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.
Title resolution pending
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
citation-role summary
background 2
method 1
citation-polarity summary
representative citing papers
A tailored quantum multi-programming workflow for the LUCJ ansatz enables parallel circuit execution with SQD/ext-SQD post-processing that mitigates cross-talk, yielding ethanol energies within 0.001 kcal/mol of classical HCI references.
Machine learning models, especially certain deep neural networks, can predict lattice thermal conductivity with useful accuracy across different generalization tests while being orders of magnitude faster than first-principles calculations.
A 1.62-trillion-atom molecular dynamics simulation achieves ab initio accuracy with 100x speedup over prior machine learning force fields and 86.9% weak scaling to 45,000 GPGPUs.
Reformulation of many-body dispersion via a correlation matrix yields pairwise force decomposition and unified energy-force-Hessian expressions.
Machine-learned force fields trained on coupled-cluster potential energy surfaces produce phonon dispersions and vibrational densities of states for solids that agree better with experiment than DFT-based models.
MACE-MPA-0 predicts Li diffusion Ea of 0.22 eV in LiF, fine-tuned version with 300 points gives 0.20 eV, close to DeePMD reference of 0.24 eV, using far less training data.
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.
-
A Quantum Multi-Programming Framework to Maximize Quantum Resources for the LUCJ Ansatz
A tailored quantum multi-programming workflow for the LUCJ ansatz enables parallel circuit execution with SQD/ext-SQD post-processing that mitigates cross-talk, yielding ethanol energies within 0.001 kcal/mol of classical HCI references.
-
Fast and Accurate Prediction of Lattice Thermal Conductivity via Machine Learning Surrogates
Machine learning models, especially certain deep neural networks, can predict lattice thermal conductivity with useful accuracy across different generalization tests while being orders of magnitude faster than first-principles calculations.
-
Trillion-atom molecular dynamics simulations with ab initio accuracy
A 1.62-trillion-atom molecular dynamics simulation achieves ab initio accuracy with 100x speedup over prior machine learning force fields and 86.9% weak scaling to 45,000 GPGPUs.
-
Structured force reformulation of many-body dispersion: towards effective atom--atom decomposition and surrogate modeling
Reformulation of many-body dispersion via a correlation matrix yields pairwise force decomposition and unified energy-force-Hessian expressions.
-
Machine-Learned Force Fields for Lattice Dynamics at Coupled-Cluster Level Accuracy
Machine-learned force fields trained on coupled-cluster potential energy surfaces produce phonon dispersions and vibrational densities of states for solids that agree better with experiment than DFT-based models.
-
Comparing fine-tuning strategies of MACE machine learning force field for modeling Li-ion diffusion in LiF for batteries
MACE-MPA-0 predicts Li diffusion Ea of 0.22 eV in LiF, fine-tuned version with 300 points gives 0.20 eV, close to DeePMD reference of 0.24 eV, using far less training data.