REVIEW 19 cited by
Crystal Diffusion Variational Autoencoder for Periodic Material Generation
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Generating the periodic structure of stable materials is a long-standing challenge for the material design community. This task is difficult because stable materials only exist in a low-dimensional subspace of all possible periodic arrangements of atoms: 1) the coordinates must lie in the local energy minimum defined by quantum mechanics, and 2) global stability also requires the structure to follow the complex, yet specific bonding preferences between different atom types. Existing methods fail to incorporate these factors and often lack proper invariances. We propose a Crystal Diffusion Variational Autoencoder (CDVAE) that captures the physical inductive bias of material stability. By learning from the data distribution of stable materials, the decoder generates materials in a diffusion process that moves atomic coordinates towards a lower energy state and updates atom types to satisfy bonding preferences between neighbors. Our model also explicitly encodes interactions across periodic boundaries and respects permutation, translation, rotation, and periodic invariances. We significantly outperform past methods in three tasks: 1) reconstructing the input structure, 2) generating valid, diverse, and realistic materials, and 3) generating materials that optimize a specific property. We also provide several standard datasets and evaluation metrics for the broader machine learning community.
Forward citations
Cited by 19 Pith papers
-
Extracting Atomic Environments for Machine Learning Interatomic Potentials
For building DFT-sized training cells from large bulk simulations, deleting atoms that collide across periodic boundaries after a cubic cut gives the most accurate forces with low energy artifacts.
-
Crystalite: A Lightweight Transformer for Efficient Crystal Modeling
A lightweight diffusion Transformer with Subatomic Tokenization and periodic geometry attention biases reaches SOTA crystal structure prediction and the best reported S.U.N. de novo discovery score among compared base...
-
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.
-
Score-based diffusion models for accurate crystal-structure inpainting and reconstruction of hydrogen positions
Adapting TD-Paint to crystal diffusion models reconstructs hydrogen positions with a LES success rate above 97%, beating unconditioned diffusion and DFT-based inpainting.
-
Discovery and recovery of crystalline materials with property-conditioned transformers
Conditioning the attention layers of a crystal-writing transformer on continuous property values enables XRD-based structure recovery and targeted generation of photovoltaic candidates.
-
MiAD: Mirage Atom Diffusion for De Novo Crystal Generation
Mirage infusion lets crystal diffusion models vary atom counts during generation and raises the S.U.N. rate on MP-20 to 8.2%.
-
Enhancing Materials Discovery with Valence Constrained Design in Generative Modeling
CrysVCD generates valence-balanced compositions with an elemental language model and then constructs their crystal structures with a diffusion model, reporting improved stability and functional property targeting.
-
Universal crystal material property prediction via multi-view geometric fusion in graph transformers
MGT fuses SE3-invariant and SO3-equivariant crystal graph representations with a task-adaptive mixture-of-experts router, achieving state-of-the-art accuracy on multiple crystal property prediction benchmarks.
-
Hybrid DiffractGPT-Rietveld Refinement Framework for Automated X-ray Diffraction Analysis
A hybrid DiffractGPT–database–Rietveld pipeline returns candidate structures for 93.8% of filtered RRUFF minerals and valid lattice parameters for 79.7% of them (and ~95–98% on an Alexandria subset).
-
How Far Can You Grow? Characterizing the Extrapolation Frontier of Graph Generative Models for Materials Science
A size-resolved benchmark shows well-behaved crystal generative models degrade by ~13% beyond training radii and follow RMSD ~ N^{1/3}, but the task is deterministic and the headline 'all models' claim is not supporte...
-
AtomBench: A Benchmarking Framework for Generative Crystal Reconstruction Models in Conventional Superconductors
On two superconductor datasets, CDVAE best reproduces lattice parameters while AtomGPT (full text) or MatterGen (abstract) best reproduces atomic coordinates, but the comparison is confounded by unequal input information.
-
AMD-Mamba: A Phenotype-Aware Multi-Modal Framework for Robust AMD Prognosis
AMD-Mamba claims a new multi-modal model and biomarker for early prediction of high-risk age-related macular degeneration, but the submitted manuscript text does not match the abstract and contains placeholder passages.
-
Beyond Atomic Geometry Representations in Materials Science: A Human-in-the-Loop Multimodal Framework
MCS-Set adds 2D projections and text labels to 20 synthetic crystal cluster families and exposes large, uneven errors across LLM baselines.
-
Property-Guided Diffusion for Inverse Design of Crystalline Materials
An adapter-based classifier-free guidance framework steers a pre-trained crystal diffusion model toward target properties and higher symmetry, with MLIP-based screening reporting modest success rates for stable magnet...
-
DiffractGPT: Atomic Structure Determination from X-ray Diffraction Patterns using Generative Pre-trained Transformer
DiffractGPT predicts crystal structures directly from simulated powder XRD patterns, and its accuracy improves when the chemical composition is provided.
-
TopoMAS: Large Language Model Driven Topological Materials Multiagent System
TopoMAS is a multi-agent LLM framework that automates retrieval, generation, and first-principles validation for topological materials, reporting 94.55% accuracy with a lightweight Qwen2.5-72B model.
-
A Survey of AI for Materials Science: Foundation Models, LLM Agents, Datasets, and Tools
This survey organizes foundation models, LLM agents, datasets, and tools in materials science into six task areas.
-
MOFGPT: Generative Design of Metal-Organic Frameworks using Language Models
A GPT model trained on MOFid strings plus reinforcement learning generates MOF candidates whose surrogate-predicted properties shift toward requested targets, but the evaluation does not validate those properties inde...
-
xChemAgents: Agentic AI for Explainable Quantum Chemistry
An LLM-based Selector and Validator choose sparse textual descriptors for molecular property prediction, reporting mixed MAE changes relative to the authors' own reduced GNN baselines rather than published state-of-the-art.
Discussion (0). Sign in to comment.