SCALE：用于正确几何空间中JEPA规划的状态校准潜在嵌入
Reperesentation Geometry Matters for Planning with JEPA World Models
浏览论文内容
中文总结 AI 辅助
该研究提出SCALE正则化器，为LeWM表示校准几何属性，在多任务、多求解器和多计算预算下均提升规划性能，证明规划依赖信息对几何的塑造作用。
中文摘要 AI 辅助
联合嵌入预测世界模型通过基于表示本身定义的代价，将预测的终端嵌入与目标嵌入进行评分来规划。获取非坍塌表示的两种突出策略是继承预训练特征空间（如DINO-WM），以及使用反坍塌正则化端到端学习嵌入（如带有SIGReg的LeWorldModel，简称LeWM）。这些策略在不同任务上展现出互补优势。虽然从两种模型的完整嵌入中都能解码出与任务相关的状态信息，但DINO-WM的主成分通常比LeWM保留更多状态信息。由于欧几里得规划代价由高方差方向主导，这一差异会影响状态对候选选择的影响强度。我们提出SCALE（State-CAlibrated Latent Embeddings，状态校准潜在嵌入），为端到端的LeWM表示赋予在DINO-WM中观察到的有利几何属性。SCALE通过将采样的成对潜在距离与标准化任务相关状态空间中的距离相关联来诱导该属性，且不替换LeWM的学习编码器。在5个任务、3种规划求解器和5种计算预算下，SCALE在每个任务-求解器组合上的平均性能均优于LeWM。潜在到状态回归控制与SCALE的完整嵌入可解码性相当或更优，但基本未改变潜在-状态距离对齐，且规划增益的一致性更低。SCALE仅添加一个轻量级训练时正则化器，无规划时开销。这些结果表明，规划不仅取决于是否存在任务相关信息，还取决于该信息是否塑造了规划器所使用的几何空间。
英文摘要
Joint-embedding predictive world models support planning through latent predictions, but unconstrained joint training can collapse distinct observations to identical embeddings. Two prominent strategies for avoiding collapse are to inherit pretrained features, as in DINO-WM, or to learn representations end-to-end with anti-collapse regularization, as in LeWorldModel (LeWM). Yet avoiding collapse does not ensure that latent distances distinguish outcomes in ways that matter for the task. In object manipulation, for example, success depends on the object's position and orientation relative to the goal. Such task-relevant state information can remain accurately decodable while barely influencing latent distance. The resulting planning cost may fail to reflect how close a predicted outcome is to the task goal. In this paper, we propose SCALE (State-CAlibrated Latent Embeddings), a method that correlates sampled pairwise latent distances with distances in task-relevant state space. Added to LeWM's existing objective, SCALE preserves its architecture, requires privileged state only during training, and adds no planning-time computation. We show that SCALE improves planning success over LeWM across manipulation and navigation tasks with multiple solvers and provide a comprehensive analysis of how SCALE reshapes representation geometry to support planning.
发表机构
- Boston University（波士顿大学）
- Unity Technologies（Unity科技公司）
机构由 AI 辅助整理，请以论文原文为准。
