Jiawei Liu

I am a final-year Ph.D. student and Amazon Fellow at University of Illinois Urbana-Champaign, working with Lingming Zhang. My research explores how Software Engineering and Programming Language can benefit and benefit from machine learning and its systems, with a focus on improving software reliability and developer productivity.
Software Engineering with Language Models
- Training models [StarCoder2] to reason [PurpCode][Code-R1] and follow diverse instructions [Magicoder]
- Evaluating code correctness [EvalPlus], efficiency [EvalPerf], without hard verifiers [CodeFavor]
- Code editing should be real-time and can be largely accelerated by multi-layer speculation [Blazedit]
Software Engineering for ML Systems
Research Impact
🎉 (July 2025) Introducing PurpCode, the first open recipe for secure code reasoning via self-improvement, winning the 🥇1st Place in Amazon Nova AI Challenge 2025 with $250K cash award!
📰 Some recent coding: R1 for Code Generation and Speculative Code Editing.
ResearchShow More
- Pre-print / PurpCode: Reasoning for Safer Code GenerationarXiv preprint arXiv:2507.19060. 2025🥇 1st Place in Amazon Nova AI Challenge 2025
- Proc. ACM Softw. Eng. 2 (ISSTA). Jun 2025
- Forty-first International Conference on Machine Learning. Jun 2024Adopted by Meta Llama 3.1, Google CodeGemma, and IBM Granite
- arXiv preprint arXiv:2402.19173. Jun 2024
- 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
- Proceedings of the ACM on Programming Languages 6 (OOPSLA1). Apr 2022
Awards & Honors
🥇1st Place, Amazon Nova AI Challenge ($250K) 2025
Illinois Innovation Award ($20K)
Amazon AICE Ph.D. Fellowship ($70K)
Jane Street Fellowship Honorable Mention
Amazon Nova AI Challenge Research Grant ($250K) 2024
OpenAI Researcher Access Program
Machine Learning and Systems Rising Stars
Warren W. Yee Memorial Fellowship
Service
Organizing: LLM4Code@ICSE (Publicity Chair)
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