Teaching AI to Understand the Physical World, with Dr. Fei-Fei Li of World Labs

**Sarah** (0:05)
Hi, listeners, and welcome back to No Priors. Today's guest is Dr. Fei-Fei Li, a pioneer in computer vision and deep learning. She created ImageNet, the groundbreaking data set that helped spark the deep learning revolution. Fei-Fei is a Stanford professor and the co-director of the Stanford Institute for Human-Centered AI. She's also led AI Google Cloud, advised international policymakers, and recently co-founded World Labs, a company dedicated to developing spatially intelligent AI. Fei-Fei, thank you for joining us today.

**Fei-Fei Li** (0:33)
Well, thanks for inviting me. This is going to be fun.

**Sarah** (0:36)
So you have made extraordinary contributions to science and policy over the past two decades. I'll start with the biggest question, why start a company now?

**Fei-Fei Li** (0:46)
Because in my heart, I want to build. I see this as such a critical and fun and exciting moment to build some extraordinary technology that everybody can use. And I believe so much in spatial intelligence and the kind of 3D world models that can empower so many people as well as so many use cases. And I think that's just, it's going to be really exciting. And I can do that with an extraordinary, extraordinarily brilliant group of young technologists.

**Sarah** (1:23)
I want to come back to, you know, the people you're working with, because I know some of your co-founders and was, you know, trying to convince them desperately to start a company a while back. And then they're like, oh, no, we have a bigger mission now with Fei-Fei. What is spatial intelligence? Can you define it for a broader audience?

**Fei-Fei Li** (1:40)
Spatial intelligence to me is the ability to to understand reason and interact and generate 3D worlds, because our world fundamentally, no matter how you say, we can project it, fundamentally, it's 3D. And it's 3D because physically it's 3D. And digitally, if there is a true 3D representation, then we can make a lot of things happen more easily, whether it's designing or creation or navigation or simulation or the experiencing of AR, VR. All this to me is part of spatial intelligence. And again, I think it's what really excites me is humans have spatial intelligence.
It's part of our core intelligent capabilities. Animals have a spatial intelligence. The entire journey of evolution also is deeply intertwined with the evolution of spatial intelligence. So it's so fundamental. Without spatial intelligence, AI would be incomplete.

**Elad** (2:54)
How does that translate into what you're doing with your company? Or is there anything you can share in terms of what that means relative to what you're building?

**Fei-Fei Li** (2:59)
Yeah. So we're cracking one of the hardest problem in AI, which is actually making world models that are fundamentally 3D. Because once you can crack that problem, you can unlock a lot of spatial intelligence problems. So we are the first company we know of that is solving the 3D generation of a nation model problem.

**Sarah** (3:28)
I have many questions, but since you are describing this first as 3D's criticality to understanding the world, does that imply you feel that the world models that World Labs will create or others in academia or in companies will create, will someday be realistically accurate, like represent physics and understand the world that we can do many more things with?

**Fei-Fei Li** (3:59)
Yeah, it should. It should be realistically accurate or plausible, so you can create a fantastical world, but it should be plausible because the geometry and the physics of it need to be plausible.
And that is fundamental to spatial intelligence.

**Sarah** (4:18)
Does that imply you have a particular point of view from a neuroscience perspective of how fundamental visual... I mean, you've always been a leader in computer vision, right? But in how important visual intelligence is versus, let's say, like large language models and textual intelligence?

**Fei-Fei Li** (4:40)
I actually do. I think from a neural and cognitive science point of view, that spatial intelligence is a really hard problem that evolution has to solve for animals. And what's really interesting is, I think animals have solved it to an extent, but not fully solved it. It's one of the hardest problems because what is the problem animal has to solve? Animals have to evolve the capability of collecting lights in something which we call eyes mostly. And then with that collection of eyes, it has to reconstruct a 3D world in their mind somehow, so that they can navigate and they can do things. And of course, they can interact. For humans, we're the most capable animal in terms of manipulation. We can do a lot of things. And all this is spatial intelligence. To me, that's just rooted in our intelligence. What is interesting is, it's not a fully solved problem, even in animals. We, for example, for humans, right?