Cross-Domain Transfer with Particle Physics Foundation Models: From Jets to Neutrino Interactions

TL;DR

This paper demonstrates that a pre-trained particle physics foundation model can be effectively transferred to neutrino experiments, outperforming models trained from scratch across various tasks and conditions.

Contribution

It introduces a general-purpose foundation model for particle physics that generalizes across energy scales, detector types, and physics processes, enabling detector-agnostic inference.

Findings

Pre-trained models outperform from-scratch models at same compute budget.

Pre-trained models perform better at same training steps.

Models generalize across energy scales and detector technologies.

Abstract

Future AI-based studies in particle physics will likely start from a foundation model to accelerate training and enhance sensitivity. As a step towards a general-purpose foundation model for particle physics, we investigate whether the OmniLearned foundation model pre-trained on diverse high-$Q^2$ simulated and real $pp$ and $ep$ collisions can be effectively transferred to a few-GeV fixed-target neutrino experiment. We process MINERvA neutrino--nucleus scattering events and evaluate pre-trained models on two types of tasks: regression of available energy and binary classification of charged-current pion final states ($\mathrm{CC1\pi^{\pm}}$, $\mathrm{CCN\pi^{\pm}}$, and $\mathrm{CC1\pi^{0}}$). Pre-trained OmniLearned models consistently outperform similarly sized models trained from scratch, achieving better overall performance at the same compute budget, as well as achieving better performance at the same number of training steps. These results suggest that particle-level foundation models acquire inductive biases that generalize across large differences in energy scale, detector technology, and underlying physics processes, pointing toward a paradigm of detector-agnostic inference in particle physics.