
World Labs, founded by Fei-Fei Li, launched Atlas, a 3D world model.
Atlas generates and simulates environments from text and video.
It aims to give AI spatial understanding for robotics.
What happened
World Labs, founded by Stanford professor Fei-Fei Li, unveiled Atlas, a multimodal world model that can generate, reconstruct, and simulate 3D environments from text, images, and video.
Why it matters
This moves AI beyond 2D content into full 3D simulation, which could be important for robotics and immersive applications. The model is designed to help machines understand and interact with physical spaces, not just generate media.
What to watch
Fei-Fei Li presented Atlas at the HumanX Conference 2026 in San Francisco, highlighting its role in advancing spatial intelligence for AI and robotics.
Ask the AI about this article →
Fei-Fei Li, a prominent AI researcher, is pushing the field toward spatial intelligence through World Labs. The unveiling of Atlas represents a shift from text and image generation to understanding and simulating the physical world in 3D. This capability could underpin future robotics applications, where AI must navigate and manipulate real or simulated environments.
The model's ability to work from text, images, and video suggests it can learn from diverse inputs to create coherent spatial representations. While the announcement notes the design goals and presentation at HumanX 2026, specific performance metrics or availability were not disclosed in the article body. The long-term significance may hinge on how well Atlas performs relative to other emerging world models, though the body provides no comparison or benchmark data at this stage.
For example, today's edition would include:
AI-summarized, only the topics you pick — one digest a day via Email, Slack, or Discord.
Free · takes 30 seconds · unsubscribe anytimeWhat is AIToday? →
Ask AI anything about this article. Q&As are published on this page for other readers too.
Solomon Technology, a Taiwanese AI 3D vision company, is showcasing two key inspection applications at Semicon…

Caterpillar announced a collaboration with FieldAI to deploy physical AI, autonomy, robotics, and NVIDIA-power…

At Commercial UAV Expo in Las Vegas, FAA officials said routine BVLOS (beyond visual line of sight) drone oper…

Caterpillar is collaborating with FieldAI to advance physical AI, autonomy, and robotics for jobsites and fact…

Renesas Electronics announced it has opened a Physical AI & Robotics Lab in Beijing, China

AWS Japan held the final presentation event for its “Physical AI Development Support Program by AWS Japan,” an…
