Hi! I'm a final-year PhD student at QMUL, interested in AI safety and interpretability. A recent focus of my work has been on designing scalable ways to break down machine learning models’ computations into parts we can interpret as humans--both to better understand their behavior and to steer them toward outcomes more aligned with our values.

Over summer 2025 I'll be a visiting student at the University of Oxford, and I previously spent a few great months as an Honorary Associate at the University of Wisconsin–Madison with Grigorios Chrysos. Prior to this, I was an intern at Huawei Noah's Ark Lab. I'm lucky to be supervised by a great team including Ioannis Patras, Mihalis A. Nicolaou, and Yannis Panagakis.

News

Selected publications

Experience

Invited talks

Teaching

Awards