NAVI-Orbital demonstrates Gemma 3 vision-language model in orbit

Arxiv CS.AI (top papers)

NAVI-Orbital runs Google's Gemma 3 vision-language model on Loft Orbital's YAM-9 satellite, performing onboard inference to prioritize data downlink. This is the first in-orbit demonstration of a VLM for autonomous Earth observation.

GemmaEarth observation

See 1 more source

A satellite is now running Google's Gemma 3 vision-language model in orbit, doing onboard inference instead of downlinking everything first3 days agoJustgototheeffinmoonDiscuss

Arxiv CS.AI (top papers)·Juan Manuel Delfa VictoriaTaran Cyriac JohnAndrew W. Herson

Jun 18, 4:00 AM