Abstract:We study whether multimodal large language models (MLLMs) can leverage crystallographic plane indices (Miller indices) as a structured latent representation for reasoning about fracture geometry. We formulate Miller indices $z = (h,k,l)$ as a latent variable governing idealized planar fracture and evaluate two complementary capabilities: (i) latent inference, where the model maps visual observations to plane hypotheses under physically valid conditions, and (ii) latent applicability assessment, where the model determines whether such a representation is meaningful for a given fracture image.
Through extensive experiments spanning synthetic data, controlled 2D--3D geometric pairs, and real-world fracture images across multiple material classes -- including ceramics, glass, metals, and concrete -- we show that MLLMs can reliably perform latent inference in idealized settings and, critically, can reject the latent representation when the underlying physics does not support it. These results suggest that MLLMs can act as physics-aware reasoning systems conditioned on structured latent priors, provided that the domain of validity is explicitly modeled.
| Subjects: | Machine Learning (cs.LG); Computational Physics (physics.comp-ph) |
| Cite as: | arXiv:2605.20416 [cs.LG] |
| (or arXiv:2605.20416v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2605.20416 arXiv-issued DOI via DataCite (pending registration) |
From: Qinwu Xu [view email]
[v1]
Tue, 19 May 2026 19:11:38 UTC (1,940 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。