Jiawei Liu


I’m a Ph.D. candidate at UIUC PL/FM/SE, working with Lingming Zhang since 2021.

I study Software Engineering, Programming Systems, and Machine Learning, with a goal to simplify the making of great software with and for machine learning and its systems. Specifically, I study automated synthesis, validation, and reasoning of programs to build reliable machine learning systems and code models:

ūüõ°ÔłŹ Automated bug finding in ML systems via test program synthesis:

  • NeuRI / ūüŹÜFSE‚Äô23
  • NNSmith / ūüŹÜASPLOS‚Äô23
  • Tzer / OOPSLA‚Äô22

ūüõ†ÔłŹ Language models for code:

ūü§ó jiawei6@illinois.edu is the shortest path to find me.

Papers Show More

  1. ICML’24
      To Appear  
    Magicoder: Empowering Code Generation with OSS-Instruct
    Yuxiang Wei, Zhe Wang,  Jiawei Liu, Yifeng Ding,  and Lingming Zhang
    Forty-first International Conference on Machine Learning. 2024
  2. Pre-print
    Emerging Platforms Meet Emerging LLMs: A Year-Long Journey of Top-Down Development
    Siyuan Feng,  Jiawei Liu, Ruihang Lai, Charlie F. Ruan, Yong Yu, Lingming Zhang,  and Tianqi Chen
    arXiv preprint arXiv:2404.09151. 2024
  3. NeurIPS’23
    Is Your Code Generated by ChatGPT Really Correct? Rigorous Evaluation of Large Language Models for Code Generation
    Jiawei Liu, Chunqiu Steven Xia, Yuyao Wang,  and Lingming Zhang
    Thirty-seventh Conference on Neural Information Processing Systems. 2023
  4. ESEC/FSE’23
    Atifact AvailableAtifact Reusable
    NeuRI: Diversifying DNN Generation via Inductive Rule Inference
    Jiawei Liu, Jinjun Peng, Yuyao Wang,  and Lingming Zhang
    Proceedings of the 31st ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering. 2023
    ūüŹÜ ¬†ACM SIGSOFT Distinguished Paper Award
  5. ASPLOS’23
    Atifact AvailableAtifact FunctionalResults Reproduced
    NNSmith: Generating Diverse and Valid Test Cases for Deep Learning Compilers
    Jiawei Liu, Jinkun Lin, Fabian Ruffy, Cheng Tan, Jinyang Li, Aurojit Panda,  and Lingming Zhang
    Proceedings of the 28th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 2. 2023
    ūüŹÜ ¬†Distinguished Artifact Award
  6. OOPSLA’22
    Atifact AvailableAtifact Reusable
    Coverage-guided tensor compiler fuzzing with joint IR-pass mutation
    Jiawei Liu, Yuxiang Wei, Sen Yang, Yinlin Deng,  and Lingming Zhang
    Proceedings of the ACM on Programming Languages 6 (OOPSLA1). Apr 2022

Invited Talk

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 Z√ľrich: 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 (Slides) May 2022


Organizing: LLM4Code@ICSE'24

Program Committee/Reviewer: TSE, TOSEM, ASE'24, NeurIPS'24, DCAA@AAAI'23, R2FM@ICLR'24

Artifact Evaluation Committee: PLDI'23, OSDI'22, ATC'22