Crystal Generation using the Fully Differentiable Pipeline and Latent Space Optimization
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866911365438898176 |
|---|---|
| author | Ridwan, Osman Goni Frapper, Gilles Xue, Hongfei Zhu, Qiang |
| author_facet | Ridwan, Osman Goni Frapper, Gilles Xue, Hongfei Zhu, Qiang |
| contents | We present a materials generation framework that couples a symmetry-conditioned variational autoencoder (CVAE) with a differentiable SO(3) power spectrum objective to steer candidates toward a specified local environment under the crystallographic constraints. In particular, we implement a fully differentiable pipeline to enable batch-wise optimization on both direct and latent crystallographic representations. Using the GPU acceleration, this implementation achieves about fivefold speed compared to our previous CPU workflow, while yielding comparable outcomes. In addition, we introduce the optimization strategy that alternatively performs optimization on the direct and latent crystal representations. This dual-level relaxation approach can effectively escape local minima defined by different objective gradients, thus increasing the success rate of generating complex structures satisfying the target local environments. This framework can be extended to systems consisting of multi-components and multi-environments, providing a scalable route to generate material structures with the target local environment. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_04606 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Crystal Generation using the Fully Differentiable Pipeline and Latent Space Optimization Ridwan, Osman Goni Frapper, Gilles Xue, Hongfei Zhu, Qiang Materials Science Artificial Intelligence Machine Learning Atomic and Molecular Clusters We present a materials generation framework that couples a symmetry-conditioned variational autoencoder (CVAE) with a differentiable SO(3) power spectrum objective to steer candidates toward a specified local environment under the crystallographic constraints. In particular, we implement a fully differentiable pipeline to enable batch-wise optimization on both direct and latent crystallographic representations. Using the GPU acceleration, this implementation achieves about fivefold speed compared to our previous CPU workflow, while yielding comparable outcomes. In addition, we introduce the optimization strategy that alternatively performs optimization on the direct and latent crystal representations. This dual-level relaxation approach can effectively escape local minima defined by different objective gradients, thus increasing the success rate of generating complex structures satisfying the target local environments. This framework can be extended to systems consisting of multi-components and multi-environments, providing a scalable route to generate material structures with the target local environment. |
| title | Crystal Generation using the Fully Differentiable Pipeline and Latent Space Optimization |
| topic | Materials Science Artificial Intelligence Machine Learning Atomic and Molecular Clusters |
| url | https://arxiv.org/abs/2601.04606 |