Fei-Fei Li on spatial intelligence and large world models
Tip: use the player's CC button to enable or switch subtitles; English captions are available on these videos.
| Item | Details |
|---|---|
| Speaker | Fei-Fei Li × Emily Chang |
| Channel | Bloomberg Live |
| Date | Jun 4, 2026 |
| Duration | 18:22 |
| Format | Video |
| Topics | #vision · #multimodal |
Why it matters
The 'Godmother of AI' Fei-Fei Li — Stanford professor, World Labs CEO, ImageNet creator — focuses on her new direction: spatial intelligence. Teaching AI not just to read text but to see the world, understand 3D space, and predict physical interactions. From 'making AI see' to 'making AI act', she explains the turning point.
Key takeaways
- Language intelligence is only half of AI — spatial intelligence is the other half: understanding the 3D world is the necessary path to AGI.
- Large World Models (LWM) don't just generate 3D scenes — they understand physical laws: gravity, occlusion, motion.
- From 'seeing' to 'doing': spatial intelligence = perception + reasoning + action — benefiting robotics, AR, and design.
- ImageNet taught AI to recognize objects; World Labs is teaching AI to understand the world.
- Academic research and productization need to run in parallel: Stanford taught her that 'curiosity-driven research + real-world product feedback' is the best loop.
Original video
- Speaker
- Fei-Fei Li × Emily Chang
- Channel
- Bloomberg Live
- Venue
- Bloomberg Tech 2026, San Francisco
- Date · Duration
- Jun 4, 2026 · 18:22
World Labs' Fei-Fei Li on Creating Large World Models
Watch the original on YouTubeSources & Further Reading
This page is grounded in the authoritative sources below — verifiable and citable by AI engines and readers.
- 👤 Person: Fei-Fei Li × Emily Chang
- # Topic: Computer VisionVisual understanding, generation and robotics
- # Topic: MultimodalUnderstanding across text, image, audio and video
Citation: Please attribute Laojin Global (laojinchuhai.com) and keep the original link.
Made by Laojin · AI that ships
365SkillAn agent-skills lab: 13 in-house skills
365Skill is our public lab for agent skills: a standard SKILL.md format, a deny-by-default publish policy, and an evals harness. It holds 13 original 365 skills — 11 public and 2 internal. Apache-2.0 — star it, install it, file issues.
More from Laojin: Sellenca · 365AIOrg · AllModelsAPI · 365Loopa · 365 Ops
Related
Linked by topic, people and hubs