Загрузка видео...

Не удалось загрузить видео

На главную

"Data stops being something you collect. It becomes something you compute." At #SIGGRAPH2026, Ming-Yu Liu, VP of NVIDIA's Cosmos Lab, laid out why world models are the data engine of physical AI. Plus, he announced Cosmos-Dreams, a neural closed-loop simulator, and showed off a full demo of it in...

NVIDIAAI's profile picture

NVIDIA AI

335,418 subscribers

15,693 просмотров • 1 месяц назад •via X (Twitter)

#SIGGRAPH2026
LIVE

Anya Rossi• Live Now

Private livecam show

Комментарии: 0

Нет доступных комментариев

Здесь появятся комментарии из оригинального поста

Похожие видео

Sat down with Rev Labaredian, VP of Omniverse & Simulation Technology @ NVIDIA, to discuss the age of physical AI, how companies are using NVIDIA's Cosmos models, and why Robotics continues to accelerate. Thank you to Rev NVIDIA Robotics NVIDIA Omniverse for taking the time!
17:04

Sat down with Rev Labaredian, VP of Omniverse & Simulation Technology @ NVIDIA, to discuss the age of physical AI, how companies are using NVIDIA's Cosmos models, and why Robotics continues to accelerate. Thank you to Rev NVIDIA Robotics NVIDIA Omniverse for taking the time!

amit

50,990 просмотров • 7 месяцев назад

1/7 Physical AI has a data problem. More compute alone won’t teach a robot how to move, grasp, react, or recover from mistakes. LLMs had the entire internet to learn from. Robots need something different: huge amounts of real action data. That’s where Axis Robotics gets interesting. $AXIS is building a data engine for Physical AI, turning robot training into something people can contribute to directly through a browser. The loop is straightforward: Generate → Collect → Process → Deploy → Correct → Repeat. What looks simple on the surface could become something much bigger underneath: a scalable way to produce the training data robots need to become genuinely useful in the physical world. The real unlock for Physical AI might not be another bigger model. It might be better data.
1:10

1/7 Physical AI has a data problem. More compute alone won’t teach a robot how to move, grasp, react, or recover from mistakes. LLMs had the entire internet to learn from. Robots need something different: huge amounts of real action data. That’s where Axis Robotics gets interesting. $AXIS is building a data engine for Physical AI, turning robot training into something people can contribute to directly through a browser. The loop is straightforward: Generate → Collect → Process → Deploy → Correct → Repeat. What looks simple on the surface could become something much bigger underneath: a scalable way to produce the training data robots need to become genuinely useful in the physical world. The real unlock for Physical AI might not be another bigger model. It might be better data.

_victorad

18,903 просмотров • 9 дней назад

It's easy for robots to nail a demo. It's much harder to get them to work reliably in the real world. The bottleneck is data. At Axis Robotics we're building a compounding data engine that combines simulation, ego-centric data and DAgger correction data at scale. Watch our CEO ChrisF(✱,✱) break down the data bottleneck, why messy data can still train good models, and what it takes to get robots out of the lab with blocmates. ⬇️
29:39

It's easy for robots to nail a demo. It's much harder to get them to work reliably in the real world. The bottleneck is data. At Axis Robotics we're building a compounding data engine that combines simulation, ego-centric data and DAgger correction data at scale. Watch our CEO ChrisF(✱,✱) break down the data bottleneck, why messy data can still train good models, and what it takes to get robots out of the lab with blocmates. ⬇️

Axis Robotics

22,634 просмотров • 23 дней назад

Explore where physical AI is headed next with the people shaping it. On Feb. 10 at 9 a.m. PT, join Ming‑Yu, Vice President of Research at NVIDIA, and Chubby♨️ from Superintelligence, for a conversation on how NVIDIA Cosmos reframes AI for a world of robots, AVs, and vision-driven systems. We'll dig into: ✅ Cosmos' origins and designing models for the physical world ✅ The scientific ideas and architectures behind Cosmos and its open models ✅ How open, reasoning-capable physical AI is changing how teams prototype, deploy, and iterate ✅ What a future of AI systems that understand space, time, and causality could unlock If you’re thinking into real‑world AI, this is the conversation to catch ➡️
0:39

Explore where physical AI is headed next with the people shaping it. On Feb. 10 at 9 a.m. PT, join Ming‑Yu, Vice President of Research at NVIDIA, and Chubby♨️ from Superintelligence, for a conversation on how NVIDIA Cosmos reframes AI for a world of robots, AVs, and vision-driven systems. We'll dig into: ✅ Cosmos' origins and designing models for the physical world ✅ The scientific ideas and architectures behind Cosmos and its open models ✅ How open, reasoning-capable physical AI is changing how teams prototype, deploy, and iterate ✅ What a future of AI systems that understand space, time, and causality could unlock If you’re thinking into real‑world AI, this is the conversation to catch ➡️

NVIDIA AI Developer

26,455 просмотров • 6 месяцев назад

NVIDIA just introduced Cosmos, a platform for world foundation models designed for robotics. ⦿ It features advanced tokenizers, an AI-accelerated data pipeline, and integration with NVIDIA Omniverse. Humanoid makers 1X, Figure, and Agility are among the first to adopt Cosmos. ⦿ Cosmos generates synthetic, physics-based data, accelerating model training and customization. ⦿ It also features a CUDA-accelerated data processing pipeline that enables developers to process, curate, and label 20 million hours of videos in 14 days using the NVIDIA Blackwell platform.
8:02

NVIDIA just introduced Cosmos, a platform for world foundation models designed for robotics. ⦿ It features advanced tokenizers, an AI-accelerated data pipeline, and integration with NVIDIA Omniverse. Humanoid makers 1X, Figure, and Agility are among the first to adopt Cosmos. ⦿ Cosmos generates synthetic, physics-based data, accelerating model training and customization. ⦿ It also features a CUDA-accelerated data processing pipeline that enables developers to process, curate, and label 20 million hours of videos in 14 days using the NVIDIA Blackwell platform.

The Humanoid Hub

129,481 просмотров • 1 год назад

This is THE moment of Physical AI! We are officially announcing Cosmos 3: Omnimodal World Models for Physical AI 🚀 - Cosmos 3 is an omnimodal world model: within a unified architecture, it can understand and generate language, images, video, audio, and actions. - It is not just a VLM, not just a video generator, not just an audio-visual generative model, and not just a physics simulator / world-action model. It can understand images and videos, generate images, videos, and audio, simulate future worlds, predict actions, and generate robot policies—enabling models to truly begin to “touch the world.” - Cosmos 3 is the #1 open-weight reasoner / T2I / I2V / robot policy across many benchmarks. Huge thanks to every teammate who fought side by side on this journey—from architecture, data, training, infra, serving, and evaluation to post-training. Every part of this project carries an incredible amount of hard work. This was my first time leading a project as Tech Lead, and I feel truly fortunate. The future of Physical AI needs models that can not only “see” and “describe” the world, but also “imagine,” “simulate,” and “act”—and eventually close the loop with the real world. I hope Cosmos 3 can become an important starting point for this direction, and I’m excited to push Physical AI into its next stage together with the open-source community. Welcome to the era of Physical AI. HuggingFace: Project Website: Code:
0:44

This is THE moment of Physical AI! We are officially announcing Cosmos 3: Omnimodal World Models for Physical AI 🚀 - Cosmos 3 is an omnimodal world model: within a unified architecture, it can understand and generate language, images, video, audio, and actions. - It is not just a VLM, not just a video generator, not just an audio-visual generative model, and not just a physics simulator / world-action model. It can understand images and videos, generate images, videos, and audio, simulate future worlds, predict actions, and generate robot policies—enabling models to truly begin to “touch the world.” - Cosmos 3 is the #1 open-weight reasoner / T2I / I2V / robot policy across many benchmarks. Huge thanks to every teammate who fought side by side on this journey—from architecture, data, training, infra, serving, and evaluation to post-training. Every part of this project carries an incredible amount of hard work. This was my first time leading a project as Tech Lead, and I feel truly fortunate. The future of Physical AI needs models that can not only “see” and “describe” the world, but also “imagine,” “simulate,” and “act”—and eventually close the loop with the real world. I hope Cosmos 3 can become an important starting point for this direction, and I’m excited to push Physical AI into its next stage together with the open-source community. Welcome to the era of Physical AI. HuggingFace: Project Website: Code:

Max Zhaoshuo Li 李赵硕

1,078,824 просмотров • 3 месяцев назад

you don’t need a robot to see physical ai in action, you just need a browser. this week I finally tried something I've wanted to do for a while: design an SO-101 scene in three.js, connect it to a real leader arm, collect teleoperation data, train an ACT model, then port it to run in the browser. the result is the first ever demo of ACT that runs locally on the web. try it yourself now at
0:35

you don’t need a robot to see physical ai in action, you just need a browser. this week I finally tried something I've wanted to do for a while: design an SO-101 scene in three.js, connect it to a real leader arm, collect teleoperation data, train an ACT model, then port it to run in the browser. the result is the first ever demo of ACT that runs locally on the web. try it yourself now at

Binh Pham

121,383 просмотров • 2 месяцев назад

Exclusive Interview with the CEO of KRAIN AI by Crypto Data Space Jared Stauffer sat down with Rabbitcoinhole to talk about what KRAIN is building, why it matters, and how you can be a part of it. Watch the full interview here:
14:41

Exclusive Interview with the CEO of KRAIN AI by Crypto Data Space Jared Stauffer sat down with Rabbitcoinhole to talk about what KRAIN is building, why it matters, and how you can be a part of it. Watch the full interview here:

KRAIN AI

31,963 просмотров • 1 год назад

SAM ALTMAN SAID THE SMARTEST SCIENTISTS IN AI ARE THE ONES WHO HELD THE ENTIRE FIELD BACK. "THE EXPERTS WERE THE PROBLEM." HE SAID THE FIELD WAS HELD BACK BY A GENERATION OF SCIENTISTS WHO WERE TOO CERTAIN ABOUT WHAT SCALING WOULD NOT PRODUCE. "THE PEOPLE WITH THE MOST CREDIBILITY WERE THE MOST WRONG." THEN HE EXPLAINED WHY. "WHEN YOU MAKE YOUR IDENTITY ABOUT A PARTICULAR BELIEF... AND THE DATA DISPROVES YOU, YOU GET STUCK." "THE SMARTER YOU ARE, THE MORE CONFIDENTLY YOU DEFEND THE WRONG POSITION." HE CALLED IT A FORM OF INSANITY. THE LESSON? THE MOMENT A BELIEF BECOMES WHO YOU ARE, IT STOPS BEING SOMETHING YOU CAN UPDATE.
1:46

SAM ALTMAN SAID THE SMARTEST SCIENTISTS IN AI ARE THE ONES WHO HELD THE ENTIRE FIELD BACK. "THE EXPERTS WERE THE PROBLEM." HE SAID THE FIELD WAS HELD BACK BY A GENERATION OF SCIENTISTS WHO WERE TOO CERTAIN ABOUT WHAT SCALING WOULD NOT PRODUCE. "THE PEOPLE WITH THE MOST CREDIBILITY WERE THE MOST WRONG." THEN HE EXPLAINED WHY. "WHEN YOU MAKE YOUR IDENTITY ABOUT A PARTICULAR BELIEF... AND THE DATA DISPROVES YOU, YOU GET STUCK." "THE SMARTER YOU ARE, THE MORE CONFIDENTLY YOU DEFEND THE WRONG POSITION." HE CALLED IT A FORM OF INSANITY. THE LESSON? THE MOMENT A BELIEF BECOMES WHO YOU ARE, IT STOPS BEING SOMETHING YOU CAN UPDATE.

Vivek Sen

69,942 просмотров • 1 месяц назад

The biggest marketplace on Earth won't be the assets humans own. It'll be the data AI needs. Everything that can be digitised is getting pulled in to train the next models. Every scientific dataset, every piece of research sitting in a university, every sensor reading off every John Deere tractor in a field. All of it feeds the machine, and almost none of it is visible to us. What comes out is an agentic economy running at machine speed. You plug your data into a vault, and agents monetise it on your behalf, trading with other agents in real time, in a marketplace we never see. The company sitting on proprietary data becomes part of it without even knowing. This is what the Economic Singularity actually looks like from the inside. The real economy stops being the one we can see and price, and moves somewhere we can't follow. You own a piece of it, or you get priced out of it. Jordi Visser.
1:27

The biggest marketplace on Earth won't be the assets humans own. It'll be the data AI needs. Everything that can be digitised is getting pulled in to train the next models. Every scientific dataset, every piece of research sitting in a university, every sensor reading off every John Deere tractor in a field. All of it feeds the machine, and almost none of it is visible to us. What comes out is an agentic economy running at machine speed. You plug your data into a vault, and agents monetise it on your behalf, trading with other agents in real time, in a marketplace we never see. The company sitting on proprietary data becomes part of it without even knowing. This is what the Economic Singularity actually looks like from the inside. The real economy stops being the one we can see and price, and moves somewhere we can't follow. You own a piece of it, or you get priced out of it. Jordi Visser.

Raoul Pal

79,047 просмотров • 1 месяц назад

Data for the Real World Diana & Austin Tindle AI has become superhuman at code, language, and images because it has enormous amounts of data to learn from. But our understanding of the physical world is still limited by sparse sensors and models built largely on intuition. Cheaper sensors and better foundation models could unlock entirely new datasets for energy, agriculture, logistics, construction, and the climate. Once you can accurately model the physical world, you can begin to control it.
1:05

Data for the Real World Diana & Austin Tindle AI has become superhuman at code, language, and images because it has enormous amounts of data to learn from. But our understanding of the physical world is still limited by sparse sensors and models built largely on intuition. Cheaper sensors and better foundation models could unlock entirely new datasets for energy, agriculture, logistics, construction, and the climate. Once you can accurately model the physical world, you can begin to control it.

Y Combinator

22,185 просмотров • 1 месяц назад

.Cohere is defining the future of sovereign AI. Autumn Moulder, VP of Engineering at Cohere, breaks down the requirements for a full AI sovereign stack at #NVIDIAGTC: ✅ Full-Stack Sovereignty: Deploying everything from the model to applications and reasoning traces within a single data center. ✅ The Power of Openness: Why open models like NVIDIA Nemotron are critical for data lineage and navigating evolving regulations.
1:05

.Cohere is defining the future of sovereign AI. Autumn Moulder, VP of Engineering at Cohere, breaks down the requirements for a full AI sovereign stack at #NVIDIAGTC: ✅ Full-Stack Sovereignty: Deploying everything from the model to applications and reasoning traces within a single data center. ✅ The Power of Openness: Why open models like NVIDIA Nemotron are critical for data lineage and navigating evolving regulations.

NVIDIA AI

10,965 просмотров • 5 месяцев назад

Transformers are not the end game. AI still needs a breakthrough I talked to Sanja Fidler, VP of AI Research at NVIDIA, leading company's Spatial Intelligence Lab, and she explains why ↓ And you should definitely watch our full conversation to understand where AI is heading and why physical AI is the next big frontier:
0:35

Transformers are not the end game. AI still needs a breakthrough I talked to Sanja Fidler, VP of AI Research at NVIDIA, leading company's Spatial Intelligence Lab, and she explains why ↓ And you should definitely watch our full conversation to understand where AI is heading and why physical AI is the next big frontier:

Turing Post

78,069 просмотров • 4 месяцев назад

Sam Altman said the smartest scientists in AI are the ones who held the entire field back. The experts were the problem. This is one of the most uncomfortable things he said all night. Altman said the field was honestly held back by a generation of scientists who were too certain about what scaling would not produce. The people with the most credibility were the most wrong. Then he explained why. It was not about intelligence. It was about identity. He said when you make your identity about a particular belief, that something will work or won't work, and then the data disproves you, you get stuck. You are too attached to the belief to let it go. You cannot see the truth anymore. The smarter you are, the more confidently you defend the wrong position. He pointed at the trolls who spent years saying scaling was a dead end, a fraud, a company destined to fail. The data kept proving them wrong. They kept repeating themselves anyway. He called that a form of insanity. Then he turned it around. He said it is a reminder in both directions. Including for the people who are currently right. The lesson is not that experts are dumb. It is that the moment a belief becomes who you are, it stops being something you can update. (Watch the full talk on YouTube at Stanford Online channel)
1:46

Sam Altman said the smartest scientists in AI are the ones who held the entire field back. The experts were the problem. This is one of the most uncomfortable things he said all night. Altman said the field was honestly held back by a generation of scientists who were too certain about what scaling would not produce. The people with the most credibility were the most wrong. Then he explained why. It was not about intelligence. It was about identity. He said when you make your identity about a particular belief, that something will work or won't work, and then the data disproves you, you get stuck. You are too attached to the belief to let it go. You cannot see the truth anymore. The smarter you are, the more confidently you defend the wrong position. He pointed at the trolls who spent years saying scaling was a dead end, a fraud, a company destined to fail. The data kept proving them wrong. They kept repeating themselves anyway. He called that a form of insanity. Then he turned it around. He said it is a reminder in both directions. Including for the people who are currently right. The lesson is not that experts are dumb. It is that the moment a belief becomes who you are, it stops being something you can update. (Watch the full talk on YouTube at Stanford Online channel)

Ihtesham Ali

697,790 просмотров • 2 месяцев назад

Why data is a trillion-dollar market "The bigger models scale, the more data you need. Data is a very durable need. If you believe in the scaling of models, then absolutely you should believe in the data market. I believe it's going to be at least a $100BN by 2030, if not $1TRN." Anastasios Nikolas Angelopoulos Do you have to scale into enterprise and mid-market to get this revenue scale or could you do it on frontier lab spend alone? Brendan (can/do) Garrett Lord Jonathan Siddharth Ali Ansari
1:23

Why data is a trillion-dollar market "The bigger models scale, the more data you need. Data is a very durable need. If you believe in the scaling of models, then absolutely you should believe in the data market. I believe it's going to be at least a $100BN by 2030, if not $1TRN." Anastasios Nikolas Angelopoulos Do you have to scale into enterprise and mid-market to get this revenue scale or could you do it on frontier lab spend alone? Brendan (can/do) Garrett Lord Jonathan Siddharth Ali Ansari

Harry Stebbings

20,976 просмотров • 29 дней назад

Announcing Mantis UMI, a pair of handheld data collection grippers for teams working on physical AI. Collect accurate bimanual manipulation data in the real world 10× faster than teleoperation. Mantis uses the exact same grippers as Axol, so you can feel what Axol feels. Data collected with Mantis transfers directly to Axol. Mantis runs on Open Source software and is modular so you can chose the tracker that works best you: Vive Tracker, Quest Controllers, and more. Collect it. Train it. Run it on Axol. Available Today 👇
0:29

Announcing Mantis UMI, a pair of handheld data collection grippers for teams working on physical AI. Collect accurate bimanual manipulation data in the real world 10× faster than teleoperation. Mantis uses the exact same grippers as Axol, so you can feel what Axol feels. Data collected with Mantis transfers directly to Axol. Mantis runs on Open Source software and is modular so you can chose the tracker that works best you: Vive Tracker, Quest Controllers, and more. Collect it. Train it. Run it on Axol. Available Today 👇

Almond Robotics

30,368 просмотров • 24 дней назад

A quick recap of our second annual Spacetech Day last week. And in case you missed it, watch the full keynote here: #AdAstra
1:33

A quick recap of our second annual Spacetech Day last week. And in case you missed it, watch the full keynote here: #AdAstra

Astra

32,434 просмотров • 3 лет назад

the micro1 robotics lab: real world data for intelligent models that co-exist in the physical world. we’re in-the-wild across 75 countries in 6,000+ unique environments collecting data. diverse movements, objects, and settings. the future of AI is as human as you can imagine. join us to start training robots today (link in comments).
1:05

the micro1 robotics lab: real world data for intelligent models that co-exist in the physical world. we’re in-the-wild across 75 countries in 6,000+ unique environments collecting data. diverse movements, objects, and settings. the future of AI is as human as you can imagine. join us to start training robots today (link in comments).

Ali Ansari

208,500 просмотров • 5 месяцев назад

🚨 Jensen Huang says everyone panicked about the AI data when MOST training data was never REAL to begin with. Ilya Sutskever told the industry pre-training was over. "Ilya said, 'We're out of data,' or something like that. 'Pre-training is over,' or something like that," Huang says. "The industry panicked, you know, that this is the end of AI." "And of course, of course that's obviously not true. We're gonna keep on scaling the amount of data that we have to train with." "A lot of that data is probably gonna be synthetic." That's where the panic came from — synthetic data sounds like cheating. "Most of the data that we are training, that we teach each other with, inform each other with, is synthetic." "It's synthetic because it didn't come out of nature." "You created it. I'm consuming it. I modify it, augment it, I regenerate it, somebody else consumes it." The textbook in your hand is synthetic. The post you're reading is synthetic. The lecture you took is synthetic. Nature didn't make any of it. Humans did. AI just learned to do the same thing — faster. "Training is now limited by compute," Huang says. "Data is now limited by compute." The data wall wasn't a wall. It was a mirror. If you're new here, follow @AiEvolutio for the latest on ChatGPT, Claude, and the AI tools shaping how we work and create. — Jensen Huang ( NVIDIA ), NVIDIA CEO, on Lex Fridman's ( Lex Fridman ) podcast
1:29

🚨 Jensen Huang says everyone panicked about the AI data when MOST training data was never REAL to begin with. Ilya Sutskever told the industry pre-training was over. "Ilya said, 'We're out of data,' or something like that. 'Pre-training is over,' or something like that," Huang says. "The industry panicked, you know, that this is the end of AI." "And of course, of course that's obviously not true. We're gonna keep on scaling the amount of data that we have to train with." "A lot of that data is probably gonna be synthetic." That's where the panic came from — synthetic data sounds like cheating. "Most of the data that we are training, that we teach each other with, inform each other with, is synthetic." "It's synthetic because it didn't come out of nature." "You created it. I'm consuming it. I modify it, augment it, I regenerate it, somebody else consumes it." The textbook in your hand is synthetic. The post you're reading is synthetic. The lecture you took is synthetic. Nature didn't make any of it. Humans did. AI just learned to do the same thing — faster. "Training is now limited by compute," Huang says. "Data is now limited by compute." The data wall wasn't a wall. It was a mirror. If you're new here, follow @AiEvolutio for the latest on ChatGPT, Claude, and the AI tools shaping how we work and create. — Jensen Huang ( NVIDIA ), NVIDIA CEO, on Lex Fridman's ( Lex Fridman ) podcast

AI Evolution

15,565 просмотров • 3 месяцев назад