World Labs

“Modeling the two D projections of a dynamic three D world is, is a function that probably can be modeled, but by putting a three D representation into the heart of a model, there's just going to be a better fit between the kind of representation that the model…”

“Because we already have the ability to create virtual interactive worlds but it costs hundreds and hundreds of millions of dollars and a ton of development time.”

“The time has come that concentrated industry Grade effort, focus effort in terms of compute data talent is, is really the answer to bringing this to life.”

“Like, this statefulness and persistence is so key in how people think about spatial reasoning and, like, developing an environment over time. Like, people don't think in this ephemeral, like, generate a thing, like, just throw it away, keep my text prompts. Li…”

“I'm taking captures I did with 2000 images of a multi room house and taking it down to like 30, 40 inputs and the fly through looks like basically the same. And this is just like totally inconceivable before. And it's all enabled by building this gracefully sc…”

“But I think that's something we're kind of realizing, and Ben was talking about this earlier today, is, like, new view prediction, this primitive that we have in Atlas, especially generative new view prediction, this is also AI complete.”

“And this is a really fundamental primitive that we think is super exciting, a super new primitive For base models that no one's ever done before, right?”

“It also works on camera poses as a native input to the model, which I don't think anyone's ever done at the pre-training phase before.”

“Each time we made the model bigger and each time we trained it for longer, each time we put it on more chips, like it got significantly better.”

“Atlas is our new next generation world model. It has three basic things. It can generate, reconstruct, and simulate the world.”

“So, so we do believe very strongly that next viewpoint prediction is, is the equivalent of next token prediction.”

“It's the first time we have a unification of pixel generation and pixel reconstruction.”

“You can do this in sequence because it's an autoregressive model. It's up to you, right, to kind of pick and choose what you add interactively into the context as you generate.”

“I don't think there's a single person out there using one monolithic model, not even C dance or whatever for their entire task. People will have this, like, you know, kind of bunch of storyboards and mood boards of images they pull out from, like, their favori…”

“So, so in the, on the path to spatial intelligence, generating pixels is definitely a early step, which we have seen with What you call it, gazillions of models. But generating pixels that are truly spatially contextualized and grounded is absolutely another m…”

“I think we're basically at the beginning, and we're basically limited by compute at this point, right? Like, data is very important, as Fei-Fei likes to point out, but, like, everything has a bottleneck, and I think the main bottleneck on continuing to scale t…”

“But now with Atlas, we can do this with just as few, through three cameras. So like no studio capture, no green screen, no expensive calibration. We can literally stick like three cameras on tri, three iPhones on tripods use these to take sort of a video of so…”

“You can input one or multiple up to a hundred frames that are views of the real world, and use those to reconstruct the real world, and that reconstruction can take the case either of a novel, a video flying through the space, or an explicit three-D reconstruc…”

“And I do believe Atlas is a significant step forward because now with every single frame, you have a, you can generate and estimate an important piece of information, which is the view, viewpoint, the camera pose, and that is the most critical information one …”

“There was no scaling law of spatial intelligence.”