Topology-Stratified Materials Discovery with A Flow-Based Generative Model
Abstract
Accurate generation of crystal structures is the foundation to the discovery of high-performance materials for extreme-environment applications, such as aerospace, additive manufacturing, and fusion energy systems. Although generative modeling has emerged as a promising approach for crystal design, its performance remains limited by the complex crystal structures and diverse chemical compositions. In this work, we develop UFO-MGen, a universal flow-based generative model that learns topological features of Wyckoff representations and leverages this information to accurately generate crystals across vast structural and chemical spaces. Compared with state-of-the-art generative models, UFO-MGen achieves the highest crystal generation success rate under a rigorous multi-stability evaluation framework, the highest SUN (stable, unique, novel) rate, and a remarkable extrapolation capability that has not been reported by previous models. Furthermore, a fine-tuning module is implemented to UFO-MGen for property-constrained crystal generation, enabling the inverse materials design toward target properties. The UFO-MGen opens a new avenue for accelerated materials discovery and providing a foundation for universal materials intelligence.
Related
- Physics-Informed and Knowledge-Driven Generative AI for Autonomous Discovery of Porous Oxide Energy Materials: Opportunities and Challenges
- Diffusion-Based Generative Screening of ABX3 Perovskite Compositions for Bandgap-Targeted Materials Discovery
- Hidden transverse-flow topology in partially coherent structured light
- Robust Signatures of Fragile Topology in Nonmagnetic Materials
- Zero-shot rib design: merging training-free generative prior with topology optimization
BibTeX
@misc{zhou2026topologystratified,
title = {{Topology-Stratified Materials Discovery with A Flow-Based Generative Model}},
author = {Jingyi Zhou and Oyshee Chowdhury and Noah Oyeniran and Chongze Hu},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.26547},
eprint = {2609.26547},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.26547},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Topology-Stratified Materials Discovery with A Flow-Based Generative Model
AU - Jingyi Zhou
AU - Oyshee Chowdhury
AU - Noah Oyeniran
AU - Chongze Hu
PY - 2026
DA - 2026/09/22
PB - arXiv
DO - 10.48550/arxiv.2609.26547
UR - https://arxiv.org/abs/2609.26547
AB - Accurate generation of crystal structures is the foundation to the discovery of high-performance materials for extreme-environment applications, such as aerospace, additive manufacturing, and fusion energy systems. Although generative modeling has emerged as a promising approach for crystal design, its performance remains limited by the complex crystal structures and diverse chemical compositions. In this work, we develop UFO-MGen, a universal flow-based generative model that learns topological features of Wyckoff representations and leverages this information to accurately generate crystals across vast structural and chemical spaces. Compared with state-of-the-art generative models, UFO-MGen achieves the highest crystal generation success rate under a rigorous multi-stability evaluation framework, the highest SUN (stable, unique, novel) rate, and a remarkable extrapolation capability that has not been reported by previous models. Furthermore, a fine-tuning module is implemented to UFO-MGen for property-constrained crystal generation, enabling the inverse materials design toward target properties. The UFO-MGen opens a new avenue for accelerated materials discovery and providing a foundation for universal materials intelligence.
ER -