Peiyuan Liao
廖培元

Boogiepop

Researcher, Programmer, Ponderer


When in doubt, Unsafe.Coerce

I am (currently, as of September 2020) the youngest Chinese Kaggle Grandmaster.

While at school, I focused/am focusing on topics that live in the intersection of machine learning and systems engineering. 2 I've had the honor of working with Han Zhao and Keyulu Xu on graph neural networks in the past.

2. For a complete list of published works and preprints, please refer to papers.bib.

Research Interests

  • Graph Neural Networks: performance, application and interpretability
  • Multimodal Machine Learning
  • Representation Learning
  • Machine Learning/Deep Learning Systems: Training and Inference DSLs, Compilers and Optimizers
  • Federated Learning
  • Object Detection and Segmentation under performance-sensitive settings (low-power, low-memory, etc.)
  • Image Retrieval
  • Currently

    I'm mainly occupied with courseworks at CMU; I'm also helping to organize an entrepreneurship/tech community based in Beijing. You are welcomed to apply by sending me an email!

    Coursework

  • 10-315 Introduction to Machine Learning
  • 15-411 Compiler Design
  • 15-312 Foundations of Programming Languages
  • Portfolio

    I'm involved in several online, computer science-related communities, including Kaggle and Codewars (real-time ranking below). My resume can be found here.

    Codewars Profile


    Research
    graph neural networks, lossy compression

    +

    graph neural networks, lossy compression
    Projects
    functional programming, deep learning DSL, data science

    +

    functional programming, deep learning DSL, data science
    Academics
    classes, majors, courses

    +

    classes, majors, courses
    Professional
    Lantern, Recurse Center, Cambricon Technologies

    +

    Lantern, Recurse Center, Cambricon Technologies
    Skills
    programming languages, natural languages, technologies

    +

    programming languages, natural languages, technologies
    Honors
    prizes and recognitions

    +

    prizes and recognitions

    Miscellaneous

    Personal Interests

  • Analytic Philosophy & its application in computer science
  • Coldplay
  • Sakanaction
  • French/Japanese
  • Film Photography

  • Prague
  • Squash
  • Contact

    Regarding my researches, academic collaboration, Kaggle team-up, or questions related to zeta/ml-arsenal:

    peiyuanl [at] andrew [dot] cmu [dot] edu

    For Lantern-related subjects, such as application, collaboration, sponsorship, etc:

    peiyuanl [at] luntan [dot] io

    Finally, anything else, like just making friends or talk about programming languages, machine learning (for fun), or what's it's like to be at recurse center:

    alexander [underscore] liao [at] outlook [dot] com

    Most of the code I've written can be found under my GitHub account: @liaopeiyuan.

    Institutional Address

    Peiyuan Liao
    5032 Forbes Avenue
    SMC 4401
    Pittsburgh, PA 15289

    ORCID iD iconhttps://orcid.org/0000-0002-4387-7940

    tr5 Homepage (possibly outdated)

    Want to become a better programmer? Join the Recurse Center!