Disclosure certainty 4/5 debate potential 1/5

Li: World Labs was founded to build spatial intelligence beyond LLMs

Fei-Fei Li · After LLMs: Spatial Intelligence and World Models — Fei-Fei Li & Justin Johnson, World Labs · Nov 25, 2025 · at 2:14

Fei-Fei Li and Justin Johnson discuss the origins and founding focus of their startup, World Labs.

0:00 / 0:30exact quote · 30.8s
▶ Watch the full episode on YouTube → 720p mp4 · rendered on demand · StarZero watermark
“I think around, you know, more than two years ago, for sure, I think both independently, both of us have been looking at the development of the large models and thinking about What's beyond language models and this idea of building world models, spatial intelligence really was natural for us. So we started talking and decided that we should just put all the eggs in one basket and focus on solving this problem and started world apps together.”

quote is from the automated transcript, cleaned for reading: filler sounds and stutters are removed, nothing is rephrased. names can be misheard (the analysis reads context, assessments check outside sources). how →

More from Fei-Fei Li

Assertion Not checkable as stated
Li: Marble is the first public high-fidelity 3D generative world model
“It's the first in-class model in the world that generates three D worlds in this level of fidelity that is in the hands of the public.”
Fei-Fei Li Nov 25, 2025 ▶ 31:06 After LLMs: Spatial Intelligence and World Models — Fei-Fei Li & Justin Johnson, World Labs
Insight
Li: LLMs can predict physical trajectories without abstracting physical laws
“I wouldn't be surprised that given enough celestial movement data, an LLM would actually predict pretty accurate movement trajectories... I wouldn't be surprised, but F equals MA or, you know, action equals reaction. That's just a whole different abstraction l…”
Fei-Fei Li Nov 25, 2025 ▶ 52:48 After LLMs: Spatial Intelligence and World Models — Fei-Fei Li & Justin Johnson, World Labs
Opinion
Li: 3D and 4D spatial structure is fundamentally unlike 1D text
“I do think the architecture of these generative models will share a lot of shareable components, but I think the deeply three D four D spatial world has a level Of structure that is fundamentally different from a purely generative signal that is one dimensiona…”
Fei-Fei Li Nov 25, 2025 ▶ 21:10 After LLMs: Spatial Intelligence and World Models — Fei-Fei Li & Justin Johnson, World Labs
Opinion
Li: Scaling can bridge visual generative AI and physical engineering
“I think this is a matter of scaling data and bettering model. I don't think there's anything fundamental that separates these two.”
Fei-Fei Li Nov 25, 2025 ▶ 27:58 After LLMs: Spatial Intelligence and World Models — Fei-Fei Li & Justin Johnson, World Labs
Opinion
Li: Marble has real potential to generate synthetic data for robotics
“Marble actually is a, Really potential for helping to generate these synthetic simulated worlds for embodied agent training.”
Fei-Fei Li Nov 25, 2025 ▶ 40:13 After LLMs: Spatial Intelligence and World Models — Fei-Fei Li & Justin Johnson, World Labs
Prediction Not checkable as stated
Li: World models will move beyond sequence-to-sequence architectures
“I think sequence to sequence is actually in world models, I think we are going to see algorithm or architecture beyond sequence to sequence.”
Fei-Fei Li Nov 25, 2025 ▶ 56:27 After LLMs: Spatial Intelligence and World Models — Fei-Fei Li & Justin Johnson, World Labs
Made with StarZero

Turn any episode into a week of clips.

This entire site, over 200 episodes transcribed, diarized, checked and made playable, runs on the StarZero media pipeline. Drop in your own episode and the podcast clipper finds the moments worth sharing, cuts them, captions them, and reframes them for every feed.