ATLAS: A Foundation Neural Sampler for Amorphous Materials

• URL: http://arxiv.org/abs/2607.19198v1
• Date: Tue, 21 Jul 2026 15:31:49 GMT
• Title: ATLAS: A Foundation Neural Sampler for Amorphous Materials
• Abstract summary: ATLAS is an efficient sampler that learns a diffusion process to generate Boltzmann-distributed amorphous structures.<n>In two-dimensionalersen systems, ATLAS reproduces parallel tempering Markov chain Monte Carlo structural distributions.<n>In Cu-Zr and Cr-Co-Ni metallic glasses, ATLAS recovers experimentally observed short-range-order trends and steers structures toward prescribed order parameters.
• Score: 38.39923274691799
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Amorphous materials exhibit exceptional mechanical and functional properties, yet their rugged energy landscapes are notoriously difficult to sample. Below the glass-transition temperature, conventional molecular dynamics and Monte Carlo become inefficient because equilibration relies on rare barrier-crossing events, while data-driven generative models are constrained by scarce and biased reference ensembles. Here, we introduce ATLAS, an efficient sampler that learns a diffusion process to generate Boltzmann-distributed amorphous structures directly from a target energy function. Parameterized by an equivariant graph neural network, ATLAS generalizes across system size, temperature, and composition. By exploiting the time reversal of the diffusion process, it enables efficient estimation of thermodynamic quantities and steering toward target observables. In two-dimensional Kob-Andersen systems, ATLAS reproduces parallel tempering Markov chain Monte Carlo structural distributions, free energies and entropies, achieving below 0.2% free energy error in the low-temperature glass regime with over 500-fold fewer energy evaluations. In Cu-Zr and Cr-Co-Ni metallic glasses, ATLAS recovers experimentally observed short-range-order trends and steers structures toward prescribed order parameters and optimized bulk moduli. Moreover, composition-amortized pretraining outperforms composition-specific training from scratch, reduces inverse-design costs by several hundred-fold, and enables sampling with expensive universal machine learning interatomic potentials. Coupled to a large language model agent, ATLAS searches an eight-element space for high-entropy metallic glasses balancing stiffness and ductility, identifying a converged Pareto frontier within 480 oracle evaluations. Together, these results establish ATLAS as a foundation model for sampling, steering and designing amorphous materials.

Related papers

• Neutron and X-ray Diffraction Reveal the Limits of Long-Range Machine Learning Potentials for Medium-Range Order in Silica Glass [2.5432391525687748]
  Glassy silica is a foundational material in optics and electronics.<n> accurately predicting its medium-range order (MRO) remains a major challenge for machine-learning interatomic potentials.<n>Here, we combine neutron and X-ray diffraction measurements with large-scale molecular dynamics driven by two MACE-based models.
  arXiv  Detail & Related papers  (2026-04-23T02:37:29Z)
• Manifold-Orthogonal Dual-spectrum Extrapolation for Parameterized Physics-Informed Neural Networks [5.601252185916962]
  Physics-informed neural networks (PINNs) have achieved notable success in modeling dynamical systems governed by partial differential equations (PDEs)<n>We propose Manifold-Orthogonal Dual-spectrum Extrapolation (MODE), a lightweight micro-architecture designed for physics operator adaptation.
  arXiv  Detail & Related papers  (2026-03-14T04:52:50Z)
• From Static Spectra to Operando Infrared Dynamics: Physics Informed Flow Modeling and a Benchmark [67.29937933325849]
  Operando IR Prediction aims to forecast the time-resolved evolution of spectral fingerprints'' from a single static spectrum.<n>OpIRSpec-7K comprises 7,118 high-quality samples across 10 distinct battery systems.<n>ABCC significantly outperforms state-of-the-art static, sequential, and generative baselines.
  arXiv  Detail & Related papers  (2026-02-20T18:58:43Z)
• Generative Modeling of Aerosol State Representations [5.772617906251992]
  Aerosol-cloud-radiation interactions remain among the most uncertain components of the Earth's climate system.<n>We present a framework for learning deep variational autoencoder models of speciated mass and number concentration distributions.<n>By compressing hundreds of original dimensions into ten latent variables, the approach enables efficient storage and processing.
  arXiv  Detail & Related papers  (2025-10-11T22:38:30Z)
• Equilibrium Matching: Generative Modeling with Implicit Energy-Based Models [52.74448905289362]
  EqM is a generative modeling framework built from an equilibrium dynamics perspective.<n>By replacing time-conditional velocities with a unified equilibrium landscape, EqM offers a tighter bridge between flow and energy-based models.
  arXiv  Detail & Related papers  (2025-10-02T17:59:06Z)
• Learning to Dissipate Energy in Oscillatory State-Space Models [51.98491034847041]
  State-space models (SSMs) are a class of networks for sequence learning.<n>We show that D-LinOSS consistently outperforms previous LinOSS methods on long-range learning tasks.
  arXiv  Detail & Related papers  (2025-05-17T23:15:17Z)
• Composition and Control with Distilled Energy Diffusion Models and Sequential Monte Carlo [18.377963220078442]
  We introduce a novel training regime for the energy function through distillation of pre-trained diffusion models.<n>We showcase the synergies between energy and score by casting the diffusion sampling procedure as a Feynman Kac model.
  arXiv  Detail & Related papers  (2025-02-18T11:47:44Z)
• Rao-Blackwell Gradient Estimators for Equivariant Denoising Diffusion [55.95767828747407]
  In domains such as molecular and protein generation, physical systems exhibit inherent symmetries that are critical to model.<n>We present a framework that reduces training variance and provides a provably lower-variance gradient estimator.<n>We also present a practical implementation of this estimator incorporating the loss and sampling procedure through a method we call Orbit Diffusion.
  arXiv  Detail & Related papers  (2025-02-14T03:26:57Z)
• Many-body Expansion Based Machine Learning Models for Octahedral Transition Metal Complexes [0.0]
  We present a modification to autocorrelation for machine learning various spin state dependent properties of octa transition metal complexes (TMCs) The new strategy is based on the many-body expansion (MBE) and allows one to tune the captured stereoisomer information by changing the truncation order of the MBE. Because the new approach incorporates insights from electronic structure theory, these models exhibit systematic generalization from homoleptic to heteroleptic complexes.
  arXiv  Detail & Related papers  (2024-10-12T21:54:22Z)
• Molecule Design by Latent Prompt Transformer [76.2112075557233]
  This work explores the challenging problem of molecule design by framing it as a conditional generative modeling task. We propose a novel generative model comprising three components: (1) a latent vector with a learnable prior distribution; (2) a molecule generation model based on a causal Transformer, which uses the latent vector as a prompt; and (3) a property prediction model that predicts a molecule's target properties and/or constraint values using the latent prompt.
  arXiv  Detail & Related papers  (2024-02-27T03:33:23Z)

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.