I am a Research Scientist at NVIDIA Research in New York City, where I work on scientific reasoning and autonomous agents. I received my PhD in Computer Science and Engineering from the University of Michigan, where I was advised by Honglak Lee and Lu Wang. My research broadly focuses on LLM reasoning, test-time learning and inference, and post-training, with a growing interest in building agents capable of autonomous scientific discovery.

Previously, I had the opportunity to work with wonderful researchers across academia and industry. In 2024, I joined the CodeGen team at Cohere, led by Matthias Gallé, where I worked on large-scale model merging. In 2023, I interned at the Allen Institute for AI (AI2), working with Iz Beltagy and Hao Peng on training language models to attribute their generated content to pretraining data. In 2021, I worked at Amazon AWS with Kathy McKeown. Earlier, I interned at Naver Labs Europe, where I explored controllable text generation and energy-based models with Hady Elsahar and Marc Dymetman.

Fun fact: I play the piano, write, and produce my own music.

Email: m[khalifa]@nvidia.com (remove brackets)

Selected Works

(For a complete list, visit my google scholar)