AMShortcut: An Inference- and Training-Efficient Inverse Design Model for Amorphous Materials

2026-03-31

AI Summary

This work addresses the inefficiency of conventional inverse design approaches for amorphous materials, which struggle to generate complex short- and medium-range structures that meet target properties due to slow training and inference. To overcome this limitation, the authors propose AMShortcut, a highly efficient probabilistic generative model that, for the first time, enables conditional generation conditioned on arbitrary combinations of multiple target properties within a single unified framework. By integrating an effective sampling strategy with a flexible conditioning mechanism, AMShortcut achieves dramatically accelerated inference with minimal sampling steps, making it suitable for large-scale amorphous systems. Experiments across three diverse amorphous datasets demonstrate that AMShortcut excels in both structural diversity and property fidelity, enabling accurate and efficient inverse design of amorphous materials.

Abstract

Amorphous materials are solids that lack long-range atomic order but possess complex short- and medium-range order. Unlike crystalline materials that can be described by unit cells containing few up to hundreds of atoms, amorphous materials require larger simulation cells with at least hundreds or often thousands of atoms. Inverse design of amorphous materials with probabilistic generative models aims to generate the atomic positions and elements of amorphous materials given a set of desired properties. It has emerged as a promising approach for facilitating the application of amorphous materials in domains such as energy storage and thermal management. In this paper, we introduce AMShortcut, an inference- and training-efficient probabilistic generative model for amorphous materials. AMShortcut enables accurate inference of diverse short- and medium-range structures in amorphous materials with only a few sampling steps, mitigating the need for an excessive number of sampling steps that hinders inference efficiency. AMShortcut can be trained once with all relevant properties and perform inference conditioned on arbitrary combinations of desired properties, mitigating the need for training one model for each combination. Experiments on three amorphous materials datasets with diverse structures and properties demonstrate that AMShortcut achieves its design goals.

Problem

• inverse design
• amorphous materials
• probabilistic generative model
• inference efficiency
• training efficiency

Innovation

• inverse design
• amorphous materials
• probabilistic generative model
• inference efficiency
• training efficiency