Improve model card for C-JEPA

README.md

@@ -1,8 +1,49 @@
 ---
 license: apache-2.0
-datasets:
-  - user/dataset-name
-base_model: user/model-name
 paper_ids:
-  - "2602.11389"
----
+- '2602.11389'
+pipeline_tag: image-feature-extraction
+datasets:
+- clevrer
+- pusht
+tags:
+- object-centric
+- world-models
+- causal-inference
+- jepa
+- representation-learning
+- vision
+---
+
+# C-JEPA: Causal-JEPA
+
+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](https://huggingface.co/papers/2602.11389).
+
+*   **Paper:** [Causal-JEPA: Learning World Models through Object-Level Latent Interventions](https://huggingface.co/papers/2602.11389)
+*   **Project Page:** [https://hazel-heejeong-nam.github.io/cjepa/](https://hazel-heejeong-nam.github.io/cjepa/)
+*   **Code:** [https://github.com/galilai-group/cjepa](https://github.com/galilai-group/cjepa)
+
+## Summary
+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.
+
+Empirically, C-JEPA demonstrates:
+*   **Improved Visual Reasoning:** Consistent gains in visual question answering, with an absolute improvement of about 20% in counterfactual reasoning compared to the same architecture without object-level masking on benchmarks like CLEVRER.
+*   **Efficient Planning:** Substantially more efficient planning in agent control tasks (e.g., Push-T), using only 1% of the total latent input features required by patch-based world models while achieving comparable performance.
+*   **Causal Inductive Bias:** A formal analysis demonstrates that object-level masking induces a causal inductive bias via latent interventions.
+
+## Architecture
+![architecture](https://hazel-heejeong-nam.github.io/cjepa/static/architecture.png)
+
+## Setup and Usage
+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](https://github.com/galilai-group/cjepa). The repository also provides model checkpoints and pre-extracted slot representations for various configurations.
+
+## Citation
+If you find this work useful, please consider citing:
+```bibtex
+@article{nam2026causal,
+  title={Causal-JEPA: Learning World Models through Object-Level Latent Interventions},
+  author={Nam, Heejeong and Le Lidec, Quentin and Maes, Lucas and LeCun, Yann and Balestriero, Randall},
+  journal={arXiv preprint arXiv:2602.11389},
+  year={2026}
+}
+```