About Me

Hello, I’m Yuwei Zhao, a Ph.D. student at the School of Computer Science, Peking University, supervised by Prof. Yingfei Xiong.

My research focuses on automated code performance optimization with large language models, with particular attention to performance gains, reliability, and transferability across programming languages and real-world projects.

Education

Publications

• Multi-Source and Cross-Scenario Strategy-Guided Code Optimization.

  Yuwei Zhao, Qianyu Xiao, Ye Cui, Yijun Yu, Yingfei Xiong.

  Under review, 2026

• SemOpt: LLM-Driven Code Optimization via Rule-Based Analysis.

  Yuwei Zhao, Yuan-An Xiao, Qianyu Xiao, Zhao Zhang, Yingfei Xiong.

  TOSEM, 2026

• Superfusion: Eliminating Intermediate Data Structures via Inductive Synthesis.

  Ruyi Ji, Yuwei Zhao, Nadia Polikarpova, Yingfei Xiong, Zhenjiang Hu.

  PLDI, 2024

• Decomposition-Based Synthesis for Applying Divide-and-Conquer-Like Algorithmic Paradigms.

  Ruyi Ji, Yuwei Zhao, Yingfei Xiong, Di Wang, Lu Zhang, Zhenjiang Hu.

  TOPLAS, 2024