This repository is a curated list of academic papers focusing on Variational Autoencoders (VAEs), disentanglement, representation learning, and generative models. It serves as a comprehensive literature resource for researchers and PhD students in machine learning and related fields, offering a structured overview of advancements in VAEs and their applications.

How It Works

The list is organized chronologically (newest to oldest) and includes papers covering various VAE-related topics, such as disentanglement, adversarial training, variational inference, and different types of VAE architectures (e.g., flow-based, autoregressive). The collection aims to provide a broad survey of the field, highlighting key research directions and methodologies.

Quick Start & Requirements

This is a curated list of papers, not a software library. No installation or specific requirements are needed to access the information. All papers are linked via arXiv or other academic repositories.

Highlighted Details

• Extensive Collection: Features approximately 900 papers, providing a deep dive into VAE research.
• Chronological Ordering: Facilitates tracking the evolution of VAE techniques and applications.
• Broad Topic Coverage: Encompasses VAEs, disentanglement, representation learning, variational inference, GANs, and more.
• Community Contribution: Open to contributions and suggestions for missing papers.

Maintenance & Community

The list is maintained by the repository owner, Matthew Vowels, who is actively seeking contributions to expand its scope.

Licensing & Compatibility

As a curated list of academic papers, it does not have a specific software license. Access to the papers is governed by their respective publishers or repositories.

Limitations & Caveats

The list is a static collection of links and does not include code implementations or experimental setups. Users must refer to the individual papers for practical application details.