multimodal — A model that works with more than text — reading images, audio, or video, and sometimes generating them too.
AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.
Why it matters
Open-sourced text/image/video-to-interactive-3D-world generation with exports aimed at game engines and embodied simulation. It provides a route to synthetic environments for robotics and AI agentAn AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.Full definition → training without hand-building scenes.
