OMat-24

The 'OMat-24' dataset/benchmark contains a collection of molecular configurations and properties used to evaluate the performance of SE(3)-equivariant graph neural networks in 3D atomistic modeling.

Papers using OMat-24 (5)

A recipe for scalable attention-based MLIPs: unlocking long-range accuracy with all-to-all node attention2026 · 2 citesEquiformerV3: Scaling Efficient, Expressive, and General SE(3)-Equivariant Graph Attention Transformers2026Scaling Machine Learning Interatomic Potentials with Mixtures of Experts2026Better without U: Impact of Selective Hubbard U Correction on Foundational MLIPs2026Open Materials 2024 (OMat24) Inorganic Materials Dataset and Models2024 · 96 cites