Proposes generative pseudo-force fields trained on quadratic pseudo-potentials from noisy equilibria as a time-step-agnostic diffusion variant for efficient molecular conformation generation with high validity on QM9.
Towards exact molecular dynamics simulations with machine-learned force fields.Nature Communications, 9:3887
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 4verdicts
UNVERDICTED 4roles
background 1polarities
background 1representative citing papers
OrbEvo uses equivariant graph transformers to learn the time evolution of TDDFT wavefunction coefficients, accurately reproducing wavefunctions, dipole moments, and absorption spectra on QM9 and MD17 molecular datasets.
DenSNet learns the Hohenberg-Kohn map to electron density with equivariant networks and delta-learning, then maps density to energy, producing stable MD trajectories whose infrared spectra match experiment and DFT on ethanol, ethanethiol, resorcinol, and polythiophene oligomers.
GNN-based MD simulators achieve stable structure-only initialization and reliable OOD generalization through inference-time physics optimization and a GNN barostat on elastic network compression tasks.
citing papers explorer
-
Generative Pseudo-Force Fields for Molecular Generation
Proposes generative pseudo-force fields trained on quadratic pseudo-potentials from noisy equilibria as a time-step-agnostic diffusion variant for efficient molecular conformation generation with high validity on QM9.
-
Orbital Transformers for Predicting Wavefunctions in Time-Dependent Density Functional Theory
OrbEvo uses equivariant graph transformers to learn the time evolution of TDDFT wavefunction coefficients, accurately reproducing wavefunctions, dipole moments, and absorption spectra on QM9 and MD17 molecular datasets.
-
Enhancing molecular dynamics with equivariant machine-learned densities
DenSNet learns the Hohenberg-Kohn map to electron density with equivariant networks and delta-learning, then maps density to energy, producing stable MD trajectories whose infrared spectra match experiment and DFT on ethanol, ethanethiol, resorcinol, and polythiophene oligomers.
-
Enabling Structure-Only Initialization and Out-of-Distribution Generalization in GNN-based Molecular Dynamics Simulators
GNN-based MD simulators achieve stable structure-only initialization and reliable OOD generalization through inference-time physics optimization and a GNN barostat on elastic network compression tasks.