Natalie Abreu
Kempner Graduate Fellow
PhD Student in Computer Science
She/Her
About
Natalie is a first-year PhD student in the ML Foundations group advised by Boaz Barak. Previously, she attended the University of Southern California where she completed a BS in Computer Science and a minor in Mathematics. During that time, she interned at Google and at MIT Lincoln Laboratory.
Research Focus
Abreu’s current research focuses on foundations of deep learning. She is broadly interested in the foundations of deep learning, particularly with respect to LLMs. This includes questions regarding the training dynamics of large models, how LLMs perform reasoning tasks, and what information these models make use of. She plans to address these questions from both theoretical and empirical approaches in order to build our understanding of deep learning and our mental models of these systems.