Tag: Vision language models

First VLM in Orbit: Loft YAM-9 Satellite Runs Google DeepMind Gemma 3 to Find Objects Autonomously

In April 2026, Loft Orbital's YAM-9 satellite became the first spacecraft to run a vision-language model (VLM) in orbit. NASA JPL's NAVI-Orbital software ran Google DeepMind's Gemma 3 to classify satellite imagery from natural language queries without downloading data to Earth.