2 papers
cond-mat.mtrl-sci2026
ZEBRA-Prop: A Zero-Shot Embedding-Based Rapid and Accessible Regression Model for Materials Properties
Ryoma Yamamoto, Akira Takahashi, Kei Terayama +2
Large language models (LLMs) exhibit substantial potential across diverse scientific disciplines, including materials science. A property prediction framework, ZEBRA-Prop (Zero-Sho…
cond-mat.mtrl-sci2025
Deep Learning-Based Extraction of Promising Material Groups and Common Features from High-Dimensional Data: A Case of Optical Spectra of Inorganic Crystals
Akira Takahashi, Yu Kumagai, Arata Takamatsu +1
We report an interpretation method for deep learning models that allows us to handle high-dimensional spectral data in materials science. The proposed method uses feature extractio…