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

arXiv:2604.12364v1 Announce Type: cross 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 (CC1pi^{pm}, CCNpi^{pm}, and CC1pi^{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.

Related

• Physics-Informed Neural Networks for Methane Sorption: Cross-Gas Transfer Learning, Ensemble Collapse Under Physics Constraints, and Monte Carlo Dropout Uncertainty Quantification
• dnaHNet: A Scalable and Hierarchical Foundation Model for Genomic Sequence Learning
• DINO-QPM: Adapting Visual Foundation Models for Globally Interpretable Image Classification
• Improving DNS Exfiltration Detection via Transformer Pretraining

Source: arXiv cs.LG | 2026-04-15