LGA employs latent-space interpolation from universal interatomic potentials for crossover in crystal structure prediction, raising HfO2 ground-state recovery to 60-95% and identifying unreported periodic structures in perovskite superlattices.
hub
Crystal diffusion variational autoencoder for periodic material generation.arXiv preprint arXiv:2110.06197
22 Pith papers cite this work. Polarity classification is still indexing.
22
Pith papers citing it
hub tools
citation-role summary
background 1
method 1
citation-polarity summary
representative citing papers
A Gaussian process surrogate gate inserted between generative crystal models and property oracles matches or exceeds ungated fine-tuning while using roughly one-fifth the oracle calls for heat capacity and bulk modulus.
ALMs unify pretrained atomistic encoder, LLM, and denoising diffusion via continuous projectors and staged training to reach SOTA on text-conditioned crystal prediction and de novo generation.
An E(3)-equivariant deep RL framework lets an O2 agent discover kinetically plausible diffusion and dissociation pathways in disordered Si/a-SiO2 without hand-crafted reaction coordinates or collective variables.
CliqueFlowmer combines clique-based model-based optimization with transformer and flow models to generate materials that optimize target properties better than generative baselines.
Error-Conditioned Neural Solvers improve PDE prediction accuracy by using the residual field as network input for learned corrections, outperforming residual-minimization methods by up to 10x on turbulent flows and generalizing better under distribution shifts.
A GPT-style model pretrained on 133M catalyst structures generates valid structures conditioned on categorical and continuous properties, achieving 98% structural validity and up to 4-fold screening efficiency gains.
MatMind is a unified LLM-based generative model for crystals that reports lowest MAE on energy above hull, bulk modulus and band gap while achieving 65.3% S.U.N. rate on unconditional generation.
CrysLDNet combines VAE and latent diffusion pretraining on unlabeled crystals to improve graph encoder performance on property prediction by about 4-5% on JARVIS and MP datasets.
Discovery via symmetry-guided ML of Netsene (bct-C24), a dynamically stable carbon allotrope exhibiting nested nodal-surface semimetal behavior with Dirac-like crossings and drumhead surface states.
Crys-JEPA introduces a joint embedding predictive architecture that creates an energy-aware latent space, enabling embedding-based stability screening and a refinement pipeline that yields up to 72.7% gains on the V.S.U.N. metric for crystal generation.
CrystalReasoner combines LLM reasoning traces with physical priors and multi-objective RL to generate valid, stable, and property-conditioned crystal structures.
Fine-tuning CHGNet on OMDB data and performing site substitution on QMOF prototypes yields novel highly magnetic MOFs.
LEGO-MOF maps MOF linkers to an equivariant latent space for continuous editing and uses test-time optimization to achieve a 147.5% average boost in pure CO2 uptake while preserving structural validity.
MCFlow uses decoupled flow time axes for atom types and crystal structures so a single model handles crystal structure prediction, de novo generation, and atom-type generation.
MatterSim delivers a single deep learning force field that simulates inorganic materials across elements, 0-5000 K, and up to 1000 GPa with near first-principles accuracy for lattice dynamics, mechanics, and Gibbs free energies.
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.
VQ-VAE concept learning enables controllable recombination of crystal motifs to generate structures with reported gains in validity-stability-uniqueness-novelty metrics on MP-20 and Alex-MP-20.
Reinforcement fine-tuning of a generative model produces new topological insulators and crystalline insulators, exemplified by Ge2Bi2O6 with a 0.26 eV full band gap.
A fine-tuned LLM called Perovskite-R1, built from curated perovskite literature and material libraries, proposes precursor additives and designs with some experimental validation showing improved stability and performance.
A survey of generative crystal modeling, multimodal learning, and closed-loop inverse design pipelines for crystalline solids, including failure modes and evaluation practices.
Review summarizing theoretical and computational progress on 2D melting in passive systems and novel non-equilibrium phenomena in active matter that deviate from the HMW theorem.
citing papers explorer
-
Latent Genetic Algorithm for Crystal Structure Prediction
LGA employs latent-space interpolation from universal interatomic potentials for crossover in crystal structure prediction, raising HfO2 ground-state recovery to 60-95% and identifying unreported periodic structures in perovskite superlattices.
-
Surrogate-Gated Generation and Foundation-Model Embeddings for Bayesian Materials Design
A Gaussian process surrogate gate inserted between generative crystal models and property oracles matches or exceeds ungated fine-tuning while using roughly one-fifth the oracle calls for heat capacity and bulk modulus.
-
Atomistic Language Models Understand and Generate Materials
ALMs unify pretrained atomistic encoder, LLM, and denoising diffusion via continuous projectors and staged training to reach SOTA on text-conditioned crystal prediction and de novo generation.
-
Bridging Atomistic Simulation and Experimental Processing Timescales with Goal-Directed Deep Reinforcement Learning
An E(3)-equivariant deep RL framework lets an O2 agent discover kinetically plausible diffusion and dissociation pathways in disordered Si/a-SiO2 without hand-crafted reaction coordinates or collective variables.
-
Offline Materials Optimization with CliqueFlowmer
CliqueFlowmer combines clique-based model-based optimization with transformer and flow models to generate materials that optimize target properties better than generative baselines.
-
Error-Conditioned Neural Solvers
Error-Conditioned Neural Solvers improve PDE prediction accuracy by using the residual field as network input for learned corrections, outperforming residual-minimization methods by up to 10x on turbulent flows and generalizing better under distribution shifts.
-
Toward Controllable Catalyst Inverse Design via Large-Scale Autoregressive Pretraining
A GPT-style model pretrained on 133M catalyst structures generates valid structures conditioned on categorical and continuous properties, achieving 98% structural validity and up to 4-fold screening efficiency gains.
-
MatMind: A Structure-Activity Knowledge-Driven Generative Foundation Model for Materials Science
MatMind is a unified LLM-based generative model for crystals that reports lowest MAE on energy above hull, bulk modulus and band gap while achieving 65.3% S.U.N. rate on unconditional generation.
-
Latent Diffusion Pretraining for Crystal Property Prediction
CrysLDNet combines VAE and latent diffusion pretraining on unlabeled crystals to improve graph encoder performance on property prediction by about 4-5% on JARVIS and MP datasets.
-
Theory-Guided, Machine-Learning-Accelerated Discovery of a 3D Carbon Nested Nodal-Surface Semimetal
Discovery via symmetry-guided ML of Netsene (bct-C24), a dynamically stable carbon allotrope exhibiting nested nodal-surface semimetal behavior with Dirac-like crossings and drumhead surface states.
-
Crys-JEPA: Accelerating Crystal Discovery via Embedding Screening and Generative Refinement
Crys-JEPA introduces a joint embedding predictive architecture that creates an energy-aware latent space, enabling embedding-based stability screening and a refinement pipeline that yields up to 72.7% gains on the V.S.U.N. metric for crystal generation.
-
CrystalReasoner: Reasoning and RL for Property-Conditioned Crystal Structure Generation
CrystalReasoner combines LLM reasoning traces with physical priors and multi-objective RL to generate valid, stable, and property-conditioned crystal structures.
-
Generation of magnetic metal-organic frameworks
Fine-tuning CHGNet on OMDB data and performing site substitution on QMOF prototypes yields novel highly magnetic MOFs.
-
LEGO-MOF: Equivariant Latent Manipulation for Editable, Generative, and Optimizable MOF Design
LEGO-MOF maps MOF linkers to an equivariant latent space for continuous editing and uses test-time optimization to achieve a 147.5% average boost in pure CO2 uptake while preserving structural validity.
-
Multimodal Crystal Flow: Any-to-Any Modality Generation for Unified Crystal Modeling
MCFlow uses decoupled flow time axes for atom types and crystal structures so a single model handles crystal structure prediction, de novo generation, and atom-type generation.
-
MatterSim: A Deep Learning Atomistic Model Across Elements, Temperatures and Pressures
MatterSim delivers a single deep learning force field that simulates inorganic materials across elements, 0-5000 K, and up to 1000 GPa with near first-principles accuracy for lattice dynamics, mechanics, and Gibbs free energies.
-
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.
-
Composable Crystals: Controllable Materials Discovery via Concept Learning
VQ-VAE concept learning enables controllable recombination of crystal motifs to generate structures with reported gains in validity-stability-uniqueness-novelty metrics on MP-20 and Alex-MP-20.
-
Design Topological Materials by Reinforcement Fine-Tuned Generative Model
Reinforcement fine-tuning of a generative model produces new topological insulators and crystalline insulators, exemplified by Ge2Bi2O6 with a 0.26 eV full band gap.
-
Perovskite-R1: a domain-specialized large language model for intelligent discovery of precursor additives and experimental design
A fine-tuned LLM called Perovskite-R1, built from curated perovskite literature and material libraries, proposes precursor additives and designs with some experimental validation showing improved stability and performance.
-
Towards Automated Discovery: A Review of Generative Models, Multimodal Learning and Closed-Loop Workflows in Inverse Materials Design
A survey of generative crystal modeling, multimodal learning, and closed-loop inverse design pipelines for crystalline solids, including failure modes and evaluation practices.
-
Two-Dimensional Phase Transitions in Classical Systems: 60 Years after the Hohenberg-Mermin-Wagner Theorem
Review summarizing theoretical and computational progress on 2D melting in passive systems and novel non-equilibrium phenomena in active matter that deviate from the HMW theorem.