About
简介
I am an Assistant Professor in Software Institute at Nanjing University. Before joining Nanjing University, I was a Research Scientist at Nanyang Technological University (NTU), advised by Prof. Yi Li. I received my Ph.D. from the School of Computing at the Australian National University (ANU), advised by Prof. Zhenchang Xing.
现任南京大学准聘助理教授。此前任职于南洋理工大学（NTU），担任 Research Scientist。于澳大利亚国立大学（ANU）计算机学院获博士学位，导师为 邢振昌教授。
研究方向聚焦可信智能软件工程，覆盖软件全生命周期，重点关注 AI 辅助开发的可理解性、可靠性与一致性。首先致力于实现人与 AI 之间对程序语义、开发意图及业务需求的双向理解；在此基础上，借助程序分析与重构优化技术，保证 AI 生成代码的质量；最终在软件持续迭代过程中，维持代码、文档、UI、配置、接口等各类工件之间的语义同步。
在 ICSE、FSE、TSE 等软件工程领域顶级会议和期刊上发表多篇论文，并获 ICSE 2024 ACM SIGSOFT 杰出论文奖。重视学术成果与实际开发的衔接，积极将研究落地为可用工具，已开发 RIdiom IDE 插件、RefactoringIdioms Python 包，以及 DeIdiom 在线平台。
My research focuses on trustworthy intelligent software engineering, addressing the entire software lifecycle with a progressive focus on three core objectives of AI-assisted development: understandability, reliability, and consistency. The work aims to first achieve mutual understanding between developers and AI systems regarding program semantics, developer intent, and business requirements. It then employs program analysis, refactoring, and optimization to ensure the quality and reliability of AI-generated code. Finally, as software evolves, it maintains semantic synchronization across all artifacts including code, documentation, UI, configurations, and APIs to keep them consistent throughout iterative development.
I have published papers in top software engineering venues, including ICSE, FSE, and TSE. My work received the ACM SIGSOFT Distinguished Paper Award at ICSE 2024.
A defining theme of my research is bridging research and practice through usable tools. I developed the RIdiom IDE plugin, the RefactoringIdioms Python package, and the DeIdiom web platform, bringing research ideas into practical software development tools.
I am looking for motivated undergraduate, Master’s, and Ph.D. students. If you are interested, please email me your CV at zejun.zhang@nju.edu.cn.
欢迎本科生、硕士生与博士生加入。请将简历发送至 zejun.zhang@nju.edu.cn。
Publications
论文
* Corresponding author * 通讯作者-
CCF-A ASE 2026 LintCFG: DSL-Driven Linter Configuration Generation for Coding StandardsThe 41st IEEE/ACM International Conference on Automated Software Engineering · Tools and Datasets Track
-
CCF-ATSE 2026 GUIGroup: Enabling Functional Layout Grouping with Multimodal Large Language ModelsIEEE Transactions on Software Engineering · Accepted
-
CCF-AFSE 2026 Still Manual? Automated Linter Configuration via DSL-Based LLM Compilation of Coding StandardsACM International Conference on the Foundations of Software Engineering · Research Full Paper
-
CCF-AFSE 2026 Deployability-Centric Infrastructure-as-Code Generation: Fail, Learn, Refine, and Succeed through LLM-Empowered DevOps SimulationACM International Conference on the Foundations of Software Engineering · Research Full Paper
-
CCF-ATSE 2024 Automated Refactoring of Non-Idiomatic Python Code with Pythonic IdiomsIEEE Transactions on Software Engineering
-
CCF-AFSE 2024 Refactoring to Pythonic Idioms: A Hybrid Knowledge-Driven Approach Leveraging Large Language ModelsACM International Conference on the Foundations of Software Engineering · Research Full Paper
-
CCF-AICSE 2024 Hard to Read and Understand Pythonic Idioms? DeIdiom and Explain Them in Non-Idiomatic Equivalent CodeThe 46th ACM/IEEE International Conference on Software Engineering · Research Track Full Paper
-
CCF-AICSE 2023 Faster or Slower? Performance Mystery of Python Idioms Unveiled with Empirical EvidenceThe 45th ACM/IEEE International Conference on Software Engineering · Research Full Paper
-
CCF-AICSE 2023 RIdiom: Automatically Refactoring Non-Idiomatic Python Code with Pythonic IdiomsThe 45th ACM/IEEE International Conference on Software Engineering · Demo Tool Paper
-
CCF-AFSE 2022 Making Python Code Idiomatic by Automatic Refactoring Non-Idiomatic Python Code with Pythonic IdiomsThe 30th ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering · Research Full Paper
-
CCF-AICSE 2021 Unveiling the Mystery of API Evolution in Deep Learning Frameworks – A Case Study of Tensorflow 2The 43rd ACM/IEEE International Conference on Software Engineering · SEIP Track Full Paper
-
CCF-BICPC 2020 Deep-Diving into Documentation to Develop Improved Java-to-Swift API MappingProceedings of the 28th International Conference on Program Comprehension · Research Track Full Paper
-
CCF-BJSS 2020 Enhancing Example-Based Code Search with Functional SemanticsJournal of Systems and Software, Volume 165
-
CCF-CSCAM 2018 Semantics-Based Code Search Using Input/Output ExamplesThe 18th International Working Conference on Source Code Analysis and Manipulation · Research Track Full Paper
-
CCF-CInternetware 2018 A Documentation-Based Constraint Generation Method for Java APIsThe 10th Asia-Pacific Symposium on Internetware · Research Full Paper
Awards
荣誉
- ACM SIGSOFT Distinguished Paper Award (ICSE 2024)
Invited Talks
受邀报告
- Monash University · Invited by Prof. John Grundy (IEEE Fellow)
- 莫纳什大学 · 受 IEEE Fellow John Grundy 教授邀请
- Nanjing University
- 南京大学
- Sun Yat-sen University
- 中山大学
Service
学术服务
Journal Reviewer
期刊审稿
- ACM Transactions on Software Engineering and Methodology (TOSEM)
- Automated Software Engineering (ASE)
Conference Reviewer
会议审稿
- The ACM International Conference on the Foundations of Software Engineering (FSE 2027) — Research Papers
- International Conference on Automated Software Engineering (ASE 2026) — Artifact Evaluation
- International Symposium on Software Testing and Analysis (ISSTA 2026) — Artifact Evaluation
- International Conference on Internetware (Internetware 2026) — Research Papers
- International Conference on AI Engineering (AIware 2025) — Benchmark & Dataset
- International Conference on Software Engineering and Knowledge Engineering (PROMISE 2026)
- International Conference on Agentic Software Engineering (AGENT 2026)
Tools
研究工具
LintCFG
Automatically transforms coding standards into formal rules and validated linter configurations, enabling end-to-end code quality enforcement.
将自然语言代码规范自动转换为形式化规则与经过验证的 Linter 配置，支持端到端的软件质量保障。
RIdiom
An automated tool for refactoring and improving Python code.
面向 Python 的自动化代码重构工具。
DeIdiom
Transforms hard-to-understand Python code into more readable equivalents to facilitate code understanding — the system behind the ICSE 2024 Distinguished Paper.
将难理解的 Python 代码转换为更易读的等价代码，帮助开发者理解代码——相关工作获 ICSE 2024 杰出论文奖。
Web Platform →Teaching
教学
- Advanced Programming with C++ · Undergraduate · Compulsory
- C++ 高级程序设计 · 本科生 · 必修课
Gray PDF / Code / Data buttons mean the URL is not filled in yet.
灰色的 PDF / Code / Data 表示链接尚未填写。