MLIP simulations show that Mn promotes incoherent interfaces with the G-phase leading to film-like GB precipitates, while Ni2Si forms irregular shapes due to coherent interfaces that develop repulsive regions.
Scalable parallel algorithm for graph neural network interatomic potentials in molecular dynamics simulations
8 Pith papers cite this work. Polarity classification is still indexing.
8
Pith papers citing it
citation-role summary
method 2
citation-polarity summary
roles
method 2polarities
use method 2representative citing papers
GFFMERGE formulates GNN force field merging as a convex embedding-alignment problem with an analytical solution, recovering near joint-training performance on MD17, MD22, LiPS20 and other benchmarks while delivering 5-27x speedups.
LSD extends speculative sampling to second-order Langevin dynamics, achieving 3-9x speedup in MD while exactly sampling from the target distribution without relative error.
Non-autoregressive ionic transport predictor learns dynamics from auxiliary trajectory data during training only, achieving over 200x speedup versus autoregressive models and lower error than non-autoregressive baselines on both dataset types.
Structural pruning of SO(3) equivariant atomistic models from large checkpoints yields 1.5-4x fewer parameters and 2.5-4x less pre-training compute than small models trained from scratch, while outperforming them on most Matbench Discovery metrics and downstream tasks.
Density diversity in training data is the key factor for making machine learning interatomic potentials transferable across thermodynamic states, outperforming temperature diversity.
Bayesian E(3)-equivariant MLPs with joint energy-force NLL loss achieve competitive accuracy while enabling uncertainty-guided active learning, OOD detection, and calibration.
Systematic tests show naive fine-tuning excels for single-task accuracy while multihead replay best preserves out-of-distribution robustness in MLIP adaptation.
citing papers explorer
-
Precipitate phase selection and grain boundary morphology in Cu-Ni-Si-Mn alloys: A machine-learning interatomic potential study
MLIP simulations show that Mn promotes incoherent interfaces with the G-phase leading to film-like GB precipitates, while Ni2Si forms irregular shapes due to coherent interfaces that develop repulsive regions.
-
GFFMERGE: Efficient Merging of Graph Neural Force Fields and Beyond
GFFMERGE formulates GNN force field merging as a convex embedding-alignment problem with an analytical solution, recovering near joint-training performance on MD17, MD22, LiPS20 and other benchmarks while delivering 5-27x speedups.
-
Speculative Sampling For Faster Molecular Dynamics
LSD extends speculative sampling to second-order Langevin dynamics, achieving 3-9x speedup in MD while exactly sampling from the target distribution without relative error.
-
Teaching Molecular Dynamics to a Non-Autoregressive Ionic Transport Predictor
Non-autoregressive ionic transport predictor learns dynamics from auxiliary trajectory data during training only, achieving over 200x speedup versus autoregressive models and lower error than non-autoregressive baselines on both dataset types.
-
Compact SO(3) Equivariant Atomistic Foundation Models via Structural Pruning
Structural pruning of SO(3) equivariant atomistic models from large checkpoints yields 1.5-4x fewer parameters and 2.5-4x less pre-training compute than small models trained from scratch, while outperforming them on most Matbench Discovery metrics and downstream tasks.
-
Density diversity in training data governs thermodynamic transferability of machine learning interatomic potentials
Density diversity in training data is the key factor for making machine learning interatomic potentials transferable across thermodynamic states, outperforming temperature diversity.
-
Bayesian E(3)-Equivariant Interatomic Potential with Iterative Restratification of Many-body Message Passing
Bayesian E(3)-equivariant MLPs with joint energy-force NLL loss achieve competitive accuracy while enabling uncertainty-guided active learning, OOD detection, and calibration.
-
Fine-tuning MLIP foundation models: strategies for accuracy and transferability
Systematic tests show naive fine-tuning excels for single-task accuracy while multihead replay best preserves out-of-distribution robustness in MLIP adaptation.