发表机构
FAIR at Meta; Chandar Research Lab; Mila - Quebec AI Institute; Polytechnique Montréal（Meta FAIR; Chandar 研究实验室; Mila - 魁北克人工智能研究所; 蒙特利尔理工学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
RoboJEPA基于JEPA架构，在12种机器人形态数据上训练，发现想象误差随计算量呈二阶幂律缩放，可预测下游规划性能，并支持零样本长时程规划，为多形态机器人世界模型建立缩放定律。
AI 中文摘要
潜在世界模型在预测未来状态和现实世界规划方面展现出了卓越的能力。然而，在实践中，我们缺乏一种原则性的方法来估计其能力如何随模型规模、数据和计算量扩展，这一开放问题阻碍了该领域的进展。在这项工作中，我们提出了RoboJEPA，一种基于联合嵌入预测架构（JEPA）的世界模型，并在涵盖12种机器人形态的大规模数据集上进行了训练。我们表明，RoboJEPA的想象误差，即其潜在滚动的误差，遵循计算量的二阶幂律，使我们能够预测远超该定律拟合规模的模型质量。我们进一步表明，下游机器人规划性能随计算量可预测地提升，且想象误差与其强相关，使其成为真实机器人评估的可靠代理。最后，我们证明了潜在世界模型可以零样本部署为机器人代理，通过规划朝向单一目标图像来解决真实硬件上需要长时程规划的任务。我们发布了所有模型检查点以及训练和机器人部署代码。据我们所知，这是首个为基于真实机器人数据训练的多形态机器人世界模型建立缩放定律的工作，而拥有80亿参数的RoboJEPA是迄今训练的最大的JEPA预测模型。
英文摘要
Latent world models have shown a remarkable ability to predict future states and to plan in the real world. In practice, however, we lack a principled way to estimate how their capabilities scale with model size, data, and compute, an open problem that slows progress in the field. In this work we present RoboJEPA, a world model based on the Joint Embedding Predictive Architecture (JEPA) and trained on a large-scale dataset spanning 12 robotic embodiments. We show that RoboJEPA's imagination error, the error of its latent rollouts, follows a second-order power law in compute, allowing us to predict model quality well beyond the scale at which the law is fit. We further show that downstream robotic planning performance improves predictably with compute, and that imagination error is strongly correlated with it, making it a reliable proxy for real-robot evaluation. Finally, we demonstrate that latent world models can be deployed zero-shot as robotic agents, planning toward a single goal image to solve tasks requiring long-horizon planning on real hardware. We release all model checkpoints together with our training and robot deployment code. To our knowledge, this is the first work to establish scaling laws for multi-embodiment robotic world models trained on real robot data, and RoboJEPA, at 8B parameters, is the largest JEPA predictor model trained to date.
