I am currently a Ph.D. candidate at the Institute of Artificial Intelligence, Beihang University, and a member of CoLab, advised by Prof. Si Liu, with an expected graduation date of 2027.01. I received my B.Eng. from Beihang University in 2021. Currently, I am also a research intern at Tencent HunYuan. My research interests lie in Large Language Models and Deep Reinforcement Learning.

Availability I am currently seeking 2027 new-graduate full-time opportunities in horizon RL. Feel free to reach out via email or WeChat.

News

  • UI-Mate was released for advancing open-weight foundation GUI agents with in-context demonstrations.
  • SPO was accepted to ICLR 2026.

Publications

My earlier research centered on computer vision and multimodal learning; I now focus on reinforcement learning and large language models. Additional publications are available on Google Scholar.

2026
Tech Report
UI-Mate teaser

UI-Mate: Advancing Open-Weight Foundation GUI Agents with In-Context Demonstrations
Zihan Ding, Longxu Dou, Qi Gao, Xiangwu Guo, Shengchao Hu, Zilong Huang, Zihang Jiang, Lei Ke, Mengcheng Lan, Weixian Lei, Hanxuan Li, Honglin Li, Xiyun Li, Zaitang Li, Leowei Liang, Xin Luo, Haozhe Ma, Jiayi Mao, Zhoujie Pan, Can Qin, Tianyuan Qu, Weiqi Wang, Wenkai Wang, Yonglin Wang, Yuxin Wang, Chenxu Wu, Yingchen Yu, Chenyu Zhang, Yuhao Zheng
Authors are listed in alphabetical order by last name.
Technical Report

ICLR 2026
SPO teaser

Single-stream Policy Optimization
Zhongwen Xu and Zihan Ding
Equal contribution
ICLR 2026

Research and Industry Experience

Tencent HunYuan Research Intern (Intern Project Up) 2026.04 - Present Mentor: Leowei Liang

Worked on long-horizon reinforcement learning for computer-use agents.

Tencent AIPD Research Intern (Rhino-Bird Elite Talent) 2025.06 - 2026.03 Mentor: Zhongwen Xu

Worked on LLM post-training to improve reasoning ability.

Meituan Research Intern 2021.09 - 2023.06 Mentor: Junshi Huang

Worked on multimodal understanding and generation.