Papers for

high energy physics simulation teams

Papers whose findings have a practical use for this group, as judged from the abstract. Open a paper to read what it means in practice.

Calochill speeds up complex particle shower simulations by 600 times

Just CaloCHILL: fast hadronic shower generation in a learned latent space

Abstract: Calorimeter showers are the most expensive part of detector simulation, and highly granular calorimeters, in which a single hadronic shower leaves thousands of energy deposits, make them more expensive still. We present CaloCHILL (Calorimeter Hits In Learned Latents), a generative model that does not produce these deposits one by one: instead it generates a compact summary of the shower in a learned latent space and expands it to full resolution only at the end. The complete shower, including the arrival time of every hit, is built in three stages: a flow-matching model first sets the number of hits and the earliest hit time in each calorimeter layer, a mean-flow model then generates the latent summary, and the decompressor of a variational autoencoder turns it into the full point cloud, giving every hit its position, energy and time. Sparse attention along the shower axis keeps this compression affordable for showers with thousands of hits. On positive-pion showers in the calorimeter of the International Large Detector, a proposed detector for the FCC-ee, CaloCHILL reproduces the main shower observables, including their time structure. This new model is 600 times faster than its predecessor, while improving on all accuracy metrics considered.

Thu 5 NovMachine Learning
The gist
Simulating particle showers in detectors is very slow because each shower produces thousands of tiny signals that need to be modeled. The authors created CaloCHILL, a new method that summarizes the whole shower in a compact form before expanding it, greatly speeding up the process. This method still captures important details like where and when the particles hit the detector. It is much faster than previous methods while remaining accurate.
Open → 2611.08606v1