正在加载视频...

视频加载失败

返回首页

We build Cosmos-Predict2 as a world foundation model for Physical AI builders — fully open and adaptable. Post-train it for specialized tasks or different output types. Available in multiple sizes, resolutions, and frame rates. 📷 Watch the repo walkthrough ⚒️ Visit for more #NVIDIACosmos #PhysicalAI

hanna_mao's profile picture

Hanzi Mao

2,437 subscribers

32,040 次观看 • 1 年前 •via X (Twitter)

健康养生科学技术教育
LIVE

Anya Rossi• Live Now

Private livecam show

8 条评论

$MIA 的头像
$MIA1 年前

from AI to AgentFi, just warming up 😉

two weeks 的头像
two weeks1 年前

Still waiting for an example that demonstrates real cake

Kubilây Ân Artwork 的头像
Kubilây Ân Artwork1 年前

Very good model. I am using. We need control net for cosmos predict 2.

8GG.ETH 的头像
8GG.ETH1 年前

Your model cracks open the cosmos but can it hatch the egg? The shell of prediction is thin, the yolk of creation runs deep.

Hiro Yamamoto 的头像
Hiro Yamamoto1 年前

OpenArm at NVIDIA! Had a great time demoing the pre-release OpenArm v1.0 to 10 members of the GEAR Lab team 🦾 Big thanks to @linkevin0 & team for the thoughtful feedback. Excited to keep building together! #OpenSource #robotics #humanoids #physicalAI #NVIDIA

AK 的头像
AK1 年前

WorldVLA Towards Autoregressive Action World Model

C's Robotics Paper Notes 的头像
C's Robotics Paper Notes1 年前

Compliant Residual DAgger: Improving Real-World Contact-Rich Manipulation with Human Corrections human correction as the expert signal in dagger to finetune the policy, supported by compliant hardware design.

Debidatta Dwibedi 的头像
Debidatta Dwibedi1 年前

Our Vision-Language-Action robot demo at #RSS2025 was eye-opening. The ultimate eval for any generalist model: new environment, new objects from audience, and new instructions. For the first time it really hit me: what if we've been underestimating what these models can do?

相关视频

#NVIDIACosmos Reason, an open, customizable, 7-billion-parameter reasoning VLM for #PhysicalAI, enables robots, autonomous vehicles and visual AI agents to: 👀 See, reason, and act in the physical world. 🛠️ Solve multistep tasks and handle ambiguous or new experiences. Get started ➡️ #SIGGRAPH2025
0:27

#NVIDIACosmos Reason, an open, customizable, 7-billion-parameter reasoning VLM for #PhysicalAI, enables robots, autonomous vehicles and visual AI agents to: 👀 See, reason, and act in the physical world. 🛠️ Solve multistep tasks and handle ambiguous or new experiences. Get started ➡️ #SIGGRAPH2025

NVIDIA AI Developer

32,772 次观看 • 1 年前

Introducing Cosmos 3: Our latest frontier model for Physical AI Cosmos 3 is the world’s first fully open omnimodel with native vision reasoning, world and action generation. Today we’re releasing Super (32B) and Nano (8B) variants.
3:13

Introducing Cosmos 3: Our latest frontier model for Physical AI Cosmos 3 is the world’s first fully open omnimodel with native vision reasoning, world and action generation. Today we’re releasing Super (32B) and Nano (8B) variants.

NVIDIA AI

427,477 次观看 • 2 个月前

Open models are accelerating development and deployment across agentic AI, physical AI, and a growing range of industries. ✨ “We have billions of dollars of supercomputers in operation, so we can develop our open models,” said NVIDIA CEO Jensen Huang in a recent keynote. “That work is starting to attract attention across industries worldwide, as we build frontier AI models in many different domains.” This includes leading open models from NVIDIA, including: ⚙️ NVIDIA Nemotron for agentic AI ⚙️ NVIDIA Cosmos and GR00T for physical AI ⚙️ NVIDIA Alpamayo for autonomous vehicles ⚙️ NVIDIA Clara for biomedical AI Learn more about open source and AI ➡️
0:20

Open models are accelerating development and deployment across agentic AI, physical AI, and a growing range of industries. ✨ “We have billions of dollars of supercomputers in operation, so we can develop our open models,” said NVIDIA CEO Jensen Huang in a recent keynote. “That work is starting to attract attention across industries worldwide, as we build frontier AI models in many different domains.” This includes leading open models from NVIDIA, including: ⚙️ NVIDIA Nemotron for agentic AI ⚙️ NVIDIA Cosmos and GR00T for physical AI ⚙️ NVIDIA Alpamayo for autonomous vehicles ⚙️ NVIDIA Clara for biomedical AI Learn more about open source and AI ➡️

NVIDIA AI

19,296 次观看 • 7 个月前

"The “ChatGPT moment” for physical AI is nearly here. 👏 Cosmos open world foundation models understand reality to create and reason about rich synthetic worlds—so self-driving cars and robots can learn from endlessly varied, physics-aware scenarios. From a single image, 3D scene, or simulator trace, Cosmos generates realistic video, brings edge cases to life, and helps autonomous systems train for the long tail. Watch the #CES2026 demo now 🎥
0:41

"The “ChatGPT moment” for physical AI is nearly here. 👏 Cosmos open world foundation models understand reality to create and reason about rich synthetic worlds—so self-driving cars and robots can learn from endlessly varied, physics-aware scenarios. From a single image, 3D scene, or simulator trace, Cosmos generates realistic video, brings edge cases to life, and helps autonomous systems train for the long tail. Watch the #CES2026 demo now 🎥

NVIDIA AI

49,809 次观看 • 7 个月前

We built maps for people. Now, we’re building a new kind of map for robotics and AI. 🤖📍 Niantic Spatial CEO John Hanke shares why this foundation will be as essential to the future of AI as digital maps were for the web. 80% of the global economy operates in the physical world. For AI to truly scale, it must move beyond chatbots and synthetic worlds. It needs to navigate, understand, and safely interact with our reality. Read more: #PhysicalAI #SpatialIntelligence #NianticSpatial
1:38

We built maps for people. Now, we’re building a new kind of map for robotics and AI. 🤖📍 Niantic Spatial CEO John Hanke shares why this foundation will be as essential to the future of AI as digital maps were for the web. 80% of the global economy operates in the physical world. For AI to truly scale, it must move beyond chatbots and synthetic worlds. It needs to navigate, understand, and safely interact with our reality. Read more: #PhysicalAI #SpatialIntelligence #NianticSpatial

Niantic Spatial 🌎

83,003 次观看 • 6 个月前

Niantic Spatial is working with Human Machine Collaboration Institute and the City of Rancho Cordova to build the foundation for the city’s first digital twin for physical AI. Roughly four square kilometers of the Innovation Region is already reconstructed and running in simulation. Read more: #NianticSpatial #PhysicalAI #DigitalTwins #SpatialAI #3DReconstruction #Robotics
0:58

Niantic Spatial is working with Human Machine Collaboration Institute and the City of Rancho Cordova to build the foundation for the city’s first digital twin for physical AI. Roughly four square kilometers of the Innovation Region is already reconstructed and running in simulation. Read more: #NianticSpatial #PhysicalAI #DigitalTwins #SpatialAI #3DReconstruction #Robotics

Niantic Spatial 🌎

29,075 次观看 • 24 天前

NVIDIA Cosmos Reason 2 is here. 🥳 An open, highly accurate reasoning vision language model for physical AI, featuring: ✅ Improved spatio-temporal understanding and timestamp precision ✅ Flexible deployment with 2B and 8B model sizes ✅ Long-context reasoning with up to 256K tokens ✅ Expanded visual perception across complex environments We also have new Cosmos releases: Predict 2.5, Transfer 2.5, and the NVIDIA GR00T N1.6 robot foundation model. 📗Read our technical blog: 🤗 Download Cosmos Reason 2 on Hugging Face:
0:57

NVIDIA Cosmos Reason 2 is here. 🥳 An open, highly accurate reasoning vision language model for physical AI, featuring: ✅ Improved spatio-temporal understanding and timestamp precision ✅ Flexible deployment with 2B and 8B model sizes ✅ Long-context reasoning with up to 256K tokens ✅ Expanded visual perception across complex environments We also have new Cosmos releases: Predict 2.5, Transfer 2.5, and the NVIDIA GR00T N1.6 robot foundation model. 📗Read our technical blog: 🤗 Download Cosmos Reason 2 on Hugging Face:

NVIDIA AI Developer

45,677 次观看 • 7 个月前

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 次观看 • 6 个月前

Physical AI needs more than maps, GPS, or pixels alone. It needs a living, geometrically accurate understanding of the real world. Niantic Spatial and Spexi are partnering to transform drone imagery into large-scale 3D intelligence for physical AI. 🔗Learn more: #NianticSpatial #Spexi #PhysicalAI #Reconstruction #GaussianSplat #DigitalTwins #Robotics #GeospatialAI #AI #GeospatialIntelligence #GEOINT #SpatialIntelligence
0:59

Physical AI needs more than maps, GPS, or pixels alone. It needs a living, geometrically accurate understanding of the real world. Niantic Spatial and Spexi are partnering to transform drone imagery into large-scale 3D intelligence for physical AI. 🔗Learn more: #NianticSpatial #Spexi #PhysicalAI #Reconstruction #GaussianSplat #DigitalTwins #Robotics #GeospatialAI #AI #GeospatialIntelligence #GEOINT #SpatialIntelligence

Niantic Spatial 🌎

27,988 次观看 • 3 个月前

We still have not fully found the origins for "Stars Come to Me", the replacement track used for "As Time Goes By" in the eng physical release of the School Idol Movie, it has a different instrumental and different lyrics
1:30

We still have not fully found the origins for "Stars Come to Me", the replacement track used for "As Time Goes By" in the eng physical release of the School Idol Movie, it has a different instrumental and different lyrics

NoodleGirl

21,864 次观看 • 1 年前

Announcing Axol: a dual-arm robot designed for teams working with physical AI. Made in America. Axol is for builders who believe robots should work, in the real world, not just staged environments, and that the future of physical AI should be open, not closed. #robotics #automation #ai #hardware
2:22

Announcing Axol: a dual-arm robot designed for teams working with physical AI. Made in America. Axol is for builders who believe robots should work, in the real world, not just staged environments, and that the future of physical AI should be open, not closed. #robotics #automation #ai #hardware

Almond Robotics

62,722 次观看 • 2 个月前

Excited to share: NVIDIA Cosmos 3 Edge is openly available, bringing frontier world models to NVIDIA Jetson Thor and other local devices for physical AI. Read the blog: Learn more about it at today’s SIGGRAPH keynote—in person or via livestream at 3:45 p.m. PT:
0:26

Excited to share: NVIDIA Cosmos 3 Edge is openly available, bringing frontier world models to NVIDIA Jetson Thor and other local devices for physical AI. Read the blog: Learn more about it at today’s SIGGRAPH keynote—in person or via livestream at 3:45 p.m. PT:

Ming-Yu Liu

49,171 次观看 • 1 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:
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

1,078,418 次观看 • 2 个月前

Introducing the Skills Manager in AI Assistant. Easily install skills from a curated collection focused on coding workflows, verified for safety, and use them in codex and claude agent across different projects. Check the thread for examples, or watch the walkthrough:
1:19

Introducing the Skills Manager in AI Assistant. Easily install skills from a curated collection focused on coding workflows, verified for safety, and use them in codex and claude agent across different projects. Check the thread for examples, or watch the walkthrough:

JetBrains

11,912 次观看 • 4 个月前

Say hello to Gemini 3.5 Transcribe! - Build apps that understand user speech / intent, even w/ multiple speakers! - Auto-detection of 85+ languages out of the box - Custom vocab adaptation for specialized jargon... SGTM:) API available now in Google AI Studio and Gemini Enterprise, or try it in the Gemini app on macOS or Rambler on Android! More details:
0:37

Say hello to Gemini 3.5 Transcribe! - Build apps that understand user speech / intent, even w/ multiple speakers! - Auto-detection of 85+ languages out of the box - Custom vocab adaptation for specialized jargon... SGTM:) API available now in Google AI Studio and Gemini Enterprise, or try it in the Gemini app on macOS or Rambler on Android! More details:

Sundar Pichai

509,824 次观看 • 2 天前

You’re already training Big Tech’s AI models. So why aren’t you getting compensated for it? With Action Model you can download our browser extension and train AI passively in the background or by completing ActionFi tasks, while earning rewards and ownership in the model itself. This is what the future of AI should look like. Ownership back in the hands of the people who help build it, not billionaire control.
0:46

You’re already training Big Tech’s AI models. So why aren’t you getting compensated for it? With Action Model you can download our browser extension and train AI passively in the background or by completing ActionFi tasks, while earning rewards and ownership in the model itself. This is what the future of AI should look like. Ownership back in the hands of the people who help build it, not billionaire control.

Action Model

26,127 次观看 • 4 个月前

We are excited to announce that Flutterwave has officially acquired Mono, Africa’s leading open banking infrastructure! 🦋 🤝 🏦 It means a faster, more secure, and frictionless payment experience for individuals, a simpler onboarding process with smarter tools for recurring payments and transactions for businesses of all sizes and a truly open payments highway for the next generation of African innovators to build on. Together, we are opening up a new world of possibilities for the continent. 🚀 Read more:
2:36

We are excited to announce that Flutterwave has officially acquired Mono, Africa’s leading open banking infrastructure! 🦋 🤝 🏦 It means a faster, more secure, and frictionless payment experience for individuals, a simpler onboarding process with smarter tools for recurring payments and transactions for businesses of all sizes and a truly open payments highway for the next generation of African innovators to build on. Together, we are opening up a new world of possibilities for the continent. 🚀 Read more:

Flutterwave

11,005 次观看 • 7 个月前