Vision2h ago
NAVI-Orbital Deploys Vision-Language Model In Orbit
On April 16, 2026, NAVI-Orbital achieved the first in-orbit demonstration of a vision-language model performing autonomous inference on a spacecraft. Using Gemma 3, the system classifies scenes and generates text descriptions entirely onboard. This eliminates downlink bottlenecks. Practitioners can now execute complex multi-modal queries without waiting for ground-station processing.