Unifying Variational Autoencoder (VAE) implementations in Pytorch (NeurIPS 2022)

Optimus: the first large-scale pre-trained VAE language model

VAE with RealNVP prior and Super-Resolution VAE in PyTorch. Code release for https://arxiv.org/abs/2006.05218.

Generative models (GAN, VAE, Diffusion Models, Autoregressive Models) implemented with Pytorch, Pytorch_lightning and hydra.

moai is a PyTorch-based AI Model Development Kit (MDK) created to improve data-driven model workflows, design and reproducibility.

Official PyTorch implementation of A Quaternion-Valued Variational Autoencoder (QVAE).

A Variational Autoencoder in PyTorch for the CelebA Dataset.

Pytorch implementation of Gaussian Mixture Variational Autoencoder GMVAE

Codebase for the paper: Not All Neuro-Symbolic Concepts Are Created Equal: Analysis and Mitigation of Reasoning Shortcuts

LeanVAE: An Ultra-Efficient Reconstruction VAE for Video Diffusion Models

Variational Autoencoder (VAE)-based molecular SMILES string generator

Codes for paper: CVQVAE: A REPRESENTATION LEARNING METHOD FOR MULTI-OMICS SINGLE CELL DATA INTEGRATION

Implementation of LiteVAE

A collection of research paper implementations in PyTorch

[WIP] RL agent for the SuperTuxKart game.

A new version of world models using Echo-state networks and random weight-fixed CNNs

Symbol emergence using Variational Auto-Encoder and Gaussian Mixture Model (Inter-GMM-VAE)~VAEを活用した実画像からの記号創発~

Pytorch Implementation of Hou, Shen, Sun, Qiu, "Deep Feature Consistent Variational Autoencoder", 2016

Implementation of CVAE. Trained CVAE on faces from UTKFace Dataset to produce synthetic faces with a given degree of happiness/smileyness.

Code to reproduce the results of the ICML 2022 paper "Mitigating Modality Collapse in Multimodal VAEs via Impartial Optimization."