world model

Gaode’s General-Purpose World Model Workshop enables users to quickly generate highly realistic AI digital worlds—capable of real-time interaction and stable operation for hours—using text and images. It can be deployed locally with a single RTX 5090, and its core model has been fully open-sourced.

AliQianwen, the first native language world model released on June 24, 2026, uses plain text to uniformly simulate seven major digital environments, allowing agents to practice in a "virtual world."

Focusing on the independent development of an embodied intelligence world model, the company creates a "digital brain" for robots that understands the laws of physics and supports real-time interaction. It is the first company in China to directly apply a world model to robotic applications.

Amap has launched the world’s first native 3D city world model. By inputting satellite imagery or text, it can generate a kilometer-scale 3D city on a consumer-grade graphics card in just 10 minutes—ready for direct import into game engines.

Google introduces an experimental AI world model that instantly generates and explores interactive 3D virtual worlds via text or images, geared toward creative, gaming and research scenarios.

DeepMind's advanced world model generates interactive, physically logical 3D virtual environments in real time from textual cues, and is widely used in gaming, education, and AGI research.