GitHub

Modern Variational Autoencoder (VAE) Implementation

Batch normalization and dropout for stability Mixed precision training for efficiency Learning rate scheduling and gradient clipping β-VAE support for disentangled representations ...
GitHub

Descript Audio Codec - VAE Variant (.dac-vae): High-Fidelity Audio Compression with Variational Autoencoder

This repository contains training and inference scripts for the Descript Audio Codec VAE variant (.dac-vae), a modified version of the original DAC that replaces the RVQGAN architecture with a ...
eLife

Disentangled multi-subject and social behavioral representations through a constrained subspace variational autoencoder (CS-VAE)

This paper is a valuable step in multi-subject behavioral modeling using an extension of the Variational Autoencoder (VAE) framework. Using a novel partition of the latent space and in tandem with a ...
IEEE

VAE-TF: A Variational Autoencoder Framework for Financial Fraud Detection

Abstract: In the context of modern digital transactions, the sheer volume and velocity of transactions necessitate robust financial fraud detection mechanisms to effectively distinguish between ...
Frontiers

VAE deep learning model with domain adaptation, transfer learning and harmonization for diagnostic classification from multi-site neuroimaging data

In large public multi-site fMRI datasets, the sample characteristics, data acquisition methods, and MRI scanner models vary across sites and datasets. This non-neural variability obscures neural ...

Black Forest Labs launches Flux.2 AI image models to challenge Nano Banana Pro and Midjourney

While Black Forest Labs previously launched with and made a name for itself on open source text-to-image models in its Flux family, today's release includes one fully open-source component: the Flux.2 ...