Abstract:We introduce a new strategy for compositional neural surrogates for radiation-matter interactions, a key task spanning domains from particle physics through nuclear and space engineering to medical physics. Exploiting the locality and the Markov nature of particle interactions, we create a \emph{next-particle prediction} kernel using hybrid discrete-continuous transformer models based on Riemannian Flow Matching on product manifolds. The model generates variable-sized typed sets of particles and radiation side effects that are the result of the interaction of an incident particle with a material volume. The resulting kernel can be composed to simulate unseen large-scale material distributions in a zero-shot manner. Unlike mechanistic simulators, our model is designed to be differentiable, provides tractable likelihoods for future downstream applications. A significant computational speed-up on GPU compared to CPU-bound mechanistic simulation is observed for single-kernel execution. We evaluate the model at the kernel level and demonstrate predictive stability over multi-round autoregressive rollouts. We additionally release a novel 20M-event radiation-matter interaction dataset for further research.
| Comments: | 10 pages, 5 figures |
| Subjects: | Machine Learning (cs.LG); High Energy Physics - Phenomenology (hep-ph) |
| Cite as: | arXiv:2605.06591 [cs.LG] |
| (or arXiv:2605.06591v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2605.06591 arXiv-issued DOI via DataCite (pending registration) |
From: Lukas Heinrich [view email]
[v1]
Thu, 7 May 2026 17:19:31 UTC (4,923 KB)
此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。 原文来自 — 版权归原作者所有。