An SE(3)-invariant autoencoder for generating the periodic structure of materials
English
Singapore, Singapore
Healthcare Financial services Manufacturing Government View
数据描述
This software implementes Crystal Diffusion Variational AutoEncoder (CDVAE), which generates the periodic structure of materials. It has several main functionalities: Generate novel, stable materials by learning from a dataset containing existing material structures. Generate materials by optimizing a specific property in the latent space, i.e. inverse design.
github.com
IP: 20.205.243.166
加载中...
相关论文
2Massive discovery of crystal structures across dimensionalities by leveraging vector quantization
ZiJie Qiu•Luozhijie Jin•Zijian Du•Hongyu Chen•Guanyao Mao等 9 人
Npj Computational Materials
2025
•2025/6/17
•Vol.11 No.1 p.1-13
Discovering new functional crystalline materials through computational methods remains a challenge in materials science. We introduce VQCrystal, a deep learning framework leveraging discrete latent representations to overcome key limitations to crystal generation and inverse design. VQCrystal employ...
Computational methodsMaterials for energy and catalysis
10.1038/S41524-025-01613-6
ISSN:2057-3960
Guiding generative models to uncover diverse and novel crystals via reinforcement learning
Hyunsoo Park•Aron Walsh
Nature Machine Intelligence
2026
•2026/7/6
•00 p.1-13
Discovering functional crystalline materials entails navigating an immense combinatorial design space. Although recent advances in generative artificial intelligence have enabled the sampling of chemically plausible compositions and structures, a fundamental challenge remains: the objective misalign...
CheminformaticsComputational methodsComputational science
10.1038/S42256-026-01262-4
ISSN:2522-5839