Key-Gram: Extensible World Knowledge for Embodied Manipulation

arXiv:2605.18556v1 Announce Type: cross Abstract: Embodied control increasingly requires models to follow compositional language instructions while reasoning over dynamic visual states. However, current vision-language-action policies and world-action models often couple linguistic knowledge with visual computation in a shared backbone or conditioning pathway, leading to modality competition and making knowledge extension dependent on backbone updates. In this paper, we introduce Key-Gram, a con