CliqueFlowmer combines clique-based model-based optimization with transformer and flow models to generate materials that optimize target properties better than generative baselines.
Space group constrained crystal generation.arXiv preprint arXiv:2402.03992, 2024
11 Pith papers cite this work, alongside 14 external citations. Polarity classification is still indexing.
11
Pith papers citing it
14
external citations · external index
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
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.
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.
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.
Conditional generative models double the rate of stable novel MAX phase structures by steering generation with MXene derivative counts and A-site binding energy surrogates, yielding five DFT-stable candidates out of ten tested.
SWORD is a symmetry-aware Wyckoff-sequence string that standardizes ordered and disordered crystals for grouping, deduplication, and novelty checks.
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.
HACO adapts MaskGIT from vision into MaskGXT with symmetry tokens and stratified sampling, reaching 79.06% METRe accuracy on MP-20 polymorph split versus 70.87% for the best baseline.
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.
citing papers explorer
-
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.
-
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.
-
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.
-
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.
-
Conditional Generative Models Enable Targeted Exploration of MAX Phase Design Space
Conditional generative models double the rate of stable novel MAX phase structures by steering generation with MXene derivative counts and A-site binding energy surrogates, yielding five DFT-stable candidates out of ten tested.
-
SWORD: Symmetry and Wyckoff-sequence of Ordered and Disordered crystals
SWORD is a symmetry-aware Wyckoff-sequence string that standardizes ordered and disordered crystals for grouping, deduplication, and novelty checks.
-
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.
-
Discovering Crystal Structure Prediction Algorithms with an AI Co-Scientist
HACO adapts MaskGIT from vision into MaskGXT with symmetry tokens and stratified sampling, reaching 79.06% METRe accuracy on MP-20 polymorph split versus 70.87% for the best baseline.
-
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.