Michael Hu

PhD student @ NYU


I am a second-year PhD student at the NYU Center for Data Science, working with Kyunghyun Cho and Tal Linzen. My work spans NLP, representation learning, and interpretability. I am supported by an NSF Graduate Research Fellowship.

In my spare time, I enjoy cooking, yoga, and playing basketball.

Previously, I completed a BSE at Princeton CS, where I spent two lovely years working with Karthik Narasimhan and Tom Griffiths.


Aug 22, 2023 New preprint: “Latent State Models of Training Dynamics.”
Sep 23, 2022 Paper accepted to NeurIPS 2022 on the outstanding papers shortlist!
arXiv link here.
Sep 1, 2022 Started a PhD at the NYU Center for Data Science as an NSF GRFP Scholar.
Oct 6, 2021 Paper accepted to NeurIPS 2021 as a spotlight presentation!
arXiv link here.
May 24, 2021 Honored to receive the Outstanding Senior Thesis Prize from Princeton CS!
Thesis abstract here.

selected publications


  1. NeurIPS
    Using Natural Language and Program Abstractions to Instill Human Inductive Biases in Machines
    Sreejan Kumar, Carlos G. Correa, Ishita Dasgupta, and 7 more authors
    NeurIPS, 2022


  1. NeurIPS
    Safe Reinforcement Learning with Natural Language Constraints
    Tsung-Yen Yang, Michael Hu, Yinlam Chow, and 2 more authors
    NeurIPS (spotlight), 2021