Li: 3D and 4D spatial structure is fundamentally unlike 1D text
Fei-Fei Li · After LLMs: Spatial Intelligence and World Models — Fei-Fei Li & Justin Johnson, World Labs · Nov 25, 2025 · at 21:10
Fei-Fei Li, co-founder of World Labs, discusses the differences between generative language models and physical world models.
0:00 / 0:24exact quote · 24.0s
▶ Watch the full episode on YouTube → 720p mp4 · rendered on demand · StarZero watermark
“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 dimensional.”
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
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.”
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…”
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.”
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.”