Yibiao YANG (杨已彪)
I am a Tenure-track Assistant Professor (准聘助理教授/特聘研究员/博导) at the School of Computer Science, Nanjing University. My research focuses on Software Engineering (SE), particularly leveraging AI and Large Language Models (LLMs) to build advanced, automated testing and debugging technologies for complex systems.
🚀 欢迎对软件工程、AI for SE、LLM 或系统可靠性方向感兴趣的优秀本科生和研究生联系我，参与科研实习或攻读硕士、博士学位！查看详情 →
I received my Ph.D. from Nanjing University under the supervision of Prof. Yuming Zhou and was a visiting student at the CREST centre, University College London, co-supervised by Prof. Mark Harman and Prof. Jens Krinke.
Research Interests
My research lies at the intersection of AI and Software Engineering, with a focus on advancing automated techniques for software validation and debugging.
News
- 2026-08 Our technique for validating optimizing SMT solvers via cross-theory approximation was accepted to OOPSLA 2026! Congratulations to Maolin(孙茂林)!
- 2026-06 Our empirical study on bugs in Verilator, a hardware description language compiler, was accepted to ISSTA 2026! Congratulations to Songyan Jiang(蒋松言) and Maolin(孙茂林) (equal contribution)!
- 2026-06 Congratulations to Hongyan(高宏艳) for winning the Excellent Master's Thesis Award and Yifan(黄一凡) for the Nomination Award of the School of Computer Science, Nanjing University (南京大学计算机学院优秀硕士学位论文奖及提名奖)!
- 2025-12 Our LLM-based test suite augmentation technique was accepted to OOPSLA 2026! Congratulations to Zeyu Lu(路则雨)!
- 2025-11 Our skeleton-guided SMT solver fuzzing technique was accepted to ACM ASPLOS 2026! Congratulations to Maolin(孙茂林)!
Older News
- 2025-12 Congratulations to Maolin(孙茂林) for being awarded the China Association for Science and Technology (CAST) Program for Doctoral Candidates of Young Talents Cultivation Project(2025年度中国科协青年科技人才培育工程博士生专项计划)!
- 2025-11 Congratulations to Qingyang(李清扬) for being awarded the Pillar of Excellence Scholarship (Top Award) (南京大学研究生栋梁特等奖学金)!
- 2025-10 Our empirical study revisiting automated compiler fault isolation was accepted to IEEE/ACM ICSE 2026! Congratulations to Qingyang(李清扬) and Maolin(孙茂林)!
- 2025-08 Our technique for validating SMT rewriters via rewrite space exploration was accepted to ACM OOPSLA 2025! Congratulations to Maolin(孙茂林)!
- 2025-04 Our attribute-guided compilation space exploration technique for unveiling compiler faults was accepted to USENIX ATC 2025! Congratulations to Jiangchang(吴江昶)!
- 2024-12 Congratulations to Maolin(孙茂林) for being awarded the NSFC Young Student Basic Research Program for PhD candidate (国家自然科学基金青年学生基础研究项目-博士生)!
- 2024-11 Our LLM-based fuzzing technique for the Rust compiler was accepted to IEEE/ACM ICSE 2025! Congratulations to Hongyan(高宏艳)!
- 2024-10 Our cross-level debugging technique for debugger toolchain validation was accepted to ACM ASPLOS 2025!
Selected Publications [Full List]
* Corresponding author; † Equal contribution.
⭐ Featured
|
Validating Optimizing SMT Solvers via Cross-Theory Approximation ContributionIRis implements the cross-theory approximation methodology to validate optimizing SMT solvers by exploiting relationships between solution spaces of different logical theories, uncovering 24 previously unknown bugs in Z3 and OptiMathSAT (20 subsequently fixed by developers).
|
|
Once4All: Skeleton-Guided SMT Solver Fuzzing with LLM-Synthesized Generators ContributionOnce4All is a novel LLM-assisted fuzzing framework for SMT solvers that synthesizes reusable term generators from documentation to efficiently ensure syntactic validity and semantic diversity, dramatically reducing computational overhead and latency.
|
|
Using a Sledgehammer to Crack a Nut? Revisiting Automated Compiler Fault Isolation ContributionThis study contributes to a deeper understanding of practical compiler fault localization by demonstrating that the simple, developer-aligned BIC-based (BASIC) strategy significantly outperforms conventional Spectrum-Based Fault Localization (SBFL) techniques.
|
|
Towards Understanding the Bugs in Verilator, a Hardware Description Language Compiler ContributionThis empirical study systematically characterizes the bugs in Verilator, a widely used hardware description language compiler, offering insights that guide future testing and debugging of HDL compilers.
|
|
Validating SMT Rewriters via Rewrite Space Exploration Supported by Generative Equality Saturation ContributionAries is a novel validation technique that thoroughly explores the SMT solver's rewrite space by using mimetic mutation and deductive rewriting to identify critical bugs, particularly in the rewrite systems.
|
|
Unveiling Compiler Faults via Attribute-Guided Compilation Space Exploration ContributionATLAS is a novel attribute-guided compiler testing approach that strategically inserts C/C++ attributes into test programs, enabling a more flexible and comprehensive exploration of the compilation space to uncover bugs in compilers like GCC and LLVM.
|
|
Debugger Toolchain Validation via Cross-Level Debugging ContributionDevil is a novel debugger toolchain validation framework that introduces Cross-Level Debugging (CLD) to compare execution traces from the same executable at different debugging levels, overcoming limitations of prior approaches by establishing robust consistency relations.
|
By Year
| 2026 |
|
OptFuzz: Enhancing Compiler Testing via LLM-Powered Compilation Option Generation |
|
Boosting Compiler Fault Localization: Getting the Best of Both Worlds by Fusing Dynamic and Historical Data |
|
Testing like Mad Libs: Fuzzing SMT Solvers with Historical Unusual Inputs Empowered by LLMs |
|
Beyond Coverage: Automatic Test Suite Augmentation for Enhanced Effectiveness Using Large Language Models |
|
Isolating Compiler Faults via Multiple Pairs of Adversarial Compilation Configurations |
| 2025 |
|
Isolating Compiler Faults through Differentiated Compilation Configurations |
|
ClozeMaster: Fuzzing Rust Compiler by Harnessing LLMs for Infilling Masked Real Programs |
| 2024 |
|
Code-Line-Level Bugginess Identification: How Far Have We Come, and How Far Have We Yet to Go? |
|
Assessing Effectiveness of Test Suites: What Do We Know and What Should We Do? |
| 2023 |
|
SMT Solver Validation Empowered by Large Pre-trained Language Models |
|
Validating SMT Solvers via Skeleton Enumeration Empowered by Historical Bug-Triggering Inputs |
|
Heterogeneous Testing for Coverage Profilers Empowered with Debugging Support |
Earlier Publications (2019 & earlier)
| 2019 |
|
Automatic Self-Validation for Code Coverage Profilers |
|
Hunting for Bugs in Code Coverage Tools via Randomized Differential Testing |
| 2016 |
|
Effort-Aware Just-in-Time Defect Prediction: Simple Unsupervised Models Could Be Better Than Supervised Models |
|
An Empirical Study on Dependence Clusters for Effort-Aware Fault-Proneness Prediction |
| 2015 |
|
Are Slice-Based Cohesion Metrics Actually Useful in Effort-Aware Post-Release Fault-Proneness Prediction? An Empirical Study |
Ph.D. Students
M.Sc. Students
- 蒋松言 Songyan Jiang (2025.09 - )
- 梁晨曦 Chenxi Liang (2025.09 - )
- 刘轩灵 Xuanling Liu (2025.09 - )
- 朱玉栋 Yudong Zhu (2025.09 - )
- 胡冰旗 Bingqi Hu (2026.09 - )
- 蒙兴 Xing Meng (2026.09 - )
- 周洪田 Hongtian Zhou (2026.09 - )
- 朱万里 Wanli Zhu (2026.09 - )
Alumni (M.Sc.)
-
高宏艳
Hongyan Gao
(2023.09 - 2026.06)
2024年国家奖学金
2024年南京大学优秀研究生标兵
2026年南京大学计算机学院优秀硕士学位论文奖 -
黄一凡
Yifan Huang
(2023.09 - 2026.06)
2026年南京大学计算机学院优秀硕士学位论文提名奖
2026年南京大学优秀毕业生 -
闫梦琪
Mengqi Yan
(2023.09 - 2026.06)
2024年南京大学研究生公益服务优秀奖
2024年南京大学优秀研究生
2025年南京大学优秀共青团员
2025年南京大学研究生英才奖学金硕士一等奖
2025年南京大学优秀研究生
2026年南京大学优秀毕业生
Awards & Honors
- 2025江苏省计算机学会优秀科技工作者
- 2025南京大学优秀研究生德育导师
- 2024江苏省计算机学会青年科技奖
- 2018江苏省优秀博士学位论文
- 2018南京大学优秀博士学位论文
Teaching
- 2026年春高级程序设计
- 2025年秋C语言程序设计基础
- 2024年秋C语言程序设计基础
- 2023年秋C语言程序设计基础
- 2022年秋C语言程序设计基础
Professional Services
- 2023.09 -CCF 高级会员
- 2026.06 -江苏省计算机学会计算机应用专委会副主任
招募信息 (Recruitment)
我们研究组常年招收有志于在软件工程、AI/LLM for SE、软件测试与调试、编译技术、系统可靠性等领域深入研究的硕士生和博士生。课题组经费充足，受国家自然科学基金（面上/青年）、江苏省自然科学基金及华为软件新技术联合实验室等项目持续支持，提供完善的计算资源和自由的学术氛围。
我期待的申请者具备以下特质（满足其一或多项）：
- 对编程、软件系统可靠性研究有浓厚的兴趣；
- 具备扎实的编程能力（如 C/C++/Python/Rust）或良好的数学/算法基础；
- 具有良好的英文阅读和写作能力。
联系方式： 如果您对课题组研究方向感兴趣，欢迎将 个人简历 (CV)、本科/研究生成绩单、简短的研究兴趣陈述 发送至我的邮箱： yangyibiao (at) nju.edu.cn。
Contact
Office
Room 722, Computer Science Building, Nanjing University
163 Xianlin Avenue, Nanjing 210023, China