Siyi Li's Homepage

About Me

I am currently building large language models (LLMs) at XPENG Robotics.

Before that, I haved worked in Tencent and Sea AI Lab on reinforcement learning (RL) for game AI.

I obtained my Ph.D degree in CSE Department from the Hong Kong University of Science and Technology. My Ph.D supervisor was Prof. Dit-Yan Yeung. I was a visiting scholar working with Prof. Matt Mason’s Manipulation Lab in Robotics Institute of Carnegie Mellon University. Before that, I got my Bachelor Degree of Engineering in June 2014 from the College of Computer Science and Technology of Zhejiang University.

We’re seeking research scientist (interns) in LLM/RL/embodied AI. Please drop me an email if you’re interested.

Zichen Liu, Siyi Li, Wee Sun Lee, Shuicheng Yan, Zhongwen Xu. Efficient Offline Policy Optimization with a Learned Model. The Eleventh International Conference on Learning Representations (ICLR), Kigali Rwanda, 1-5 May 2023.
[Paper]
Siyi Li, Jiaji Zhou, Zhenzhong Jia, Dit-Yan Yeung, and Matthew T. Mason. Learning accurate objectness instance segmentation from photo-realistic rendering for robotic manipulation. Proceedings of the 2018 International Symposium on Experimental Robotics (ISER), Buenos Aires, Argentina, 5-8 November 2018.
[Paper]
Siyi Li, Tianbo Liu, Chi Zhang, Dit-Yan Yeung, and Shaojie Shen. Learning unmanned aerial vehicle control for autonomous target following. Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence (IJCAI), Stockholm, Sweden, 13-19 July 2018.
[Paper]
Siyi Li, Dit-Yan Yeung. Visual object tracking for unmanned aerial vehicles: A benchmark and new motion models. Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence (AAAI), pp.4140-4146, San Francisco, California, USA, 4-9 February 2017.
[Paper] [Project Page] [Data]

Zhongwen Xu, Xianliang Wang, Siyi Li, Tao Yu, Liang Wang, Qiang Fu, Wei Yang. Agents Play Thousands of 3D Video Games. CoRR abs/2503.13356 (2025) [Paper]
Naiyan Wang, Siyi Li, Abhinav Gupta, Dit-Yan Yeung. Transferring rich feature hierarchies for robust visual tracking. CoRR abs/1501.04587 (2015) [Paper] [Code]
A survey on methods and applications of deep reinforcement learning. PhD Qualifying Exam, 2017. [Paper][Slides]

COMP2711 Discrete Mathematical Tools for Computer Science, Spring 2015, Teaching Assistant.
COMP1022Q Introduction to Computing with Excel VBA, Fall 2015, Teaching Assistant.
COMP5212 Machine Learning, Spring 2016, Teaching Assistant.