Saved in:
Bibliographic Details
Main Authors: Caron, Sascha, Dobreva, Nadezhda, Kimpel, Maarten, Odyurt, Uraz, Pshenov, Slav, Bazan, Roberto Ruiz de Austri, Shalugin, Eugene, Wolffs, Zef, Zhao, Yue
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2509.26411
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914392088510464
author Caron, Sascha
Dobreva, Nadezhda
Kimpel, Maarten
Odyurt, Uraz
Pshenov, Slav
Bazan, Roberto Ruiz de Austri
Shalugin, Eugene
Wolffs, Zef
Zhao, Yue
author_facet Caron, Sascha
Dobreva, Nadezhda
Kimpel, Maarten
Odyurt, Uraz
Pshenov, Slav
Bazan, Roberto Ruiz de Austri
Shalugin, Eugene
Wolffs, Zef
Zhao, Yue
contents High-Energy Physics experiments are rapidly escalating in generated data volume, a trend that will intensify with the upcoming High-Luminosity LHC upgrade. This surge in data necessitates critical revisions across the data processing pipeline, with particle track reconstruction being a prime candidate for improvement. In our previous work, we introduced "TrackFormers", a collection of Transformer-based one-shot encoder-only models that effectively associate hits with expected tracks. In this study, we extend our earlier efforts by conducting detailed investigations into more custom Transformer attention mechanisms, a new design combining geometric projection and lightweight clustering, and a joint model conditioning classification on a regressor's predictions. Furthermore, we discuss new datasets that allow the training on hit level for a range of physics processes. These developments collectively aim to boost both the accuracy and potentially the efficiency of our tracking models, offering a robust solution to meet the demands of next-generation high-energy physics experiments.
format Preprint
id arxiv_https___arxiv_org_abs_2509_26411
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle TrackFormers Part 2: Enhanced Transformer-Based Models for High-Energy Physics Track Reconstruction
Caron, Sascha
Dobreva, Nadezhda
Kimpel, Maarten
Odyurt, Uraz
Pshenov, Slav
Bazan, Roberto Ruiz de Austri
Shalugin, Eugene
Wolffs, Zef
Zhao, Yue
High Energy Physics - Experiment
Machine Learning
High-Energy Physics experiments are rapidly escalating in generated data volume, a trend that will intensify with the upcoming High-Luminosity LHC upgrade. This surge in data necessitates critical revisions across the data processing pipeline, with particle track reconstruction being a prime candidate for improvement. In our previous work, we introduced "TrackFormers", a collection of Transformer-based one-shot encoder-only models that effectively associate hits with expected tracks. In this study, we extend our earlier efforts by conducting detailed investigations into more custom Transformer attention mechanisms, a new design combining geometric projection and lightweight clustering, and a joint model conditioning classification on a regressor's predictions. Furthermore, we discuss new datasets that allow the training on hit level for a range of physics processes. These developments collectively aim to boost both the accuracy and potentially the efficiency of our tracking models, offering a robust solution to meet the demands of next-generation high-energy physics experiments.
title TrackFormers Part 2: Enhanced Transformer-Based Models for High-Energy Physics Track Reconstruction
topic High Energy Physics - Experiment
Machine Learning
url https://arxiv.org/abs/2509.26411