AbdelStark/jepa-rs

Joint Embedding Predictive Architecture for World Models, written in Rust.

35
/ 100
Emerging

This project helps machine learning researchers build and experiment with 'world models' that learn about images and videos. You feed it raw image or video data, and it learns to predict hidden information within that data by understanding underlying patterns. It's designed for researchers working on advanced AI models, particularly those interested in self-supervised learning for visual data.

Use this if you are an AI researcher or machine learning engineer looking to implement or experiment with Joint Embedding Predictive Architectures (JEPA) for understanding complex visual data without explicit labels.

Not ideal if you are looking for a high-level, pre-packaged solution for standard image classification or object detection, or if you prefer working exclusively within a Python ecosystem.

AI research self-supervised learning computer vision video understanding representation learning
No Package No Dependents
Maintenance 10 / 25
Adoption 6 / 25
Maturity 11 / 25
Community 8 / 25

How are scores calculated?

Stars

8

Forks

1

Language

Rust

License

MIT

Last pushed

Mar 13, 2026

Monthly downloads

4

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/AbdelStark/jepa-rs"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.