Abstract: Variational auto-encoders (VAEs) are widely used in generative modeling and representation learning, with applications ranging from image generation to data compression. However, ...

Climate change makes accurate weather prediction and large-scale data analysis increasingly crucial, but the sheer volume of weather data strains data storage and sharing. Here we introduce Aeolus, a ...

Official implementation of RAVE: A variational autoencoder for fast and high-quality neural audio synthesis (article link) by Antoine Caillon and Philippe Esling. If you use RAVE as a part of a music ...

Given the complexity and dynamic nature of short-term load sequence data, coupled with prevalent errors in traditional forecasting methods, this study introduces a novel approach for short-term load ...

Abstract: In this paper we demonstrate methods for reliable and efficient training of discrete representation using Vector-Quantized Variational Auto-Encoder models (VQ-VAEs). Discrete latent variable ...

We propose an approach for joint trajectory analysis of multiple single-cell sequencing data, combining Bayesian hierarchical models with variational autoencoders. Based on a coherent statistical ...

Shape measurements are crucial for evolutionary and developmental biology; however, they present difficulties in the objective and automatic quantification of arbitrary shapes. Conventional approaches ...