DGLD applies domain-gated latent diffusion with label-quality gating and multi-task guidance to discover 12 novel energetic material leads validated by DFT, outperforming SMILES-LSTM, SELFIES-GA, and REINVENT baselines in novelty and on-target performance.
A look at the density functional theory zoo with the advanced GMTKN55 database for general main group thermochemistry
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
citation-role summary
background 3
dataset 1
citation-polarity summary
representative citing papers
Constraint-aware neural networks clone known semilocal XC functionals more accurately in self-consistent calculations, transfer well from molecules to solids, and outperform unconstrained models across multiple tests.
Skala is a neural XC functional trained on wavefunction data that beats state-of-the-art hybrids on main-group chemistry benchmarks at semi-local computational cost.
ADC-G3W2 reformulates vertex corrections to the GW self-energy as nonperturbative resummations within the ADC framework to guarantee positive semi-definiteness of the self-energy.
A neural network LDA functional overfit to water data achieves 1 kcal/mol errors on ionization and atomization energies and matches PBE/B3LYP on WATER27 binding energies after transfer learning from one datum.
The paper establishes an exact N-centered ensemble DFT formalism unifying neutral and charged excitations and introduces three practical strategies: weight-dependent scaling of ground-state functionals, quasi-degenerate ensemble perturbation theory, and quantum bath embedding for excited states.
XRTS benchmark on warm dense Al demonstrates that uniform-electron-gas models overestimate plasmon resonance energy by up to 8 eV while ab initio calculations including disorder agree with experiment.
citing papers explorer
-
DGLD: Domain-Gated Latent Diffusion for the Discovery of Novel Energetic Materials
DGLD applies domain-gated latent diffusion with label-quality gating and multi-task guidance to discover 12 novel energetic material leads validated by DFT, outperforming SMILES-LSTM, SELFIES-GA, and REINVENT baselines in novelty and on-target performance.
-
Constraint-aware functional cloning for stable and transferable machine-learned density functional theory
Constraint-aware neural networks clone known semilocal XC functionals more accurately in self-consistent calculations, transfer well from molecules to solids, and outperform unconstrained models across multiple tests.
-
Accurate and scalable exchange-correlation with deep learning
Skala is a neural XC functional trained on wavefunction data that beats state-of-the-art hybrids on main-group chemistry benchmarks at semi-local computational cost.
-
An Algebraic-Diagrammatic Construction for Vertex Corrections to the $GW$ Self-Energy
ADC-G3W2 reformulates vertex corrections to the GW self-energy as nonperturbative resummations within the ADC framework to guarantee positive semi-definiteness of the self-energy.
-
Overfitting by design: neural network density functionals for water
A neural network LDA functional overfit to water data achieves 1 kcal/mol errors on ionization and atomization energies and matches PBE/B3LYP on WATER27 binding energies after transfer learning from one datum.
-
Ensemble density functional theory of excited states: Exact N-centered formalism and practical opportunities
The paper establishes an exact N-centered ensemble DFT formalism unifying neutral and charged excitations and introduces three practical strategies: weight-dependent scaling of ground-state functionals, quasi-degenerate ensemble perturbation theory, and quantum bath embedding for excited states.
-
A Momentum-Resolved X-ray Thomson Scattering Benchmark of Electronic-Response Models in Warm Dense Aluminium
XRTS benchmark on warm dense Al demonstrates that uniform-electron-gas models overestimate plasmon resonance energy by up to 8 eV while ab initio calculations including disorder agree with experiment.