English

GLOW: A Unified Particle Flow Transformer

High Energy Physics - Experiment 2025-08-28 v1 High Energy Physics - Phenomenology

Abstract

We present GLOW, a transformer-based particle flow model that combines incidence matrix supervision from HGPflow with a MaskFormer architecture. Evaluated on CLIC detector simulations, GLOW achieves state-of-the-art performance and, together with prior work, demonstrates that a single unified transformer architecture can effectively address diverse reconstruction tasks in particle physics.

Cite

@article{arxiv.2508.20092,
  title  = {GLOW: A Unified Particle Flow Transformer},
  author = {Dmitrii Kobylianskii and Samuel Van Stroud and Kwok Yiu Wong and Max Hart and Etienne Dreyer and Eilam Gross and Gabriel Facini and Tim Scanlon},
  journal= {arXiv preprint arXiv:2508.20092},
  year   = {2025}
}

Comments

4 pages, 4 figures

R2 v1 2026-07-01T05:08:52.387Z