Zhaoxu (Josh) Zhang (张兆旭)

Email: zhaoxu dot zhang dot 1 at gmail dot com
Google Scholar | LinkedIn

I am a Software Engineering researcher with a strong interest in developing automated solutions to enhance the reliability and efficiency of software development.

Currently, I work as a Research Scientist at Meta, where I focus on leveraging Generative AI to improve developer productivity. Prior to this, I interned at Amazon AWS on the automated reasoning team, where I explored neural-symbolic reasoning methods to mitigate hallucinations in large language models. I also interned at Samsung Research America, applying agentic AI approaches to the analysis of security bug reports.

I earned my Ph.D. in the Department of Computer Science, University of Southern California (USC), supervised by Prof. William G.J. Halfond. My Ph.D. research focused on automatically generating UI tests for mobile applications from natural language descriptions. I received my B.Eng. degree at Southern University of Science and Technology (SUSTech) in 2020 supervised by Prof. Yepang Liu.

Education

  • University of Southern California
    Sep. 2020 - Jun. 2025
    Ph.D. in Computer Science
    Honor: Graduate School Fellowship
    Los Angeles, California USA
  • Southern University of Science and Technology
    Sep. 2016 - Jun. 2020
    B.E. in Computer Science
    Honor: Summa Cum Laude
    Shenzhen, Guangdong China

Publications

* denotes equal contribution

  1. [PACMSE-FSE 2025] Zhaoxu Zhang, Komei Yu, Tingting Yu, William G.J. Halfond. Automated Recognition of Buggy Behaviors from Mobile Bug Reports. In the the ACM on Software Engineering Issue FSE 2025, Trondheim, Norway, June 23-27, 2025 (Acceptance Rate 135/515=26%).

  2. [MSR 2025] Dingbang Wang, Zhaoxu Zhang, Sidong Feng, William G.J. Halfond, Tingting Yu. An Empirical Study on Leveraging Images in Automated Bug Report Reproduction. In the the International Conference on Mining Software Repositories, Ottawa, Canada, April 28-29, 2025.

  3. [ISSTA 2024] Dingbang Wang, Yu Zhao, Sidong Feng, Zhaoxu Zhang, William G.J. Halfond, Chunyang Chen, Xiaoxia Sun, Jiangfan Shi, Tingting Yu. Feedback-Driven Automated Whole Bug Report Reproduction for Android Apps.. In the the ACM International Symposium on Software Testing and Analysis, Vienna, Austria, Sept 16-20, 2024. [pdf]

  4. [PACMSE-FSE 2024] Zhaoxu Zhang, Fazle Mohammed Tawsif, Komei Ryu, Tingting Yu, William G.J. Halfond. Mobile Bug Report Reproduction via Global Search on the App UI Model. In the the ACM on Software Engineering Issue FSE 2024, Porto de Galinhas, Brazil, July 15-19, 2024 (Acceptance Rate 121/483=25%). [pdf]

  5. [ISSTA 2023] Zhaoxu Zhang, Robert Winn, Yu Zhao, Tingting Yu, William G.J. Halfond. Automatically Reproducing Android Bug Reports Using Natural Language Processing and Reinforcement Learning. In the 32nd ACM SIGSOFT International Symposium on Software Testing and Analysis, Seattle, Washington, USA, July 17-21, 2023 (Acceptance Rate 117/372=31.4%). [pdf] [website] [tool]

  6. [SANER 2020] Zhaoxu Zhang*, Hengcheng Zhu*, Ming Wen, Yida Tao, Yepang Liu, Yingfei Xiong. How Do Python Framework APIs Evolve? An Exploratory Study. In the 27th IEEE International Conference on Software Analysis, Evolution and Reengineering London, Ontario, Canada, February 18-21, 2020. [pdf] [slides] [talk]

Service

  • Journal reviewer: TSE 2024 (sub-reviewer), TOSEM 2023, IoT 2023 (sub-reviewer)
  • PC member: ISSTA 2023 Artifact Evaluation Track

Honors and Award

  • Summa Cum Laude Graduate, 南方科技大学十佳毕业生 (June 2020)
  • SUSTech Annual Outstanding Student, First Level (October 2018)
  • SUSTech Annual Outstanding Student, First Level (October 2017)