AI RESEARCH
A universal vision transformer for fast calorimeter simulations
arXiv CS.LG
•
ArXi:2601.05289v2 Announce Type: replace-cross The high-dimensional complex nature of detectors makes fast calorimeter simulations a prime application for modern generative machine learning. Vision transformers (ViTs) can emulate the Geant4 response with unmatched accuracy and are not limited to regular geometries. Starting from the CaloDREAM architecture, we nstrate the robustness and scalability of ViTs on regular and irregular geometries, and multiple detectors.