FMO-xTB implements FMO2 and FMO3 expansions with GFN1-xTB including analytic gradients, achieving near-linear scaling and high accuracy on benchmarks like water clusters, organic aggregates, polyalanine, and B-DNA.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
physics.chem-ph 2years
2026 2representative citing papers
Multitask learning on linear-scaling GFN1-xTB orbital charges cuts energy MAE by 46% and data needs by 5x versus energy-only MLIPs while outperforming DFT atomic charge augmentation.
citing papers explorer
-
FMO-xTB: Fragment molecular orbital method with GFN1-xTB for large-scale quantum-mechanical simulations
FMO-xTB implements FMO2 and FMO3 expansions with GFN1-xTB including analytic gradients, achieving near-linear scaling and high accuracy on benchmarks like water clusters, organic aggregates, polyalanine, and B-DNA.
-
Multitask learning with semiempirical orbital charges enables sample-efficient MLIPs
Multitask learning on linear-scaling GFN1-xTB orbital charges cuts energy MAE by 46% and data needs by 5x versus energy-only MLIPs while outperforming DFT atomic charge augmentation.