We propose a Crystal Diffusion Variational Autoencoder (CDVAE) that captures the physical inductive bias of material stability. By learning from the data distribution of stable materials, the decoder generates
The crystal diffusion variational autoencoder (CDVAE) is a machine learning model that leverages score matching to generate realistic crystal structures that preserve crystal symmetry. In this study, we leverage novel diffusion probabilistic (DP) models to denoise atomic coordinates rather than adopting ...
A notable example is the Crystal Diffusion Variational Autoencoder (CDVAE) developed by Tian Xie et al.,6 which successfully integrates a diffusion model with a VAE for crystal generation. Furthermore, the Cond-CDVAE model17 extends this approach by allowing the incorporation of user-defined ...
In CDVAE20, a diffusion network is trained to generate material structures21, in which a diffusion process within their diffusion variational autoencoder moves atoms into positions in the lower energy space to generate stable crystals. All these models have difficulty in generation of high quality ...
This paper proposes the Con-CDVAE model, an extension of the Crystal Diffusion Variational Autoencoder (CDVAE), for conditional crystal generation. We introduce innovative components, design a two-step training method, and develop three unique generation strategies to enhance model performance. The ...
(CSP) via a conditional crystal diffusion variational autoencoder (Cond-CDVAE) approach, which is tailored to allow user-defined material and physical parameters such as composition and pressure. This model is trained on an expansive dataset containing over 670,000 local minimum structures, including...
S. Crystal diffusion variational autoencoder for periodic material generation. In International Conference on Learning Representations (2021). Yao, Z. et al. Inverse design of nanoporous crystalline reticular materials with deep generative models. Nat. Mach. Intell. 3, 76–86 (2021). Article ...
In CDVAE20, a diffusion network is trained to generate material structures21, in which a diffusion process within their diffusion variational autoencoder moves atoms into positions in the lower energy space to generate stable crystals. All these models have difficulty in generation of high quality ...
Exploring Local Crystal Symmetry with Rotationally Invariant Variational AutoencodersAn abstract is not available for this content so a preview has been provided. As you have access to this content, a full PDF is available via the 'Save PDF' action button....
Finally, as a neural language model, CrystaLLM can leverage the established practice of fine-tuning, allowing the pre-trained model to be adapted for the prediction of materials properties. There is far less precedent in fine-tuning models based on diffusion and variational autoencoder architectures...