Machine learning potentials (MLPs) have become an indispensable tool in large-scale atomistic simulations. However, most MLPs today are trained on data computed using relatively cheap density ...

A preprint version of the article is available at ChemRxiv. To train ML models on the SUNSET data, we initially investigated several existing representations for encoding the compositional and ...

Autograph first extracts loops and builds dependency graphs capturing instruction semantics and data flow, which are then converted into embeddings by Graph Neural Network. These embeddings are then ...

Across modern data-intensive disciplines, the union of numerical computation, statistics, and machine learning has become ...