I am a postdoctoral scholar at the Halıcıoğlu Data Science Institute, UC San Diego, working with Dmitriy Drusvyatskiy and Mikhail Belkin.
My research focuses on making foundational advances to improve our understanding of deep learning-based systems and making them more reliable and trustworthy. I use both theoretical tools and empirical insights to analyze the optimization and generalization dynamics of ML models, improve their robustness to distributional shifts, and, generally, develop faithful abstractions of ML model behavior.
I completed my PhD in Computer Science at USC, advised by Vatsal Sharan of the USC CS Theory Group, working closely with Christos Thrampoulidis and Mahdi Soltanolkotabi. Before that, I graduated from IIT Roorkee with a bachelor’s in ECE, where I worked on generative adversarial network-based methods for compressive sensing MRI reconstruction.
Besides research, I enjoy being outdoors, hiking, reading, and swimming.
News
- Aug 2026Started as a postdoc at HDSI, UCSD.
- May 2026Passed my Thesis Defense at USC.
- May 2026Co-organizing MOSS workshop at COLM 2026.
- April 2026Selected for the USC Viterbi Best Research Assistant Award (one per dept).
- March 2026Invited Talk at CPAL 2026 as a Rising Star.
Publications
Preprints
Understanding Contextual Recall in Transformers: How Finetuning Enables In-Context Reasoning over Pretraining Knowledge
2026
2025
In-Context Occam’s Razor: How Transformers Prefer Simpler Hypotheses on the Fly
COLM 2025; MOSS Workshop at ICML 2025 (Oral)