正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

🤖 Physical AI is evolving weekly, but many models are trained on robots with limited payload capacity--restricting their real-world utility. 💪 To truly deploy AI in physical spaces, we need stronger hardware to unlock these models' full potential. Vega is capable of lifting 15+ lbs! 🚀 What applications will... show more

Dexmate

1,885 subscribers

21,310 次观看 • 1 年前 •via X (Twitter)

健康养生科学技术教育

Anya Rossi• Live Now

Private livecam show

2 条评论

Lukas Die Kunst 的头像

Lukas Die Kunst1 年前

Vega's strength could revolutionize aerospace components and Industry 4.0 applications. Exciting times for Physical AI!

The Rundown AI 的头像

The Rundown AI2 年前

AI won't replace you, but a person using AI will. Join 500,000+ readers and learn how to use AI in just 5 minutes a day (for free).

相关视频

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 ➡️

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 次观看 • 6 个月前

'When do you think we will get robots that have human level capabilities?' 🤖 Rowland Manthorpe travels to Las Vegas for CES 2026, the world’s biggest tech show, to find out whether the age of physical AI and robots has truly arrived. Watch in full:

'When do you think we will get robots that have human level capabilities?' 🤖 Rowland Manthorpe travels to Las Vegas for CES 2026, the world’s biggest tech show, to find out whether the age of physical AI and robots has truly arrived. Watch in full:

Sky News

22,747 次观看 • 7 个月前

Field AI raised $405M in funding and introduced Field Foundation Models These models are designed to grapple with uncertainties and the physical constraints of the real world, enabling safe robot behaviors when navigating in new environments

Field AI raised $405M in funding and introduced Field Foundation Models These models are designed to grapple with uncertainties and the physical constraints of the real world, enabling safe robot behaviors when navigating in new environments

Brett Adcock

15,136 次观看 • 1 年前

AI Guidance for Physical Work David Lieb Much of the AI conversation focuses on which desk jobs will get replaced. But for physical work, AI can't yet act in the world. With multimodal models and ubiquitous hardware, there’s an opportunity to give workers live AI coaching that dramatically reduces training time and unlocks skilled labor at scale.

AI Guidance for Physical Work David Lieb Much of the AI conversation focuses on which desk jobs will get replaced. But for physical work, AI can't yet act in the world. With multimodal models and ubiquitous hardware, there’s an opportunity to give workers live AI coaching that dramatically reduces training time and unlocks skilled labor at scale.

Y Combinator

26,533 次观看 • 6 个月前

Robots Doing Stuff #61 | Bimanual Nut Pick and Threading This is a real customer task: one step in a longer multi-part sequence we’re training in our labs. Threading requires precise alignment, force control, and fine manipulation. These are foundational capabilities for industrial dexterity applications that are currently inaccessible with traditional automation. We teleoperate these tasks to collect the data that trains our Physical AI. Next stop: autonomous. Visit to learn more about our Physical AI-enabled automation solutions. #Dexterity #DexterousHand #RobotHand #Robotics #RobotsDoingStuff #SanctuaryAI

Robots Doing Stuff #61 | Bimanual Nut Pick and Threading This is a real customer task: one step in a longer multi-part sequence we’re training in our labs. Threading requires precise alignment, force control, and fine manipulation. These are foundational capabilities for industrial dexterity applications that are currently inaccessible with traditional automation. We teleoperate these tasks to collect the data that trains our Physical AI. Next stop: autonomous. Visit to learn more about our Physical AI-enabled automation solutions. #Dexterity #DexterousHand #RobotHand #Robotics #RobotsDoingStuff #SanctuaryAI

Sanctuary AI

38,039 次观看 • 1 个月前

Today I assembled the first batch of reBot DevArm in the U.S! First one on the planet! 🇺🇸⚙️ But this isn’t about a robot arm. This is about what happens when open source hits robotics. For years: •Hardware was locked •Robotics was expensive •Embodied AI was out of reach Now? Anyone can get their hands on: •6 DOF manipulation •Real precision (<0.2 mm repeatability) •Full stack access (ROS, Isaac Sim, LeRobot) This is how movements start. Not in labs. Not behind paywalls. But in the hands of builders. Massive respect to Seeed Studio for pushing true open-source robotics forward! We’re about to see: → Thousands of robot arms trained like athletes → Real-world datasets explode → Physical AI built in garages, not just research labs At SoloTech , this is the unlock we’ve been waiting for, training and deploying Physical AI skill models on real hardware, anywhere. No sims. No vaporware. No excuses. Production Grade Physical AI. Want to get access? Check out the Physical AI Gym in San Francisco or DM me.

Today I assembled the first batch of reBot DevArm in the U.S! First one on the planet! 🇺🇸⚙️ But this isn’t about a robot arm. This is about what happens when open source hits robotics. For years: •Hardware was locked •Robotics was expensive •Embodied AI was out of reach Now? Anyone can get their hands on: •6 DOF manipulation •Real precision (<0.2 mm repeatability) •Full stack access (ROS, Isaac Sim, LeRobot) This is how movements start. Not in labs. Not behind paywalls. But in the hands of builders. Massive respect to Seeed Studio for pushing true open-source robotics forward! We’re about to see: → Thousands of robot arms trained like athletes → Real-world datasets explode → Physical AI built in garages, not just research labs At SoloTech , this is the unlock we’ve been waiting for, training and deploying Physical AI skill models on real hardware, anywhere. No sims. No vaporware. No excuses. Production Grade Physical AI. Want to get access? Check out the Physical AI Gym in San Francisco or DM me.

Dhruv Diddi

31,439 次观看 • 4 个月前

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.

1/7 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

18,832 次观看 • 3 天前

🚨 Breaking News: Solo Tech won at CES 2026. 🦾🏆 In a 10×10 booth, we showcased the highest density of working robots on the floor proving that the future of AI is physical, performant, and deployable today. Up close with real systems. No slides. No simulations. Just Physical AI in action. Alongside leaders shaping what’s next NVIDIA Robotics , Sharpa , and Boston Dynamics the message was clear: This is the ChatGPT moment for robotics. And it won’t happen behind screens. It will happen in Robotics Gyms spaces around the world where machines train, models adapt, and builders learn by doing. The era of AI that acts has begun. #BreakingNews #CES2026 #SoloTech #PhysicalAI #RoboticsGym #EdgeAI

🚨 Breaking News: Solo Tech won at CES 2026. 🦾🏆 In a 10×10 booth, we showcased the highest density of working robots on the floor proving that the future of AI is physical, performant, and deployable today. Up close with real systems. No slides. No simulations. Just Physical AI in action. Alongside leaders shaping what’s next NVIDIA Robotics , Sharpa , and Boston Dynamics the message was clear: This is the ChatGPT moment for robotics. And it won’t happen behind screens. It will happen in Robotics Gyms spaces around the world where machines train, models adapt, and builders learn by doing. The era of AI that acts has begun. #BreakingNews #CES2026 #SoloTech #PhysicalAI #RoboticsGym #EdgeAI

Dhruv Diddi

14,821 次观看 • 7 个月前

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.

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 次观看 • 1 个月前

Chelsea Finn (Chelsea Finn) on building general-purpose robotics, and bringing intelligence into the physical world. At AI Startup School in San Francisco. 00:00 - General Purpose Robots 00:11 - Challenges in Robotics Applications 00:57 - Physical Intelligence: A New Approach 01:47 - Learning from Language Models 02:08 - Data Sources for Training Robots 03:32 - Training with Real-World Data 04:39 - Initial Successes and Challenges 09:10 - Breakthrough in Robot Training 11:03 - Improving Performance 15:43 - Expanding Capabilities 17:34 - Robots in Unseen Environments 25:54 - Handling Open-Ended Prompts 29:36 - Evaluating Robot Performance 30:03 - Future Directions and Challenges 31:27 - Audience Q&A

Chelsea Finn (Chelsea Finn) on building general-purpose robotics, and bringing intelligence into the physical world. At AI Startup School in San Francisco. 00:00 - General Purpose Robots 00:11 - Challenges in Robotics Applications 00:57 - Physical Intelligence: A New Approach 01:47 - Learning from Language Models 02:08 - Data Sources for Training Robots 03:32 - Training with Real-World Data 04:39 - Initial Successes and Challenges 09:10 - Breakthrough in Robot Training 11:03 - Improving Performance 15:43 - Expanding Capabilities 17:34 - Robots in Unseen Environments 25:54 - Handling Open-Ended Prompts 29:36 - Evaluating Robot Performance 30:03 - Future Directions and Challenges 31:27 - Audience Q&A

Y Combinator

129,834 次观看 • 1 年前

Physical AI hits production speed on automotive assembly! 👀 Sanctuary AI just achieved 99,5%+ success on a wire plugging task at a Tier 1 automotive supplier, 2.54 seconds per task, validated against live production benchmarks. The system matched the customer's actual production line throughput. The task sounds simple. But if you look closer, it's not. Inserting flexible wires into moving targets on a conveyor requires contact-rich dexterity, force sensing, real-time adaptation. Materials shift. Targets move. This has stayed out of reach for traditional automation. Instead of waiting for humanoid hardware to mature, Sanctuary AI is deploying Physical AI on existing commercial robotic platforms (Universal Robots in this case). So their solution is fully hardware-agnostic. Deploy today on what you already have. Scale to next-gen humanoids later. Olivia Norton (co-founder, CTO): "Physical AI adoption is gated by AI that meets both performance and cycle time requirements. That's what customers are seeking, and that's what we are delivering." Looks like manufacturing, logistics, and other labor-constrained industries don't need to wait. Read more here: ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →

Physical AI hits production speed on automotive assembly! 👀 Sanctuary AI just achieved 99,5%+ success on a wire plugging task at a Tier 1 automotive supplier, 2.54 seconds per task, validated against live production benchmarks. The system matched the customer's actual production line throughput. The task sounds simple. But if you look closer, it's not. Inserting flexible wires into moving targets on a conveyor requires contact-rich dexterity, force sensing, real-time adaptation. Materials shift. Targets move. This has stayed out of reach for traditional automation. Instead of waiting for humanoid hardware to mature, Sanctuary AI is deploying Physical AI on existing commercial robotic platforms (Universal Robots in this case). So their solution is fully hardware-agnostic. Deploy today on what you already have. Scale to next-gen humanoids later. Olivia Norton (co-founder, CTO): "Physical AI adoption is gated by AI that meets both performance and cycle time requirements. That's what customers are seeking, and that's what we are delivering." Looks like manufacturing, logistics, and other labor-constrained industries don't need to wait. Read more here: ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →

Lukas Ziegler

45,757 次观看 • 2 个月前

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).

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

208,233 次观看 • 5 个月前

Breaking news: Cosmos 3 is here. They are attempting to do something completely new 🤯 Why is Physical AI much harder than building a chatbot? Understanding the world is not enough, robots need to predict it and act inside it. That's the idea behind NVIDIA Cosmos 3: → Reasoning model understands what's happening from video, images, text, and actions. → World model generates future states of the environment. → Action model generates the actions needed to achieve a goal. Previous systems often stitched these capabilities together using separate models. Cosmos 3 combines them into a single architecture with two components: ▪️ Reasoner Tower Analyzes observations and builds an understanding of objects, motion, interactions, and physical context. ▪️ Generator Tower Uses that understanding to generate future videos and action sequences that obey physical constraints. So Cosmos 3 moves from: Perception → Model A Prediction → Model B Actions → Model C to: Perception + Prediction + Actions → One unified system. The goal is to make robots, autonomous vehicles, and smart environments better at answering three questions: 1. What is happening? 2. What will happen next? 3. What should I do? That's a big shift from today's AI, which mostly focuses on generating text. And check the benchmarks! Physical AI needs to generate decisions that survive contact with the real world. 🚗🤖

Breaking news: Cosmos 3 is here. They are attempting to do something completely new 🤯 Why is Physical AI much harder than building a chatbot? Understanding the world is not enough, robots need to predict it and act inside it. That's the idea behind NVIDIA Cosmos 3: → Reasoning model understands what's happening from video, images, text, and actions. → World model generates future states of the environment. → Action model generates the actions needed to achieve a goal. Previous systems often stitched these capabilities together using separate models. Cosmos 3 combines them into a single architecture with two components: ▪️ Reasoner Tower Analyzes observations and builds an understanding of objects, motion, interactions, and physical context. ▪️ Generator Tower Uses that understanding to generate future videos and action sequences that obey physical constraints. So Cosmos 3 moves from: Perception → Model A Prediction → Model B Actions → Model C to: Perception + Prediction + Actions → One unified system. The goal is to make robots, autonomous vehicles, and smart environments better at answering three questions: 1. What is happening? 2. What will happen next? 3. What should I do? That's a big shift from today's AI, which mostly focuses on generating text. And check the benchmarks! Physical AI needs to generate decisions that survive contact with the real world. 🚗🤖

Turing Post

13,836 次观看 • 2 个月前

Elon Musk says Optimus is the infinite money glitch. Not because robots are valuable. Because robots can make more robots. Musk explained that humanoid robots improve through three exponential trends multiplied together: digital intelligence, AI chip capability, and electromechanical dexterity. But the real unlock is that the robot can start making the robots. "So you have a recursive multiplicative exponential," he said. "This is a supernova." Musk's thesis is that once you have a physical robot capable of manufacturing, the production curve stops being linear and becomes self-replicating. Every robot built accelerates the building of the next one. The implication is that the companies that control physical manufacturing will control AI's future, not the ones with the best models. The bottleneck is not intelligence. It is atoms.

Elon Musk says Optimus is the infinite money glitch. Not because robots are valuable. Because robots can make more robots. Musk explained that humanoid robots improve through three exponential trends multiplied together: digital intelligence, AI chip capability, and electromechanical dexterity. But the real unlock is that the robot can start making the robots. "So you have a recursive multiplicative exponential," he said. "This is a supernova." Musk's thesis is that once you have a physical robot capable of manufacturing, the production curve stops being linear and becomes self-replicating. Every robot built accelerates the building of the next one. The implication is that the companies that control physical manufacturing will control AI's future, not the ones with the best models. The bottleneck is not intelligence. It is atoms.

Shruti

59,306 次观看 • 2 个月前

Anthropic's Sholto Douglas describes the concept of a software-only singularity: "It's one where the models are far better at digital tasks than they are at physical ones. And so we see rapid change in the digital world with models, and relatively little change in the physical world. So information and software changes dramatically, and this ends up having some pretty weird effects." "It means that maybe like the drivers of what have been the last couple decades of progress in the economy turn around." "And I think we'll see that flow on into the physical world but at a delay. So you get much better at doing chip design. You get much better at training AI models. AI models get a lot faster. Chips get a lot better. The general economy gets a lot more efficient because the sort of information and message parsing that is much of the rest of the economy ends up becoming much more efficient." "But at the same time you don't yet have robots providing limitless physical abundance. Science probably progresses really fast up to the degree that you need interaction with labs or larger particle colliders or something like this. And then you go, 'Okay well I need to build the robots.'"

Anthropic's Sholto Douglas describes the concept of a software-only singularity: "It's one where the models are far better at digital tasks than they are at physical ones. And so we see rapid change in the digital world with models, and relatively little change in the physical world. So information and software changes dramatically, and this ends up having some pretty weird effects." "It means that maybe like the drivers of what have been the last couple decades of progress in the economy turn around." "And I think we'll see that flow on into the physical world but at a delay. So you get much better at doing chip design. You get much better at training AI models. AI models get a lot faster. Chips get a lot better. The general economy gets a lot more efficient because the sort of information and message parsing that is much of the rest of the economy ends up becoming much more efficient." "But at the same time you don't yet have robots providing limitless physical abundance. Science probably progresses really fast up to the degree that you need interaction with labs or larger particle colliders or something like this. And then you go, 'Okay well I need to build the robots.'"

TBPN

208,090 次观看 • 6 个月前

As Larry Ellison explains, there are two types of AI models: real-time models, also called AI on the edge, where you need ultra-low latency decisions (think autonomous driving or robotics), and models that don’t need an immediate response, like ChatGPT, where the system has time to reason. Real-time models require local compute inside the device, and these chips have nothing to do with the GPUs running in data centers. The AI-on-the-edge market is still largely untapped — and it’s going to be a multi-trillion-dollar opportunity. I believe $AMD will be one of the biggest beneficiaries

As Larry Ellison explains, there are two types of AI models: real-time models, also called AI on the edge, where you need ultra-low latency decisions (think autonomous driving or robotics), and models that don’t need an immediate response, like ChatGPT, where the system has time to reason. Real-time models require local compute inside the device, and these chips have nothing to do with the GPUs running in data centers. The AI-on-the-edge market is still largely untapped — and it’s going to be a multi-trillion-dollar opportunity. I believe $AMD will be one of the biggest beneficiaries

Daniel

151,698 次观看 • 8 个月前

Without World Models, There Is No AGI. Google Just Proved It. If AGI ever happens, it will not come from bigger chatbots alone. From the very start of this interview, one thing is crystal clear: without world models, we will never reach AGI. And right now, Google is leading with its world simulator Genie 3. Here is the core of what Demis Hassabis explains in this conversation: • World models are the missing core of AGI Hassabis says his deepest long term focus has always been world models and simulations. Not just language. Not just prediction. Actual internal simulations of reality. • LLMs are impressive, but incomplete Language models understand more about the world than expected because human language encodes a lot of reality. Still, language is only a shadow of the real thing. • What text can never fully teach Reality includes things text struggles to express: •3D space and spatial dynamics •Physical causality and mechanics •Sensorimotor experience like movement, force, smell, or balance • Experience beats description To close the gap, AI must learn from interaction and experience, not just static text. That is how you build an internal world simulator. • Why Genie 3 matters With Google DeepMind pushing systems like Genie 3, AI starts to model reality itself, not just talk about it. • Robots and real world assistants depend on this True robotics, smart glasses, and universal assistants require AI that understands the physical world you live in, not just your screen. Bottom line: AGI will not emerge from better text prediction. It will emerge from systems that can simulate, predict, and understand reality itself. Right now, Google is clearly ahead on that path. Curious what you think. Are world models the real AGI unlock, or just another stepping stone?

Without World Models, There Is No AGI. Google Just Proved It. If AGI ever happens, it will not come from bigger chatbots alone. From the very start of this interview, one thing is crystal clear: without world models, we will never reach AGI. And right now, Google is leading with its world simulator Genie 3. Here is the core of what Demis Hassabis explains in this conversation: • World models are the missing core of AGI Hassabis says his deepest long term focus has always been world models and simulations. Not just language. Not just prediction. Actual internal simulations of reality. • LLMs are impressive, but incomplete Language models understand more about the world than expected because human language encodes a lot of reality. Still, language is only a shadow of the real thing. • What text can never fully teach Reality includes things text struggles to express: •3D space and spatial dynamics •Physical causality and mechanics •Sensorimotor experience like movement, force, smell, or balance • Experience beats description To close the gap, AI must learn from interaction and experience, not just static text. That is how you build an internal world simulator. • Why Genie 3 matters With Google DeepMind pushing systems like Genie 3, AI starts to model reality itself, not just talk about it. • Robots and real world assistants depend on this True robotics, smart glasses, and universal assistants require AI that understands the physical world you live in, not just your screen. Bottom line: AGI will not emerge from better text prediction. It will emerge from systems that can simulate, predict, and understand reality itself. Right now, Google is clearly ahead on that path. Curious what you think. Are world models the real AGI unlock, or just another stepping stone?

VraserX e/acc

23,784 次观看 • 8 个月前

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:

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

1,078,418 次观看 • 2 个月前