GLOW: A Unified Particle Flow Transformer
GLOW: A Unified Particle Flow Transformer
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.
Dmitrii Kobylianskii、Samuel Van Stroud、Kwok Yiu Wong、Max Hart、Etienne Dreyer、Eilam Gross、Gabriel Facini、Tim Scanlon
物理学信息科学、信息技术
Dmitrii Kobylianskii,Samuel Van Stroud,Kwok Yiu Wong,Max Hart,Etienne Dreyer,Eilam Gross,Gabriel Facini,Tim Scanlon.GLOW: A Unified Particle Flow Transformer[EB/OL].(2025-08-27)[2025-09-05].https://arxiv.org/abs/2508.20092.点此复制
评论