Signal and structure
RF I/Q paired with machine-readable labels and generation provenance.
Research direction
A staged path toward models that can connect raw RF, structured scene truth, and verified natural-language descriptions.
RF I/Q paired with machine-readable labels and generation provenance.
Natural-language annotations grounded in structured scene truth and checked before release.
Radar, satellite and navigation, spectrum environments, and wireless sensing—each only promoted when evidence supports it.
Language annotations will be generated from traceable scene structure, checked for schema and evidence compatibility, and qualified before they are presented as a corpus modality. “Next” describes the intended research sequence, not a release date.
Radar, satellite and navigation, spectrum environments, and wireless sensing remain under development. We publish no class counts, specifications, availability, or dates for those domains until the work supports them.