5 papers · 1 filter
Point-cloud generative models for fast calorimeter simulation across particles and geometries
Thorsten Buss, Henry Day-Hall, Frank Gaede +7
Detailed Geant4 simulation of calorimeter showers is the largest single computing cost of collider experiments, and the High-Luminosity LHC will need about ten times more simulated…
Cross-geometry transfer and model collapse in point cloud calorimeter shower generation
Thorsten Buss, Frank Gaede, Gregor Kasieczka +2
Particle shower simulation is a major computational cost in high-energy physics. Monte Carlo methods such as Geant4 are accurate but expensive, while most machine learning surrogat…
Transferable Fast Calorimeter Shower Generation via Multi-Geometry Pre-training
Thorsten Buss, Henry Day-Hall, Frank Gaede +4
Detailed Geant4 simulation of calorimeter showers dominates the computing budget of high-energy physics experiments. Deep generative surrogates reduce this cost, but they have rema…
Cross-Geometry Transfer Learning in Fast Electromagnetic Shower Simulation
Frank Gaede, Gregor Kasieczka, Lorenzo Valente
Accurate particle shower simulation remains a critical computational bottleneck for high-energy physics. Traditional Monte Carlo methods, such as Geant4, are computationally prohib…
CaloClouds3: Ultra-Fast Geometry-Independent Highly-Granular Calorimeter Simulation
Thorsten Buss, Henry Day-Hall, Frank Gaede +7
We present CaloClouds3, a model for the fast simulation of photon showers in the barrel of a high granularity detector. This iteration demonstrates for the first time how a pointcl…