDance Seed

ICLR · 2026Oral
Project arXiv

PhyGile: Physics-Prefix Guided Motion Generation for Agile General Humanoid Motion Tracking

Jiacheng Bao*, Haoran Yang*, Yucheng Xin*, Junhong Liu, Yuecheng Xu, Han Liang, Pengfei Han, Xiaoguang Ma, Dong Wang, Bin Zhao

IROS · 2026
Project arXiv Code

InterAgent: Physics-based Multi-agent Command Execution via Diffusion on Interaction Graphs

Bin Li*, Ruichi Zhang*, Han Liang+, Jingyan Zhang, Juze Zhang, Xin Chen, Lan Xu, Jingyi Yu, Jingya Wang+

CVPR · 2026
Project arXiv Code

Media2Face: Co-speech Facial Animation Generation with Multi-Modality Guidance

Qingcheng Zhao, Pengyu Long, Qixuan Zhang, Dafei Qin, Han Liang, Longwen Zhang, Yingliang Zhang, Jingyi Yu, Lan Xu

SIGGRAPH · 2024
Project Paper arXiv Video

OMG: Towards Open-vocabulary Motion Generation via Mixture of Controllers

Han Liang, Jiacheng Bao, Ruichi Zhang, Sihan Ren, Yuecheng Xu, Sibei Yang, Xin Chen, Jingyi Yu, Lan Xu

CVPR · 2024
Project Paper arXiv Video

InterGen: Diffusion-based Multi-human Motion Generation under Complex Interactions

Han Liang, Wenqian Zhang, Wenxuan Li, Jingyi Yu, Lan Xu

IJCV · 2024
Project Paper arXiv Video Code

HybridCap: Inertia-aid Monocular Capture of Challenging Human Motions

Han Liang, Yannan He, Chengfeng Zhao, Mutian Li, Jingya Wang, Jingyi Yu, Lan Xu

AAAI · 2023Oral
Project Paper arXiv Video
Education

Where I studied

UESTC · 电子科技大学

B.E. in Computer Software Engineering

I obtained my bachelor's degree from the University of Electronic Science and Technology of China.

Experience

Where I worked