arXiv:2605.27679v1 Announce Type: cross Abstract: We construct and evaluate group-equivariant neural networks for the prediction of the two-dimensional $Q$-tensor order parameter of nematic liquid crystals from synthetically generated microscopic textures. Seven architectures, equivariant to cyclic groups $C_k$ of order $k$ for $k=4,\,8,\,16,\,32,\,64,\,128,\, 256$, are built using a combination of weight-sharing constraints, equivariant activations and regularization techniques. To do this, we construct rotation-like permutation matrix groups with elements $\varrho_{C_k}(g)$ that act on row-w
The continuous advancements in AI research, particularly in equivariant neural networks, allow for more sophisticated processing of physical phenomena like liquid crystal behavior.
This development enables more accurate and efficient simulation and prediction of material properties, crucial for advanced materials science and potentially chip design.
The ability to precisely model complex anisotropic materials using AI could accelerate materials discovery and optimization for various technological applications.
- · Materials scientists
- · Hardware developers
- · AI researchers
- · Display technology manufacturers
- · Traditional simulation software vendors
- · Companies reliant on less precise material design
Improved understanding and design of nematic liquid crystals and other complex materials.
Faster development cycles for new display technologies, advanced sensors, or specialized optics.
Potential for integration into large-scale automated material design platforms, impacting sectors like compute supply chain.
This signal links to a primary source. Continuum Brief monitors and indexes it as part of the live intelligence stream — we do not republish source content.
Read at arXiv cs.LG