🤖 AI Summary
This work addresses the high computational cost of traditional simulation tools like Geant4 in modeling particle showers within complex, high-dimensional calorimeter geometries. The authors propose a general-purpose generative model based on the Vision Transformer (ViT), which is, to the best of their knowledge, the first successful application of ViT to fast simulation of both electromagnetic and hadronic showers, accommodating both regular and irregular detector geometries. Leveraging large-scale pretraining followed by fine-tuning on target detectors, the model generates full showers in 10–100 milliseconds on a single GPU, achieving orders-of-magnitude speedup. The generated showers exhibit statistical fidelity indistinguishable from Geant4 across multiple metrics while demonstrating strong generalization across diverse geometric configurations.
📝 Abstract
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 demonstrate the robustness and scalability of ViTs on regular and irregular geometries, and multiple detectors. Our results show that ViTs generate electromagnetic and hadronic showers statistically indistinguishable from Geant4 in multiple evaluation metrics, while maintaining the generation time in the $\mathcal{O}(10-100)$ ms on a single GPU. Furthermore, we show that pretraining on a large dataset and fine-tuning on the target geometry leads to reduced training costs and higher data efficiency, or altogether improves the fidelity of generated showers.