Fourier Transformers for Latent Crystallographic Diffusion and Generative Modeling

• URL: http://arxiv.org/abs/2602.12045v1
• Date: Thu, 12 Feb 2026 15:11:12 GMT
• Title: Fourier Transformers for Latent Crystallographic Diffusion and Generative Modeling
• Authors: Jed A. Duersch, Elohan Veillon, Astrid Klipfel, Adlane Sayede, Zied Bouraoui,
• Abstract summary: New crystalline materials call for generative models that handle periodic boundary conditions, crystallographic symmetries, and physical constraints.<n>We propose a reciprocal-space generative pipeline that represents crystals through a truncated Fourier transform of the species-resolved unit-cell density.
• Score: 15.281839359113446
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The discovery of new crystalline materials calls for generative models that handle periodic boundary conditions, crystallographic symmetries, and physical constraints, while scaling to large and structurally diverse unit cells. We propose a reciprocal-space generative pipeline that represents crystals through a truncated Fourier transform of the species-resolved unit-cell density, rather than modeling atomic coordinates directly. This representation is periodicity-native, admits simple algebraic actions of space-group symmetries, and naturally supports variable atomic multiplicities during generation, addressing a common limitation of particle-based approaches. Using only nine Fourier basis functions per spatial dimension, our approach reconstructs unit cells containing up to 108 atoms per chemical species. We instantiate this pipeline with a transformer variational autoencoder over complex-valued Fourier coefficients, and a latent diffusion model that generates in the compressed latent space. We evaluate reconstruction and latent diffusion on the LeMaterial benchmark and compare unconditional generation against coordinate-based baselines in the small-cell regime ($\leq 16$ atoms per unit cell).

Related papers

• Parallel Complex Diffusion for Scalable Time Series Generation [50.01609741902786]
  PaCoDi is a spectral-native architecture that decouples generative modeling in the frequency domain.<n>We show that PaCoDi outperforms existing baselines in both generation quality and inference speed.
  arXiv  Detail & Related papers  (2026-02-10T14:31:53Z)
• C2NP: A Benchmark for Learning Scale-Dependent Geometric Invariances in 3D Materials Generation [2.3982445219832678]
  We introduce Crystal-to-Nanoparticle (C2NP), a benchmark for evaluating generative models when moving between infinite crystalline unit cells and finite nanoparticles.<n>C2NP defines two complementary tasks: (i) generating nanoparticles of specified radii from periodic unit cells, testing whether models capture surface truncation and geometric constraints; and (ii) recovering bulk lattice parameters and space-group symmetry from finite particle configurations.
  arXiv  Detail & Related papers  (2026-01-27T01:25:50Z)
• 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)
• CryoSplat: Gaussian Splatting for Cryo-EM Homogeneous Reconstruction [48.45613121595709]
  cryogenic electron microscopy (cryo-EM) facilitates the determination of macromolecular structures at near-atomic resolution.<n>The core computational task in single-particle cryo-EM is to reconstruct the 3D electrostatic potential of a molecule from noisy 2D projections acquired at unknown orientations.<n>We propose cryoSplat, a GMM-based method that integrates Gaussian splatting with the physics of cryo-EM image formation.
  arXiv  Detail & Related papers  (2025-08-06T23:24:43Z)
• 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)
• UniGenX: a unified generative foundation model that couples sequence, structure and function to accelerate scientific design across proteins, molecules and materials [62.72989417755985]
  We present UniGenX, a unified generative model for function in natural systems.<n>UniGenX represents heterogeneous inputs as a mixed stream of symbolic and numeric tokens.<n>It achieves state-of-the-art or competitive performance for the function-aware generation across domains.
  arXiv  Detail & Related papers  (2025-03-09T16:43:07Z)
• ReciNet: Reciprocal Space-Aware Long-Range Modeling for Crystalline Property Prediction [28.923772205970497]
  ReciNet is a novel architecture that integrates geometric GNNs and reciprocal blocks to model short-range and long-range interactions.<n>We show that ReciNet achieves state-of-the-art predictive accuracy across a range of crystal property prediction tasks.
  arXiv  Detail & Related papers  (2025-02-04T22:31:39Z)
• Grand canonical generative diffusion model for crystalline phases and grain boundaries [8.159060728081203]
  The diffusion model has emerged as a powerful tool for generating atomic structures for materials science. This work calls attention to the deficiency of current particle-based diffusion models, which represent atoms as a point cloud. We develop a solution, the grand canonical diffusion model, which adopts an alternative voxel-based representation with continuous rather than fixed number of particles.
  arXiv  Detail & Related papers  (2024-08-28T07:49:29Z)
• 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)
• Message-Passing Neural Quantum States for the Homogeneous Electron Gas [41.94295877935867]
  We introduce a message-passing-neural-network-based wave function Ansatz to simulate extended, strongly interacting fermions in continuous space. We demonstrate its accuracy by simulating the ground state of the homogeneous electron gas in three spatial dimensions.
  arXiv  Detail & Related papers  (2023-05-12T04:12:04Z)
• Unified Fourier-based Kernel and Nonlinearity Design for Equivariant Networks on Homogeneous Spaces [52.424621227687894]
  We introduce a unified framework for group equivariant networks on homogeneous spaces. We take advantage of the sparsity of Fourier coefficients of the lifted feature fields. We show that other methods treating features as the Fourier coefficients in the stabilizer subgroup are special cases of our activation.
  arXiv  Detail & Related papers  (2022-06-16T17:59:01Z)
• Renormalization to localization without a small parameter [0.0]
  We study the wave function localization properties in a d-dimensional model of randomly spaced particles with isotropic hopping potential depending solely on Euclidean interparticle distances. Due to the generality of this model usually called the Euclidean random matrix model, it arises naturally in various physical contexts such as studies of vibrational modes, artificial atomic systems, liquids and glasses, ultracold gases and photon localization phenomena.
  arXiv  Detail & Related papers  (2020-01-17T19:00:06Z)
• Probing chiral edge dynamics and bulk topology of a synthetic Hall system [52.77024349608834]
  Quantum Hall systems are characterized by the quantization of the Hall conductance -- a bulk property rooted in the topological structure of the underlying quantum states. Here, we realize a quantum Hall system using ultracold dysprosium atoms, in a two-dimensional geometry formed by one spatial dimension. We demonstrate that the large number of magnetic sublevels leads to distinct bulk and edge behaviors.
  arXiv  Detail & Related papers  (2020-01-06T16:59:08Z)

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.