Pushi Zhang (张蒲石)

Researcher & AI Engineer

Google Scholar | Email: zpschang@gmail.com | Github: zpschang

About Me

I am a researcher and AI engineer passionate about developing intelligent robotics systems that can perceive, understand, and interact with the physical world.

Currently, I work at X Square Robot, where I focus on building advanced robotics systems that bridge the gap between AI research and real-world applications.

Previously, I was a researcher at Microsoft Research Asia in Li Zhao’s group, where I led the Vision-based Game-Testing AI project in collaboration with the Microsoft Xbox team.

Recent News

  • Sep 2025: Released codes and models of PIG-Nav, which achieves strong performance in image-goal navigations
  • Aug 2025: Released Villa-X: Enhancing Latent Action Modeling in Vision-Language-Action Models
  • Oct 2024: Released IGOR: Image-Goal Representations as Atomic Control Units for Foundation Models in Embodied AI

Selected Publications

  • Villa-X: Enhancing Latent Action Modeling in Vision-Language-Action Models
    arXiv 2025 [PDF] [Code] [Website]

  • PIG-Nav: Key Insights for Pretrained Image Goal Navigation Models
    arXiv 2025 [PDF] [Demo] [Code]

  • What Do Latent Action Models Actually Learn?
    NeurIPS 2025 [PDF]

  • IGOR: Image-GOal Representations are the Atomic Control Units for Foundation Models in Embodied AI
    Arxiv 2024 [PDF] [Website]

  • IG-Net: Image-Goal Network for Offline Visual Navigation on A Large-Scale Game Map
    Baiting Zhu*, Pushi Zhang*, Xin-Qiang Cai*, Li Zhao, Masashi Sugiyama, Jiang Bian
    NeurIPS 2023 Robot Learning Workshop [PDF] [Demo]

  • Distributional Pareto-Optimal Multi-Objective Reinforcement Learning
    Xin-Qiang Cai*, Pushi Zhang*, Li Zhao, Jiang Bian, Masashi Sugiyama, Ashley J. Llorens
    NeurIPS 2023 [PDF] [Code]

  • Asking Before Action: Gather Information in Embodied Decision Making with Language Models
    Xiaoyu Chen, Shenao Zhang, Pushi Zhang, Li Zhao, Jianyu Chen
    arXiv 2023 [PDF]

  • An Adaptive Deep RL Method for Non-Stationary Environments with Piecewise Stable Context
    Xiaoyu Chen, Xiangming Zhu, Yufeng Zheng, Pushi Zhang, Li Zhao, Wenxue Cheng, Peng Cheng, Yongqiang Xiong, Tao Qin, Jianyu Chen, Tie-Yan Liu
    NeurIPS 2022 [PDF]

  • Distributional Reinforcement Learning for Multi-Dimensional Reward Functions
    Pushi Zhang, Xiaoyu Chen, Li Zhao, Wei Xiong, Tao Qin, Tie-Yan Liu
    NeurIPS 2021 [PDF] [Code]

  • Independence-aware Advantage Estimation
    Pushi Zhang, Li Zhao, Guoqing Liu, Jiang Bian, Minlie Huang, Tao Qin, Tie-Yan Liu
    IJCAI 2021 [PDF]

  • Demonstration Actor Critic
    Guoqing Liu, Li Zhao, Pushi Zhang, Jiang Bian, Tao Qin, Nenghai Yu, Tie-Yan Liu
    Neurocomputing 2021 [PDF]

About Myself

I hope to make a positive impact by conducting research that contributes meaningfully to society. My goal is to create knowledge and solutions that benefit the world and inspire others along the way.

Last update: 2025.10.5