Track finding and particle identification performance with particle physics foundation models
Abstract
Modern high energy nuclear and particle physics experiments produce large amounts of sparse data that must be reduced significantly in size before performing physics analysis. Recently, there has been an effort to evaluate Foundation Models as a potential tool for performing data analysis. These models have been shown to learn features in high dimensional datasets based on the multi-modal data they are trained on. To show their effectiveness at performing complex pattern recognition tasks, such as reconstructing charged particles in a magnetic field, we evaluated the performance of a Foundation Model based reconstruction on several downstream tasks with a dataset composed of spacepoints in a Time Projection Chamber. We show that the performance of the Foundation Model based data analysis significantly improves upon that of traditional methods, and furthermore can be adapted to learn additional tasks that are not necessarily related to the initial training objective.
Related
- Leveraging Industrial Foundation Models at the Edge of Particle Physics Detectors via Distillation Learning and Hardware Co-design
- Panda Diplomacy: Foundation Model Pre-training across Particle Imaging Detectors for High Energy and Nuclear Physics
- Towards Foundation Models on Hardware Accelerators for Particle Physics
- Machine-learned particle flow as a foundation model for collider physics
- Prompting Particle Physics: Tokenized Multi-modal Foundation Models for Combinatorially Many Tasks
BibTeX
@misc{li2026track,
title = {{Track finding and particle identification performance with particle physics foundation models}},
author = {Shuhang Li and Haiwang Yu and Gabor Galgoczi and Yeonju Go and Yi Huang and David Park and Michael Peters and Christopher Pinkenburg and Christof Roland and Jin Huang and Yihui Ren and Joseph D. Osborn},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.31180},
eprint = {2610.31180},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.31180},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Track finding and particle identification performance with particle physics foundation models
AU - Shuhang Li
AU - Haiwang Yu
AU - Gabor Galgoczi
AU - Yeonju Go
AU - Yi Huang
AU - David Park
AU - Michael Peters
AU - Christopher Pinkenburg
AU - Christof Roland
AU - Jin Huang
AU - Yihui Ren
AU - Joseph D. Osborn
PY - 2026
DA - 2026/10/23
PB - arXiv
DO - 10.48550/arxiv.2610.31180
UR - https://arxiv.org/abs/2610.31180
AB - Modern high energy nuclear and particle physics experiments produce large amounts of sparse data that must be reduced significantly in size before performing physics analysis. Recently, there has been an effort to evaluate Foundation Models as a potential tool for performing data analysis. These models have been shown to learn features in high dimensional datasets based on the multi-modal data they are trained on. To show their effectiveness at performing complex pattern recognition tasks, such as reconstructing charged particles in a magnetic field, we evaluated the performance of a Foundation Model based reconstruction on several downstream tasks with a dataset composed of spacepoints in a Time Projection Chamber. We show that the performance of the Foundation Model based data analysis significantly improves upon that of traditional methods, and furthermore can be adapted to learn additional tasks that are not necessarily related to the initial training objective.
ER -