PLuM multimodal transformer improves top and H->bb jet tagging by jointly processing particle constituents and Lund plane splittings, yielding 25% higher background rejection at 25% di-Higgs efficiency.
Title resolution pending
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
representative citing papers
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.
Spectral-function features fed to a dense network improve expected gluino-mass reach by ~150 GeV over ATLAS Gtt-0L-C and ~250 GeV over kinematics-only ML for the fully hadronic channel.
A one-step generative model for calorimeter showers, using MeanFlow, a learned Gaussian-mixture prior, and a physics-constrained loss, matches diffusion-model quality at far fewer evaluations.
Transformers trained on cosmic ray simulations learn physically plausible features in positional encodings for symmetric air showers and in attention mechanisms for galaxy-origin particles.
Compares ensemble, Bayesian, and evidential regression approaches for uncertainty quantification in amplitude surrogates and shows they detect localized training data issues.
citing papers explorer
-
Particle-Lund Multimodality in Jet Taggers
PLuM multimodal transformer improves top and H->bb jet tagging by jointly processing particle constituents and Lund plane splittings, yielding 25% higher background rejection at 25% di-Higgs efficiency.
-
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.
-
Machine learning fully hadronic events with spectral functions
Spectral-function features fed to a dense network improve expected gluino-mass reach by ~150 GeV over ATLAS Gtt-0L-C and ~250 GeV over kinematics-only ML for the fully hadronic channel.
-
CaloTrilogy: Toward a Breakthrough in One-Step, End-to-End, Physics-Guided Shower Generation for Modern Calorimeters
A one-step generative model for calorimeter showers, using MeanFlow, a learned Gaussian-mixture prior, and a physics-constrained loss, matches diffusion-model quality at far fewer evaluations.
-
What exactly did the Transformer learn from our physics data?
Transformers trained on cosmic ray simulations learn physically plausible features in positional encodings for symmetric air showers and in attention mechanisms for galaxy-origin particles.
-
Amplitude Uncertainties Everywhere All at Once
Compares ensemble, Bayesian, and evidential regression approaches for uncertainty quantification in amplitude surrogates and shows they detect localized training data issues.