kevinghst/H-JEPA

LeWAM: End-to-End World and Action Modeling with JEPAs

Official code for AdaJEPA: An Adaptive Latent World Model

Code, data and weights for the paper **What drives success in physical planning with Joint-Embedding Predictive World Models?**

[ECCV 2026] VLA-JEPA: Enhancing Vision-Language-Action Model with Latent World Model

Mastering Diverse Domains through World Models

INTACT: Isomorphic Intent-to-Action Learning for Search-Free World Models.

An open source library designed to provide community examples of Joint Embedding Predictive Architectures (JEPAs). It contains code and examples for learning representations from images, video, and action-conditioned video, as well as planning using JEPA-based models.

Official code base for LeWorldModel: Stable End-to-End Joint-Embedding Predictive Architecture from Pixels