I am a DPhil student of WhiRL at University of Oxford, advised by Prof. Shimon Whiteson. I’m also a member of AIMS CDT. I’m generally interested in improving the efficiency and generalization of reinforcement learning (RL) to make it more applicable in real world. I mainly focus on meta-RL and multi-task RL to achieve this goal, with application in domains such as robotics and science.

Previously, I graduated from Tsinghua University with Bachelor in Electronic Engineering and Master in Computer Science, working on automated machine learning with Prof. Wenwu Zhu.

I’m graduating soon and looking for job opportunities. If you find my background a good fit, let’s chat!

Email / Google Scholar / Github / Zhihu 知乎

Education

• University of Oxford (2020 - 2025), DPhil in Computer Science, supervised by Prof. Shimon Whiteson
• Tsinghua University (2017 - 2020), MSc in Computer Science, supervised by Prof. Wenwu Zhu.
• Tsinghua University (2013 - 2017), BSc in Electronic Engineering

Work Experience

• Huawei, London (2023.8 - 2023.12)
• Mila (2019.12 - 2020.3), advised by Prof. Jian Tang
• University of Freiburg (2019.7 - 2019.9), advised by Prof. Frank Hutter

Publications

• Efficient Domain Adaptation of Robotic Foundation Models via Hypernetwork-Generated LoRA
  NeurIPS 2024 AFM Workshop
  Zheng Xiong*, Siddhant Sharma*, Kang Li, Risto Vuorio, Shimon Whiteson

• Distilling Morphology-Conditioned Hypernetworks for Efficient Universal Morphology Control
  ICML 2024
  Zheng Xiong, Risto Vuorio, Jacob Beck, Matthieu Zimmer, Kun Shao, Shimon Whiteson
  Paper

• Pangu-Agent: A Fine-Tunable Generalist Agent with Structured Reasoning
  Filippos Christianos*, Georgios Papoudakis*, Matthieu Zimmer, Thomas Coste, Zhihao Wu, Jingxuan Chen, Khyati Khandelwal, James Doran, Xidong Feng, Jiacheng Liu, Zheng Xiong, Yicheng Luo, Jianye Hao, Kun Shao, Haitham Bou-Ammar, Jun Wang
  Paper

• Recurrent Hypernetworks are Surprisingly Strong in Meta-RL
  NeurIPS 2023
  Jacob Beck, Risto Vuorio, Zheng Xiong, Shimon Whiteson
  Paper

• Universal Morphology Control via Contextual Modulation
  ICML 2023
  Zheng Xiong, Jacob Beck, Shimon Whiteson
  Paper / Code

• A Survey of Meta-Reinforcement Learning
  Jacob Beck*, Risto Vuorio*, Evan Zheran Liu, Zheng Xiong, Luisa Zintgraf, Chelsea Finn, Shimon Whiteson
  Paper

• On the practical consistency of meta-reinforcement learning algorithms
  NeurIPS 2021 Meta Learning Workshop
  Zheng Xiong, Luisa Zintgraf, Jacob Beck, Risto Vuorio, Shimon Whiteson
  Paper

• Graph policy network for transferable active learning on graphs
  NeurIPS 2020
  Shengding Hu, Zheng Xiong, Meng Qu, Xingdi Yuan, Marc-Alexandre Côté, Zhiyuan Liu, Jian Tang
  Paper / Code

• Auto-Lifelong: An AutoML System for Lifelong Machine Learning
  ICML 2019 AutoML Workshop (contributed talk). The second-place winning solution to NeurIPS 2018 AutoML Challenge
  Zheng Xiong, Wenpeng Zhang, Jiyan Jiang, Wenwu Zhu
  Paper / Code