Aishik Ghosh
Aishik Ghosh is a physicist who applies AI to particle physics, astrophysics and fundamental physics. In 2020, he defended a University of Paris-Saclay thesis on GAN-based ATLAS calorimeter simulation and off-shell Higgs measurements in four-lepton events. He coauthored studies of uncertainty-aware classifiers in 2021, GAN-based hadronization in 2022, and machine-learning likelihoods for neutron-star inference in 2023. Before Georgia Tech, he was a postdoctoral scholar at UC Irvine and an affiliate at Berkeley Lab; he shared the 2025 Breakthrough Prize in Fundamental Physics as part of CERN's ATLAS experiment and became a principal investigator on a Spring 2026 AI4Science Center grant. As of October 2026, he is an assistant professor of physics at Georgia Tech, where his group develops AI methods for theoretical physics, particle physics and astrophysics.
- Badges
Timeline
-
2020
A particle-physics thesis
In November 2020, he defends his particle-physics PhD at the University of Paris-Saclay with a thesis on GAN-based ATLAS calorimeter simulation and off-shell Higgs measurements in four-lepton events.
-
2021
Uncertainty-aware classifiers
In 2021, he coauthors a study with Benjamin Nachman and Daniel Whiteson on classifiers that model systematic uncertainties; the authors report higher sensitivity on Higgs-to-tau data.
-
2022
A GAN for Herwig
In 2022, he coauthors a study with Xiangyang Ju, Benjamin Nachman and Andrzej Siodmok that replaces part of Herwig's cluster model with a GAN. The authors show that it reproduces the kinematic properties of cluster decays.
-
2023
Machine learning for neutron stars
In 2023, he coauthors a study that uses machine-learning-derived likelihoods to infer neutron-star mass and radius from stellar spectra. The study reports 11.8% narrower parameter residuals in its most realistic scenario.
-
April 2024
UC Irvine postdoc, Berkeley affiliate
By April 2024, he is a researcher at UC Irvine and Berkeley Lab, developing ML methods for particle and astrophysics. Before joining Georgia Tech, he works as a postdoctoral scholar at UC Irvine and an affiliate at Berkeley National Laboratory.
-
2025
An ATLAS Breakthrough Prize
In 2025, he receives the Breakthrough Prize in Fundamental Physics as part of CERN's ATLAS experiment.
-
December 2025
An AI4Science seed grant
In December 2025, he and Vijay Ganesh are named principal investigators for a Spring 2026 AI4Science Center seed grant on combining verified AI and domain knowledge for theoretical physics.
-
As of October 2026
Assistant professor at Georgia Tech
By December 2025, he is an assistant professor in Georgia Tech's School of Physics. As of October 2026, his group designs neuro-symbolic algorithms for theoretical physics, high-dimensional statistical inference for particle physics and astrophysics, and AI-powered simulations.
Career
- Since 2025Georgia Institute of TechnologyAssistant Professor
- University of California, IrvinePostdoctoral Scholar
- Office of ScienceAffiliate
Education
- 2020Université Paris-SaclayPhD
Sources and credits
Photo: We have no published photo of Aishik Ghosh yet. Send us a free-licensed photo.
- About - Prof. Aishik Ghosh’s Group
- Aishik Ghosh “Simulation of the ATLAS Electromagnetic Calorimeter using Generative Adversarial Networks and Offshell Higgs Boson Coupling Measurements in the Four-Lepton Decay Channel at the LHC” (Pôle PHE) (November 13, 2020) · IJCLab Events Directory (Indico)
- Uncertainty-aware machine learning for high energy physics | Phys. Rev. D
- Towards a Deep Learning Model for Hadronization
- Deducing Neutron Star Equation of State from Telescope Spectra with Machine-learning-derived Likelihoods
- Aishik Ghosh: Performing Statistics with Artificial Intelligence in Physics | Bakar Institute of Digital Materials for the Planet
- aghosh369 | School of Physics
- AI4Science Center Awards Inaugural Seed Grants | School of Physics
