Загрузка видео...

Не удалось загрузить видео

Возникла проблема при загрузке этого видео. Это может быть связано с временными проблемами сети или видео может быть недоступно.

На главную

Fei-Fei Li on what simulation can do for robotics that real-world data can't: "You play out events that haven't happened, or cannot happen... And while you play it out, you learn how to act in it." "That's really important in robotics, because we cannot possibly have enough real-world data... show more

a16z

1,075,885 subscribers

35,772 просмотров • 1 месяц назад •via X (Twitter)

Наука и технологии

Anya Rossi• Live Now

Private livecam show

Комментарии: 9

Фото профиля Oleg Bilozor

Oleg Bilozor1 месяц назад

The thing that gets me is 'events that cannot happen.' You're not just filling data gaps, you're training on physics edge cases that would take decades to encounter in the real world, if they ever happened at all.

Фото профиля sindikitil

sindikitil1 месяц назад

Simulation lets you stress-edge cases that'd take decades to hit in meatspace. The long-tail distribution problem.

Фото профиля Winston B.

Winston B.1 месяц назад

Billions of hours of simulation only matter if they're the scenarios that almost never happen on real roads, the ones that decide whether a policy holds up under pressure. Same case for robotics generally. The data you need most is the data you'd otherwise wait years to collect naturally, so simulation ends up being the only practical way to get it.

Фото профиля 踏空 Sidelined Capital

踏空 Sidelined Capital1 месяц назад

The expensive part is deciding which impossible events teach robustness and which teach the robot to exploit a simulator bug.

Фото профиля Bobby

Bobby1 месяц назад

Semper Fidelis

Фото профиля Fred Almeida

Fred Almeida1 месяц назад

I was doing this in 2016. Nothing new. We were even coding at the kernal level to improve the number of simulations. in 2017 we were at 12x the speed of 2016. We thought everyone was doing this (imposter syndrome sucks) but they weren't. Today we can train in an hour (constrained RL + SP + CL) what would take 1000 years in real world data. Even at the edge of the technology. People still don't understand this. Almost everyone that thinks they understand AI but haven't worked in it for the last 15 years will have a hard time understanding the foundations.

Фото профиля Ted | unfair.so

Ted | unfair.so1 месяц назад

training robots by building worlds = minecraft

Фото профиля PromptKing | Evidence & Integrity for Agentic AI

PromptKing | Evidence & Integrity for Agentic AI1 месяц назад

The same logic applies to agent governance. You cannot wait for the model swap, the budget breach, or the unauthorized escalation to discover whether the boundary held. You have to play the trajectory out first — under the actual policy — before the work is allowed to run. That’s why simulate-before-enforce exists. The events that would break the proof are the ones you must never let happen for real. One outcome. Many models. One law. One proof.

Фото профиля Our Ascent Live

Our Ascent Live1 месяц назад

The future of robotics should not only be technically intelligent @drfeifei. It should be publicly shaped. Citizen-led. AI-enhanced. 📡🗽

Похожие видео

World Labs CEO Dr. Fei-Fei Li & SceniX Co-Founder Yunzhu Li on the data bottleneck in robotics and how world models help: "The lack of data in training, the lack of data in evaluation, this is very, very different from language models, where data is abundant on the internet." "And we know that in order for robotics to work, we have to somehow unlock the power of scaling law. But where does that come from?" "It's a profound problem that everybody's battling with in robotics." "We see a lot of unlock in being able to do this whole process through the modeling of the environments." "Being able to create these digital worlds... that's just going to unlock so much more potential for being able to replace all the costly and the unsafe data in the real environments with the data generated from the worlds for robots to be able to do scalable learning and evaluations." Fei-Fei Li Yunzhu Li martin_casado

World Labs CEO Dr. Fei-Fei Li & SceniX Co-Founder Yunzhu Li on the data bottleneck in robotics and how world models help: "The lack of data in training, the lack of data in evaluation, this is very, very different from language models, where data is abundant on the internet." "And we know that in order for robotics to work, we have to somehow unlock the power of scaling law. But where does that come from?" "It's a profound problem that everybody's battling with in robotics." "We see a lot of unlock in being able to do this whole process through the modeling of the environments." "Being able to create these digital worlds... that's just going to unlock so much more potential for being able to replace all the costly and the unsafe data in the real environments with the data generated from the worlds for robots to be able to do scalable learning and evaluations." Fei-Fei Li Yunzhu Li martin_casado

a16z

77,024 просмотров • 1 месяц назад

Fei-Fei Li (Fei-Fei Li) on limitations of LLMs. "There's no language out there in nature. You don't go out in nature and there's words written in the sky for you.. There is a 3D world that follows laws of physics." Language is purely generated signal.

Fei-Fei Li (Fei-Fei Li) on limitations of LLMs. "There's no language out there in nature. You don't go out in nature and there's words written in the sky for you.. There is a 3D world that follows laws of physics." Language is purely generated signal.

Rohan Paul

1,854,092 просмотров • 1 год назад

World Labs CEO Dr. Fei-Fei Li explains says "world model" has become an overloaded term & explains what each kind of world model does: "Right now there are three ways of calling world models when it comes to spatial intelligence." "One is what I call a renderer, when the model puts beautiful pixels on the screen." "Another kind of world model is what we call a planner. That is more for machines, more for robots." "The third kind, which I think is the linchpin of the three, is a simulator." "A simulator could become a renderer. The simulator could become a planner. But this layer is a huge critical path to unlock spatial intelligence. And that's what World Labs is working on." Fei-Fei Li at Bloomberg Tech live with Emily Chang

World Labs CEO Dr. Fei-Fei Li explains says "world model" has become an overloaded term & explains what each kind of world model does: "Right now there are three ways of calling world models when it comes to spatial intelligence." "One is what I call a renderer, when the model puts beautiful pixels on the screen." "Another kind of world model is what we call a planner. That is more for machines, more for robots." "The third kind, which I think is the linchpin of the three, is a simulator." "A simulator could become a renderer. The simulator could become a planner. But this layer is a huge critical path to unlock spatial intelligence. And that's what World Labs is working on." Fei-Fei Li at Bloomberg Tech live with Emily Chang

a16z

112,217 просмотров • 3 месяцев назад

The moment is right to push forward into a new frontier for AI — one that is as fundamental as language, says Fei-Fei Li. That frontier is visual spatial intelligence. With Justin Johnson (Justin Johnson), her cofounder at World Labs, and a16z's martin_casado, Fei-Fei explains what unlocking this technology could mean, and why we’re in the midst of a “Cambrian explosion”:

The moment is right to push forward into a new frontier for AI — one that is as fundamental as language, says Fei-Fei Li. That frontier is visual spatial intelligence. With Justin Johnson (Justin Johnson), her cofounder at World Labs, and a16z's martin_casado, Fei-Fei explains what unlocking this technology could mean, and why we’re in the midst of a “Cambrian explosion”:

a16z

476,992 просмотров • 2 лет назад

I don't know if you really understand what these people just did... They built an AI that looks at a few casual real-world videos or photos and instantly turns them into a full 3D playground. You can MOVE THE CAMERA HOWEVER YOU WANT, change the lighting, move objects around, and even let physics play out like in the real world. View events from impossible angles because Atlas knows what was there. This is massive! Let's take robotics. Until now training robots meant collecting tons of expensive real-world data. Now a handful of recordings can become thousands of different simulated situations. Robots can practice the same task in new rooms, with different objects and lighting without anyone having to film it all again. For the industry it means we can train robots way faster and cheaper. Home robots, warehouse robots, whatever... they can learn new environments at scale instead of staying stuck in the lab. This is one of the first real bridges between “cool AI video models” and actual physical machines that have to work in the real world. Blog: The team behind World Labs: Fei-Fei Li, Justin Johnson, Ben Mildenhall and Yunzhu Li. The video is from David Pantera. Follow for more insights into robotics and AI. —— Weekly robotics and AI insights. Subscribe free:

I don't know if you really understand what these people just did... They built an AI that looks at a few casual real-world videos or photos and instantly turns them into a full 3D playground. You can MOVE THE CAMERA HOWEVER YOU WANT, change the lighting, move objects around, and even let physics play out like in the real world. View events from impossible angles because Atlas knows what was there. This is massive! Let's take robotics. Until now training robots meant collecting tons of expensive real-world data. Now a handful of recordings can become thousands of different simulated situations. Robots can practice the same task in new rooms, with different objects and lighting without anyone having to film it all again. For the industry it means we can train robots way faster and cheaper. Home robots, warehouse robots, whatever... they can learn new environments at scale instead of staying stuck in the lab. This is one of the first real bridges between “cool AI video models” and actual physical machines that have to work in the real world. Blog: The team behind World Labs: Fei-Fei Li, Justin Johnson, Ben Mildenhall and Yunzhu Li. The video is from David Pantera. Follow for more insights into robotics and AI. —— Weekly robotics and AI insights. Subscribe free:

Ilir Aliu

271,773 просмотров • 13 дней назад

Today at Stanford, Fei-Fei Li (Fei-Fei Li),Cofounder/CEO World Labs, gave one of the clearest explanations I’ve heard of what a World Model really is. She broke it down into three layers: 1️⃣ Rendering — What does the world look like? This is where most of today’s video generation models operate: generating increasingly realistic and beautiful pixels. The question is: Can AI generate what the world looks like? The primary consumer is humans. 2️⃣ Simulation — How does the world actually work? Fei-Fei gave a simple example: “How will this bottle move? If I pour the water out, how will the water flow?” This goes far beyond generating something that looks realistic. The model needs to understand physics, spatial relationships, cause and effect, and how the world changes over time. The consumers are both humans and machines. 3️⃣ Planning — What should happen next? This is where things get really interesting. AI doesn't just render the world or simulate what might happen. It uses its understanding of the world to decide: What should I do next? At this layer, the primary consumer is the machine itself. And this connects directly to two enormous opportunities: Autonomous driving and robotics. The progression is powerful: Rendering → Simulation → Planning The real promise of World Models isn't simply generating better videos. It's building AI that can understand the world, predict what happens next, and ultimately take intelligent action in the physical world.

Today at Stanford, Fei-Fei Li (Fei-Fei Li),Cofounder/CEO World Labs, gave one of the clearest explanations I’ve heard of what a World Model really is. She broke it down into three layers: 1️⃣ Rendering — What does the world look like? This is where most of today’s video generation models operate: generating increasingly realistic and beautiful pixels. The question is: Can AI generate what the world looks like? The primary consumer is humans. 2️⃣ Simulation — How does the world actually work? Fei-Fei gave a simple example: “How will this bottle move? If I pour the water out, how will the water flow?” This goes far beyond generating something that looks realistic. The model needs to understand physics, spatial relationships, cause and effect, and how the world changes over time. The consumers are both humans and machines. 3️⃣ Planning — What should happen next? This is where things get really interesting. AI doesn't just render the world or simulate what might happen. It uses its understanding of the world to decide: What should I do next? At this layer, the primary consumer is the machine itself. And this connects directly to two enormous opportunities: Autonomous driving and robotics. The progression is powerful: Rendering → Simulation → Planning The real promise of World Models isn't simply generating better videos. It's building AI that can understand the world, predict what happens next, and ultimately take intelligent action in the physical world.

PaulFang

11,470 просмотров • 1 месяц назад

Fei-Fei Li: “There’s nothing artificial about AI. It’s inspired by people. It’s created by people. And most importantly, it impacts people.” Watch the full interview with World Labs CEO Fei-Fei Li on Lenny's Podcast (Lenny Rachitsky):

Fei-Fei Li: “There’s nothing artificial about AI. It’s inspired by people. It’s created by people. And most importantly, it impacts people.” Watch the full interview with World Labs CEO Fei-Fei Li on Lenny's Podcast (Lenny Rachitsky):

a16z

63,672 просмотров • 10 месяцев назад

World Labs CEO Dr. Fei-Fei Li says AI must change how we teach and evaluate students: "AI must change learning. AI must change K-16 learning." "The most precious resource of our entire world is human capital." "When we have gotten the technology that can answer standardized tests... when AI can do better than an average human, it's not about humans are bad. It's about we need to change the education system." "We need to change how we evaluate. We need to change the way we empower teachers to educate the next generation of students where they can use these tools, be empowered, and do things that we can never imagine." "All of the kids today should not be scared of AI. They should feel the human agency to lead AI, to use AI in the right way, and to use AI to make the impact that they want to make for the world." Fei-Fei Li at Bloomberg Tech live with Emily Chang

World Labs CEO Dr. Fei-Fei Li says AI must change how we teach and evaluate students: "AI must change learning. AI must change K-16 learning." "The most precious resource of our entire world is human capital." "When we have gotten the technology that can answer standardized tests... when AI can do better than an average human, it's not about humans are bad. It's about we need to change the education system." "We need to change how we evaluate. We need to change the way we empower teachers to educate the next generation of students where they can use these tools, be empowered, and do things that we can never imagine." "All of the kids today should not be scared of AI. They should feel the human agency to lead AI, to use AI in the right way, and to use AI to make the impact that they want to make for the world." Fei-Fei Li at Bloomberg Tech live with Emily Chang

a16z

81,845 просмотров • 3 месяцев назад

World Labs CEO Fei-Fei Li on the need for world models: "There's no language out there. You don't go out in nature and there's words written in the sky for you." "There is a 3D world out there that follows laws of physics, that has its own structures due to materials. To fundamentally back that information out and be able to represent it and be able to generate it is just fundamentally quite a different problem." "We will be borrowing useful ideas from language and LLMs, but this is fundamentally, philosophically a different problem."

World Labs CEO Fei-Fei Li on the need for world models: "There's no language out there. You don't go out in nature and there's words written in the sky for you." "There is a 3D world out there that follows laws of physics, that has its own structures due to materials. To fundamentally back that information out and be able to represent it and be able to generate it is just fundamentally quite a different problem." "We will be borrowing useful ideas from language and LLMs, but this is fundamentally, philosophically a different problem."

a16z

202,274 просмотров • 13 дней назад

World Labs co-founders Justin Johnson and Dr. Fei-Fei Li say LLMs use next-token prediction, but spatial intelligence has its own equivalent: Justin: "The soft definition of AI-completeness is there's this fundamental primitive that's an AI task. But if I could solve this AI task in its full, broadest generality, it would solve any intelligence problem." "The classic example in LLMs is that next-token prediction is AI-complete... I think from Ilya: there's a mystery novel, the thing has to read the whole novel, and the final sentence is, 'And the killer was.' Predict the next token. You could basically frame any kind of intelligence task in terms of that." "So clearly next-token prediction is something people believe is AI-complete." "New-view prediction, this primitive that we have in Atlas, especially generative new-view prediction, is also AI-complete." "I want to have a world where Martin is writing a proof of the Riemann hypothesis on the blackboard, and then the camera pans over to the next whiteboard." Fei-Fei: "Evolution had to solve new-viewpoint prediction by making animals move. Nature gave animals eyes, but nature didn't give trees eyes. Why? Because when you move, you see a new viewpoint... We do believe very strongly that next-viewpoint prediction is the equivalent of next-token prediction." Justin Johnson Fei-Fei Li martin_casado

World Labs co-founders Justin Johnson and Dr. Fei-Fei Li say LLMs use next-token prediction, but spatial intelligence has its own equivalent: Justin: "The soft definition of AI-completeness is there's this fundamental primitive that's an AI task. But if I could solve this AI task in its full, broadest generality, it would solve any intelligence problem." "The classic example in LLMs is that next-token prediction is AI-complete... I think from Ilya: there's a mystery novel, the thing has to read the whole novel, and the final sentence is, 'And the killer was.' Predict the next token. You could basically frame any kind of intelligence task in terms of that." "So clearly next-token prediction is something people believe is AI-complete." "New-view prediction, this primitive that we have in Atlas, especially generative new-view prediction, is also AI-complete." "I want to have a world where Martin is writing a proof of the Riemann hypothesis on the blackboard, and then the camera pans over to the next whiteboard." Fei-Fei: "Evolution had to solve new-viewpoint prediction by making animals move. Nature gave animals eyes, but nature didn't give trees eyes. Why? Because when you move, you see a new viewpoint... We do believe very strongly that next-viewpoint prediction is the equivalent of next-token prediction." Justin Johnson Fei-Fei Li martin_casado

a16z

87,299 просмотров • 9 дней назад

For all of history, humanity shared one 3D world. World Labs co-founder Fei-Fei Li says spatial intelligence now lets us generate and reconstruct infinite universes for creativity, travel, storytelling, even socialization. “It suddenly will enable us to live in a multiverse way.”

For all of history, humanity shared one 3D world. World Labs co-founder Fei-Fei Li says spatial intelligence now lets us generate and reconstruct infinite universes for creativity, travel, storytelling, even socialization. “It suddenly will enable us to live in a multiverse way.”

a16z

204,131 просмотров • 1 год назад

Old footage sitting in your camera roll could now be reconstructable as a 3D scene. World Labs co-founders Ben Mildenhall and Fei-Fei Li on how Atlas got there: Ben: "In a casual sense... I took three photos of this object, or six photos of this room. I look at the photos, I can understand in my mind how those piece together. I can fill in the gaps and get it." "But there's never really been any reconciliation between those data-driven priors and the brute force dense reconstruction, which is much more akin to scientific or medical imaging... When we say dense, we really mean dense." "This room, I want like 100, 200, 300 photos to capture it. And what we're trying to do is bring that down to like three. We're saying like 50, 100x reduction." "At that scale it completely flips that calculus on its head of what type of captures you reconstruct. You can go back to existing imagery you have. You can go to stuff you find on the internet and even build scenes out of that. You can go to casual videos and unearth a lot of footage that in the past we would never have treated as reconstructable, and bring it to life as 3D." "This is something we've been playing around with a lot with Atlas. Taking old clips. I've taken a bunch of my own old captures that never worked before and put them through the system and seen a reconstruction for the first time." Fei-Fei: "The Stanford demo is underappreciated. Anywhere between 3 to 25 images, you can reconstruct that entire Stanford quad... Everything you see is generated, but according to the laws of reconstruction. And this is really magical." Ben Mildenhall Fei-Fei Li

Old footage sitting in your camera roll could now be reconstructable as a 3D scene. World Labs co-founders Ben Mildenhall and Fei-Fei Li on how Atlas got there: Ben: "In a casual sense... I took three photos of this object, or six photos of this room. I look at the photos, I can understand in my mind how those piece together. I can fill in the gaps and get it." "But there's never really been any reconciliation between those data-driven priors and the brute force dense reconstruction, which is much more akin to scientific or medical imaging... When we say dense, we really mean dense." "This room, I want like 100, 200, 300 photos to capture it. And what we're trying to do is bring that down to like three. We're saying like 50, 100x reduction." "At that scale it completely flips that calculus on its head of what type of captures you reconstruct. You can go back to existing imagery you have. You can go to stuff you find on the internet and even build scenes out of that. You can go to casual videos and unearth a lot of footage that in the past we would never have treated as reconstructable, and bring it to life as 3D." "This is something we've been playing around with a lot with Atlas. Taking old clips. I've taken a bunch of my own old captures that never worked before and put them through the system and seen a reconstruction for the first time." Fei-Fei: "The Stanford demo is underappreciated. Anywhere between 3 to 25 images, you can reconstruct that entire Stanford quad... Everything you see is generated, but according to the laws of reconstruction. And this is really magical." Ben Mildenhall Fei-Fei Li

a16z

48,116 просмотров • 10 дней назад

Elon Musk in new interview on how Tesla’s Optimus robot will learn more quickly: "What we're going to need to do is build a lot of robots and put them in a kind of like a "Optimus Academy" so they can do self-play in reality. We're actually building that out. We're gonna have at least 10,000 Optimus robots, maybe 20,000 or 30,000, that are doing self-play and testing different tasks. Tesla has quite a good reality generator. A physics-accurate reality generator that we made for the cars. We'll do the same things for the robots, and actually have done that for the robots. You can do millions of simulated robots in a simulated world, and you use the tens of thousands in the real world to close the simulation to reality gap.”

Elon Musk in new interview on how Tesla’s Optimus robot will learn more quickly: "What we're going to need to do is build a lot of robots and put them in a kind of like a "Optimus Academy" so they can do self-play in reality. We're actually building that out. We're gonna have at least 10,000 Optimus robots, maybe 20,000 or 30,000, that are doing self-play and testing different tasks. Tesla has quite a good reality generator. A physics-accurate reality generator that we made for the cars. We'll do the same things for the robots, and actually have done that for the robots. You can do millions of simulated robots in a simulated world, and you use the tens of thousands in the real world to close the simulation to reality gap.”

Sawyer Merritt

250,956 просмотров • 7 месяцев назад

Fei-Fei Li ( Fei-Fei Li ) beautifully explains Robotics. She defines robotics not by form, like humanoids or cars, but by function: they are any "embodied machines" that must perceive, understand, and act within a physical, 3D space. This core requirement is "spatial intelligence," the unifying principle of all robotics, allowing them to perform tasks and even collaborate with humans. Throughout all of human history, we have been confined to a single, shared reality: the "physical Earth 3D world." This singularity has been our only playground. However, new technologies that combine 3D generation and reconstruction are shattering this limitation. We can now create "infinite universes"—a multiverse of digital worlds for countless purposes, from training robots to enabling creativity, travel, and storytelling. This leap from one physical world to an infinite multiverse unlocks boundless possibilities for human imagination and interaction. Video from a16z

Fei-Fei Li ( Fei-Fei Li ) beautifully explains Robotics. She defines robotics not by form, like humanoids or cars, but by function: they are any "embodied machines" that must perceive, understand, and act within a physical, 3D space. This core requirement is "spatial intelligence," the unifying principle of all robotics, allowing them to perform tasks and even collaborate with humans. Throughout all of human history, we have been confined to a single, shared reality: the "physical Earth 3D world." This singularity has been our only playground. However, new technologies that combine 3D generation and reconstruction are shattering this limitation. We can now create "infinite universes"—a multiverse of digital worlds for countless purposes, from training robots to enabling creativity, travel, and storytelling. This leap from one physical world to an infinite multiverse unlocks boundless possibilities for human imagination and interaction. Video from a16z

Rohan Paul

41,441 просмотров • 8 месяцев назад

Fei-Fei Li ( Fei-Fei Li ) beautifully explains Robotics. She defines robotics not by form, like humanoids or cars, but by function: they are any "embodied machines" that must perceive, understand, and act within a physical, 3D space. This core requirement is "spatial intelligence," the unifying principle of all robotics, allowing them to perform tasks and even collaborate with humans. Throughout all of human history, we have been confined to a single, shared reality: the "physical Earth 3D world." This singularity has been our only playground. However, new technologies that combine 3D generation and reconstruction are shattering this limitation. We can now create "infinite universes"—a multiverse of digital worlds for countless purposes, from training robots to enabling creativity, travel, and storytelling. This leap from one physical world to an infinite multiverse unlocks boundless possibilities for human imagination and interaction. Video from a16z

Fei-Fei Li ( Fei-Fei Li ) beautifully explains Robotics. She defines robotics not by form, like humanoids or cars, but by function: they are any "embodied machines" that must perceive, understand, and act within a physical, 3D space. This core requirement is "spatial intelligence," the unifying principle of all robotics, allowing them to perform tasks and even collaborate with humans. Throughout all of human history, we have been confined to a single, shared reality: the "physical Earth 3D world." This singularity has been our only playground. However, new technologies that combine 3D generation and reconstruction are shattering this limitation. We can now create "infinite universes"—a multiverse of digital worlds for countless purposes, from training robots to enabling creativity, travel, and storytelling. This leap from one physical world to an infinite multiverse unlocks boundless possibilities for human imagination and interaction. Video from a16z

Rohan Paul

51,174 просмотров • 4 месяцев назад

Language models process data as one-dimensional sequences of tokens — ideal for text, but limited for understanding the physical world. In contrast, spatial intelligence embraces a 3D representation, unlocking a deeper understanding of space and time. More from martin_casado's interview with Fei-Fei Li and Justin Johnson:

Language models process data as one-dimensional sequences of tokens — ideal for text, but limited for understanding the physical world. In contrast, spatial intelligence embraces a 3D representation, unlocking a deeper understanding of space and time. More from martin_casado's interview with Fei-Fei Li and Justin Johnson:

a16z

64,662 просмотров • 2 лет назад

One month into joining World Labs, it’s been incredible to witness Atlas come to life under the leadership of Justin Johnson, Ben Mildenhall, and Fei-Fei Li. 🚀 Proud to contribute on the robotics side and show how Atlas can bridge world models and physical AI: turning a few casual real-world recordings into interactive simulations with controllable objects, motions, lighting, and environments. And this is just the beginning. Very excited about what Atlas can unlock for robot learning at scale!! 🤖

One month into joining World Labs, it’s been incredible to witness Atlas come to life under the leadership of Justin Johnson, Ben Mildenhall, and Fei-Fei Li. 🚀 Proud to contribute on the robotics side and show how Atlas can bridge world models and physical AI: turning a few casual real-world recordings into interactive simulations with controllable objects, motions, lighting, and environments. And this is just the beginning. Very excited about what Atlas can unlock for robot learning at scale!! 🤖

Yunzhu Li

40,652 просмотров • 13 дней назад

"Visual-spatial intelligence is as fundamental as language." Fei-Fei Li says world models are the key to letting AI see the world, reason about it, interact with it, navigate it, and even 'build civilization upon it.' "It's very natural for me that World Labs' north star is to unlock spatial intelligence. The moment to me is right to do it." "We've got these ingredients—we've got compute, we've got a much deeper understanding of data, way deeper than [the ImageNet days]... and we've got some advancement of algorithms."

"Visual-spatial intelligence is as fundamental as language." Fei-Fei Li says world models are the key to letting AI see the world, reason about it, interact with it, navigate it, and even 'build civilization upon it.' "It's very natural for me that World Labs' north star is to unlock spatial intelligence. The moment to me is right to do it." "We've got these ingredients—we've got compute, we've got a much deeper understanding of data, way deeper than [the ImageNet days]... and we've got some advancement of algorithms."

a16z

32,387 просмотров • 6 месяцев назад

World Labs co-founders Justin Johnson and Dr. Fei-Fei Li say Atlas unifies the two things computer vision has always kept apart: Justin: "Historically, reconstruction has been its own subfield in computer vision with its own specialized tasks and models. Generation is what all the text-to-video models are really good at." "Those are great for creative applications if I want to imagine something that's never been there before." "But now with Atlas, for the first time, we're putting these two different parts of visual intelligence together in one model. It can do both 3D reconstruction and generation together in one architecture." "We had to make it multimodal from the start. This thing natively works on text, images, videos, and camera poses as a native input to the model... It uses 3D as a native modality that it works on." Fei-Fei: "Computer vision has been around for more than half a century... Our field traditionally has multiple tracks. You go to a computer vision conference: you have the pixel generation track, you have some recognition track, and you have a 3D reconstruction track." "This is an elegant model that unifies the problem of reconstruction and generation by anchoring on viewpoints and viewpoint estimation. That's just incredibly powerful." Justin Johnson Fei-Fei Li

World Labs co-founders Justin Johnson and Dr. Fei-Fei Li say Atlas unifies the two things computer vision has always kept apart: Justin: "Historically, reconstruction has been its own subfield in computer vision with its own specialized tasks and models. Generation is what all the text-to-video models are really good at." "Those are great for creative applications if I want to imagine something that's never been there before." "But now with Atlas, for the first time, we're putting these two different parts of visual intelligence together in one model. It can do both 3D reconstruction and generation together in one architecture." "We had to make it multimodal from the start. This thing natively works on text, images, videos, and camera poses as a native input to the model... It uses 3D as a native modality that it works on." Fei-Fei: "Computer vision has been around for more than half a century... Our field traditionally has multiple tracks. You go to a computer vision conference: you have the pixel generation track, you have some recognition track, and you have a 3D reconstruction track." "This is an elegant model that unifies the problem of reconstruction and generation by anchoring on viewpoints and viewpoint estimation. That's just incredibly powerful." Justin Johnson Fei-Fei Li

a16z

40,573 просмотров • 8 дней назад