这篇论文提出 AdaJEPA，能让世界模型在测试时自动适应，一次梯度步就大幅提升规划成功率，解决分布偏移问题。
AdaJEPA 是一种自适应潜在世界模型，在模型预测控制 (MPC) 闭环内执行测试时自适应。它利用观测到的下一状态转换作为自监督适应信号，无需额外专家演示即可持续校准世界模型。在多个目标达成任务中，AdaJEPA 仅需每个 MPC 重规划步一次梯度更新即可显著提升规划成功率。
AdaJEPA: An Adaptive Latent World Model
Latent world models enable planning from high-dimensional observations by predicting future states in a compact latent space. However, these models are typically kept frozen at test time: when their predictions become inaccurate, planning can fail, especially under test-time distribution shift. To address this, we propose AdaJEPA, an adaptive latent world model that performs test-time adaptation within the closed loop of model predictive control (MPC). After training, AdaJEPA plans and executes the first action chunk, uses the observed next-state transition as a self-supervised adaptation signal, and replans with the updated model. This closed-loop update continuously recalibrates the world model without additional expert demonstrations. Across a range of goal-reaching tasks, AdaJEPA substantially improves planning success with as few as one gradient step per MPC replanning step.