Scholar
Lei Zhang
Google Scholar ID: K8di4JwAAAAJ
Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences
Citations & Impact
Citations
4,606
H-index
11
i10-index
12
Publications
16
Co-authors
6
list available
Publications
Resume (English only)
Academic Achievements
- Published several academic papers, including 'CodeArena: Evaluating and Aligning CodeLLMs on Human Preference' (EMNLP'25), 'SWE-Flow: Synthesizing Software Engineering Data in a Test-Driven Manner' (ICML'25), and more. Contributed to multiple technical reports such as the Qwen3-Coder Technical Report and the Qwen3 Technical Report.
Research Experience
- During his Ph.D. studies at the University of Chinese Academy of Sciences, he served as a core contributor for multiple technical reports, responsible for infrastructure implementation and training data synthesis for Agentic Coding. As an intern at Alibaba Qwen Group, he was responsible for integrating and conducting code evaluation (EvalPlus, Multiple, LiveCodeBench, BigCodeBench) for iterative model development.
Education
- Ph.D. in Computer Application Technology, University of Chinese Academy of Sciences, 2021-present; B.Sc. in Computer Science, University of Chinese Academy of Sciences, 2017-2021.
Background
- Research interests include Agentic Coding, Agentic Reinforcement Learning, and Natural Language Processing. Currently, a Ph.D. student at the University of Chinese Academy of Sciences, Beijing, China, and an intern at Alibaba Qwen Group, conducting research on Large Language Models (LLMs) and their applications.
