This repository is a curated list of academic papers, code, and resources related to "World Models" in AI. It targets researchers, engineers, and practitioners in fields like General Video Generation, Embodied AI, and Autonomous Driving, providing a comprehensive overview of the state-of-the-art and emerging trends.

How It Works

This repository functions as a structured bibliography, categorizing papers by their application area and contribution type (e.g., foundational, surveys, benchmarks). It aims to consolidate research efforts, enabling users to quickly identify relevant work and understand the landscape of world model development.

Quick Start & Requirements

This is a curated list of papers and does not require installation or execution. Links to papers, code, and websites are provided for each entry.

Highlighted Details

• Extensive coverage of recent (2024-2025) research papers.
• Categorization across General World Models, Embodied AI, VLA, and Autonomous Driving.
• Includes dedicated sections for Surveys and Benchmarks & Evaluation.
• Provides direct links to papers, code repositories, and project websites where available.

Maintenance & Community

The repository is maintained by leofan90. Contributions are welcomed via pull requests or email. A citation format is provided for users who find the resource useful.

Licensing & Compatibility

The repository itself is a list of links and does not have a specific software license. Individual papers and code repositories are subject to their own licenses.

Limitations & Caveats

This is a curated list and does not represent a runnable software project. The quality and availability of linked code or resources depend on the original authors. The rapid pace of research means the list may require frequent updates to remain fully comprehensive.