This repository contains the weights and code for
Causal-JEPA (C-JEPA), a simple and flexible object-centric world model architecture presented in the paper
Causal-JEPA: Learning World Models through Object-Level Latent Interventions.
World models require robust relational understanding to support prediction, reasoning, and control. While object-centric representations provide a useful abstraction, they are not sufficient to capture interaction-dependent dynamics. C-JEPA is a simple and flexible object-centric world model that extends masked joint embedding prediction from image patches to object-centric representations. By applying object-level masking that requires an object's state to be inferred from other objects, C-JEPA induces latent interventions with counterfactual-like effects and prevents shortcut solutions, making interaction reasoning essential.
C-JEPA relies on object-centric encoders (like VideoSAUR or SAVi) to extract representations. For detailed environment setup, dataset preparation, and training/evaluation scripts, please refer to the
official GitHub repository. The repository also provides model checkpoints and pre-extracted slot representations for various configurations.
1@article{nam2026causal,
2 title={Causal-JEPA: Learning World Models through Object-Level Latent Interventions},
3 author={Nam, Heejeong and Le Lidec, Quentin and Maes, Lucas and LeCun, Yann and Balestriero, Randall},
4 journal={arXiv preprint arXiv:2602.11389},
5 year={2026}
6}
