Jiawei Liu

avatar-v1.png

I am a final-year Ph.D. student and Amazon Fellow at University of Illinois Urbana-Champaign, working with Lingming Zhang. I think about how to productively build necessarily complex systems that are reliable.

Software Engineering with Language Models
Developing models and evaluators to generate high-quality code:
Software Correctness via Automated Testing
Building automated tools to improve the reliability of ML systems and to simplify its deployment:
  • Automating test program synthesis [NeuRI][NNSmith][Tzer], which has found 300+ critical bugs for daily ML frameworks and compilers
  • Engineering ML systems and compilers productively using top-down development [TapML] and pattern languages [Relax]
Research Impact
My work (i) automatically finds 300+ critical bugs in ML systems like PyTorch, winning ACM SIGSOFT Distinguished Paper Award and Distinguished Artifact Award, and (ii) builds LLMs and evaluators for code with wide industrial adoptions. My research has been generously supported by Amazon PhD Fellowship, Illinois Innovation Award, Yee Memorial Fellowship, and grants from Amazon and OpenAI.

📰 Some recent coding: R1 for Code Generation and Speculative Code Editing.

ResearchShow More

  1. arXiv preprint arXiv:2507.19060. 2025
    🥇 1st Place in Amazon Nova AI Challenge 2025
  2. Proc. ACM Softw. Eng. 2 (ISSTA). Jun 2025
  3. Forty-first International Conference on Machine Learning. Jun 2024
    Adopted by Meta Llama 3.1, Google CodeGemma, and IBM Granite
  4. Anton LozhkovRaymond LiLoubna Ben AllalFederico Cassano, Joel Lamy-Poirier, Nouamane Tazi, Ao Tang, Dmytro Pykhtar,  Jiawei LiuYuxiang Wei and 56 more authors
    arXiv preprint arXiv:2402.19173. Jun 2024
  5. Thirty-seventh Conference on Neural Information Processing Systems. Jun 2023
    1M dataset downloads; integrated by various major companies
  6. Proceedings of the 31st ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering. Jun 2023
    🏆 ACM SIGSOFT Distinguished Paper Award
  7. Proceedings of the 28th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 2. Jun 2023
    🏆 Distinguished Artifact Award
  8. Proceedings of the ACM on Programming Languages 6 (OOPSLA1). Apr 2022

Service

Organizing: LLM4Code@ICSE (Publicity Chair)

Program Committee/Reviewer: ASE, TSE, TOSEM, NeurIPS, ICLR

Artifact Evaluation Committee: PLDI, OSDI, ATC

Invited Talk

NLP+SE Seminar, UT Austin: Smelling the Quality of LLM-generated Code Mar 2025

Programming Systems, Uber: Evaluating LLMs for Correct & Efficient Code Generation Sept 2024

ARiSE Lab, Columbia University: Simplify the Making of Great Software in the ML Era April 2024

Snowflake GenAI: Rigorous Evaluation of LLMs for Code (Slides) Feb 2024

AST Lab, ETH Zürich: Generating Test-Cases for ML Compilers (Slides) Jan 2024

GAI4SE, NC State University: LLMs for Software Testing (Guest Lecture) Nov 2023

Apache TVM Conference: Automating DL Compiler Bug Finding with NNSmith Mar 2023

SAMPL, University of Washington: Coverage-Guided Tensor Compiler Fuzzing May 2022