Beyond Multimodal Alignment: Certifying Physical Language through Response Substitution and Ordered Execution
Research
Source: arXiv cs.ROPublish time unverified
arXiv:2608.19492v1 Announce Type: cross Abstract: World models increasingly treat compact multimodal representations as interfaces between perception and physical interaction, yet existing probes do not establish whether different sensors carry the same executable meaning or whether that meaning survives a new action composition.