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 ...

Self-supervised Human Activity Recognition (HAR) has been gradually gaining a lot of attention in ubiquitous computing community. Its current focus primarily lies in how to overcome the challenge of ...

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 ...