Chuyao Fu

Email · Google Scholar · GitHub

my_photo.jpg

I am Chuyao Fu, a senior undergraduate student in Electronic Information Engineering at SUSTech. My research focuses on world models for robot learning, including representation learning, generative modeling, and the interaction between learned world models and robot control policies.

At SUSTech, I am advised by Prof. Qinghu Meng and Prof. Hong Zhang. I also conduct research with the PKU HMI Lab under Prof. Shanghang Zhang. I am currently spending Fall 2026 at UC Berkeley.

My long-term goal is to build robots that understand physical dynamics and interactions, enabling them to generalize beyond imitation.

News

Jul 31, 2026 Our latest action-conditioned world model, code-named SisyphusWorld, reached #2 on the WorldArena leaderboard and was featured by Synced.
Jun 24, 2026 FORCE, our work on efficient reinforcement fine-tuning for VLA models, is now available on arXiv.
May 01, 2026 Mask World Model was accepted to ICML 2026.
Mar 24, 2026 ProDrive and EchoArena were accepted to the CVPR 2026 GigaBrain Challenge Workshop.
Jun 20, 2025 I joined the PKU HMI Lab and the Embodied Multimodal Large Model Research Center at BAAI as an undergraduate research intern.

Selected Publications All publications

  1. ProDrive: Proactive Planning for Autonomous Driving via Ego-Environment Co-Evolution
    ProDrive: Proactive Planning for Autonomous Driving via Ego-Environment Co-Evolution
    Chuyao Fu, Shengzhe Gan, Zhuoli Ouyang, and 6 more authors
    In CVPR GigaBrain Challenge Workshop, 2026
    arXiv
  2. Token-World: Policy-Oriented World Modeling in VLM Token Space for Robot Manipulation
    Token-World: Policy-Oriented World Modeling in VLM Token Space for Robot Manipulation
    Chuyao Fu, Xiaowei Chi, Yuhan Rui, and 14 more authors
    Submitted to ICRA 2027
    PDF
  3. AxisField-GS: Feed-Forward Articulation Recovery from Single-State Semantic Gaussian Assets
    AxisField-GS: Feed-Forward Articulation Recovery from Single-State Semantic Gaussian Assets
    Shengzhe Gan*, Chuyao Fu*, Yugong Wang, and 2 more authors
    Submitted to ICASSP 2027. * Equal contribution.
    PDF
  4. Mask World Model: Predicting What Matters for Robust Robot Policy Learning
    Mask World Model: Predicting What Matters for Robust Robot Policy Learning
    Yunfan Lou, Xiaowei Chi, Xiaojie Zhang, and 9 more authors
    ICML, 2026
    arXiv