A unified open-source codebase for advanced world models, integrating perception-centered world-model methods across visual generation, reasoning, VLA, and simulation-related tasks.

An interactive notebook-based breakdown of the MiniMind codebase, designed to make the training pipeline and implementation details of small language models easier to study from scratch.

A Datawhale open-source project providing practical toy-code implementations for classical machine learning methods, accompanying hands-on study of Machine Learning by Zhihua Zhou.