To speed up the optimization process, we transform the corresponding problem into a lower-dimensional latent space learned by a variational autoencoder. This is trained on a total of 6839 different 2D ...

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 ...

This article proposes a new underwater thruster fault detection and identification method based on adversarial variational autoencoder (AdvVAE). Adversarial training and variational autoencoders are ...

Microsoft surprises MS-DOS fans with remake of ancient text editor that works on Linux It's funny how useful a 34-year-old software design can still be.