I started in Jan 2022 as a PhD student at Mila, where I study deep learning under the supervision of Yoshua Bengio.

Before that, I was an AI researcher at Microsoft working on the large-scale deployment of GPT-3, principled approaches to the training of large deep learning model, and theories of infinitely wide neural networks. I'm broadly interested in machine learning and natural language processing.

I spent a year as an AI resident at Microsoft Research, after graduating with a BSc in Computer Science and Cognitive Science from Johns Hopkins University. While at JHU, I worked for the Center for Language and Speech Processing and was advised by Ben Van Durme.

Some Publications

Tuning Large Neural Networks via Zero-Shot Hyperparameter Transfer
NeurIPS 2021
[Paper | Blog | Code | TheRegister | SyncedReview]

LoRA: Low-Rank Adaptation of Large Language Models
ICLR 2022
[Paper | Code]

GFlowNet Foundations
Pre-print
[Paper]

Feature Learning in Infinite-Width Neural Networks
ICML 2021
[Paper | Blog | Code]

Improved Image Wasserstein Attacks and Defenses
Best Paper at ICLR Trustworthy ML Workshop 2020
[Paper | Code]

Randomized smoothing of all shapes and sizes
ICML 2020
[Paper | Code]

Improved Lexically Constrained Decoding for Translation and Monolingual Rewriting
NAACL 2019
[Paper | Dataset]