In this repo, AE(Auto Encoder) and VAE(Variational Auto Encoder) are implemented, and are experimented with different model structures and super parameters.

Geometric Dynamic Variational Autoencoders (GD-VAEs) for learning embedding maps for nonlinear dynamics into general latent spaces. This includes methods for standard latent spaces or manifold latent ...

In this work, we first propose to use compressive autoencoders instead. These networks, which can be seen as variational autoencoders with a flexible latent prior, are smaller and easier to train than ...

Self-supervised learning approaches, such as masked autoencoder (MAE) reconstruction and contrastive ... and contrastive learning is utilized on the features extracted from the encoders of both MAEs.