I am a PhD student at MIT, where I am advised by Aleksander Mądry. Previously, I spent two great years at Microsoft Research with Praneeth Netrapalli and Prateek Jain. Before that, I studied CS and Stats at UIUC. I have also interned at Apple MLR, Google Research, and Akuna Capital.

I am broadly interested in understanding and steering large-scale machine learning models. Specifically, my recent work focuses on developing tools for analyzing model behavior via targeted interventions to learning algorithms, training data, in-context information, and learned representations. Outside of research, I enjoy cricket and tennis.


Papers

Understanding Compute-Parameter Trade-offs in Mixture-of-Experts Language Models
ContextCite: Attributing Model Generation to Context
Decomposing and Editing Predictions by Modeling Model Computation
ModelDiff: A Framework for Comparing Learning Algorithms
Do Input Gradients Highlight Discriminative Features?
The Pitfalls of Simplicity Bias in Neural Networks
Growing Attributed Networks through Local Processes