Physics-informed diffusion models for extrapolating crystal structures beyond known motifs

• URL: http://arxiv.org/abs/2510.23181v1
• Date: Mon, 27 Oct 2025 10:21:35 GMT
• Title: Physics-informed diffusion models for extrapolating crystal structures beyond known motifs
• Authors: Andrij Vasylenko, Federico Ottomano, Christopher M. Collins, Rahul Savani, Matthew S. Dyer, Matthew J. Rosseinsky,
• Abstract summary: We develop a physics-informed diffusion method, supported by chemically grounded validation protocol.<n> Conditioning on these metrics improves generative performance across architectures.<n>Results show that while generative models are not substitutes for crystal structure prediction, their chemically informed, diversity-guided outputs can enhance CSP efficiency.
• Score: 2.154846250399764
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Discovering materials with previously unreported crystal frameworks is key to achieving transformative functionality. Generative artificial intelligence offers a scalable means to propose candidate crystal structures, however existing approaches mainly reproduce decorated variants of established motifs rather than uncover new configurations. Here we develop a physics-informed diffusion method, supported by chemically grounded validation protocol, which embeds descriptors of compactness and local environment diversity to balance physical plausibility with structural novelty. Conditioning on these metrics improves generative performance across architectures, increasing the fraction of structures outside 100 most common prototypes up to 67%. When crystal structure prediction (CSP) is seeded with generative structures, most candidates (97%) are reconstructed by CSP, yielding 145 (66%) low-energy frameworks not matching any known prototypes. These results show that while generative models are not substitutes for CSP, their chemically informed, diversity-guided outputs can enhance CSP efficiency, establishing a practical generative-CSP synergy for discovery-oriented exploration of chemical space.

Related papers

• Universal Fine-Grained Symmetry Inference and Enforcement for Rigorous Crystal Structure Prediction [3.5802790319269717]
  Crystal structure prediction (CSP) aims to predict the three-dimensional atomic arrangement of a crystal from its composition.<n>Existing deep learning models often treat crystallographic symmetry only as a soft or rely on space group and Wyckoff templates retrieved from known structures.<n>In contrast, our approach leverages large language models to encode chemical semantics and directly generate fine-grained Wyckoff patterns from composition.
  arXiv  Detail & Related papers  (2026-02-19T08:43:25Z)
• CrystalFormer-CSP: Thinking Fast and Slow for Crystal Structure Prediction [2.110303171517621]
  We present CrystalFormerCSP, an efficient framework that unifies data-driven and physics-driven optimization approaches to predict stable crystal structures for given chemical compositions.<n>The approach combines pretrained generative models for space-group-informed structure generation and a universal machine learning force field for energy minimization.<n>We demonstrate the effectiveness of CrystalFormer-CSP on benchmark problems and showcase its usage via web interface and language model integration.
  arXiv  Detail & Related papers  (2025-12-20T07:22:58Z)
• OXtal: An All-Atom Diffusion Model for Organic Crystal Structure Prediction [63.318434943975255]
  We introduce OXtal, a large-scale 100M parameter all-atom diffusion model that learns the conditional joint distribution over intramolecular conformations and periodic packing.<n>By leveraging a large dataset of 600K experimentally validated crystal structures, OXtal achieves orders-of-improvement over prior ab initio machine learning CSP methods.<n> OXtal attains over 80% packing similarity rate, demonstrating its ability to model both thermodynamic and kinetic regularities of molecular crystallization.
  arXiv  Detail & Related papers  (2025-12-07T20:46:30Z)
• CrystalDiT: A Diffusion Transformer for Crystal Generation [52.45780803467369]
  We present CrystalDiT, a diffusion transformer for crystal structure generation that achieves state-of-the-art performance.<n>CrystalDiT employs a unified transformer that imposes a powerful inductive bias: treating lattice and atomic properties as a single, interdependent system.
  arXiv  Detail & Related papers  (2025-08-13T12:53:32Z)
• Transformer-Enhanced Variational Autoencoder for Crystal Structure Prediction [16.846289696048647]
  We propose a Transformer-Enhanced Variational Autoencoder for Crystal Structure Prediction (TransVAE-CSP)<n>TransVAE-CSP learns the characteristic distribution space of stable materials, enabling both the reconstruction and generation of crystal structures.<n> Experimental results on the carbon_24, perov_5, and mp_20 datasets demonstrate that TransVAE-CSP outperforms existing methods in structure reconstruction and generation tasks.
  arXiv  Detail & Related papers  (2025-02-13T15:45:36Z)
• Open Materials Generation with Stochastic Interpolants [14.939468363546384]
  Open Materials Generation (OMatG) is a unifying framework for the generative design and discovery of crystalline materials.<n>OMatG employs inorganic interpolants to bridge an arbitrary base distribution to the target distribution of inorganic crystals.<n>We benchmark OMatG's performance on two tasks: Crystal Structure Prediction and 'de novo' generation.
  arXiv  Detail & Related papers  (2025-02-04T18:56:47Z)
• deCIFer: Crystal Structure Prediction from Powder Diffraction Data using Autoregressive Language Models [1.231476564107544]
  We introduce an autoregressive language model that performs crystal structure prediction (CSP) from powder diffraction data.<n>The presented model, deCIFer, generates crystal structures in the widely used Crystallographic Information File (CIF) format.<n>We train deCIFer on nearly 2.3M crystal structures and validate on diverse sets of PXRD patterns for characterizing challenging inorganic crystal systems.
  arXiv  Detail & Related papers  (2025-02-04T10:09:47Z)
• Efficient Symmetry-Aware Materials Generation via Hierarchical Generative Flow Networks [52.13486402193811]
  New solid-state materials require rapidly exploring the vast space of crystal structures and locating stable regions. Existing methods struggle to explore large material spaces and generate diverse samples with desired properties and requirements. We propose a novel generative model employing a hierarchical exploration strategy to efficiently exploit the symmetry of the materials space to generate crystal structures given desired properties.
  arXiv  Detail & Related papers  (2024-11-06T23:53:34Z)
• Crystalformer: Infinitely Connected Attention for Periodic Structure Encoding [10.170537065646323]
  Predicting physical properties of materials from their crystal structures is a fundamental problem in materials science. We show that crystal structures are infinitely repeating, periodic arrangements of atoms, whose fully connected attention results in infinitely connected attention. We propose a simple yet effective Transformer-based encoder architecture for crystal structures called Crystalformer.
  arXiv  Detail & Related papers  (2024-03-18T11:37:42Z)
• Accurate Crystal Structure Prediction of New 2D Hybrid Organic Inorganic Perovskites [0.0]
  Low dimensional hybrid organic-inorganic perovskites (HOIPs) represent a promising class of electronically active materials for both light absorption and emission. We present an accurate, efficient, transferable and widely applicable machine learning interatomic potential (MLIP) for predicting the structure of new 2D HOIPs.
  arXiv  Detail & Related papers  (2024-03-11T17:39:08Z)
• Scalable Diffusion for Materials Generation [99.71001883652211]
  We develop a unified crystal representation that can represent any crystal structure (UniMat) UniMat can generate high fidelity crystal structures from larger and more complex chemical systems. We propose additional metrics for evaluating generative models of materials.
  arXiv  Detail & Related papers  (2023-10-18T15:49:39Z)
• Latent Conservative Objective Models for Data-Driven Crystal Structure Prediction [62.36797874900395]
  In computational chemistry, crystal structure prediction is an optimization problem. One approach to tackle this problem involves building simulators based on density functional theory (DFT) followed by running search in simulation. We show that our approach, dubbed LCOMs (latent conservative objective models), performs comparably to the best current approaches in terms of success rate of structure prediction.
  arXiv  Detail & Related papers  (2023-10-16T04:35:44Z)
• Crystal-GFN: sampling crystals with desirable properties and constraints [103.79058968784163]
  We introduce Crystal-GFN, a generative model of crystal structures that sequentially samples structural properties of crystalline materials. In this paper, we use as objective the formation energy per atom of a crystal structure predicted by a new proxy machine learning model trained on MatBench. The results demonstrate that Crystal-GFN is able to sample highly diverse crystals with low (median -3.1 eV/atom) predicted formation energy.
  arXiv  Detail & Related papers  (2023-10-07T21:36:55Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.