OMat24 releases a new open dataset of 110M+ DFT calculations and EquiformerV2 models achieving SOTA on Matbench Discovery with F1>0.9 for stability and 20 meV/atom accuracy for formation energies.
Forces are not enough: Benchmark and critical evaluation for machine learning force fields with molecular simulations
13 Pith papers cite this work, alongside 163 external citations. Polarity classification is still indexing.
13
Pith papers citing it
163
external citations · external index
citation-role summary
background 2
citation-polarity summary
roles
background 2polarities
background 2representative citing papers
CliffordSTF couples Clifford multivectors to rank-2 and rank-3 symmetric-traceless tensor tracks through bilinear cross-track contractions, lifting force cosine similarity from 0.055 to 0.551 on rMD17 while outperforming CG-free baselines.
SOAP and SOAP-Muon optimizers deliver faster convergence and higher final accuracy than Adam for NequIP and Allegro MLIPs, with the largest gains under partial force supervision.
MatterSim delivers a single deep learning force field that simulates inorganic materials across elements, 0-5000 K, and up to 1000 GPa with near first-principles accuracy for lattice dynamics, mechanics, and Gibbs free energies.
A new general-purpose ACE interatomic potential for niobium is trained on diverse DFT data and validated on phonons, high-pressure behavior, dislocation barriers, and a near-million-atom fracture simulation.
An agentic HPC skill automates NEB microkinetics, recovers from common failures, and benchmarks ~12 universal MLIPs against DFT for CO2 sublimation on graphite.
Universal MLIPs serve as configuration generators whose DFT-relabeled subsamples enable one-shot or iterative training of material-specific MLIPs that recover accurate reactive energy profiles with 600-2000 DFT calculations.
Machine-learning interatomic potentials trained on prior ab initio data for multiple DFT functionals are used to compare water dynamical properties, with RPBE-D3/zd identified as best matching experiment and further validated across conditions.
AtomisticSkills is a new harness framework with 100+ human-curated skills that lets general AI agents perform atomistic research tasks including simulations, screening, and analysis, shown on electrolyte design, CO2 capture, drug screening, and catalyst tasks.
The EDDP machine-learned potential for lead predicts the observed FCC-HCP phase transition at ~15 GPa, unlike EAM and MEAM models, when paired with nested sampling.
NEPMaker uses D-optimality active learning to identify and locally embed extrapolative atomic environments from large simulations into periodic structures for training neuroevolution potentials, aiming to cut extrapolation errors in complex materials.
Deep learning architectures tailored to protein hierarchy combined with sequence-space search algorithms are used to improve prediction of protein complex structures and to design new interacting sequences.
Differentiable hybrid force fields fuse physical skeletons with neural corrections to deliver fast, accurate, and top-down calibratable simulation for autonomous electrolyte discovery.
citing papers explorer
-
Open Materials 2024 (OMat24) Inorganic Materials Dataset and Models
OMat24 releases a new open dataset of 110M+ DFT calculations and EquiformerV2 models achieving SOTA on Matbench Discovery with F1>0.9 for stability and 20 meV/atom accuracy for formation energies.
-
Geometric Algebra Meets Cartesian Tensors: Higher-Order Equivariance for Interatomic Potentials
CliffordSTF couples Clifford multivectors to rank-2 and rank-3 symmetric-traceless tensor tracks through bilinear cross-track contractions, lifting force cosine similarity from 0.055 to 0.551 on rMD17 while outperforming CG-free baselines.
-
Beyond Adam: SOAP and Muon for Faster, Label-Efficient Training of Machine Learning Interatomic Potentials
SOAP and SOAP-Muon optimizers deliver faster convergence and higher final accuracy than Adam for NequIP and Allegro MLIPs, with the largest gains under partial force supervision.
-
MatterSim: A Deep Learning Atomistic Model Across Elements, Temperatures and Pressures
MatterSim delivers a single deep learning force field that simulates inorganic materials across elements, 0-5000 K, and up to 1000 GPa with near first-principles accuracy for lattice dynamics, mechanics, and Gibbs free energies.
-
A general-purpose atomic cluster expansion interatomic potential for niobium
A new general-purpose ACE interatomic potential for niobium is trained on diverse DFT data and validated on phonons, high-pressure behavior, dislocation barriers, and a near-million-atom fracture simulation.
-
Toward Exascale AI for Science: A Scalable AI Skill for Autonomous Microkinetics Discovery
An agentic HPC skill automates NEB microkinetics, recovers from common failures, and benchmarks ~12 universal MLIPs against DFT for CO2 sublimation on graphite.
-
Universal Interatomic Potentials as Configuration-Space Generators for One-Shot and Iterative Fine-Tuning of Ab Initio-Accurate Material-Specific Models
Universal MLIPs serve as configuration generators whose DFT-relabeled subsamples enable one-shot or iterative training of material-specific MLIPs that recover accurate reactive energy profiles with 600-2000 DFT calculations.
-
Dynamical properties of ab initio water from machine-learning potentials
Machine-learning interatomic potentials trained on prior ab initio data for multiple DFT functionals are used to compare water dynamical properties, with RPBE-D3/zd identified as best matching experiment and further validated across conditions.
-
Harnessing AtomisticSkills for Agentic Atomistic Research
AtomisticSkills is a new harness framework with 100+ human-curated skills that lets general AI agents perform atomistic research tasks including simulations, screening, and analysis, shown on electrolyte design, CO2 capture, drug screening, and catalyst tasks.
-
Benchmarking empirical and machine-learned interatomic potentials using phase diagram predictions for Lead
The EDDP machine-learned potential for lead predicts the observed FCC-HCP phase transition at ~15 GPa, unlike EAM and MEAM models, when paired with nested sampling.
-
NEPMaker: Active learning of neuroevolution machine learning potential for large cells
NEPMaker uses D-optimality active learning to identify and locally embed extrapolative atomic environments from large simulations into periodic structures for training neuroevolution potentials, aiming to cut extrapolation errors in complex materials.
-
Deep Learning for Protein Complex Prediction and Design
Deep learning architectures tailored to protein hierarchy combined with sequence-space search algorithms are used to improve prediction of protein complex structures and to design new interacting sequences.
-
Differentiable hybrid force fields support scalable autonomous electrolyte discovery
Differentiable hybrid force fields fuse physical skeletons with neural corrections to deliver fast, accurate, and top-down calibratable simulation for autonomous electrolyte discovery.