Chenyuan Yang

Chenyuan Yang

PhD student at UIUC

About Me

I am Chenyuan Yang (杨晨源), a PhD student at University of Illinois at Urbana-Champaign advised by Prof. Lingming Zhang since 2022 Fall. I received my B.S. degree with honors from Nanjing University, advised by Prof. Yanyan Jiang.

My research covers the interaction of software systems and machine learning, with the goal of enhancing the reliability of large-scale systems. To this end, I leverage and optimize testing, reasoning, and verification techniques powered by ML and large language models. To date, my research has detected 630+ critical bugs for ML systems, C/C++ compilers, and operating systems, including 40 CVEs.

My research has been generously supported by Capital One PhD Fellowship.

Research Areas

🔧 System Reliability for ML

Synthesizing diverse & high-quality tensor programs across inference (FreeFuzz, DeepREL), training (NablaFuzz), and optimization components (WhiteFox) in ML systems, along with test oracles.

🤖 ML for System Reliability

LLM for Testing

Designing LLM-driven workflows to synthesize tests (TitanFuzz, WhiteFox), test generators (KernelGPT), and static analyzers (KNighter) for large-scale software systems. Evaluating LLMs' code reasoning via test generation (TestEval).

LLM for Verification

Training and evaluating LLMs to generate verification proofs for code (AutoVerus).

Selected Publications

For a full list of publications, please refer to Publications.

SOSP 2025

KNighter: Transforming Static Analysis with LLM-Synthesized Checkers

Chenyuan Yang, Zijie Zhao, Zichen Xie, Haoyu Li, Lingming Zhang
The 31st Symposium on Operating Systems Principles, Oct 2025
Paper Code
OOPSLA 2025

AutoVerus: Automated Proof Generation for Rust Code

Chenyuan Yang, Xuheng Li, Md Rakib Hossain Misu, Jianan Yao, Weidong Cui, Yeyun Gong, Chris Hawblitzel, Shuvendu Lahiri, Jacob R. Lorch, Shuai Lu, Fan Yang, Ziqiao Zhou, Shan Lu
Object-Oriented Programming, Systems, Languages, and Applications 2025 (in PACM PL), Oct 2025
Paper Code Website
ASPLOS 2025

KernelGPT: Enhanced Kernel Fuzzing via Large Language Models

Chenyuan Yang, Zijie Zhao, Lingming Zhang
30th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, March 2025
Paper Code
OOPSLA 2024

WhiteFox: White-box Compiler Fuzzing Empowered by Large Language Models

Chenyuan Yang, Yinlin Deng, Runyu Lu, Jiayi Yao, Jiawei Liu, Reyhaneh Jabbarvand, Lingming Zhang
Object-Oriented Programming, Systems, Languages, and Applications 2024 (in PACM PL), Oct 2024
Paper Code Slides
ISSTA 2023

Large Language Models are Zero-Shot Fuzzers: Fuzzing Deep-Learning Libraries via Large Language Models

Yinlin Deng, Chunqiu Steven Xia, Haoran Peng, Chenyuan Yang, Lingming Zhang
32nd International Symposium on Software Testing and Analysis, July 2023
Paper Code
ICSE 2023

Fuzzing Automatic Differentiation in Deep-Learning Libraries

Chenyuan Yang, Yinlin Deng, Jiayi Yao, Yuxing Tu, Hanchi Li, Lingming Zhang
45th International Conference on Software Engineering, May 2023
Paper Code Slides

* denotes joint first authors

Internships

Microsoft Research, Systems Research Group Summmer 2025

Microsoft Research, Systems Research Group Summmer 2024

Google Labs, Project Starline Summmer 2023