Cell-level Transformers classify collimated ALP photon-jets versus single photons with AUC 0.98 and regress diphoton mass to ~64 MeV, beating shower-shape and other ML baselines in an ATLAS-like GEANT4 simulation.
Title resolution pending
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
representative citing papers
A distributed arithmetic algorithm for CMVM operations on FPGAs reduces area by up to one third and latency for quantized neural networks, integrated into hls4ml.
Sequential ML models classify quenched jets with >93% accuracy and show sensitivity to medium implementation details that traditional observables miss.
Physics-informed GNNs with four detector-aware graph constructions and a custom message passing layer achieve MAE 0.8525 for pT estimation on CMS trigger data with over 55% fewer parameters than baselines.
μ-ORCA achieves 0.93 μs end-to-end latency for a 6-layer DeepSets model on AMD ACAP VEK280 by direct AIE inter-layer communication and overhead-aware design space exploration, delivering 1.70-1.83× speedup over prior ACAP frameworks.
citing papers explorer
-
Transformer-based machine learning using low-level calorimeter signals for collimated photon identification at collider experiments
Cell-level Transformers classify collimated ALP photon-jets versus single photons with AUC 0.98 and regress diphoton mass to ~64 MeV, beating shower-shape and other ML baselines in an ATLAS-like GEANT4 simulation.
-
da4ml: Distributed Arithmetic for Real-time Neural Networks on FPGAs
A distributed arithmetic algorithm for CMVM operations on FPGAs reduces area by up to one third and latency for quantized neural networks, integrated into hls4ml.
-
Jet Quenching Identification via Supervised Learning in Simulated Heavy-Ion Collisions
Sequential ML models classify quenched jets with >93% accuracy and show sensitivity to medium implementation details that traditional observables miss.
-
Physics-Informed Graph Neural Networks for Transverse Momentum Estimation in CMS Trigger Systems
Physics-informed GNNs with four detector-aware graph constructions and a custom message passing layer achieve MAE 0.8525 for pT estimation on CMS trigger data with over 55% fewer parameters than baselines.
-
{\mu}-ORCA: Optimizing Acceleration for Microsecond-Scale Deep Neural Network Inference on ACAP
μ-ORCA achieves 0.93 μs end-to-end latency for a 6-layer DeepSets model on AMD ACAP VEK280 by direct AIE inter-layer communication and overhead-aware design space exploration, delivering 1.70-1.83× speedup over prior ACAP frameworks.