We show that the Lorentz-Equivariant Geometric Algebra Transformer (L-GATr) yields state-of-the-art performance for a wide range of machine learning tasks at the Large Hadron Collider. L-GATr represents data in a geometric algebra over space-time and is equivariant under Lorentz transformations. The underlying architecture is a versatile and scalable transformer, which is able to break symmetries if needed. We demonstrate the power of L-GATr for amplitude regression and jet classification, and then benchmark it as the first Lorentz-equivariant generative network. For all three LHC tasks, we find significant improvements over previous architectures.
@article{arxiv.2411.00446,
title = {A Lorentz-Equivariant Transformer for All of the LHC},
author = {Johann Brehmer and Víctor Bresó and Pim de Haan and Tilman Plehn and Huilin Qu and Jonas Spinner and Jesse Thaler},
journal= {arXiv preprint arXiv:2411.00446},
year = {2025}
}