Chenyuan Yang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Chenyuan Yang has a total of 24 co-authors. Here are the top co-authors by number of shared publications:
- Lingming Zhang
University of Illinois at Urbana-Champaign, Champaign, USA
4 shared publications - Yinlin Deng
University of Illinois at Urbana-Champaign, Champaign, USA
2 shared publications - Zijie Zhao
University of Illinois at Urbana-Champaign, Champaign, USA
2 shared publications - Chris Hawblitzel
Microsoft Research, Redmond, WA, USA
1 shared publication - Chunqiu Steven Xia
University of Illinois at Urbana-Champaign, Urbana, USA
1 shared publication - Dylan Zhang
University of Illinois Urbana-Champaign University of Chicago
1 shared publication
Latest Publications
- Open Access
- 12 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 655-669
KNighter: Transforming Static Analysis with LLM-Synthesized Checkers
- 12 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 655-669
Open AccessKNighter: Transforming Static Analysis with LLM-Synthesized Checkers
- Open Access
- 9 October 2025
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Programming Languages
- Vol. 9 (OOPSLA2) , 3454-3482
AutoVerus: Automated Proof Generation for Rust Code
Generative AI has shown its value for many software engineering tasks. Still in its infancy, large language model (LLM)-based proof generation lags behind LLM-based code generation. In this paper, we present AutoVerus. AutoVerus uses LLMs to automatically generate correctness proof for Rust code. AutoVerus is designed to match the unique features of Verus, a verification tool that can prove the correctness of Rust code using proofs and specifications also written in Rust. AutoVerus consists of a network of agents that are crafted and orchestrated to mimic human experts' three phases of proof construction: preliminary proof generation, proof refinement guided by generic tips, and proof debugging guided by verification errors. To thoroughly evaluate AutoVerus and help foster future research in this direction, we have built a benchmark suite of 150 non-trivial proof tasks, based on existing code-generation benchmarks and verification benchmarks. Our evaluation shows that AutoVerus can automatically generate correct proof for more than 90% of them, with more than half of them tackled in less than 30 seconds or 3 LLM calls.
- 9 October 2025
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Programming Languages
- Vol. 9 (OOPSLA2) , 3454-3482
Open AccessAutoVerus: Automated Proof Generation for Rust Code
Generative AI has shown its value for many software engineering tasks. Still in its infancy, large language model (LLM)-based proof generation lags behind LLM-based code generation. In this paper, we present AutoVerus. AutoVerus uses LLMs to automatically generate correctness proof for Rust code. AutoVerus is designed to match the unique features of Verus, a verification tool that can prove the correctness of Rust code using proofs and specifications also written in Rust. AutoVerus consists of a network of agents that are crafted and orchestrated to mimic human experts' three phases of proof construction: preliminary proof generation, proof refinement guided by generic tips, and proof debugging guided by verification errors. To thoroughly evaluate AutoVerus and help foster future research in this direction, we have built a benchmark suite of 150 non-trivial proof tasks, based on existing code-generation benchmarks and verification benchmarks. Our evaluation shows that AutoVerus can automatically generate correct proof for more than 90% of them, with more than half of them tackled in less than 30 seconds or 3 LLM calls.
- Top Cited PapersOpen Access
- 30 March 2025
- Published by Association for Computing Machinery (ACM)
- p. 560-573
KernelGPT: Enhanced Kernel Fuzzing via Large Language Models
- 30 March 2025
- Published by Association for Computing Machinery (ACM)
- p. 560-573
Top Cited PapersOpen AccessKernelGPT: Enhanced Kernel Fuzzing via Large Language Models
- Top Cited PapersOpen Access
- 8 October 2024
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Programming Languages
- Vol. 8 (OOPSLA2) , 709-735
WhiteFox: White-Box Compiler Fuzzing Empowered by Large Language Models
Compiler correctness is crucial, as miscompilation can falsify program behaviors, leading to serious consequences over the software supply chain. In the literature, fuzzing has been extensively studied to uncover compiler defects. However, compiler fuzzing remains challenging: Existing arts focus on black- and grey-box fuzzing, which generates test programs without sufficient understanding of internal compiler behaviors. As such, they often fail to construct test programs to exercise intricate optimizations. Meanwhile, traditional white-box techniques, such as symbolic execution, are computationally inapplicable to the giant codebase of compiler systems. Recent advances demonstrate that Large Language Models (LLMs) excel in code generation/understanding tasks and even have achieved state-of-the-art performance in black-box fuzzing. Nonetheless, guiding LLMs with compiler source-code information remains a missing piece of research in compiler testing. To this end, we propose W hite F ox , the first white-box compiler fuzzer using LLMs with source-code information to test compiler optimization, with a spotlight on detecting deep logic bugs in the emerging deep learning (DL) compilers. W hite F ox adopts a multi-agent framework: (i) an LLM-based analysis agent examines the low-level optimization source code and produces requirements on the high-level test programs that can trigger the optimization; (ii) an LLM-based generation agent produces test programs based on the summarized requirements. Additionally, optimization-triggering tests are also used as feedback to further enhance the test generation prompt on the fly. Our evaluation on the three most popular DL compilers ( i.e ., PyTorch Inductor, TensorFlow-XLA, and TensorFlow Lite) shows that W hite F ox can generate high-quality test programs to exercise deep optimizations requiring intricate conditions, practicing up to 8 times more optimizations than state-of-the-art fuzzers. To date, W hite F ox has found in total 101 bugs for the compilers under test, with 92 confirmed as previously unknown and 70 already fixed. Notably, W hite F ox has been recently acknowledged by the PyTorch team, and is in the process of being incorporated into its development workflow. Finally, beyond DL compilers, W hite F ox can also be adapted for compilers in different domains, such as LLVM, where WHiteFox has already found multiple bugs.
- 8 October 2024
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Programming Languages
- Vol. 8 (OOPSLA2) , 709-735
Top Cited PapersOpen AccessWhiteFox: White-Box Compiler Fuzzing Empowered by Large Language Models
Compiler correctness is crucial, as miscompilation can falsify program behaviors, leading to serious consequences over the software supply chain. In the literature, fuzzing has been extensively studied to uncover compiler defects. However, compiler fuzzing remains challenging: Existing arts focus on black- and grey-box fuzzing, which generates test programs without sufficient understanding of internal compiler behaviors. As such, they often fail to construct test programs to exercise intricate optimizations. Meanwhile, traditional white-box techniques, such as symbolic execution, are computationally inapplicable to the giant codebase of compiler systems. Recent advances demonstrate that Large Language Models (LLMs) excel in code generation/understanding tasks and even have achieved state-of-the-art performance in black-box fuzzing. Nonetheless, guiding LLMs with compiler source-code information remains a missing piece of research in compiler testing. To this end, we propose W hite F ox , the first white-box compiler fuzzer using LLMs with source-code information to test compiler optimization, with a spotlight on detecting deep logic bugs in the emerging deep learning (DL) compilers. W hite F ox adopts a multi-agent framework: (i) an LLM-based analysis agent examines the low-level optimization source code and produces requirements on the high-level test programs that can trigger the optimization; (ii) an LLM-based generation agent produces test programs based on the summarized requirements. Additionally, optimization-triggering tests are also used as feedback to further enhance the test generation prompt on the fly. Our evaluation on the three most popular DL compilers ( i.e ., PyTorch Inductor, TensorFlow-XLA, and TensorFlow Lite) shows that W hite F ox can generate high-quality test programs to exercise deep optimizations requiring intricate conditions, practicing up to 8 times more optimizations than state-of-the-art fuzzers. To date, W hite F ox has found in total 101 bugs for the compilers under test, with 92 confirmed as previously unknown and 70 already fixed. Notably, W hite F ox has been recently acknowledged by the PyTorch team, and is in the process of being incorporated into its development workflow. Finally, beyond DL compilers, W hite F ox can also be adapted for compilers in different domains, such as LLVM, where WHiteFox has already found multiple bugs.
- Top Cited PapersOpen Access
- 6 February 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-13
Large Language Models are Edge-Case Generators: Crafting Unusual Programs for Fuzzing Deep Learning Libraries
Bugs in Deep Learning (DL) libraries may affect almost all downstream DL applications, and it is crucial to ensure the quality of such systems. It is challenging to generate valid input programs for fuzzing DL libraries, since the input programs need to satisfy both the syntax/semantics of the supported languages (e.g., Python) and the tensor/operator constraints for constructing valid computational graphs. Recently, the TitanFuzz work demonstrates that modern Large Language Models (LLMs) can be directly leveraged to implicitly learn all the language and DL computation constraints to generate valid programs for fuzzing DL libraries (and beyond). However, LLMs tend to generate ordinary programs following similar patterns/tokens with typical programs seen in their massive pre-training corpora (e.g., GitHub), while fuzzing favors unusual inputs that cover edge cases or are unlikely to be manually produced. To fill this gap, this paper proposes FuzzGPT, the first approach to priming LLMs to synthesize unusual programs for fuzzing. FuzzGPT is mainly built on the well-known hypothesis that historical bug-triggering programs may include rare/valuable code ingredients important for bug finding. Meanwhile, while traditional techniques leveraging such historical information require intensive human efforts to both design dedicated generators and ensure the syntactic/semantic validity of generated programs, FuzzGPT demonstrates that this process can be fully automated via the intrinsic capabilities of LLMs (including fine-tuning and in-context learning), while being generalizable and applicable to challenging domains. While FuzzGPT can be applied with different LLMs, this paper focuses on the powerful GPT-style models: Codex and CodeGen. Moreover, FuzzGPT also shows the potential of directly leveraging the instruction-following capability of the recent ChatGPT for effective fuzzing. The experimental study on two popular DL libraries (PyTorch and TensorFlow) shows that FuzzGPT can substantially outperform TitanFuzz, detecting 76 bugs, with 49 already confirmed as previously unknown bugs, including 11 high-priority bugs or security vulnerabilities.
- 6 February 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-13
Top Cited PapersOpen AccessLarge Language Models are Edge-Case Generators: Crafting Unusual Programs for Fuzzing Deep Learning Libraries
Bugs in Deep Learning (DL) libraries may affect almost all downstream DL applications, and it is crucial to ensure the quality of such systems. It is challenging to generate valid input programs for fuzzing DL libraries, since the input programs need to satisfy both the syntax/semantics of the supported languages (e.g., Python) and the tensor/operator constraints for constructing valid computational graphs. Recently, the TitanFuzz work demonstrates that modern Large Language Models (LLMs) can be directly leveraged to implicitly learn all the language and DL computation constraints to generate valid programs for fuzzing DL libraries (and beyond). However, LLMs tend to generate ordinary programs following similar patterns/tokens with typical programs seen in their massive pre-training corpora (e.g., GitHub), while fuzzing favors unusual inputs that cover edge cases or are unlikely to be manually produced. To fill this gap, this paper proposes FuzzGPT, the first approach to priming LLMs to synthesize unusual programs for fuzzing. FuzzGPT is mainly built on the well-known hypothesis that historical bug-triggering programs may include rare/valuable code ingredients important for bug finding. Meanwhile, while traditional techniques leveraging such historical information require intensive human efforts to both design dedicated generators and ensure the syntactic/semantic validity of generated programs, FuzzGPT demonstrates that this process can be fully automated via the intrinsic capabilities of LLMs (including fine-tuning and in-context learning), while being generalizable and applicable to challenging domains. While FuzzGPT can be applied with different LLMs, this paper focuses on the powerful GPT-style models: Codex and CodeGen. Moreover, FuzzGPT also shows the potential of directly leveraging the instruction-following capability of the recent ChatGPT for effective fuzzing. The experimental study on two popular DL libraries (PyTorch and TensorFlow) shows that FuzzGPT can substantially outperform TitanFuzz, detecting 76 bugs, with 49 already confirmed as previously unknown bugs, including 11 high-priority bugs or security vulnerabilities.