We present EB-JEPA, an open-source library for learning representations and world models using Joint-Embedding Predictive Architectures (JEPAs). JEPAs learn to predict in representation space rather than pixel space, avoiding the pitfalls of generative modeling while capturing semantically meaningful features suitable for downstream tasks. Our library provides modular, self-contained implementations that illustrate how representation learning techniques developed for image-level self-supervised learning can transfer to video, where temporal dynamics add complexity, and ultimately to action-conditioned world models, where the model must additionally learn to predict the effects of control inputs. Each example is designed for single-GPU training within a few hours, making energy-based self-supervised learning accessible for research and education. We provide ablations of JEA components on CIFAR-10. Probing these representations yields 91% accuracy, indicating that the model learns useful features. Extending to video, we include a multi-step prediction example on Moving MNIST that demonstrates how the same principles scale to temporal modeling. Finally, we show how these representations can drive action-conditioned world models, achieving a 97% planning success rate on the Two Rooms navigation task. Comprehensive ablations reveal the critical importance of each regularization component for preventing representation collapse. Code is available at https://github.com/facebookresearch/eb_jepa.

翻译：我们提出了EB-JEPA，这是一个开源库，用于通过联合嵌入预测架构（JEPAs）学习表征和世界模型。JEPA在表征空间而非像素空间中进行预测，避免了生成式建模的陷阱，同时捕获适用于下游任务的语义上有意义的特征。我们的库提供了模块化、自包含的实现，展示了为图像级自监督学习开发的表征学习技术如何迁移到视频（其中时间动态性增加了复杂性），并最终迁移到动作条件的世界模型（其中模型还必须学习预测控制输入的效果）。每个示例设计为在单GPU上数小时内完成训练，使基于能量的自监督学习在研究和教育中易于使用。我们在CIFAR-10上对JEPA组件进行了消融实验。对这些表征进行探测取得了91%的准确率，表明模型学习了有用的特征。扩展到视频，我们包含了一个Moving MNIST上的多步预测示例，展示了相同原理如何扩展到时间建模。最后，我们展示了这些表征如何驱动动作条件的世界模型，在Two Rooms导航任务上达到了97%的规划成功率。全面的消融实验揭示了每个正则化组件在防止表征坍塌中的关键重要性。代码可在https://github.com/facebookresearch/eb_jepa获取。