{"ID":2877064,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.20541","arxiv_id":"2508.20541","title":"Machine-learning based particle-flow algorithm in CMS","abstract":"The particle-flow (PF) algorithm provides a global event description by reconstructing final-state particles and is central to event reconstruction in CMS. Recently, end-to-end machine learning (ML) approaches have been proposed to directly optimize physical quantities of interest and to leverage heterogeneous computing architectures. One such approach, machine-learned particle flow (MLPF), uses a transformer model to infer particles directly from tracks and clusters in a single pass. We present recent CMS developments in MLPF, including training datasets, model architecture, reconstruction metrics, and integration with offline reconstruction software.","short_abstract":"The particle-flow (PF) algorithm provides a global event description by reconstructing final-state particles and is central to event reconstruction in CMS. Recently, end-to-end machine learning (ML) approaches have been proposed to directly optimize physical quantities of interest and to leverage heterogeneous computin...","url_abs":"https://arxiv.org/abs/2508.20541","url_pdf":"https://arxiv.org/pdf/2508.20541v1","authors":"[\"Farouk Mokhtar\"]","published":"2025-08-28T08:28:47Z","proceeding":"hep-ex","tasks":"[\"hep-ex\",\"cs.LG\"]","methods":"[\"Transformer\"]","has_code":false}