Kahaan Gandhi

Hi! I’m a senior in astrophysics at Caltech, where I study neural operators in Anima Anandkumar’s AI + Science Lab. I’m broadly interested in AI for science, machine learning, and large-scale data infrastructure. One of my favorite examples of data at that scale comes from the first photo of a black hole: astronomers collected so much data that the hard drives had to be flown around the world on commercial planes.

Previously, I worked on software at Cloudflare and NASA Jet Propulsion Laboratory. I’ve also done research at the University of Cambridge, Haverford College, and the Climate Modeling Alliance.

My other interests include pool, astrophotography, skiing, and Thai iced teas.

Selected Publications

Counterfactual Predictions in Scientific Emulators Without Controlled Experiments2026
Dingling Yao, Kahaan Gandhi, Valentin Duruisseaux, Boris Bonev, Francesco Locatello, Anima Anandkumar
arXiv preprint
arXiv
Open Source Planning & Control System with Language Agents for Autonomous Scientific Discovery2025
Licong Xu, Milind Sarkar, Anto I. Lonappan, Íñigo Zubeldia, Pablo Villanueva-Domingo, Santiago Casas, Christian Fidler, Chetana Amancharla, Ujjwal Tiwari, Adrian Bayer, Chadi Ait Ekioui, Miles Cranmer, Adrian Dimitrov, James Fergusson, Kahaan Gandhi, Sven Krippendorf, Andrew Laverick, Julien Lesgourgues, Antony Lewis, Thomas Meier, Blake Sherwin, Kristen Surrao, Francisco Villaescusa-Navarro, Chi Wang, Xueqing Xu, Boris Bolliet
ICML 2025 Workshop on Machine Learning for Astrophysics (ML4Astro)
arXiv code
An 18–25 GHz Spectroscopic Survey of Dense Cores in the Chamaeleon I Molecular Cloud2025
Dariusz C. Lis, William D. Langer, Jorge L. Pineda, Kahaan Gandhi, Karen Willacy, Paul F. Goldsmith, Susanna Widicus Weaver, Liton Majumdar, Youngmin Seo, Shinji Horiuchi, Cheikh Bop, François Lique
Astronomy & Astrophysics
arXiv code

“If people sat outside and looked at the stars each night, I’ll bet they’d live a lot differently.”