Chengpeng Wang

Bio

Chengpeng Wang is a Post-Doctoral Researcher in Department of Computer Science at Purdue University, West Lafayette, working with Prof. Xiangyu Zhang. He will be joining the School of Computing (SoC) at the National University of Singapore (NUS) as an Assistant Professor starting in August 2026. His research mainly focuses on the use of program analysis, especially static analysis, to improve software reliability and performance. Currently, his research is centered around the intersection of symbolic analysis and machine learning, specifically large language models, aiming to provide code quality assurance in AI-assisted software development.

Chengpeng has published extensively at premium venues of software engineering (ICSE, FSE, ASE, ISSTA, TOSEM, TSE), programming languages (OOPSLA, ECOOP), systems (ATC, ASPLOS, EuroSys, TOCS), and machine learning/natural language processing (ICML, NeurIPS, EMNLP). His research received awards including ACM SIGPLAN Distinguished Paper Award and ASPLOS Best Paper Award. He obtained his Ph.D. degree at Hong Kong University of Science and Technology (HKUST), supervised by Prof. Charles Zhang. During his Ph.D. study, he also enjoyed several industrial experiences in Sourcebrella, Ant Group, and Veridise. Before that, he received his master and bachelor degrees at Tsinghua University (THU).

Prospective Students

I am looking for Ph.D./RA/Intern students to join my group at the NUS. I am especially interested in working with self-motivated students who have strong backgrounds in Program Analysis, Code LLMs, LLM-aided Program Analysis, and (Coding) Agents. If you’re interested, please drop me an email (wang6590@purdue.edu) with your CV.

News

• 📚 (Pinned) We are actively maintaining the paper list of CodeLLMPaper. Welcome to star, fork, and contribute.
• (02/2026) I am serving on the program committee of ICSE'27. Please consider submitting your work!
• (11/2025) I released RepoSlice, an eduational framework of LLM-driven program slicing. Here is the tutorial.
• (11/2025) I was honored to receive the ASE 2025 Distinguished Reviewer Award.
• (09/2025) Our work RFCAudit was accepted by ASE'25. It has detected dozens of functional bugs in network protocol implementations. Congratulations to Mingwei!
• (09/2025) Our benchmark CoRe was accepted by NeurIPS'25 (Spotlight). It is a high-quality, human-verified benchmark designed to evaluate LLMs on fundamental static analysis tasks. Congratulations to Danning and Mingwei!
• (07/2025) We released the preprint of BugScope, an agent that learns to detect diverse bugs from examples. It beats Cursor BugBot and CodeRabbit, detecting 2× more real-world bugs with high precision. Check out the preprint for detailed comparisons!
• (05/2025) Excited to announce that RepoAudit was accepted to ICML 2025! It had successfully uncovered over 200 zero-day vulnerabilities in high-profile open-source projects. Welcome to explore our work through our preprint, code, and bug gallery.
• (03/2025) Our work on Protocol Parser Testing was accepted by ISSTA'25. Congratulations to Mingwei!
• (01/2025) I delivered an invited talk titled Advances in AI-powered Code Security to CodeQL team @ GitHub. Here are the slides and recording.
• (11/2024) I was invited to present LLM-aided static analysis at Boston Computation Club. Here are the slides and recording.
• (09/2024) Our work LLMDFA was accepted by NeurIPS'24.
• (09/2024) Our work LLMSAN was accepted by Findings of EMNLP'24.
• (04/2024) Our work GiantSan received Best Paper Award at ASPLOS 2024. Congratulations to Hao!
• (12/2023) I passed my Ph.D. defense and officially obtained Ph.D. degree on the last day of 2023!

Research Directions

• Neuro-Symbolic Static Analysis:
  
  
  • Library/Bug specification inference [FSE'24][EuroSys'25]
  • Compilation-free and customizable static analysis [EMNLP'24][NeurIPS'24][NeurIPS'25]
  • Repository-level LLM-driven code auditing [ICML'25][ASE'25][arxiv'25]
• Fundamental Problems in Program Analysis:
  
  
  • Precise memory modeling [OOPSLA'22][TOSEM'22][FSE'24][ASPLOS'24a][TOCS'25]
  • Precise and scalable static bug detection [TOSEM'23][ICSE'24][ICSE'24][TSE'24a][FSE'25][TOSEM'25]
  • User-friendly static analysis infrastructure [ECOOP'23][ASPLOS'24b]
• Domain-Specific Static Analysis and its Applications:
  
  
  • Bug detection and repair: Build maintenance systems [ISSTA'20][ASE'22][TSE'24b]
  • Code understanding and refactoring: FinTech systems [ICSE'23][ASE'23]
  • Testing: Database management systems [ATC'23][ISSTA'24], Network protocol parsers [ISSTA'25][ASE'25]

Selected Publications [Full List]

• RepoAudit: An Autonomous LLM-Agent for Repository-Level Code Auditing
  Jinyao Guo#, Chengpeng Wang#, Xiangzhe Xu, Zian Su, and Xiangyu Zhang

  (#:Equal Contribution)
  International Conference on Machine Learning (ICML), July, 2025.

• LLMDFA: Analyzing Dataflow in Code with Large Language Models
  Chengpeng Wang, Wuqi Zhang, Zian Su, Xiangzhe Xu, Xiaoheng Xie, and Xiangyu Zhang

  Annual Conference on Neural Information Processing Systems (NeurIPS), Dec, 2024.

• Sanitizing Large Language Models in Bug Detection with Data-Flow
  Chengpeng Wang, Wuqi Zhang, Zian Su, Xiangzhe Xu, and Xiangyu Zhang

  Findings of Empirical Methods in Natural Language Processing (Findings of EMNLP), Nov, 2024.

• DAInfer: Inferring API Aliasing Specifications from Library Documentation via Neurosymbolic Optimization
  Chengpeng Wang, Jipeng Zhang, Rongxin Wu, and Charles Zhang

  ACM International Conference on the Foundations of Software Engineering (FSE), July, 2024.

• DCLink: Bridging Data Constraint Changes and Implementations in FinTech Systems
  Wensheng Tang#, Chengpeng Wang#, Peisen Yao, Rongxin Wu, Xianjin Fu, Gang Fan, and Charles Zhang

  (#:Equal Contribution)
  The IEEE/ACM International Conference on Automated Software Engineering (ASE), Sept, 2023.

• Synthesizing Conjunctive Queries for Code Search
  Chengpeng Wang, Peisen Yao, Wensheng Tang, Gang Fan, and Charles Zhang

  European Conference on Object-Oriented Programming (ECOOP), July, 2023.

• Verifying Data Constraint Equivalence in FinTech Systems
  Chengpeng Wang, Gang Fan, Peisen Yao, Fuxiong Pan, and Charles Zhang

  The IEEE/ACM International Conference on Software Engineering (ICSE), May, 2023.

• Anchor: Fast and Precise Value-Flow Analysis for Containers via Memory Orientation
  Chengpeng Wang, Wenyang Wang, Peisen Yao, Qingkai Shi, Jinguo Zhou, Xiao Xiao, and Charles Zhang

  The ACM Transactions on Software Engineering and Methodology (TOSEM), Sept, 2022.

• Complexity-Guided Container Replacement Synthesis
  Chengpeng Wang, Peisen Yao, Wensheng Tang, Qingkai Shi, and Charles Zhang

  The ACM SIGPLAN Conference on Objected Oriented Programming, Systems, Languages and Applications (OOPSLA), Nov, 2022.

  ACM SIGPLAN Distinguished Paper Award

Awards

ASE Distinguished Reviewer Award, ACM SIGSOFT 2025

NeurIPS Spotlight Paper, NeurIPS 2025

Postdoc Travel Award, Purdue University, 2024

ACM SIGARCH Best Paper Award, ASPLOS 2024

UGC Research Travel Grant, HKUST, 2022~2023

Ant Group Outstanding Collaboration Award, 2023

ACM SIGPLAN Distinguished Paper Award, OOPSLA 2022

ACM SIGPLAN PAC Award, 2022

Outstanding Tutor Award (2019), Student Learning and Development Center, THU

Future Scholar Scholarship (2016), Graduate School, THU

Scholarship for Academic Excellence (2013, 2014), THU

Teaching

CS 510: Software Engineering, Purdue University, Fall 2025

CS 592: AI and Security, Purdue University, Fall 2024

COMP 3021: Java Programming, HKUST, Spring 2022 & Fall 2022 & Spring 2023

COMP 4631: Computer and Communication Security, HKUST, Fall 2021

COMP 3111/H: Software Engineering, HKUST, Fall 2020

COMP 2011: Programming with C++, HKUST, Spring 2020

Haskell: Functional Language Programming, THU, Spring 2019

Automaton and Formal Logic, THU, Fall 2018

Drop-in Tutoring for STEM Courses, THU, Spring/Fall 2018/2019

Service

Program Committee Member

ICSE'27, PLDI'26, ISSTA'26, FSE'26, LLM4Code'26, NeurIPS'25, ASE'25, ISSRE'25, Forge'25, FSE'25, ISSTA'25, SPLASH'24 SRC, ASE'24 (industrial track), ISSRE'24, Forge'24

Journal Reviewer

ACM Transactions on Software Engineering and Methodology (TOSEM), IEEE Transactions on Software Engineering (TSE)

Artifact Evaluation Committee

OOPSLA'24, PLDI'23, FSE'22, ISSTA'22

Volunteer

Student Volunteer @ SPLASH 2022, Student Volunteer @ ISSTA 2019

Mentoring