From Molecules to Materials: Pre-training Large Generalizable Models for Atomic Property Prediction

Published in arXiv preprint arXiv:2310.16802, 2023

Citation: Nima Shoghi, Adeesh Kolluru, John Kitchin, Zachary Ulissi, C. Zitnick, Brandon Wood, arXiv preprint arXiv:2310.16802, 2023.

[Accepted at ICLR 2023!] Introduces Joint Multi-domain Pre-training (JMP), an approach that advances atomic property prediction by training on multiple datasets across diverse chemical domains simultaneously, significantly improving accuracy and setting or matching the state-of-the-art in many tasks.

Access paper here