OmniLearned: A Foundation Model Framework for All Tasks Involving Jet Physics

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Bhimji, Wahid, Harris, Chris, Mikuni, Vinicius, Nachman, Benjamin
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866917361973460992
author Bhimji, Wahid
Harris, Chris
Mikuni, Vinicius
Nachman, Benjamin
author_facet Bhimji, Wahid
Harris, Chris
Mikuni, Vinicius
Nachman, Benjamin
contents Foundation models use large datasets to build an effective representation of data that can be deployed on diverse downstream tasks. Previous research developed the OmniLearn foundation model for jet physics, using unique properties of particle physics, and showed that it could significantly advance discovery potential across collider experiments. This paper introduces a major upgrade, resulting in the OmniLearned framework. This framework has three new elements: (1) updates to the model architecture and training, (2) using over one billion jets used for training, and (3) providing well-documented software for accessing all datasets and models. We demonstrate OmniLearned with three representative tasks: top-quark jet tagging with the community Delphes-based benchmark dataset, b-tagging with ATLAS full simulation, and anomaly detection with CMS experimental data. In each case, OmniLearned is the state of the art, further expanding the discovery potential of past, current, and future collider experiments.
format Preprint
id arxiv_https___arxiv_org_abs_2510_24066
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle OmniLearned: A Foundation Model Framework for All Tasks Involving Jet Physics
Bhimji, Wahid
Harris, Chris
Mikuni, Vinicius
Nachman, Benjamin
High Energy Physics - Phenomenology
Foundation models use large datasets to build an effective representation of data that can be deployed on diverse downstream tasks. Previous research developed the OmniLearn foundation model for jet physics, using unique properties of particle physics, and showed that it could significantly advance discovery potential across collider experiments. This paper introduces a major upgrade, resulting in the OmniLearned framework. This framework has three new elements: (1) updates to the model architecture and training, (2) using over one billion jets used for training, and (3) providing well-documented software for accessing all datasets and models. We demonstrate OmniLearned with three representative tasks: top-quark jet tagging with the community Delphes-based benchmark dataset, b-tagging with ATLAS full simulation, and anomaly detection with CMS experimental data. In each case, OmniLearned is the state of the art, further expanding the discovery potential of past, current, and future collider experiments.
title OmniLearned: A Foundation Model Framework for All Tasks Involving Jet Physics
topic High Energy Physics - Phenomenology
url https://arxiv.org/abs/2510.24066