mlsanityData to 7 Oct 2026

A Lorentz-Equivariant Transformer for All of the LHC

arXiv 2411.00446 ↗First posted 1 Nov 2024hep-ph cs.LG hep-excited by 27

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 27 papers in the map (data through 7 Oct 2026). Builds on 35 of its 85 references that are in the map. First posted on arXiv 1 Nov 2024.

Builds on

35 of 85 references.

References · 35

  1. 2017Attention Is All You Needcited by 59,932
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2022Flow Matching for Generative Modelingcited by 5,426
  4. 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 4,993
  5. 2018Neural Ordinary Differential Equationscited by 3,733
  6. 2022FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awarenesscited by 3,611
  7. 2016Gaussian Error Linear Units (GELUs)cited by 3,431
  8. 2017Deep Setscited by 1,394
  9. 2021Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gaugescited by 1,131
  10. 2020On Layer Normalization in the Transformer Architecturecited by 906
  11. 2023Stochastic Interpolants: A Unifying Framework for Flows and Diffusionscited by 897
  12. 2023Symbolic Discovery of Optimization Algorithmscited by 423
23 more
  1. 2021Scalars are universal: Equivariant machine learning, structured like classical physicscited by 127
  2. 2022Particle Transformer for Jet Taggingcited by 95
  3. 2018Energy Flow Networks: Deep Sets for Particle Jetscited by 83
  4. 2017CaloGAN: Simulating 3D High Energy Particle Showers in Multi-Layer Electromagnetic Calorimeters with Generative Adversarial Networkscited by 78
  5. 2019ParticleNet: Jet Tagging via Particle Cloudscited by 64
  6. 2023Clifford Group Equivariant Neural Networkscited by 54
  7. 2023Geometric Algebra Transformercited by 46
  8. 2015Jet-Images -- Deep Learning Editioncited by 41
  9. 2024Lorentz-Equivariant Geometric Algebra Transformers for High-Energy Physicscited by 36
  10. 2024CaloChallenge 2022: A Community Challenge for Fast Calorimeter Simulationcited by 34
  11. 2019How to GAN away Detector Effectscited by 28
  12. 2019LHC analysis-specific datasets with Generative Adversarial Networkscited by 26
  13. 2022PELICAN: Permutation Equivariant and Lorentz Invariant or Covariant Aggregator Network for Particle Physicscited by 26
  14. 2017QCD-Aware Recursive Neural Networks for Jet Physicscited by 22
  15. 2023End-To-End Latent Variational Diffusion Models for Inverse Problems in High Energy Physicscited by 22
  16. 2023Explainable Equivariant Neural Networks for Particle Physics: PELICANcited by 22
  17. 2022An unfolding method based on conditional Invertible Neural Networks (cINN) using iterative trainingcited by 20
  18. 2023CaloClouds II: Ultra-Fast Geometry-Independent Highly-Granular Calorimeter Simulationcited by 20
  19. 2024The Landscape of Unfolding with Machine Learningcited by 20
  20. 2023Improving Generative Model-based Unfolding with Schr"odinger Bridgescited by 13
  21. 2023Euclidean, Projective, Conformal: Choosing a Geometric Algebra for Equivariant Transformerscited by 12
  22. 2021Optimising simulations for diphoton production at hadron colliders using amplitude neural networkscited by 9
  23. 2024Optimal Equivariant Architectures from the Symmetries of Matrix-Element Likelihoodscited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 2; 2025: 15; 2026: 10.

27 papers.

Sort:

By area:

  1. 2025Large Physics Models: Towards a collaborative approach with Large Language Models and Foundation Modelscited by 14
  2. 2025OmniJet-αC: Learning point cloud calorimeter simulations using generative transformerscited by 14
  3. 2025Lorentz Local Canonicalization: How to Make Any Network Lorentz-Equivariantcited by 12
  4. 2026Neural Scaling Laws for Boosted Jet Taggingcited by 11
  5. 2025Foundation models for high-energy physicscited by 10
  6. 2025CaloHadronic: a diffusion model for the generation of hadronic showerscited by 8
  7. 2024Generative Unfolding with Distribution Mappingcited by 6
  8. 2025RINO: Renormalization Group Invariance with No Labelscited by 6
  9. 2026Scaling laws for amplitude surrogatescited by 5
  10. 2025Hybrid Diffusion Policies with Projective Geometric Algebra for Efficient Robot Manipulation Learningcited by 3
  11. 2025Forecasting Generative Amplificationcited by 3
  12. 2025Enhancing next token prediction based pre-training for jet foundation modelscited by 3
15 more
  1. 2026AllShowers: One model for all calorimeter showerscited by 3
  2. 2024Extrapolating Jet Radiation with Autoregressive Transformerscited by 2
  3. 2025Stable and Interpretable Jet Physics with IRC-Safe Equivariant Feature Extractioncited by 2
  4. 2025A First Full Physics Benchmark for Highly Granular Calorimeter Surrogatescited by 2
  5. 2026Approximate Equivariance via Projection-based Regularisationcited by 2
  6. 2025Generating particle physics Lagrangians with transformerscited by 1
  7. 2025BitHEP -- The Limits of Low-Precision ML in HEPcited by 1
  8. 2025Latent Representation Learning in Heavy-Ion Collisions with MaskPoint Transformercited by 1
  9. 2026jBOT: Semantic Jet Representation Clustering Emerges from Self-Distillationcited by 1
  10. 2026Pointwise Metrics Mislead: An Evaluation Protocol for Multimodal Inverse Problemscited by 1
  11. 2026Unknown Unknowns: Model Misspecification in Machine Learning for Physicscited by 1
  12. 2025Learnable cut flow for high energy physicscited by 0
  13. 2026Softly Induced Functional Simplicity: Implications for Neural Network Generalisation, Robustness, and Distillationcited by 0
  14. 2026Event Generation with Parallel Langevin Sampling and Learned Stein Diagnosticscited by 0
  15. 2026Machine learning for the LHC physics program: a 2025-2026 stocktakecited by 0