Calorimeter shower simulations are computationally expensive, and generative models offer an efficient alternative. However, achieving a balance between accuracy and speed remains a challenge, with distribution tail modeling being a key limitation. Invertible generative network CaloINN provides a trade-off between simulation quality and efficiency. The ongoing study targets introducing a set of post-processing modifications of analysis-level observables aimed at improving the accuracy of distribution tails. As part of interTwin project initiative developing an open-source Digital Twin Engine, we implemented the CaloINN within the interTwin AI framework.
Cite
@article{arxiv.2509.26527,
title = {Interdisciplinary Digital Twin Engine InterTwin for calorimeter simulation},
author = {Corentin Allaire and Vera Maiboroda and David Rousseau},
journal= {arXiv preprint arXiv:2509.26527},
year = {2026}
}
Comments
5 pages, 1 figure, proceedings for The 2nd European AI for Fundamental Physics Conference (EuCAIFCon2025)