IAFormer uses boost-invariant pairwise quantities and differential attention to create a sparse Transformer that achieves state-of-the-art classification on top-quark and quark-gluon jet datasets while using over an order of magnitude fewer parameters than prior Particle Transformer models.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2025 2verdicts
UNVERDICTED 2representative citing papers
With 6×10^{12} Z bosons at FCC-ee, invisible B-meson branching fractions above 7.6×10^{-9} could be excluded at 90% CL using rectangular cuts and a multiclass BDT on simulated signal and background.
citing papers explorer
-
IAFormer: Interaction-Aware Transformer network for collider data analysis
IAFormer uses boost-invariant pairwise quantities and differential attention to create a sparse Transformer that achieves state-of-the-art classification on top-quark and quark-gluon jet datasets while using over an order of magnitude fewer parameters than prior Particle Transformer models.
-
Prospects of searches for invisible $B$-meson decays at FCC-ee
With 6×10^{12} Z bosons at FCC-ee, invisible B-meson branching fractions above 7.6×10^{-9} could be excluded at 90% CL using rectangular cuts and a multiclass BDT on simulated signal and background.