Photo of Yash Ejjagiri

About Me

I am Yash Ejjagiri, a SURA/CRESST II Research Assistant at NASA Goddard Space Flight Center (GSFC), where I develop neural-network emulators of pulse-profile models for NICER X-ray data to constrain neutron-star mass, radius, and magnetic field geometries.

Before GSFC, I spent three years in Professor Xin Liu’s AstroAI group at the National Center for Supercomputing Applications (NCSA) at University of Illinois Urbana-Champaign (UIUC), developing DeepDISC, a deep-learning framework for joint detection, deblending, classification, and photometric redshift estimation in next-generation surveys, with a focus on combining Roman and Rubin LSST imaging.

I am also a research contributor in EleutherAI’s Summer of Open AI Research, testing whether astronomy foundation models encode physical galaxy properties.

In May 2025, I graduated from UIUC with a B.S. in Computer Science + Astronomy, with minors in Physics and Mathematics.

I am broadly interested in applying machine learning to large-scale astrophysical surveys, with a particular interest in field-level inference, simulation-based inference, and multi-scale emulators for cosmology.

Here is my CV, and feel free to check out my presentations and talks.

Presentations and Talks

2 Nov 2026
Annapolis, MD

JSI 2026 Workshop: A NICER Legacy: Neutron Stars, Black Holes, and Time-Domain Astronomy

2D Energy Resolved NN emulators @ JSI NICER Workshop

4 Jan 2026
Phoenix, AZ

247th Meeting of the American Astronomical Society

DeepDISC Roman + Rubin LSST deblending @ AAS 247

21 Jul 2025
Champaign, IL

Dark Energy Science Collaboration Meeting 2025

DeepDISC Roman + Rubin LSST deblending @ LSST DESC July 2025 Collaboration Meeting

all presentations and talks

Posts

3 Jun 2026

My First Post!

Testing out Hugo with Typo theme