This repository is an "awesome list" curating research papers on layout generation, a multi-modal problem involving the creation of visual arrangements for flyers, magazines, UIs, and images. It serves researchers and practitioners in computer vision and graphic design by cataloging key advancements and providing links to papers and code.

How It Works

The list compiles papers that explore various techniques for layout generation, including Transformer-based diffusion models, large multimodal models, and generative adversarial networks (GANs). These approaches aim to achieve content-aware, controllable, and aesthetically pleasing layout designs, often by leveraging large language models or diffusion processes for synthesis.

Quick Start & Requirements

This is a curated list of research papers and does not involve direct installation or execution. Links to papers and associated code repositories are provided for each entry.

Highlighted Details

• Comprehensive collection of papers from 2014 to 2024, covering major conferences like CVPR, ECCV, NeurIPS, and ICLR.
• Includes links to both research papers and, where available, associated code repositories for reproducibility.
• Features a variety of methodologies, from early GANs and VAEs to recent diffusion models and LLM-based approaches.
• Organised chronologically by publication year for easy tracking of research progression.

Maintenance & Community

The list is maintained by JosephKJ and actively seeks contributions via pull requests to expand its coverage.

Licensing & Compatibility

The repository itself is likely under a permissive license (e.g., MIT, Apache 2.0) as is common for "awesome lists," but the linked papers and code repositories will have their own specific licenses.

Limitations & Caveats

The list explicitly states it is not exhaustive and relies on community contributions for updates. It serves as a directory of research rather than a runnable software project.