Xiaochuan Li

Xiaochuan Li 李晓川

Language Technologies Institute,
Carnegie Mellon University

Email: xiaochu4 [at] andrew.cmu.edu

I am a first-year Ph.D. student at Carnegie Mellon University, advised by Prof. Chenyan Xiong. My research interests lie in Machine Learning and Natural Language Processing, with a particular focus on data-centric large language models. I am keen on:

  • The relationship between data and model performance.
  • Tracing the origins of model capabilities (e.g., reasoning) to their data sources.
  • Generating higher-quality and more effective training data.

Prior to attending CMU, I earned my bachelor's degree in Software Engineering with the highest honors from Tsinghua University in 2025. During my exchange at the University of Hong Kong, I was fortunate to work with Prof. Tao Yu on computer-use agents.

Publications

(* stands for equal contribution)

Scaling Computer-Use Grounding via UI Decomposition and Synthesis

Tianbao Xie*, Jiaqi Deng*, Xiaochuan Li*, Junlin Yang*, Haoyuan Wu, Jixuan Chen, Wenjing Hu, Xinyuan Wang, Yuhui Xu, Zekun Wang, Yiheng Xu, Junli Wang, Doyen Sahoo, Tao Yu, Caiming Xiong

arXiv 2025

Montessori-Instruct: Generate Influential Training Data Tailored for Student Learning

Xiaochuan Li, Zichun Yu, Chenyan Xiong

ICLR 2025

OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments

Tianbao Xie, Danyang Zhang, Jixuan Chen, Xiaochuan Li, Siheng Zhao, Ruisheng Cao, Toh Jing Hua, Zhoujun Cheng, Dongchan Shin, Fangyu Lei, Yitao Liu, Yiheng Xu, Shuyan Zhou, Silvio Savarese, Caiming Xiong, Victor Zhong, Tao Yu

NIPS 2024 D&B Track 2024

Experience

Research Intern

Qwen Team
2024.11 - 2025.08

Build a large-scale reinforcement learning infrastructure suitable for training computer-use agents; develop the Qwen3-Coder model.

Selected Honors & Awards

Outstanding Graduates

Tsinghua University

2025

Special-Class Scholarship

Tsinghua University

2024

Comprehensive Excellence Scholarship

Tsinghua University

2023