🔍 Intelligence Synthesis JP/EN
Ethics · Regulation · Technology — Pharma Practice Notes

AI and the World's Hard Problems · Physics · arXiv · 2026-10-22

Lorentz-Equivariant Geometric Algebra Transformers for Top-Quark Event Reconstruction

Lorentz-equivariant geometric algebra transformers (LGaTr) were evaluated on three top-quark event identification and reconstruction tasks. Geometric algebra provides a common Lorentz-covariant representation for four-momenta and typed physical objects. LGaTr outperformed baseline networks in tW versus top-quark pair separation and full event reconstruction, with performance comparable to or better than standard Transformer-based networks.

Read the original ↗

All items →