grounding — Tying a model's answers to checkable sources — retrieved documents, live data, tool results — instead of letting it answer from memory alone.
context window — The maximum amount of text a model can consider at once — its working memory for the current conversation or task.
Why it matters
Atlas takes camera geometry as a native input rather than text hints, generates up to a minute of 1440p video from as little as one image, and produces explicit 3D output for real-to-sim robotics work. It will power future Marble releases.
