Physicist · MIT
Jose M.
Munoz Arias
I am driven by solving hard problems. My current research combines precision measurements and nuclear theory to explore foundamental questions about the universe.
Published as Jose M. Munoz
About
A featherless biped, curious by nature and trained as a scientist.
I am a Physics PhD student at MIT in the Laboratory for Nuclear Science, at the García Ruiz group. I work on several aspects of nuclear science, trying to tackle the problem of bridging our theoretical understanding of fundamental interactions to what we can measure in the lab. This relies heavily on statistical modeling, controlled approximations and computational methods.
My path has crossed a few fields. Before nuclear physics I worked on particle physics with the CMS experiment at CERN. Spent a few years as a ML engineer working on industry applications of deep learning and synthetic data. And additionally, some research in the areas of neutrino phenomenology, econometrics, and more recently generative models.
Selected work
Global Framework for Emulation of Nuclear Calculations
A hierarchical Bayesian neural network (BANNANE) that emulates ab initio nuclear calculations across the chart, predicting energies and charge radii together with calibrated uncertainties.
Physical Review Letters 136, 082501 · 2026↗
Nuclear Charge Radii of Aluminium Isotopes at the Proton Drip Line
arXiv:2605.09139 · 2026
Linking Electromagnetic Moments to Nuclear Interactions with a Global Physics-Driven Machine-Learning Emulator
arXiv:2603.26905 · 2026
Discovering Nuclear Models from Symbolic Machine Learning
Communications Physics 8, 101 · 2025
A General Framework for Equivariant Neural Networks on Reductive Lie Groups
NeurIPS 36 (2023) · 2023
See all publications on Google Scholar → Full research & publications →