SlotVLA: Towards Modeling of Object-Relation Representations in Robotic Manipulation

ArXi:2511.06754v3 Announce Type: replace-cross Inspired by how humans reason over discrete objects and their relationships, we explore whether compact object-centric and object-relation representations can form a foundation for multitask robotic manipulation. Most existing robotic multitask models rely on dense embeddings that entangle both object and background cues, raising concerns about both efficiency and interpretability. In contrast, we study object-relation-centric representations as a pathway to structured, efficient, and explainable visuomotor control.