Causal-JEPA：通过对象级潜在掩码学习世界模型
Causal-JEPA: Learning World Models through Object-Level Latent Masking
AI总结：
提出C-JEPA，一种通过对象级潜在掩码扩展联合嵌入预测的对象中心世界模型，在视觉问答和智能体控制任务中分别提升反事实推理20%和仅用1%潜在特征实现高效规划。
摘要：
世界模型需要稳健的关系理解以支持预测、推理和控制。虽然对象中心表示提供了有用的抽象，但不足以捕捉依赖交互的动态。因此，我们提出C-JEPA，一种简单灵活的对象中心世界模型，将掩码联合嵌入预测从图像块扩展到对象中心表示。通过掩码对象级潜在变量并要求每个掩码对象状态从周围上下文中推断，C-JEPA在训练期间施加了结构化的部分可观测性，创建了类似反事实的预测查询，阻止捷径解决方案，并在学习目标下使依赖交互的预测成为必要。实验上，C-JEPA在视觉问答中取得了一致的提升，与没有对象级掩码的相同架构相比，反事实推理绝对提高了约20%。在智能体控制任务中，C-JEPA仅使用基于块的世界模型所需总潜在输入特征的1%，即可实现相当的性能，从而实现了更高效的规划。最后，我们提供了形式化分析，证明对象级掩码通过控制可观测性引入了有用的归纳偏置。我们的代码可在https://github.com/galilai-group/cjepa获取。
英文摘要：
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. We therefore propose C-JEPA, a simple and flexible object-centric world model that extends masked joint embedding prediction from image patches to object-centric representations. By masking object-level latents and requiring each masked object state to be inferred from the surrounding context, C-JEPA imposes structured partial observability during training, creating counterfactual-like prediction queries that discourage shortcut solutions and make interaction-dependent prediction necessary under the learning objective. Empirically, C-JEPA leads to consistent gains in visual question answering, with an absolute improvement of about 20% in counterfactual reasoning over the same architecture without object-level masking. On agent control tasks, C-JEPA enables substantially more efficient planning by using only 1% of the total latent input features required by patch-based world models, while achieving comparable performance. Finally, we provide a formal analysis demonstrating that object-level masking induces useful inductive bias by controlling observability. Our code is available at https://github.com/galilai-group/cjepa.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
