Varun Babbar

Varun Babbar

PhD student in Machine Learning @ Duke University

About

Hi! I'm Varun Babbar, a PhD candidate in Machine Learning at Duke University, advised by Cynthia Rudin. I also work closely with Margo Seltzer. I'm currently a Research Scientist Intern in the AI Foundations team at Capital One New York, training specialized foundation models for tabular data.


Before my PhD, I was an Applied Scientist at JP Morgan London, working on developing machine learning models for automated source code understanding. This work led to a pending patent on an LLM-based workflow for automated software development and a paper on representation learning for code repositories.


I graduated from the University of Cambridge in 2022 with a BA + MEng in Information and Computer Engineering, ranking in the top 5% of my class. During my time at Cambridge, I've collaborated with Umang Bhatt and Adrian Weller on human-aligned uncertainty quantification and risk control, Sean Moran on federated learning for Covid-19 diagnosis, and Rafal Mantiuk on developing visual loss functions for image-to-image translation models.

Research Interests

My research focuses on making machine learning models more interpretable, reliable, and actionable in real-world settings. I develop methods that balance predictive performance with transparency, including:
  • Interpretable models via discrete optimization — fast algorithms for near-optimal decision trees and rule-based models on tabular datasets (ICML 2025 Oral; 3 ICML 2026 papers, including 1 Spotlight)
  • Human-aligned uncertainty quantification — prediction sets and risk control optimized for joint human-machine collaboration (IJCAI 2022 Oral; NeurIPS 2022 Workshop)
  • Understanding distribution shifts - diagnostic tools that explain distribution shifts in tabular, time series, and vision datasets (JMLR 2025)
  • Foundation models for tabular data - mechanistic interpretability, inductive biases, uncovering regimes where interpretable models perform better

Random Facts

Here are the cities I've lived in (in chronological order):
New Delhi     Mumbai     Singapore     Mumbai     Cambridge     London     Durham, North Carolina     New York City

Here are the languages I am fluent in: English, Hindi, French.

My non-sporting interests are quite random: Rubik’s cubes, chess, and playing the ukulele!

I love playing basketball and squash: I was part of Cambridge's Varsity squash team. We toured a lot in and around Cambridgeshire, playing against county clubs and university teams alike. I'm still active in Duke's squash and basketball communities, though I only play for recreation.