Guoxi Zhang

prof_pic.jpg

Beijing Institute for General Artificial Intelligence,

2 Yiheyuan Road, Haidian,

Beijing, China 100089.

I am a research scientist at Beijing Institute for General Artificial Intelligence. Previously, I was a PhD student in Graduate School of Informatics, Kyoto university, where I have the fortune to work with Prof. Hisashi Kashima.

My research interests include reinforcement learning and its application in robot learning and neuro-symbolic artificial intelligence. In particular, I am working on using RL for controlling legged robots and leveraging the foundation models in policy learning recently.

News

Jan 28, 2025 Our paper, SYNERGAI: Perception Alignment for Human-Robot Collaboration, has been accepted by ICRA 2025.
Sep 16, 2024 Our paper, VickreyFeedback: Cost-efficient Data Construction for Reinforcement Learning from Human Feedback, has been accepted by PRIMA 2024.
Jun 13, 2024 Our paper, End-to-End Neuro-Symbolic Reinforcement Learning with Textual Explanations, has been selected as a spotlight paper of ICML 2024.

Selected Publications

  1. SYNERGAI: Perception Alignment for Human-Robot Collaboration
    Yixin Chen, Guoxi Zhang, Yaowei Zhang, and 4 more authors
    In Proceedings of the 2025 IEEE International Conference on Robotics and Automation, Atlanta, GA, USA, 2025
  2. End-to-End Neuro-Symbolic Reinforcement Learning with Textual Explanations  Spotlight (top 3.5%)
    Lirui Luo, Guoxi Zhang, Hongming Xu, and 3 more authors
    In Proceedings of the Forty-First International Conference on Machine Learning, Vienna, Austria, 2024