Bumblebee: Foundation Model for Particle Physics Discovery
High Energy Physics - Experiment
2024-12-12 v1 Machine Learning
High Energy Physics - Phenomenology
Abstract
Bumblebee is a foundation model for particle physics discovery, inspired by BERT. By removing positional encodings and embedding particle 4-vectors, Bumblebee captures both generator- and reconstruction-level information while ensuring sequence-order invariance. Pre-trained on a masked task, it improves dileptonic top quark reconstruction resolution by 10-20% and excels in downstream tasks, including toponium discrimination (AUROC 0.877) and initial state classification (AUROC 0.625). The flexibility of Bumblebee makes it suitable for a wide range of particle physics applications, especially the discovery of new particles.
Cite
@article{arxiv.2412.07867,
title = {Bumblebee: Foundation Model for Particle Physics Discovery},
author = {Andrew J. Wildridge and Jack P. Rodgers and Ethan M. Colbert and Yao yao and Andreas W. Jung and Miaoyuan Liu},
journal= {arXiv preprint arXiv:2412.07867},
year = {2024}
}
Comments
5 pages, 3 figures, submitted to Machine Learning and the Physical Sciences Workshop, NeurIPS 2024