galilai-group/stable-worldmodel
A platform for reproducible world model research and evaluation
Python2.1K stars260 forks+362 today
Topics
#deep-learning#pytorch#jepa#world-model#model-predictive-control
What it does
stable-worldmodel is a Python platform designed to facilitate reproducible research and evaluation of world models in AI, providing standardized environments and tools for data collection, training, and model-predictive control evaluation.
Star history
Not enough history yet — 1 day(s) recorded. The daily snapshot builds this up.
Tracking
- Last trending
- 2026-05-30
Creator kit
Hook
Elevate your world model research with stable-worldmodel - a unified platform for reproducible studies and evaluations. #AI #MachineLearning
Content angles
- Create tutorials on how to use stable-worldmodel for training and evaluating world models.
- Publish case studies demonstrating the effectiveness of using stable-worldmodel in real-world applications.
- Develop comparative analyses showcasing different world model approaches within the stable-worldmodel framework.
Who should care
AI researchers, machine learning engineers, academics, and developers interested in reproducible research and evaluation of world models.