Matter Sciences

52 items

Mendeley Data Sep 16, 2026
This work assembles a corrosion inhibitor dataset from 5,597 publications using a multi-agent extraction pipeline, releasing a manually verified IE_datasets.xlsx, LLM-extracted json_extracted.zip, and IE_PH_4_materials.xlsx for model construction, with fields covering reference metadata, inhibitor name and composition, anodic/cathodic/mixed type, film mechanism, SMILES, corrosion material name, grade, composition, processing and heat treatment, corrosive medium, medium type, concentration and temperature, and test temperature, test time, inhibitor concentration, test method and inhibition efficiency percentage.
This work assembles a corrosion inhibitor dataset from 5,597 publications using a multi-agent extraction pipeline, releasing a manually verified IE_datasets.xlsx, LLM-extracted json_extracted.zip, and IE_PH_4_materials.xlsx for model construction, with fields covering reference metadata, inhibitor name and composition, anodic/cathodic/mixed type, film mechanism, SMILES, corrosion material name, grade, composition, processing and heat treatment, corrosive medium, medium type, concentration and temperature, and test temperature, test time, inhibitor concentration, test method and inhibition efficiency percentage.
A corrosion inhibitor dataset built from 5,597 publications
This work assembles a corrosion inhibitor dataset from 5,597 publications using a multi-agent extraction pipeline, releasing a manually verified IE_datasets.xlsx, LLM-extracted json_extracted.zip, and IE_PH_4_materials.xlsx for model construction, with fields covering reference metadata, inhibitor name and composition, anodic/cathodic/mixed type, film mechanism, SMILES, corrosion material name, grade, composition, processing and heat treatment, corrosive medium, medium type, concentration and temperature, and test temperature, test time, inhibitor concentration, test method and inhibition efficiency percentage.
This work assembles a corrosion inhibitor dataset from 5,597 publications using a multi-agent extraction pipeline, releasing a manually verified IE_datasets.xlsx, LLM-extracted json_extracted.zip, and IE_PH_4_materials.xlsx for model construction, with fields covering reference metadata, inhibitor name and composition, anodic/cathodic/mixed type, film mechanism, SMILES, corrosion material name, grade, composition, processing and heat treatment, corrosive medium, medium type, concentration and temperature, and test temperature, test time, inhibitor concentration, test method and inhibition efficiency percentage.
Nature nanotechnology Sep 15, 2026
This work demonstrates wafer-scale monolithic 3D integration on 200-mm silicon wafers with three tiers of atomic-layer-deposited indium oxide (InOx)-based devices (more than 100,000 fabricated), including ferroelectric, enhancement-mode and depletion-mode field-effect transistors, achieving threshold voltage standard deviations as low as 0.04 V, average electron mobilities up to 91.6 cm²V⁻¹s⁻¹ and fully functional cross-tier circuits, and develops a four-tier 3D computing-in-memory accelerator targeting large-language-model workloads using a custom InOx process design kit, delivering 1.4× to 2.9× speed-up and comparable energy-delay product improvements over 2D baselines.
This work demonstrates wafer-scale monolithic 3D integration on 200-mm silicon wafers with three tiers of atomic-layer-deposited indium oxide (InOx)-based devices (more than 100,000 fabricated), including ferroelectric, enhancement-mode and depletion-mode field-effect transistors, achieving threshold voltage standard deviations as low as 0.04 V, average electron mobilities up to 91.6 cm²V⁻¹s⁻¹ and fully functional cross-tier circuits, and develops a four-tier 3D computing-in-memory accelerator targeting large-language-model workloads using a custom InOx process design kit, delivering 1.4× to 2.9× speed-up and comparable energy-delay product improvements over 2D baselines.
Monolithic 3D integration of atomic-layer-deposited oxide semiconductors on 200-mm silicon wafers
This work demonstrates wafer-scale monolithic 3D integration on 200-mm silicon wafers with three tiers of atomic-layer-deposited indium oxide (InOx)-based devices (more than 100,000 fabricated), including ferroelectric, enhancement-mode and depletion-mode field-effect transistors, achieving threshold voltage standard deviations as low as 0.04 V, average electron mobilities up to 91.6 cm²V⁻¹s⁻¹ and fully functional cross-tier circuits, and develops a four-tier 3D computing-in-memory accelerator targeting large-language-model workloads using a custom InOx process design kit, delivering 1.4× to 2.9× speed-up and comparable energy-delay product improvements over 2D baselines.
This work demonstrates wafer-scale monolithic 3D integration on 200-mm silicon wafers with three tiers of atomic-layer-deposited indium oxide (InOx)-based devices (more than 100,000 fabricated), including ferroelectric, enhancement-mode and depletion-mode field-effect transistors, achieving threshold voltage standard deviations as low as 0.04 V, average electron mobilities up to 91.6 cm²V⁻¹s⁻¹ and fully functional cross-tier circuits, and develops a four-tier 3D computing-in-memory accelerator targeting large-language-model workloads using a custom InOx process design kit, delivering 1.4× to 2.9× speed-up and comparable energy-delay product improvements over 2D baselines.
Chemical Communications Sep 15, 2026
This review organizes lithium-sulfur battery catalyst research around the fundamental chemistry of sulfur conversion and its rate-limiting steps, links catalyst modulation strategies to descriptors, groups descriptors into electronic, thermodynamic, and structural categories with their property-performance relationships, and points toward universal descriptors as well as the potential roles of in situ characterization, computational modeling, and artificial intelligence in descriptor construction and the design of highly active catalysts.
This review organizes lithium-sulfur battery catalyst research around the fundamental chemistry of sulfur conversion and its rate-limiting steps, links catalyst modulation strategies to descriptors, groups descriptors into electronic, thermodynamic, and structural categories with their property-performance relationships, and points toward universal descriptors as well as the potential roles of in situ characterization, computational modeling, and artificial intelligence in descriptor construction and the design of highly active catalysts.
Rational design of advanced electrocatalysts based on reactivity descriptors for high-performance lithium-sulfur batteries
This review organizes lithium-sulfur battery catalyst research around the fundamental chemistry of sulfur conversion and its rate-limiting steps, links catalyst modulation strategies to descriptors, groups descriptors into electronic, thermodynamic, and structural categories with their property-performance relationships, and points toward universal descriptors as well as the potential roles of in situ characterization, computational modeling, and artificial intelligence in descriptor construction and the design of highly active catalysts.
This review organizes lithium-sulfur battery catalyst research around the fundamental chemistry of sulfur conversion and its rate-limiting steps, links catalyst modulation strategies to descriptors, groups descriptors into electronic, thermodynamic, and structural categories with their property-performance relationships, and points toward universal descriptors as well as the potential roles of in situ characterization, computational modeling, and artificial intelligence in descriptor construction and the design of highly active catalysts.
arXiv Sep 14, 2026
Using vacancies in the semiconductor Sb2Se3 as a case study, this work finds that current foundation machine learning interatomic potentials trained on bulk data do not reliably identify defect ground states, and introduces global defect charge embeddings in the MACE architecture together with a multi-fidelity training strategy combining low-cost PBE data with high-quality HSE06 data, achieving ground-state identification within 0.05 Å and defect formation energies and thermodynamic transition levels within 0.02 eV of hybrid-functional DFT at a fixed defect supercell size, while uncovering global minima missed by standard defect search workflows.
Using vacancies in the semiconductor Sb2Se3 as a case study, this work finds that current foundation machine learning interatomic potentials trained on bulk data do not reliably identify defect ground states, and introduces global defect charge embeddings in the MACE architecture together with a multi-fidelity training strategy combining low-cost PBE data with high-quality HSE06 data, achieving ground-state identification within 0.05 Å and defect formation energies and thermodynamic transition levels within 0.02 eV of hybrid-functional DFT at a fixed defect supercell size, while uncovering global minima missed by standard defect search workflows.
Multi-fidelity Machine Learning Interatomic Potentials for Charged Point Defects
Using vacancies in the semiconductor Sb2Se3 as a case study, this work finds that current foundation machine learning interatomic potentials trained on bulk data do not reliably identify defect ground states, and introduces global defect charge embeddings in the MACE architecture together with a multi-fidelity training strategy combining low-cost PBE data with high-quality HSE06 data, achieving ground-state identification within 0.05 Å and defect formation energies and thermodynamic transition levels within 0.02 eV of hybrid-functional DFT at a fixed defect supercell size, while uncovering global minima missed by standard defect search workflows.
Using vacancies in the semiconductor Sb2Se3 as a case study, this work finds that current foundation machine learning interatomic potentials trained on bulk data do not reliably identify defect ground states, and introduces global defect charge embeddings in the MACE architecture together with a multi-fidelity training strategy combining low-cost PBE data with high-quality HSE06 data, achieving ground-state identification within 0.05 Å and defect formation energies and thermodynamic transition levels within 0.02 eV of hybrid-functional DFT at a fixed defect supercell size, while uncovering global minima missed by standard defect search workflows.
Nature Communications Sep 14, 2026
The work introduces exponentially tilted thermodynamic maps (expTM), which add an exponential tilting factor to the Gaussian prior of thermodynamic maps so that the prior mean and variance correspond to pressure or chemical potential and to temperature, enabling thermodynamically correct sampling at arbitrary temperature, pressure, or chemical potential from only a few observations far from the phase boundary; the authors reproduce the lattice-gas phase transition in the grand canonical ensemble using two data points (density difference within 0.05 except near the critical chemical potential) and predict CO2 phase transitions under varying pressure in the isothermal-isobaric ensemble, identifying an intermediate state between Phase I and Phase III at roughly 4.5–5.4 GPa.
The work introduces exponentially tilted thermodynamic maps (expTM), which add an exponential tilting factor to the Gaussian prior of thermodynamic maps so that the prior mean and variance correspond to pressure or chemical potential and to temperature, enabling thermodynamically correct sampling at arbitrary temperature, pressure, or chemical potential from only a few observations far from the phase boundary; the authors reproduce the lattice-gas phase transition in the grand canonical ensemble using two data points (density difference within 0.05 except near the critical chemical potential) and predict CO2 phase transitions under varying pressure in the isothermal-isobaric ensemble, identifying an intermediate state between Phase I and Phase III at roughly 4.5–5.4 GPa.
Predicting phase transitions across temperature, pressure, and chemical potential using exponentially tilted thermodynamic maps
The work introduces exponentially tilted thermodynamic maps (expTM), which add an exponential tilting factor to the Gaussian prior of thermodynamic maps so that the prior mean and variance correspond to pressure or chemical potential and to temperature, enabling thermodynamically correct sampling at arbitrary temperature, pressure, or chemical potential from only a few observations far from the phase boundary; the authors reproduce the lattice-gas phase transition in the grand canonical ensemble using two data points (density difference within 0.05 except near the critical chemical potential) and predict CO2 phase transitions under varying pressure in the isothermal-isobaric ensemble, identifying an intermediate state between Phase I and Phase III at roughly 4.5–5.4 GPa.
The work introduces exponentially tilted thermodynamic maps (expTM), which add an exponential tilting factor to the Gaussian prior of thermodynamic maps so that the prior mean and variance correspond to pressure or chemical potential and to temperature, enabling thermodynamically correct sampling at arbitrary temperature, pressure, or chemical potential from only a few observations far from the phase boundary; the authors reproduce the lattice-gas phase transition in the grand canonical ensemble using two data points (density difference within 0.05 except near the critical chemical potential) and predict CO2 phase transitions under varying pressure in the isothermal-isobaric ensemble, identifying an intermediate state between Phase I and Phase III at roughly 4.5–5.4 GPa.
npj Computational Materials Sep 14, 2026
This work introduces a modular, large language model (LLM)-powered agent pipeline that automatically extracts and structures composition–process–property attributes of concrete materials from tables and text in scientific publications, achieving F1 scores up to 0.98 across 17 open and proprietary models and, within about one hour, extracting over 10,000 records from 278 papers screened from more than 27,000 publications; after postprocessing this yields the largest open laboratory database for blended cement concrete with nearly 9,000 high-quality records and over 100 attributes, and machine learning analyses indicate that large, diverse, information-rich datasets improve both in-distribution accuracy and out-of-distribution generalization to unseen materials systems.
This work introduces a modular, large language model (LLM)-powered agent pipeline that automatically extracts and structures composition–process–property attributes of concrete materials from tables and text in scientific publications, achieving F1 scores up to 0.98 across 17 open and proprietary models and, within about one hour, extracting over 10,000 records from 278 papers screened from more than 27,000 publications; after postprocessing this yields the largest open laboratory database for blended cement concrete with nearly 9,000 high-quality records and over 100 attributes, and machine learning analyses indicate that large, diverse, information-rich datasets improve both in-distribution accuracy and out-of-distribution generalization to unseen materials systems.
Large language model-enabled automated data extraction for concrete materials informatics
This work introduces a modular, large language model (LLM)-powered agent pipeline that automatically extracts and structures composition–process–property attributes of concrete materials from tables and text in scientific publications, achieving F1 scores up to 0.98 across 17 open and proprietary models and, within about one hour, extracting over 10,000 records from 278 papers screened from more than 27,000 publications; after postprocessing this yields the largest open laboratory database for blended cement concrete with nearly 9,000 high-quality records and over 100 attributes, and machine learning analyses indicate that large, diverse, information-rich datasets improve both in-distribution accuracy and out-of-distribution generalization to unseen materials systems.
This work introduces a modular, large language model (LLM)-powered agent pipeline that automatically extracts and structures composition–process–property attributes of concrete materials from tables and text in scientific publications, achieving F1 scores up to 0.98 across 17 open and proprietary models and, within about one hour, extracting over 10,000 records from 278 papers screened from more than 27,000 publications; after postprocessing this yields the largest open laboratory database for blended cement concrete with nearly 9,000 high-quality records and over 100 attributes, and machine learning analyses indicate that large, diverse, information-rich datasets improve both in-distribution accuracy and out-of-distribution generalization to unseen materials systems.
RSC Advances Sep 14, 2026
This review surveys how machine learning and artificial intelligence, combined with high-throughput first-principles calculations and experimental databases, are used to predict key spintronic magnetic properties (such as Curie temperature, magnetocrystalline anisotropy energy, magnetic moment, spin Hall conductivity, Dzyaloshinskii–Moriya interaction, coercivity, and tunneling magnetoresistance), discusses descriptor engineering, graph neural networks, and physics-informed learning, reviews AI-assisted screening and inverse design across Heusler alloys, topological spin systems, and two-dimensional magnets, and outlines a future roadmap toward physics-guided, uncertainty-aware, and autonomous closed-loop optimization.
This review surveys how machine learning and artificial intelligence, combined with high-throughput first-principles calculations and experimental databases, are used to predict key spintronic magnetic properties (such as Curie temperature, magnetocrystalline anisotropy energy, magnetic moment, spin Hall conductivity, Dzyaloshinskii–Moriya interaction, coercivity, and tunneling magnetoresistance), discusses descriptor engineering, graph neural networks, and physics-informed learning, reviews AI-assisted screening and inverse design across Heusler alloys, topological spin systems, and two-dimensional magnets, and outlines a future roadmap toward physics-guided, uncertainty-aware, and autonomous closed-loop optimization.
Artificial Intelligence-Driven Magnetic Property Prediction and Materials Discovery for Next-Generation Spintronics
This review surveys how machine learning and artificial intelligence, combined with high-throughput first-principles calculations and experimental databases, are used to predict key spintronic magnetic properties (such as Curie temperature, magnetocrystalline anisotropy energy, magnetic moment, spin Hall conductivity, Dzyaloshinskii–Moriya interaction, coercivity, and tunneling magnetoresistance), discusses descriptor engineering, graph neural networks, and physics-informed learning, reviews AI-assisted screening and inverse design across Heusler alloys, topological spin systems, and two-dimensional magnets, and outlines a future roadmap toward physics-guided, uncertainty-aware, and autonomous closed-loop optimization.
This review surveys how machine learning and artificial intelligence, combined with high-throughput first-principles calculations and experimental databases, are used to predict key spintronic magnetic properties (such as Curie temperature, magnetocrystalline anisotropy energy, magnetic moment, spin Hall conductivity, Dzyaloshinskii–Moriya interaction, coercivity, and tunneling magnetoresistance), discusses descriptor engineering, graph neural networks, and physics-informed learning, reviews AI-assisted screening and inverse design across Heusler alloys, topological spin systems, and two-dimensional magnets, and outlines a future roadmap toward physics-guided, uncertainty-aware, and autonomous closed-loop optimization.
Journal of Chemical Information and Modeling Sep 14, 2026
This Perspective argues that chemistry and language have followed a comparable representational trajectory—from tacit practitioner knowledge to systematic symbols and then to geometric, navigable spaces—and builds on this to propose a conceptual framework in which molecular properties are interpreted as forms of chemical meaning emerging from molecular structure, treating semantic interpolation in latent spaces and alchemical transformations in molecular simulation as related strategies for navigating continuous manifolds that connect discrete chemical states, while proposing a Chemical Imitation Game as a possible framework for evaluating molecular AI beyond syntactic validity toward chemically meaningful reasoning.
This Perspective argues that chemistry and language have followed a comparable representational trajectory—from tacit practitioner knowledge to systematic symbols and then to geometric, navigable spaces—and builds on this to propose a conceptual framework in which molecular properties are interpreted as forms of chemical meaning emerging from molecular structure, treating semantic interpolation in latent spaces and alchemical transformations in molecular simulation as related strategies for navigating continuous manifolds that connect discrete chemical states, while proposing a Chemical Imitation Game as a possible framework for evaluating molecular AI beyond syntactic validity toward chemically meaningful reasoning.
The Chemical Imitation Game: Navigating Spaces of Meaning in Language and Chemistry
This Perspective argues that chemistry and language have followed a comparable representational trajectory—from tacit practitioner knowledge to systematic symbols and then to geometric, navigable spaces—and builds on this to propose a conceptual framework in which molecular properties are interpreted as forms of chemical meaning emerging from molecular structure, treating semantic interpolation in latent spaces and alchemical transformations in molecular simulation as related strategies for navigating continuous manifolds that connect discrete chemical states, while proposing a Chemical Imitation Game as a possible framework for evaluating molecular AI beyond syntactic validity toward chemically meaningful reasoning.
This Perspective argues that chemistry and language have followed a comparable representational trajectory—from tacit practitioner knowledge to systematic symbols and then to geometric, navigable spaces—and builds on this to propose a conceptual framework in which molecular properties are interpreted as forms of chemical meaning emerging from molecular structure, treating semantic interpolation in latent spaces and alchemical transformations in molecular simulation as related strategies for navigating continuous manifolds that connect discrete chemical states, while proposing a Chemical Imitation Game as a possible framework for evaluating molecular AI beyond syntactic validity toward chemically meaningful reasoning.
Computational Materials Science Sep 14, 2026
This work introduces PolyGraphPy, an open-source unified Python framework that automates Density Functional Tight Binding (DFTB+) quantum-mechanics calculations to build structured datasets for monomers, homopolymers, and alternating copolymers, employs Bayesian Graph Neural Networks with stochastic graph representations for property prediction such as static polarizability together with uncertainty quantification, and incorporates two complementary generative models, a SELFIES-based Generative Pre-trained Transformer and a BRICS graph-fragmentation Genetic Algorithm, for de novo design of targeted molecules, demonstrated on a dataset of acrylates as a highly customizable end-to-end pipeline.
This work introduces PolyGraphPy, an open-source unified Python framework that automates Density Functional Tight Binding (DFTB+) quantum-mechanics calculations to build structured datasets for monomers, homopolymers, and alternating copolymers, employs Bayesian Graph Neural Networks with stochastic graph representations for property prediction such as static polarizability together with uncertainty quantification, and incorporates two complementary generative models, a SELFIES-based Generative Pre-trained Transformer and a BRICS graph-fragmentation Genetic Algorithm, for de novo design of targeted molecules, demonstrated on a dataset of acrylates as a highly customizable end-to-end pipeline.
PolyGraphPy: A unified Python framework for atomistic simulation and machine learning-driven polymer design
This work introduces PolyGraphPy, an open-source unified Python framework that automates Density Functional Tight Binding (DFTB+) quantum-mechanics calculations to build structured datasets for monomers, homopolymers, and alternating copolymers, employs Bayesian Graph Neural Networks with stochastic graph representations for property prediction such as static polarizability together with uncertainty quantification, and incorporates two complementary generative models, a SELFIES-based Generative Pre-trained Transformer and a BRICS graph-fragmentation Genetic Algorithm, for de novo design of targeted molecules, demonstrated on a dataset of acrylates as a highly customizable end-to-end pipeline.
This work introduces PolyGraphPy, an open-source unified Python framework that automates Density Functional Tight Binding (DFTB+) quantum-mechanics calculations to build structured datasets for monomers, homopolymers, and alternating copolymers, employs Bayesian Graph Neural Networks with stochastic graph representations for property prediction such as static polarizability together with uncertainty quantification, and incorporates two complementary generative models, a SELFIES-based Generative Pre-trained Transformer and a BRICS graph-fragmentation Genetic Algorithm, for de novo design of targeted molecules, demonstrated on a dataset of acrylates as a highly customizable end-to-end pipeline.
Journal of Chemical Information and Modeling Sep 14, 2026
This paper presents a method for autogenerating domain-specific question-answering data, builds MagQA with 168,080 magnetic-materials QA pairs, and uses it to finetune BERT-style models; on a manually annotated magnetic-materials test set, a vanilla BERT-base-cased finetuned on MagQA mixed with SQuAD v2 (MagBERT_MagQA_Mixed) achieves the best result with an F1 of 78.43% and an exact-match score of 72.84%, indicating that, given sufficiently large and high-quality domain-specific QA data, domain-specific BERT models need only be finetuned from vanilla BERT without domain-adaptive pretraining.
This paper presents a method for autogenerating domain-specific question-answering data, builds MagQA with 168,080 magnetic-materials QA pairs, and uses it to finetune BERT-style models; on a manually annotated magnetic-materials test set, a vanilla BERT-base-cased finetuned on MagQA mixed with SQuAD v2 (MagBERT_MagQA_Mixed) achieves the best result with an F1 of 78.43% and an exact-match score of 72.84%, indicating that, given sufficiently large and high-quality domain-specific QA data, domain-specific BERT models need only be finetuned from vanilla BERT without domain-adaptive pretraining.
Autogenerating a Domain-Specific Question-Answering Data Set to Enable High-Performing Language Models for Magnetic Materials
This paper presents a method for autogenerating domain-specific question-answering data, builds MagQA with 168,080 magnetic-materials QA pairs, and uses it to finetune BERT-style models; on a manually annotated magnetic-materials test set, a vanilla BERT-base-cased finetuned on MagQA mixed with SQuAD v2 (MagBERT_MagQA_Mixed) achieves the best result with an F1 of 78.43% and an exact-match score of 72.84%, indicating that, given sufficiently large and high-quality domain-specific QA data, domain-specific BERT models need only be finetuned from vanilla BERT without domain-adaptive pretraining.
This paper presents a method for autogenerating domain-specific question-answering data, builds MagQA with 168,080 magnetic-materials QA pairs, and uses it to finetune BERT-style models; on a manually annotated magnetic-materials test set, a vanilla BERT-base-cased finetuned on MagQA mixed with SQuAD v2 (MagBERT_MagQA_Mixed) achieves the best result with an F1 of 78.43% and an exact-match score of 72.84%, indicating that, given sufficiently large and high-quality domain-specific QA data, domain-specific BERT models need only be finetuned from vanilla BERT without domain-adaptive pretraining.

Page 5 · showing 10