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

TL;DR

OmniLearned is an upgraded foundation model framework for jet physics that leverages over a billion jets, improving performance across multiple collider experiment tasks and providing accessible software tools.

Contribution

The paper introduces OmniLearned, a major upgrade with new architecture, extensive training data, and software, advancing foundation models for all jet physics tasks.

Findings

State-of-the-art performance in jet tagging tasks

Effective anomaly detection in collider data

Enhanced discovery potential in collider experiments

Abstract

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.