SAL-T enhances the linformer with spatially aware kinematic partitioning and convolutions to match full-attention transformer performance on jet tagging while keeping linear complexity and lower latency.
The CMS Particle Flow Algorithm
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
A particle flow event-reconstruction algorithm has been successfully deployed in the CMS experiment and is nowadays used by most of the analyses. It aims at identifying and reconstructing individually each particle arising from the LHC proton-proton collision, by combining the information from all the subdetectors. The resulting particle-flow event reconstruction leads to an improved performance for the reconstruction of jets and MET, and for the identification of electrons, muons, and taus. The algorithm and its performance will be described. The commissioning phase, during which it was demonstrated that the algorithm was performing as expected from the simulation up to a high level of precision, will be presented. Finally, a selection of recent improvements in the CMS analyses obtained thanks to the particle-flow algorithm will be discussed.
fields
cs.LG 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Spatially Aware Linear Transformer (SAL-T) for Particle Jet Tagging
SAL-T enhances the linformer with spatially aware kinematic partitioning and convolutions to match full-attention transformer performance on jet tagging while keeping linear complexity and lower latency.