更好的槽，更好的世界：以对象为中心的世界模型中的表示质量与鲁棒性
Better Slots, Better Worlds: Representation Quality & Robustness in Object-Centric World Models
浏览论文内容
中文总结 AI 辅助
该研究通过受控实验分析以对象为中心的世界模型，发现槽质量与规划成功率正相关，槽绑定良好时可减少辅助输入，且在分布偏移下其鲁棒性优于LeWM，预训练特征是鲁棒性关键因素。
中文摘要 AI 辅助
从离线轨迹学习世界模型可使智能体通过规划完成不同任务。以对象为中心（OC）的表示方法将场景分解为一组绑定到场景中对象的槽，该方法被提出作为一种归纳偏置，用于构建更具样本效率、泛化能力更强的世界模型。然而，现有的以对象为中心的世界模型（OCWM）将槽编码器视为给定部分，且仅在分布内进行评估，这使得以对象为中心的归纳偏置是否确实对规划有帮助，以及OCWM中哪些部分驱动了该特性仍不明确。我们针对视觉模型预测控制中的OCWM开展了一项受控研究，研究围绕两个维度展开：以对象为中心的表示质量，以及与以场景为中心的模型相比在分布偏移下的泛化能力。我们发现：（i）规划成功率与无监督槽质量指标（FG-ARI、mBO）呈正相关，不过在槽质量较高时该增益会达到饱和；（ii）当槽绑定良好时，现有方法所依赖的辅助本体感受输入和掩码归纳偏置不再必要；（iii）在未见过的分布偏移下，槽绑定良好的OCWM整体上比端到端训练的以场景为中心的LeWM更鲁棒，而基于类似冻结预训练特征构建的DINO-WM仍具有竞争力——这表明预训练特征是鲁棒性的关键贡献因素。
英文摘要
Learning world models from offline trajectories enables agents to accomplish different tasks through planning. Object-centric (OC) representations, which decompose a scene into a set of slots that bind to its objects, have been proposed as an inductive bias for world models that are more sample-efficient and generalize better. Yet prior object-centric world models (OCWMs) take the slot encoder as given and evaluate only in-distribution, leaving open whether the object-centric bias actually delivers for planning and what within the OCWM drives it. We conduct a controlled study of OCWMs for visual model-predictive control along two axes: object-centric representation quality and generalization under distribution shift relative to scene-centric models. We find that (i) planning success correlates positively with unsupervised slot-quality metrics (FG-ARI, mBO), though the gains saturate at high slot quality; (ii) with well-bound slots, the auxiliary proprioception inputs and masking inductive bias that prior methods relied on become unnecessary; and (iii) under unseen distribution shifts, the OCWM with well-bound slots is more robust overall than the end-to-end trained scene-centric LeWM, while DINO-WM, built on similar frozen pretrained features, remains competitive -- pointing to pretrained features as a key contributor to robustness.
