SLayerGen generates crystals invariant to any space or layer group via autoregressive lattice and Wyckoff sampling plus equivariant diffusion, achieving gains over bulk models on diperiodic materials after correcting a prior loss inconsistency for hexagonal groups.
Baseline reference
Title resolution pending
Baseline reference. 50% of citing Pith papers use this work as a benchmark or comparison.
31
Pith papers citing it
11.6k
external citations · Crossref
Baseline
50% of classified citations
citation-role summary
dataset 7
background 3
citation-polarity summary
authors
co-cited works
representative citing papers
MP2SS reduces finite-size errors in periodic MP2 to millihartree accuracy at coarser k-point meshes for gapped systems via auxiliary function subtraction.
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.
LitXBench is a new benchmark for extracting complete experiments from scientific papers, with results showing frontier LLMs outperform multi-turn pipelines by up to 0.37 F1 due to better handling of processing steps.
AQVolt26 is a new high-temperature halide dataset that improves universal ML interatomic potentials for distorted configurations while showing that near-equilibrium relaxation data is not universally helpful.
Electrospinning-Data.org is a FAIR data platform that organizes electrospinning experiments into a structured, failure-inclusive corpus to enable predictive modeling and inverse design of nanofiber morphologies.
A new rapid synthesis method allows efficient production of isotope-enriched MoO3 crystals with control over both Mo and O isotopic content for phonon engineering.
Micromagnetic simulations of magnetoelastic coupling in exchange-decoupled Co/Ni islets predict a 52 dB/mm change in SAW transmission at 3.8 GHz depending on the magnetic state of neighboring islets.
IRNet uses per-layer residual shortcuts in fully connected networks to achieve better prediction accuracy and training convergence than prior ML methods on OQMD and Materials Project datasets for material properties.
RADAR-PD introduces a modality-aware ML system that generates phase hypotheses from elemental constraints and performs recursive multiphase analysis with physics-constrained verification on experimental diffraction data.
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 facet-resolved adsorption energy distribution method with ML force fields identifies active and methanol-selective alloy nanocatalyst surfaces for CO2 hydrogenation.
aim2dat is a new Python toolkit providing interfaces for database queries, high-throughput DFT workflows, and machine learning integration to handle large material datasets.
Multi-fidelity bandits screen 529 ZnO co-dopants with 81% fewer DFT calls, identify Y2Cu2 co-doped ZnO (1.84 eV) as optimal for visible-light band gaps, and release all 583 calculations plus code.
Physics-informed graph attention networks predict multi-phase equilibria in Ag-Bi-Cu-Sn alloys with 96% exact-set accuracy on in-domain data and strong generalization to unseen sections.
An ontology-aligned framework for atomistic simulations that integrates over 750,000 triples to enable interoperable data querying and automated provenance tracking.
deCIFer trains an autoregressive LM on 2.3 million structures with synthetic PXRD noise to generate CIF files, reporting 94% structural match rate on synthetic inorganic test sets.
Ab initio DFT calculations find zinc vacancies and interstitials dominate defects in Zn3P2, producing p-type behavior via shallow acceptors, with Frenkel pair formation partially compensating conductivity and thermodynamically limiting n-type doping.
PRISMat generates crystal slabs with mean absolute errors of 0.188 eV/A² for cleavage energy and 2.79 eV for work function, reducing error by 4× versus the next best model while using less inference time.
Electrostatic screening of stoichiometric slabs and surface dipoles predicts stable facets and morphologies in ionic crystals faster than DFT, with predictions matching experiments on tested materials.
Binding sfTA produces bilayer binding correlation energies closer to twist-averaged CCSD than standard sfTA by incorporating binding interactions into twist-angle selection.
SA-ADAPT reaches near-CASSCF accuracy for a multiconfigurational surface chemistry benchmark using far fewer operators than SA-fUCCSD, with a modified selection scheme speeding convergence.
DFT calculations show guest atom ionization potential controls stability and rattler motion in A8T27Pn19 clathrates, spin-orbit coupling matters for heavy elements, and synthesis yields new compounds but misses the target phases.
Quantum-chemical bonding descriptors improve machine learning predictions of materials properties and enable symbolic regression to recover intuitive expressions for force constants and thermal conductivity.
citing papers explorer
-
SLayerGen: a Crystal Generative Model for all Space and Layer Groups
SLayerGen generates crystals invariant to any space or layer group via autoregressive lattice and Wyckoff sampling plus equivariant diffusion, achieving gains over bulk models on diperiodic materials after correcting a prior loss inconsistency for hexagonal groups.
-
Reduction of finite-size effects for second-order M{\o}ller-Plesset perturbation theory with singularity subtraction
MP2SS reduces finite-size errors in periodic MP2 to millihartree accuracy at coarser k-point meshes for gapped systems via auxiliary function subtraction.
-
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.
-
LitXBench: A Benchmark for Extracting Experiments from Scientific Literature
LitXBench is a new benchmark for extracting complete experiments from scientific papers, with results showing frontier LLMs outperform multi-turn pipelines by up to 0.37 F1 due to better handling of processing steps.
-
AQVolt26: High-Temperature r$^2$SCAN Halide Dataset for Universal ML Potentials and Solid-State Batteries
AQVolt26 is a new high-temperature halide dataset that improves universal ML interatomic potentials for distorted configurations while showing that near-equilibrium relaxation data is not universally helpful.
-
Electrospinning-Data.org: A FAIR, Structured Knowledge Resource for Nanofiber Fabrication
Electrospinning-Data.org is a FAIR data platform that organizes electrospinning experiments into a structured, failure-inclusive corpus to enable predictive modeling and inverse design of nanofiber morphologies.
-
Rapid synthesis of dual-element isotope-enriched alpha-MoO3 crystals by reactive vapor transport
A new rapid synthesis method allows efficient production of isotope-enriched MoO3 crystals with control over both Mo and O isotopic content for phonon engineering.
-
Magnetically Programmable Surface Acoustic Wave Filters: Device Concept and Predictive Modeling
Micromagnetic simulations of magnetoelastic coupling in exchange-decoupled Co/Ni islets predict a 52 dB/mm change in SAW transmission at 3.8 GHz depending on the magnetic state of neighboring islets.
-
IRNet: A General Purpose Deep Residual Regression Framework for Materials Discovery
IRNet uses per-layer residual shortcuts in fully connected networks to achieve better prediction accuracy and training convergence than prior ML methods on OQMD and Materials Project datasets for material properties.
-
Automated multiphase identification and refinement in powder diffraction using mismatch-tolerant machine learning
RADAR-PD introduces a modality-aware ML system that generates phase hypotheses from elemental constraints and performs recursive multiphase analysis with physics-constrained verification on experimental diffraction data.
-
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.
-
Selectivity- and Activity-Aware Catalyst Descriptors for CO$_2$ Hydrogenation on Alloy Nanocatalysts using Machine-Learned Force Fields
A facet-resolved adsorption energy distribution method with ML force fields identifies active and methanol-selective alloy nanocatalyst surfaces for CO2 hydrogenation.
-
aim2dat: A Python infrastructure for automated ab initio material modeling and data analysis
aim2dat is a new Python toolkit providing interfaces for database queries, high-throughput DFT workflows, and machine learning integration to handle large material datasets.
-
Accelerated Dopant Screening in Oxide Semiconductors via Multi-Fidelity Contextual Bandits and a Three-Tier DFT Validation Funnel
Multi-fidelity bandits screen 529 ZnO co-dopants with 81% fewer DFT calls, identify Y2Cu2 co-doped ZnO (1.84 eV) as optimal for visible-light band gaps, and release all 583 calculations plus code.
-
Multi-Label Phase Diagram Prediction in Complex Alloys via Physics-Informed Graph Attention Networks
Physics-informed graph attention networks predict multi-phase equilibria in Ag-Bi-Cu-Sn alloys with 96% exact-set accuracy on in-domain data and strong generalization to unseen sections.
-
Ontology-based knowledge graph infrastructure for interoperable atomistic simulation data
An ontology-aligned framework for atomistic simulations that integrates over 750,000 triples to enable interoperable data querying and automated provenance tracking.
-
deCIFer: Crystal Structure Prediction from Powder Diffraction Data using Autoregressive Language Models
deCIFer trains an autoregressive LM on 2.3 million structures with synthetic PXRD noise to generate CIF files, reporting 94% structural match rate on synthetic inorganic test sets.
-
Intrinsic Point Defects and Frenkel Pair Formation in Photovoltaic Absorber Zn$_3$P$_2$: Regulating $p$-type Conductivity through Growth and Annealing Conditions
Ab initio DFT calculations find zinc vacancies and interstitials dominate defects in Zn3P2, producing p-type behavior via shallow acceptors, with Frenkel pair formation partially compensating conductivity and thermodynamically limiting n-type doping.
-
PRISMat: Policy-Driven, Permutation-Invariant Autoregressive Material Generation
PRISMat generates crystal slabs with mean absolute errors of 0.188 eV/A² for cleavage energy and 2.79 eV for work function, reducing error by 4× versus the next best model while using less inference time.
-
Accelerated Prediction of Surface Stability and Particle Morphology in Ionic Crystals via Electrostatic Screening
Electrostatic screening of stoichiometric slabs and surface dipoles predicts stable facets and morphologies in ionic crystals faster than DFT, with predictions matching experiments on tested materials.
-
A Single Twist-Angle Selection Method for the Electronic Structure of Bilayer Materials
Binding sfTA produces bilayer binding correlation energies closer to twist-averaged CCSD than standard sfTA by incorporating binding interactions into twist-angle selection.
-
State-Averaged Quantum Algorithms for Multiconfigurational Surface Chemistry: A Benchmark on Rh@TiO2(110)
SA-ADAPT reaches near-CASSCF accuracy for a multiconfigurational surface chemistry benchmark using far fewer operators than SA-fUCCSD, with a modified selection scheme speeding convergence.
-
Stability and superstructural ordering of alkali-triel-pnictide clathrates A$_8$T$_{27}$Pn$_{19}$
DFT calculations show guest atom ionization potential controls stability and rattler motion in A8T27Pn19 clathrates, spin-orbit coupling matters for heavy elements, and synthesis yields new compounds but misses the target phases.
-
A critical assessment of bonding descriptors for predicting materials properties
Quantum-chemical bonding descriptors improve machine learning predictions of materials properties and enable symbolic regression to recover intuitive expressions for force constants and thermal conductivity.
-
Rational Design Principles for Na- and Li-ion Carbon Anodes from Interlayer Spacing Control
DFT and cluster-expansion calculations identify 4.21 Å as the threshold above which Na intercalates readily in graphite-like carbon while Li capacity peaks narrowly near 3.75 Å with AA stacking preferred for both ions.
-
Virp: neural network-accelerated prediction of physical properties in site-disordered materials
A pipeline samples site-disordered material configurations with 400 virtual cells when the supercell is large enough, improving computational feasibility over quasirandom or cluster expansion methods.
-
AIMBio-Mat: An AI-Native FAIR Platform for Closed-Loop Materials Discovery and Biomedical Translation
AIMBio-Mat is a conceptual blueprint for an AI-native, FAIR, governance-aware decision layer that formulates biomedical-materials discovery as constrained multi-objective optimization under uncertainty.
-
KadiAssistant: A conversational AI Agent for information retrieval in Kadi4Mat
KadiAssistant is a privacy-by-design conversational AI that pairs a self-hosted LLM with semantic search to retrieve and structure information from the Kadi4Mat research data platform while respecting fine-grained permissions.
-
General expression for the energy and the equation of state for polycrystalline solids
Semi-empirical analytical expressions for energy and EOS of polycrystalline solids are proposed and shown to match DFT results for many compounds up to 300 GPa at accuracy comparable to Birch-Murnaghan.
-
Building a Regional Data-Centric Materials Science Ecosystem for Processing-Rich Materials Innovation in the Great Plains
Proposes a regional data-centric materials science ecosystem for the Great Plains, identifying five barriers to data sharing and outlining a staged roadmap illustrated by a high-purity germanium pilot.
- Learning Thermoelectric Transport from Crystal Structures via Multiscale Graph Neural Network