Ouail Kitouni

Ouail Kitouni

Ph.D. Student

Massachusetts Institute of Technology


[wa-ill kitoonee] 🔊

I am interested in the science of deep learning. Recently, I’ve been very excited about topics like reasoning, multi-modal foundation models, and safe and scalable deep learning. During my time at Microsoft Research, I worked on developing a knowledge base generative model towards a knowledge-augmented LLM approach to improve interpretability and limit hallucination. At FAIR, I worked on new pre-training objectives to make LLMs more data-efficient (learn more with less) and improve their knowledge storage and planning capabilities.


  • Science of Deep Learning
  • (Mechanistic) Interpretability
  • Reasoning in Foundation Models
  • Safety and Robustness


  • Interdisciplinary Ph.D. in Physics and Statistics, 2019 - Present

    Massachusetts Institute of Technology

  • BSc in Physics and Mathematics, 2019

    University of Rochester



Research Scientist Intern

Meta AI

Jan 2024 – May 2024 NYC, NY

Research Intern

Microsoft Research

May 2023 – Aug 2023 Cambridge, UK

Machine Learning Researcher Intern

NASA/SETI Frontier Development Lab

May 2022 – Aug 2022 Mountain View, CA

Recent Publications

Miscellaneous Projects

Monotonic Networks

Monotonic Networks

A small package to make neural networks monotonic in any subset of their inputs (this works for individual neurons, too!).

MoDe: Controlling Classifier Bias

MoDe: Controlling Classifier Bias

A regularization to make neural networks’ output independent from certain features.

Bell Inequality Experiment

Bell Inequality Experiment

An experiment to demonstrate the non-locality of quantum mechanics through the violation of Bell’s Inequality.