Colin White

About

I design algorithms that create advanced AI algorithms.

I am Head of Research at Abacus.AI. I graduated from Carnegie Mellon University with a Ph.D. in computer science, advised by Nina Balcan and supported by the NDSEG Fellowship. I received my undergraduate degree from Amherst College.

For more, see my CV (last updated Jan. 2024).

My work focuses on automating the search for high-performing deep learning models, as well as explaining and de-biasing them, from both a theoretical and empirical lens. Much of my work involves designing innovative methods by drawing insights from large-scale studies (ref1, ref2, ref3) and designing tools for better benchmarking of machine learning techniques (ref4, ref5, ref6).

News

    • • Feb 21, 2024: Smaug-72B is the first open-source LLM to surpass 80% on the HuggingFace Open LLM Leaderboard. Read the paper here.
    • • Sep 21, 2023: I was a Senior Area Chair for the NeurIPS Track on Datasets and Benchmarks 2023.
    • • Sep 12-15, 2023: I was a Program Chair for AutoML 2023. Mark your calendars for Sep 9-12, AutoML'24 in Paris!
    • • Jan 22, 2023: New survey on neural architecture search. Email me if you have comments!
    • • Jul 25, 2022: I gave a tutorial on neural architecture search with Debadeepta Dey, at AutoML 2022. View the talk here, and the slides here.

Preprints

Publications

Professional
Service

  • Senior Area Chair for NeurIPS Track on Datasets and Benchmarks 2023
    Program Chair for AutoML 2023
    Local Chair and Area Chair for AutoML 2022
    Co-organizer for the 8th AutoML Workshop at ICML 2021
    Top 10% of reviewers at NeurIPS 2022
    Top 10% of reviewers at ICML 2022
    Top 10% of reviewers at ICLR 2022
    Top 10% of reviewers at NeurIPS 2021
    Top 10% of reviewers at ICML 2021
    Top 10% of reviewers at NeurIPS 2020