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.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
hep-ex 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
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.