BRICKS: Compositional Neural Markov Kernels for Zero-Shot Radiation-Matter Simulation

MCML Authors

Lukas Heinrich

Prof. Dr.

Collaborating PI

Data Science in Physics

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.

misc HKH+26

---

Preprint

May. 2026

---

Authors

R. Hildebrandt • E. Kourlitis • B. Hashemi • M. Bünstorf • T. Meyer • N. Boskov • M. Kagan • D. Rosenbaum • S. Ganguly • L. Heinrich

---

Links

arXiv

---

Research Area

 C3 | Physics and Geo Sciences