Ayush Khot

PhD Student in Computer Science, University of Illinois at Urbana-Champaign

NSF Graduate Research Fellow

akhot2 [AT] illinois.edu

About

I a second year Ph.D. student in Computer Science at University of Illinois at Urbana-Champaign and a National Science Foundation Graduate Research Fellow (NSF GRFP). I develop machine learning methods for high-energy physics and geospatial science. My research addresses challenges in reliable ML for the real world: uncertainty quantification, out-of-distribution detection, causality, and foundation model embeddings.

My contributions include:

My goal is to develop transparent and effective models for real-world deployment, with a focus on high-energy physics and geospatial applications. If you would like to collaborate on any of these topics and beyond, please reach out!

Bio

I hold dual bachelor's degrees in Physics and Computer Science from the University of Illinois at Urbana-Champaign. During my undergrad, I interned at Argonne and Brookhaven National Laboratory. I am also a contributor to NVIDIA PhysicsNeMo. I like listening to music and playing my violin as well!

News

Publications

Most recent publications on Google Scholar.
* Equal contribution. ‡ Alphabetical order.

thumbnail for Spatial Deconfounder: Interference-Aware Deconfounding for Spatial Causal Inference

Spatial Deconfounder: Interference-Aware Deconfounding for Spatial Causal Inference

Ayush Khot*, Miruna Oprescu*, Maresa Schröder, Ai Kagawa, Xihaier Luo

ICML'26: International Conference on Machine Learning. 2026.

thumbnail for Applying Foundation Model Embeddings towards Urban Livability Evaluation

Applying Foundation Model Embeddings towards Urban Livability Evaluation

Ayush Khot, Wen Zhou, Shaowen Wang

ACM SIGSPATIAL'26: International Conference on Advances in Geographic Information Science. 2026.

thumbnail for Evidential Deep Learning for Uncertainty Quantification and Out-of-Distribution Detection in Jet Identification using Deep Neural Networks

Evidential Deep Learning for Uncertainty Quantification and Out-of-Distribution Detection in Jet Identification using Deep Neural Networks

Ayush Khot, Xiwei Wang, Avik Roy, Volodymyr Kindratenko, Mark S. Neubauer

Machine Learning: Science and Technology. 2025.

thumbnail for Evidential Deep Learning for Probabilistic Modelling of Extreme Storm Events

Evidential Deep Learning for Probabilistic Modelling of Extreme Storm Events

Ayush Khot, Xihaier Luo, Ai Kagawa, Shinjae Yoo

NeurIPS'24: Machine Learning and the Physical Sciences. 2024.

thumbnail for A Detailed Study of Interpretability of Deep Neural Network based Top Taggers

A Detailed Study of Interpretability of Deep Neural Network based Top Taggers

Ayush Khot, Mark S. Neubauer, Avik Roy

Machine Learning: Science and Technology. 2025.

Spatial Deconfounder: Interference-Aware Deconfounding for Spatial Causal Inference

Ayush Khot*, Miruna Oprescu*, Maresa Schröder, Ai Kagawa, Xihaier Luo

ICML'26: International Conference on Machine Learning. 2026.

Applying Foundation Model Embeddings towards Urban Livability Evaluation

Ayush Khot, Wen Zhou, Shaowen Wang

ACM SIGSPATIAL'26: International Conference on Advances in Geographic Information Science. 2026.

Evidential Deep Learning for Uncertainty Quantification and Out-of-Distribution Detection in Jet Identification using Deep Neural Networks

Ayush Khot, Xiwei Wang, Avik Roy, Volodymyr Kindratenko, Mark S. Neubauer

Machine Learning: Science and Technology. 2025.

Evidential Deep Learning for Probabilistic Modelling of Extreme Storm Events

Ayush Khot, Xihaier Luo, Ai Kagawa, Shinjae Yoo

NeurIPS'24: Machine Learning and the Physical Sciences. 2024.

A Detailed Study of Interpretability of Deep Neural Network based Top Taggers

Ayush Khot, Mark S. Neubauer, Avik Roy

Machine Learning: Science and Technology. 2025.

Vitæ

Full CV in PDF.

Website Design

This website was created using Jekyll and is based on a template by Martin Saveski. A huge thank you to Martin for designing this fantastic theme! You can find the code used to build the site in this GitHub repo.