Jiawei Liu

avatar.jpg

I am a 2nd-year PhD student at UIUC PLFMSE advised by Lingming Zhang.

I am interested in programming systems and deep learning, with a goal to improve the reliability, programmability and efficiency of modern systems.

Take a look at NNSmith, our recently released DNN synthesizer for automatically validating DL systems (esp. compilers).

🤗 Feel free to drop me an email if you are interested in my research.

Papers

  1. Pre-print
    Is Your Code Generated by ChatGPT Really Correct? Rigorous Evaluation of Large Language Models for Code Generation
    arXiv preprint arXiv:2305.01210. 2023
  2. ESEC/FSE’23
    To Appear
    NeuRI: Diversifying DNN Generation via Inductive Rule Inference
    Jiawei LiuJinjun PengYuyao Wang,  and Lingming Zhang
    arXiv preprint arXiv:2302.02261. 2023
  3. ASPLOS’23
    🏆 Distinguished Artifact
    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
  4. OOPSLA’22
    Atifact AvailableAtifact Reusable
    Coverage-guided tensor compiler fuzzing with joint IR-pass mutation
    Jiawei LiuYuxiang Wei, Sen Yang, Yinlin Deng,  and Lingming Zhang
    Proceedings of the ACM on Programming Languages 6 (OOPSLA1). Apr 2022
  5. ACMMM’21 (OSC)
    Fast and Flexible Human Pose Estimation with HyperPose
    Yixiao Guo,  Jiawei Liu, Guo Li, Luo Mai,  and Hao Dong
    Proceedings of the 29th ACM International Conference on Multimedia. Apr 2021
*PL conferences such as PLDI and OOPSLA at most offer available + reusable badges but reviewers reproduced our results anyways.

Internship

Google Cloud, Smr. 2023   SDC

OctoML, Smr. 2022   Pattern Language

Alibaba DAMO, Smr. 2021 GNN Serving

ByteDance AI Lab, Spr. 2020   DNN Serving

Services

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

Reviewer: AAAI-DCAA'23

Talks

NNSmith: Generating Diverse and Valid Test Cases for Deep Learning Compilers Coverage-Guided Tensor Compiler Fuzzing with Joint IR-Pass Mutation