MPtrj
Emerging6papers using it
2024first seen
The 'MPtrj' dataset is an inorganic benchmark used to evaluate the performance of machine learning interatomic potentials in predicting potential energy surfaces.
Papers using MPtrj (6)
- Information Routing in Atomistic Foundation Models: How Task Alignment and Equivariance Shape Linear DisentanglementExpanding Universal Machine Learning Interatomic Potentials to 97 Elements Towards Nuclear ApplicationsBetter without U: Impact of Selective Hubbard U Correction on Foundational MLIPsFacet: highly efficient E(3)-equivariant networks for interatomic potentialsFastCHGNet: Training one Universal Interatomic Potential to 1.5 Hours with 32 GPUsOpen Materials 2024 (OMat24) Inorganic Materials Dataset and Models