SciPost Submission Page
Fast, accurate, and precise detector simulation with vision transformers
by Luigi Favaro, Andrea Giammanco, Claudius Krause
This is not the latest submitted version.
Submission summary
| Authors (as registered SciPost users): | Luigi Favaro · Claudius Krause |
| Submission information | |
|---|---|
| Preprint Link: | https://arxiv.org/abs/2509.25169v1 (pdf) |
| Code repository: | https://github.com/luigifvr/vit4hep |
| Data repository: | https://calochallenge.github.io/homepage/ |
| Date submitted: | Sept. 30, 2025, 10:15 a.m. |
| Submitted by: | Luigi Favaro |
| Submitted to: | SciPost Physics Proceedings |
| Proceedings issue: | The 2nd European AI for Fundamental Physics Conference (EuCAIFCon2025) |
| Ontological classification | |
|---|---|
| Academic field: | Physics |
| Specialties: |
|
| Approach: | Computational |
Abstract
The speed and fidelity of detector simulations in particle physics pose compelling questions about LHC analysis and future colliders. The sparse high-dimensional data, combined with the required precision, provide a challenging task for modern generative networks. We present a comparison between solutions with different trade-offs, including accurate Conditional Flow Matching and faster coupling-based Normalising Flows. Vision Transformers allows us to emulate the energy deposition from detailed Geant4 simulations. We evaluate the networks using high-level observables, neural network classifiers, and sampling timings, showing minimum deviations from Geant4 while achieving faster generation. We use the CaloChallenge benchmark datasets for reproducibility and further development.
Current status:
Reports on this Submission
Report #1 by Anonymous (Referee 1) on 2025-11-5 (Invited Report)
The referee discloses that the following generative AI tools have been used in the preparation of this report:
I used ChatGPT-4 on 4/11/2025 to pass the review text through a grammar check.
Report
The article is well written and logically structured, presenting a comprehensive and technically sound study. Given that the primary motivation for exploring generative models in this context is to develop faster alternatives to GEANT4 Monte Carlo simulations, it might be beneficial to include a reference to the typical time required by GEANT4 to simulate a single calorimeter shower, even if it is generally executed on CPUs rather than GPUs as in the case of the generative approaches.
Recommendation
Publish (easily meets expectations and criteria for this Journal; among top 50%)