Materium: An Autoregressive Approach for Material Generation

• URL: http://arxiv.org/abs/2512.07486v1
• Date: Mon, 08 Dec 2025 12:14:42 GMT
• Title: Materium: An Autoregressive Approach for Material Generation
• Authors: Niklas Dobberstein, Jan Hamaekers,
• Abstract summary: Materium is an autoregressive transformer for generating crystal structures.<n>It places atoms at precise fractional coordinates, enabling fast, scalable generation.<n>The model can be trained in a few hours on a single GPU.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We present Materium: an autoregressive transformer for generating crystal structures that converts 3D material representations into token sequences. These sequences include elements with oxidation states, fractional coordinates and lattice parameters. Unlike diffusion approaches, which refine atomic positions iteratively through many denoising steps, Materium places atoms at precise fractional coordinates, enabling fast, scalable generation. With this design, the model can be trained in a few hours on a single GPU and generate samples much faster on GPUs and CPUs than diffusion-based approaches. The model was trained and evaluated using multiple properties as conditions, including fundamental properties, such as density and space group, as well as more practical targets, such as band gap and magnetic density. In both single and combined conditions, the model performs consistently well, producing candidates that align with the requested inputs.

Related papers

• Zatom-1: A Multimodal Flow Foundation Model for 3D Molecules and Materials [51.342983349686556]
  General-purpose 3D chemical modeling encompasses molecules and materials, requiring both generative and predictive capabilities.<n>We introduce Zatom-1, the first end-to-end, fully open-source foundation model that unifies generative and predictive learning of 3D molecules and materials.
  arXiv  Detail & Related papers  (2026-02-24T20:52:39Z)
• GaussianEM: Model compositional and conformational heterogeneity using 3D Gaussians [18.57590175845086]
  We present GaussianEM, a pseudo-atomic framework that simultaneously models compositional and conformational heterogeneity from cryo-EM images.<n>This approach provides an intuitive and interpretable description of conformational changes, preserves local structural consistency along the transition trajectories, and naturally bridges the gap between density-based models and corresponding atomic models.
  arXiv  Detail & Related papers  (2025-12-25T09:36:52Z)
• 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)
• Towards Unified and Lossless Latent Space for 3D Molecular Latent Diffusion Modeling [90.23688195918432]
  3D molecule generation is crucial for drug discovery and material science.<n>Existing approaches typically maintain separate latent spaces for invariant and equivariant modalities.<n>We propose textbfUAE-3D, a multi-modal VAE that compresses 3D molecules into latent sequences from a unified latent space.
  arXiv  Detail & Related papers  (2025-03-19T08:56:13Z)
• Towards Symmetry-Aware Generation of Periodic Materials [64.21777911715267]
  We propose SyMat, a novel material generation approach that can capture physical symmetries of periodic material structures. SyMat generates atom types and lattices of materials through generating atom type sets, lattice lengths and lattice angles with a variational auto-encoder model. We show that SyMat is theoretically invariant to all symmetry transformations on materials and demonstrate that SyMat achieves promising performance on random generation and property optimization tasks.
  arXiv  Detail & Related papers  (2023-07-06T01:05:34Z)
• Wigner kernels: body-ordered equivariant machine learning without a basis [0.0]
  We propose a novel density-based method which involves computing Wigner kernels'' Wigner kernels are fully equivariant and body-ordered kernels that can be computed iteratively with a cost that is independent of the radial-chemical basis. We present several examples of the accuracy of models based on Wigner kernels in chemical applications.
  arXiv  Detail & Related papers  (2023-03-07T18:34:55Z)
• A Score-based Geometric Model for Molecular Dynamics Simulations [33.158796937777886]
  We propose a novel model called ScoreMD to estimate the gradient of the log density of molecular conformations. With multiple architectural improvements, we outperforms state-of-the-art baselines on MD17 and isomers of C7O2H10. This research provides new insights into the acceleration of new material and drug discovery.
  arXiv  Detail & Related papers  (2022-04-19T05:13:46Z)
• GeoDiff: a Geometric Diffusion Model for Molecular Conformation Generation [102.85440102147267]
  We propose a novel generative model named GeoDiff for molecular conformation prediction. We show that GeoDiff is superior or comparable to existing state-of-the-art approaches.
  arXiv  Detail & Related papers  (2022-03-06T09:47:01Z)
• Crystal Diffusion Variational Autoencoder for Periodic Material Generation [29.558155407825115]
  We propose a Crystal Diffusion Variational Autoencoder (CDVAE) that captures the 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. 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.
  arXiv  Detail & Related papers  (2021-10-12T17:49:49Z)
• Optimal radial basis for density-based atomic representations [58.720142291102135]
  We discuss how to build an adaptive, optimal numerical basis that is chosen to represent most efficiently the structural diversity of the dataset at hand. For each training dataset, this optimal basis is unique, and can be computed at no additional cost with respect to the primitive basis. We demonstrate that this construction yields representations that are accurate and computationally efficient.
  arXiv  Detail & Related papers  (2021-05-18T17:57:08Z)
• Data-driven learning of nonlocal models: from high-fidelity simulations to constitutive laws [3.1196544696082613]
  We show that machine learning can improve the accuracy of simulations of stress waves in one-dimensional composite materials. We propose a data-driven technique to learn nonlocal laws for stress wave propagation models.
  arXiv  Detail & Related papers  (2020-12-08T01:46:26Z)

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.