Tag
This paper introduces DyRIS, an LLM-agent framework using dynamic few-shot retrieval and rule-guided inference to predict space groups of double perovskites, achieving competitive accuracy and significantly improving performance on minority space-group classes.
A tool for designing unit cells in 2D wallpaper groups, aiding researchers and educators in crystallography and materials science.
This paper investigates whether multimodal large language models (MLLMs) can leverage Miller indices as a latent representation to reason about crystallographic fracture geometry from visual inputs, evaluating their ability to infer physically valid plane hypotheses and determine when such representation is applicable across materials like ceramics, glass, metals, and concrete.
A blog post discusses the rarity of naturally occurring quasicrystals, which have only been found in a few exotic locations such as the Khatyrka meteorite, a lightning strike in Nebraska, and the Trinity atomic bomb test site.