Symmetry-Breaking De Novo Crystal Generation via Markovian Jump Diffusion

• URL: http://arxiv.org/abs/2608.13457v1
• Date: Thu, 13 Aug 2026 16:41:48 GMT
• Title: Symmetry-Breaking De Novo Crystal Generation via Markovian Jump Diffusion
• Abstract summary: We propose a novel diffusion-based framework that generates full structure specifications by reversing from the lowest-symmetry priors.<n>Our model, dubbed emphSymmetry-breaking Crystal Diffusion (SbCD), introduces a principled approach to explicitly incorporate inter-space-group transitions into the generative process.<n>In de novo generation experiments on MP20 and MPTS-52, SbCD outperforms its symmetry-preserving counterpart by a substantial margin.
• Score: 50.136954476803766
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Generating crystals has recently attracted significant interest due to their broad applications in materials science. However, existing generative models struggle to produce complete crystallographic specifications, limiting their ability to capture global symmetry and structural dependencies. In particular, current state-of-the-art approaches generate crystals only up to site symmetries and rely on sampling space groups from empirical distributions during generation. Inspired by \emph{spontaneous symmetry breaking} in physics, where crystals break symmetries under external conditions, we propose a novel diffusion-based framework that generates full structure specifications by reversing from the lowest-symmetry priors. Our method leverages a Markovian jump-diffusion process to model these symmetry-breaking dynamics, enabling it to traverse different space groups in a physically motivated manner. Our model, dubbed \emph{Symmetry-breaking Crystal Diffusion} (SbCD), introduces a principled approach to explicitly incorporate inter-space-group transitions into the generative process. In de novo generation experiments on MP20 and MPTS-52, SbCD outperforms its symmetry-preserving counterpart by a substantial margin, offering a promising perspective for generative modeling of crystalline materials.

Related papers

• DynaCrys: Crystal Generation with Dynamic Space-Group Diffusion [5.921382963861245]
  We introduce DynaCrys, a generative model for crystals in which the space group co-evolves with Wyckoff occupations and elements.<n>Across large-scale evaluations using two independent relaxation-and-evaluation engines, DynaCrys best-in-class performance in symmetry-aware discovery of stable, unique, and novel crystals.
  arXiv  Detail & Related papers  (2026-08-07T16:45:51Z)
• 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)
• Kinetic Langevin Diffusion for Crystalline Materials Generation [8.275553926021168]
  We introduce Kinetic Langevin Diffusion for Materials (KLDM), a novel diffusion model for crystalline materials generation.<n>By coupling coordinates with auxiliary Euclidean variables representing velocities, the diffusion process is now offset to a flat space.<n>We evaluate KLDM on both Crystal Structure Prediction (CSP) and De-novo Generation (DNG) tasks.
  arXiv  Detail & Related papers  (2025-07-04T14:18:26Z)
• WyckoffDiff -- A Generative Diffusion Model for Crystal Symmetry [10.980666029958932]
  We propose a generative model, Wyckoff Diffusion, which generates symmetry-based descriptions of crystals.<n>In addition to respecting symmetry by construction, the discrete nature of our model enables fast generation.<n>As a proof-of-concept study, we use WyckoffDiff to find new materials below the convex hull of thermodynamical stability.
  arXiv  Detail & Related papers  (2025-02-10T14:04:23Z)
• SymmCD: Symmetry-Preserving Crystal Generation with Diffusion Models [20.39521603857931]
  We propose SymmCD, a novel diffusion-based generative model that explicitly incorporates crystallographic symmetry into the generative process.<n>We showcase the competitive performance of SymmCD on a subset of the Materials Project, obtaining diverse and valid crystals with realistic symmetries and predicted properties.
  arXiv  Detail & Related papers  (2025-02-05T21:48:48Z)
• A Periodic Bayesian Flow for Material Generation [20.62877413439857]
  We introduce CrysBFN, a novel crystal generation method by proposing a periodic Bayesian flow.<n>To successfully realize the concept of periodic Bayesian flow, CrysBFN integrates a new entropy conditioning mechanism.<n>Experiments over both crystal ab initio generation and crystal structure prediction tasks demonstrate the superiority of CrysBFN.
  arXiv  Detail & Related papers  (2025-02-04T05:07:13Z)
• 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)
• Geometric Trajectory Diffusion Models [58.853975433383326]
  Generative models have shown great promise in generating 3D geometric systems. Existing approaches only operate on static structures, neglecting the fact that physical systems are always dynamic in nature. We propose geometric trajectory diffusion models (GeoTDM), the first diffusion model for modeling the temporal distribution of 3D geometric trajectories.
  arXiv  Detail & Related papers  (2024-10-16T20:36:41Z)
• Geometric Neural Diffusion Processes [55.891428654434634]
  We extend the framework of diffusion models to incorporate a series of geometric priors in infinite-dimension modelling. We show that with these conditions, the generative functional model admits the same symmetry.
  arXiv  Detail & Related papers  (2023-07-11T16:51:38Z)
• Unbalanced Diffusion Schr\"odinger Bridge [71.31485908125435]
  We introduce unbalanced DSBs which model the temporal evolution of marginals with arbitrary finite mass. This is achieved by deriving the time reversal of differential equations with killing and birth terms. We present two novel algorithmic schemes that comprise a scalable objective function for training unbalanced DSBs.
  arXiv  Detail & Related papers  (2023-06-15T12:51:56Z)

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.