AI RESEARCH
From Word2Vec to Transformers: Text-Derived Composition Embeddings for Filtering Combinatorial Electrocatalysts
arXiv CS.CL
•
ArXi:2603.08881v1 Announce Type: cross Compositionally complex solid solution electrocatalysts span vast composition spaces, and even one materials system can contain candidate compositions than can be measured exhaustively. Here we evaluate a label-free screening strategy that represents each composition using embeddings derived from scientific texts and prioritizes candidates based on similarity to two property concepts.