This repository serves as a curated, categorized, and dated list of deep learning research papers, with a focus on identifying state-of-the-art contributions. It is intended for researchers, engineers, and students seeking to navigate the rapidly evolving landscape of deep learning literature across various domains like computer vision, natural language processing, and audio synthesis. The primary benefit is a structured overview of influential papers, often with direct links to their arXiv versions or associated code.

How It Works

The project organizes deep learning papers by task and date, providing permanent links to either arXiv or a repository copy. Each entry includes the paper's title, date, and a link to its paper (often arXiv) and, where available, its code repository. This structured approach allows users to quickly identify seminal works, track progress within specific subfields, and access implementations for reproducibility or further experimentation.

Quick Start & Requirements

This repository is a curated list and does not require installation or execution. It serves as a reference guide.

Highlighted Details

• Papers are categorized into major areas: Code, Text, Visual, Audio, and Other.
• Within each category, papers are further sub-categorized by specific tasks (e.g., Visual: Object Recognition, Image Captioning; Text: Summarization, Translation).
• Many entries include direct links to associated code repositories (e.g., GitHub), facilitating practical application and verification.
• The list includes seminal papers like "Attention Is All You Need," "BERT," "YOLOv3," and "U-Net."

Maintenance & Community

The repository is maintained by sbrugman. Contributions are welcomed via pull requests for adding or updating paper information and code links.

Licensing & Compatibility

The repository itself is likely under a permissive license (e.g., MIT, Apache 2.0) given its nature as a curated list. However, the licensing of the linked papers and code repositories varies and must be checked individually.

Limitations & Caveats

The repository prioritizes open-access versions (arXiv) over potentially peer-reviewed, published versions, advising users to verify the authoritative source. Some linked code repositories may be outdated, difficult to reproduce, or lack comprehensive documentation.