Junwei Zhang is currently a Research Fellow (also known as an Assistant Research Professor) at the State Key Laboratory of Blockchain and Data Security, Zhejiang University.
He received his Ph.D. in Software Engineering from Zhejiang University in 2025, under the supervision of Prof. Shanping Li, Assoc. Prof. Lingfeng Bao, and Asst. Prof. Zhongxin Liu, with co-supervision from Prof. Xin Xia and Assoc. Prof. Xing Hu. Before that, he received his master’s and bachelor’s degrees in Software Engineering from Chongqing University in 2021 and 2018, respectively, advised by Prof. Min Gao.
His research interests lie in software engineering, particularly AI for SE, AI for software testing, and mining software repositories, with work on automated unit test generation and evolution, vulnerability analysis, and software engineering benchmarks.
🔥 News
- 2026.09: I was invited to serve on the Journal of Systems & Software. Welcome to submit your papers.
- 2026.09: Our paper, “Bug Whisperer: Unleashing LLMs to Craft Context-Aware Tests Guided by Path Constraints and Bug Clues,” has been accepted by TOSEM.
- 2026.08: I was invited to serve on the Program Committee of FSE 2027 (Industry Track). Welcome to submit your papers.
- 2026.06: Our experience paper on evaluating large language models in unit test evolution was accepted at ISSTA 2026.
Show earlier news
- 2026: Our research agenda on LLM-based unit test generation was accepted by TOSEM, and HieraTest was accepted at SANER 2026.
- 2026: I was invited to serve as Web Chair of FORGE 2026 and on the Program Committee of the ICSME 2026 Research Papers Track.
- 2025: Our paper, “Less is More: On the Importance of Data Quality for Unit Test Generation,” received an ACM SIGSOFT Distinguished Paper Award at FSE 2025. 🏅
📝 Publications
Notation: * denotes a corresponding author. Junwei Zhang is highlighted in each author list. Publication identifiers follow the original list.
2026
[J8] Bug Whisperer: Unleashing LLMs to Craft Context-Aware Tests Guided by Path Constraints and Bug Clues
- Xin Xia, Junwei Zhang*, Xing Hu, and Shanping Li
- ACM Transactions on Software Engineering and Methodology (TOSEM), 2026. Accepted.
[C13] On the Evaluation of Large Language Models in Unit Test Evolution (Experience Paper)
- Weichang Liu, Junwei Zhang*, Yuqing Niu, Bo Zhou, and Shanping Li
- International Symposium on Software Testing and Analysis (ISSTA), 2026. Accepted (Experience Paper).
[C12] A Closer Look at the Malicious Pre-Trained Models on Hugging Face
- Junwei Zhang, Xing Hu*, Xin Xia, David Lo, and Shanping Li
- 1st Journal Ahead Workshop (JAWS), 2026. Accepted.
- Junwei Zhang, Xing Hu*, Cuiyun Gao, Xin Xia, and Shanping Li
- ACM Transactions on Software Engineering and Methodology (TOSEM), 2026. Accepted.
[C11] HieraTest: Hierarchical Dependency–Driven Framework with Multi-Strategy Repair for LLM-based Unit Test Generation
- Weichang Liu, Junwei Zhang*, Xiaochun Zhu, and Bo Zhou
- 33rd International Conference on Software Analysis, Evolution and Reengineering (SANER), 2026. Accepted (Full Paper).
2025
[J6] Assessing and Advancing Benchmarks for Evaluating Large Language Models in Software Engineering Tasks
- Xing Hu, Feifei Niu*, Junkai Chen, Xin Zhou, Junwei Zhang, Junda He, Xin Xia, and David Lo
- ACM Transactions on Software Engineering and Methodology (TOSEM), 2025. Accepted (Full Paper).
[C10] Multi-Stage Generation of Rust Unit Tests with LLMs
- Yongqian Chen, Junwei Zhang, Xing Hu*, and Xin Xia
- 32nd Asia-Pacific Software Engineering Conference (APSEC), 2025. Accepted (Full Paper).
- Junwei Zhang, Xing Hu*, Shing-Chi Cheung, Xin Xia, and Shanping Li
- ACM Transactions on Software Engineering and Methodology (TOSEM), 2025. Accepted (Full Paper).
- ACM
[C9] Enhancing Automated Unit Test Generation with Large Language Models: A Strategic Research Agenda
- Junwei Zhang, Xing Hu*, Cuiyun Gao, Xin Xia, and Shanping Li
- SE 2030 @ FSE, 2025. Accepted (Full Paper).
[C8] Less is More: On the Importance of Data Quality for Unit Test Generation
[C7] TRACETS4J: A Traceable Unit Test Generation Dataset
- Xuancheng Jin, Zhuang Liu, Junwei Zhang, Xing Hu*, and Xin Xia
- 32nd International Conference on Software Analysis, Evolution and Reengineering (SANER), 2025. Accepted (Full Paper).
- IEEE
2024
[C6] Dual Prompt-Based Few-Shot Learning for Automated Vulnerability Patch Localization
- Junwei Zhang, Xing Hu*, Lingfeng Bao, Xin Xia, and Shanping Li
- International Conference on Software Analysis, Evolution and Reengineering (SANER), 2024. Accepted (Full Paper).
- IEEE
[C5] Pre-training by Predicting Program Dependencies for Vulnerability Analysis Tasks
[C4] Inside Bug Report Templates: An Empirical Study on Bug Report Templates in Open-Source Software
- Junwei Zhang, Zhongxin Liu, Lingfeng Bao, Zhenchang Xing, Xing Hu, and Xin Xia
- Internetware, 2024.
- ACM
2023
[J4] Vulnerability Detection by Learning from Syntax-Based Execution Paths of Code
- Junwei Zhang, Zhongxin Liu, Xing Hu, Xin Xia, and Shanping Li
- IEEE Transactions on Software Engineering (TSE), 2023. Accepted (Full Paper).
- IEEE
2022
[J3] Gray-Box Shilling Attack: An Adversarial Learning Approach
- Zongwei Wang, Min Gao, Jundong Li, Junwei Zhang, and Jiang Zhong
- ACM Transactions on Intelligent Systems and Technology (TIST), 13(5): 82:1–82:21, 2022.
- ACM
2021
[J2] Path-based reasoning over heterogeneous networks for recommendation via bidirectional modeling
- Junwei Zhang, Min Gao, Junliang Yu, Linda Yang, Zongwei Wang, and Qingyu Xiong
- Neurocomputing, 461: 438–449, 2021.
- Preprint · ScienceDirect
[J1] Recommender systems based on generative adversarial networks: A problem-driven perspective
- Min Gao, Junwei Zhang, Junliang Yu, Jundong Li, Junhao Wen, and Qingyu Xiong
- Information Sciences, 546: 1166–1185, 2021.
- Preprint · ScienceDirect
[C3] Double-Scale Self-Supervised Hypergraph Learning for Group Recommendation
[C2] PATR: A Novel Poisoning Attack Based on Triangle Relations Against Deep Learning-Based Recommender Systems
- Meiling Chao, Min Gao, Junwei Zhang, Zongwei Wang, Quanwu Zhao, and Yulin He
- CollaborateCom, Part II, 2021, pp. 435–450.
- Springer
2019
[C1] Nonlinear Transformation for Multiple Auxiliary Information in Music Recommendation
- Junwei Zhang, Min Gao, Junliang Yu, Xinyi Wang, Yuqi Song, and Qingyu Xiong
- IJCNN, 2019, pp. 1–8.
- IEEE
📖 Education
- 2021.09 – 2025.06, Ph.D. in Software Engineering, Zhejiang University, Hangzhou, Zhejiang, China.
- Advisors: Prof. Shanping Li, Assoc. Prof. Lingfeng Bao, and Asst. Prof. Zhongxin Liu.
- Co-advisors: Dr. Xin Xia and Assoc. Prof. Xing Hu.
- 2018.09 – 2021.06, Master’s Degree in Software Engineering, Chongqing University, Chongqing, China.
- Advisor: Prof. Min Gao.
- 2014.09 – 2018.06, Bachelor’s Degree in Software Engineering, Chongqing University, Chongqing, China.
- Advisor: Prof. Min Gao.
💼 Experience
- Research Fellow (Assistant Research Professor), State Key Laboratory of Blockchain and Data Security, Zhejiang University.
- Current position.
- 2022.01 – 2025.01, Research Intern, Huawei, Hangzhou, China.
- Advisors: Dr. Xin Xia and Dr. Kui Liu.
📚 Academic Services
Program Committee Member
Conference Organization
- 2026: Web Chair, FORGE.
Journal Reviewer
- IEEE Transactions on Software Engineering (TSE)
- ACM Transactions on Software Engineering and Methodology (TOSEM)
- Empirical Software Engineering (ESE)
- Journal of Systems & Software (JSS)
- Automated Software Engineering Journal (ASEJ)
- Journal of Software: Evolution and Process
- Frontiers of Computer Science (FCS)
- Expert Systems with Applications (ESWA)
- Engineering Applications of Artificial Intelligence (EAAI)
🔗 Useful Links
- How to Write a Great Research Paper
- Experimentation in Software Engineering
- Mining Massive Data Sets
- Deep Learning Reading List