AI 中文总结
提出溯因世界建模框架，通过分层状态金字塔从预测未来中推断潜在因果，提升物理预测、因果推理和动作理解性能。
AI 中文摘要
世界建模的核心挑战在于学习能够捕捉世界如何演化的表征。然而，现有的世界模型主要表征未来状态，而没有明确捕捉其演化背后的潜在原因，这限制了它们推理世界为何及如何变化的能力。为解决这一局限，我们提出溯因世界建模（AWM），一个通过从预测的未来中溯因地推断潜在原因来学习结构化因果表征的框架。具体而言，我们通过分层溯因状态金字塔（HASP）实现AWM，该金字塔将推断出的世界状态组织为三个互补的组成部分——实体、动态和关系——分别捕捉存在什么、如何变化以及实体如何交互。通过联合推理当前观测及其预测的未来，HASP溯因地推断这些潜在因素，并将它们整合为用于下游推理的结构化状态表征。据我们所知，AWM是首个将溯因状态推断引入潜空间世界建模以学习世界动态结构化表征的框架。在物理预测、因果推理和动作理解上的实验证明了我们方法的有效性。与最先进的潜空间世界模型V-JEPA相比，AWM在物理预测AUROC上提高了10.7%，因果推理准确率提高了16.8%，动作Top-1准确率提高了68.0%。
英文摘要
The central challenge of world modeling is to learn representations that capture how the world evolves. However, existing world models predominantly represent future states without explicitly capturing the latent causes underlying their evolution, limiting their ability to reason about why and how the world changes. To address this limitation, we propose Abductive World Modeling (AWM), a framework that learns structured causal representations by abductively inferring latent causes from predicted futures. Specifically, we realize AWM through the Hierarchical Abductive State Pyramid (HASP), which organizes the inferred world state into three complementary components - Entity, Dynamic, and Relation - capturing what exists, how it changes, and how entities interact, respectively. By jointly reasoning over the current observation and its predicted future, HASP abductively infers these latent factors and integrates them into a structured state representation for downstream reasoning. To the best of our knowledge, AWM is the first framework to introduce abductive state inference into latent-space world modeling for learning structured representations of world dynamics. Experiments across physical prediction, causal reasoning, and action understanding demonstrate the effectiveness of our approach. Compared with V-JEPA, a state-of-the-art latent-space world model, AWM improves physical prediction AUROC by 10.7%, causal reasoning accuracy by 16.8%, and action Top-1 accuracy by 68.0%.
Comments21 pages, 4 figures
