I am a fourth-year PhD student in the School of Computer Science at Peking University, advised by Prof. Hao Dong. Previously I was under the supervision of Prof. Yizhou Wang in the Center on Frontiers of Computing Studies (CFCS), PKU. I obtained my Bachelor degree in 2021, from the School of Electronics Engineering and Computer Science of Peking University.

My research interest lies in building adaptive embodied agents that align with human values. Specifically, I focus on Robot Learning, LLM-based Agent and Reinforcement Learning.

πŸ”₯ News

  • 2025.06:Β  AdaRPG accepted at ICCV 2025! πŸŽ‰
  • 2025.04:Β  AdaManip Code Release! Check our repository!
  • 2025.01:Β  AdaManip accepted at ICLR 2025! πŸŽ‰
  • 2024.05:Β  PACE accepted at ICML 2024! πŸŽ‰

πŸ“ Publications

* denotes equal contribution

ICLR 2025
sym

AdaManip: Adaptive Articulated Object Manipulation Environments and Policy Learning

Yuanfei Wang*, Xiaojie Zhang*, Ruihai Wu*, Yu Li, Yan Shen, Mingdong Wu, Zhaofeng He, Yizhou Wang, Hao Dong

International Conference on Learning Representations (ICLR) 2025

[Webpage] [Paper] [Code] [Video]

ICCV 2025
sym

Adaptive Articulated Object Manipulation On The Fly with Foundation Model Reasoning and Part Grounding

Xiaojie Zhang*, Yuanfei Wang*, Ruihai Wu*, Kunqi Xu, Yu Li, Liuyu Xiang, Hao Dong, Zhaofeng He

International Conference on Computer Vision (ICCV) 2025

[Paper(Coming Soon)]

arxiv
sym

From Strangers to Assistants: Fast Desire Alignment for Embodied Agent-User Adaptation

Yuanfei Wang, Xinju Huang, Fangwei Zhong, Yaodong Yang, Yizhou Wang, Yuanpei Chen, Hao Dong

arxiv preprint, in submission

[Paper]

arxiv
sym

Boosting Universal LLM Reward Design through Heuristic Reward Observation Space Evolution

Zen Kit Heng†, Zimeng Zhao†, Tianhao Wu*, Yuanfei Wang*, Mingdong Wu, Yangang Wang, Hao Dong

arxiv preprint, in submission

[Webpage] [Paper]

ICML 2024
sym

Fast Peer Adaptation with Context-aware Exploration

Long Ma*, Yuanfei Wang*, Fangwei Zhong, Song-Chun Zhu, Yizhou Wang

International Conference on Machine Learning (ICML) 2024

[Webpage] [Paper] [Code]

ICLR 2022
sym

ToM2C: Target-oriented Multi-agent Communication and Cooperation with Theory of Mind

Yuanfei Wang*, Fangwei Zhong*, Jing Xu, Yizhou Wang

International Conference on Learning Representations (ICLR) 2022

[Paper] [Code]

πŸŽ– Honors and Awards

  • Samsung Scholarship, Peking University, 2022.09
  • Third Class Scholarship, Peking University, 2020.09
  • Schlumberger Scholarship, Peking University, 2019.09
  • Outstanding Graduate Award, Peking University, 2021.06
  • Merit Student Award, Peking University, 2019,2020,2022
  • Academic Excellence Award, Peking University, 2018,2023

πŸ“– Educations

  • 2021.09 - now: Ph.D. in Computer Science, Peking University
  • 2017.09 - 2021.06: B.Sc. in Intelligence Science and Technology, Peking University

πŸ’¬ Invited Talks

  • 2022.07: Multi-Agent Communication and Cooperation with Theory of Mind, RLChina Forum. [Video] [bilibili]
  • 2022.05: Cognition Inspired Multi-Agent Communication and Cooperation, Beijing Institute for General Artificial Intelligence(BIGAI).