A Chinese retailer's free model draws the world as you walk into it.
The Chinese retailer JD.com released a world model called JoyAI-Echo WM in Beijing on 9 September. The company says it makes 720p video, sound and speech as the viewer moves, and tops a navigation test. JD open-sourced the model and is planning a home-built cluster of 100,000 AI chips.
Why it mattersWorld models are the base layer for robots, games and self-driving, and this one is free. A shopping company shipping one shows the work has spread past the big AI labs.
▶ Related video: World Models: The Frontier of Physical AI | Physical AI Day at SIGGRAPH 2026
Read in the app — free, in 9 languages
Related stories
Google's newest world model builds worlds you can hear and talk to.2026-10-28OpenAI's new mid-size model costs half as much as the one before.
2026-10-27Block's new voice AI learned to talk without reading any text.
2026-10-25Moonshot's new Kimi trails only three models on an independent index.
2026-10-24A free Chinese image model passed a million downloads in a week.
2026-10-23