Scholar
Chenyuan Yang
Google Scholar ID: 2M-Bb9EAAAAJ
University of Illinois Urbana-Champaign
System Reliability
Machine Learning
Follow
Homepage
↗
Google Scholar
↗
Citations & Impact
All-time
Citations
1,147
H-index
10
i10-index
10
Publications
11
Co-authors
6
list available
Contact
Email
cy54@illinois.edu
CV
Open ↗
Twitter
Open ↗
GitHub
Open ↗
Publications
9 items
VeruSAGE: A Study of Agent-Based Verification for Rust Systems
2025
Cited
0
Lookahead Tree-Based Rollouts for Enhanced Trajectory-Level Exploration in Reinforcement Learning with Verifiable Rewards
2025
Cited
0
Multilingual Routing in Mixture-of-Experts
2025
Cited
0
A Multi-Dimensional Constraint Framework for Evaluating and Improving Instruction Following in Large Language Models
2025
Cited
0
KNighter: Transforming Static Analysis with LLM-Synthesized Checkers
2025
Cited
0
Automated Proof Generation for Rust Code via Self-Evolution
arXiv.org · 2024
Cited
3
AutoVerus: Automated Proof Generation for Rust Code
arXiv.org · 2024
Cited
2
TESTEVAL: Benchmarking Large Language Models for Test Case Generation
arXiv.org · 2024
Cited
0
Load more
Resume (English only)
Academic Achievements
Paper accepted at SOSP 2025: 'KNighter: Transforming Static Analysis with LLM-Synthesized Checkers'
Paper accepted at OOPSLA 2025: 'AutoVerus: Automated Proof Generation for Rust Code' — Distinguished Artifact Award
Paper accepted at ASPLOS 2025: 'KernelGPT: Enhanced Kernel Fuzzing via Large Language Models'
Paper accepted at OOPSLA 2024: 'WhiteFox: White-box Compiler Fuzzing Empowered by Large Language Models'
Co-authored paper at ISSTA 2023: 'Large Language Models are Zero-Shot Fuzzers'
First-authored paper at ICSE 2023: 'Fuzzing Automatic Differentiation in Deep-Learning Libraries'
Led or contributed to research projects: FreeFuzz, DeepREL, NablaFuzz, WhiteFox, TitanFuzz, KernelGPT, KNighter, TestEval, AutoVerus
Background
PhD student at University of Illinois at Urbana-Champaign (UIUC) since Fall 2022, advised by Prof. Lingming Zhang
Research focuses on the intersection of software systems and machine learning, aiming to enhance the reliability of large-scale systems
Leverages and optimizes ML- and LLM-powered testing, reasoning, and verification techniques
Research has detected 630+ critical bugs in ML systems, C/C++ compilers, and operating systems, including 40 CVEs
Supported by the Capital One PhD Fellowship
Co-authors
6 total
Co-author 1
Co-author 2
Co-author 3
Zijie Zhao
University of Illinois at Urbana-Champaign
Jiawei Liu
University of Illinois Urbana-Champaign
Shan Lu
Professor of Computer Science, University of Chicago
×
Welcome back
Sign in to Agora
Welcome back! Please sign in to continue.
Email address
Password
Forgot password?
Continue
Do not have an account?
Sign up