BRICKS creates compositional neural Markov kernels via hybrid transformers and Riemannian Flow Matching on product manifolds to enable zero-shot simulation of radiation-matter interactions across arbitrary material distributions.
The model was trained on a batch-size of 212 over 100 epochs with 20M total events (simulations) and incoming particle types ∈[e −, e+, γ]
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
BRICKS: Compositional Neural Markov Kernels for Zero-Shot Radiation-Matter Simulation
BRICKS creates compositional neural Markov kernels via hybrid transformers and Riemannian Flow Matching on product manifolds to enable zero-shot simulation of radiation-matter interactions across arbitrary material distributions.