Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

#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

108,816 subscribers

32,772 views • 10 months ago •via X (Twitter)

Science & Technology Education #NVIDIACosmos #PhysicalAI

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

Reasoning is the next frontier for autonomous vehicles. Matt Cragun, Director of Product Management for Autonomous Vehicles and Simulation at NVIDIA, demonstrates how the Alpamayo family of open models, simulation tools, and datasets enables AVs to perceive, reason, and act safely in complex scenarios. Learn more →

Reasoning is the next frontier for autonomous vehicles. Matt Cragun, Director of Product Management for Autonomous Vehicles and Simulation at NVIDIA, demonstrates how the Alpamayo family of open models, simulation tools, and datasets enables AVs to perceive, reason, and act safely in complex scenarios. Learn more →

NVIDIA DRIVE

24,411 views • 5 months ago

Wow. That's cool. Researchers just released World, an open-source Unreal Engine 5 simulator for training and testing LLM and VLM agents in realistic 3D environments. The platform supports RGB, depth, and segmentation sensors, along with navigation, vehicles, pedestrians, robots and procedural city generation. It's built with a Gym-like Python interface, it allows AI agents to learn physical and social reasoning in complex virtual worlds before real world deployment. We're moving from AI that only understands information to AI that can perceive, reason and act inside realistic simulated environments.

Wow. That's cool. Researchers just released World, an open-source Unreal Engine 5 simulator for training and testing LLM and VLM agents in realistic 3D environments. The platform supports RGB, depth, and segmentation sensors, along with navigation, vehicles, pedestrians, robots and procedural city generation. It's built with a Gym-like Python interface, it allows AI agents to learn physical and social reasoning in complex virtual worlds before real world deployment. We're moving from AI that only understands information to AI that can perceive, reason and act inside realistic simulated environments.

SciTech Era

47,197 views • 1 month ago

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

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

Hanzi Mao

31,952 views • 1 year ago

Everything that moves will be autonomous, and #physicalAI will embody robots of every kind. 🤖 Discover how NVIDIA Omniverse and #NVIDIACosmos are enabling robots to learn through simulation, training, and real-world experience. Watch the full video ▶️

Everything that moves will be autonomous, and #physicalAI will embody robots of every kind. 🤖 Discover how NVIDIA Omniverse and #NVIDIACosmos are enabling robots to learn through simulation, training, and real-world experience. Watch the full video ▶️

NVIDIA Robotics

56,496 views • 1 year ago

Devtools for AI Agents Nicolas Dessaigne AI agents are the next wave: autonomous tools that reason, decide, and amplify human productivity. We’re funding startups building devtools for agents, whether you’re creating agent builders or building blocks to perform complex tasks.

Devtools for AI Agents Nicolas Dessaigne AI agents are the next wave: autonomous tools that reason, decide, and amplify human productivity. We’re funding startups building devtools for agents, whether you’re creating agent builders or building blocks to perform complex tasks.

Y Combinator

113,448 views • 1 year ago

Our vision is for AI that uses world models to adapt in new and dynamic environments and efficiently learn new skills. We’re sharing V-JEPA 2, a new world model with state-of-the-art performance in visual understanding and prediction. V-JEPA 2 is a 1.2 billion-parameter model, trained on video, that can enable zero-shot planning in robots—allowing them to plan and execute tasks in unfamiliar environments. Learn more about V-JEPA 2 ➡️ As we continue working toward our goal of achieving advanced machine intelligence (AMI), we’re also releasing three new benchmarks for evaluating how well existing models can reason about the physical world from video. Learn more and download the new benchmarks ➡️

Our vision is for AI that uses world models to adapt in new and dynamic environments and efficiently learn new skills. We’re sharing V-JEPA 2, a new world model with state-of-the-art performance in visual understanding and prediction. V-JEPA 2 is a 1.2 billion-parameter model, trained on video, that can enable zero-shot planning in robots—allowing them to plan and execute tasks in unfamiliar environments. Learn more about V-JEPA 2 ➡️ As we continue working toward our goal of achieving advanced machine intelligence (AMI), we’re also releasing three new benchmarks for evaluating how well existing models can reason about the physical world from video. Learn more and download the new benchmarks ➡️

AI at Meta

309,942 views • 1 year ago

The coming merger of AI agents with the physical world. iddris, founder/CEO of Open Matter and I have a wide-ranging conversation about how the next platform shift may not be just AI chat, robotics, smart glasses, or autonomous cars separately. It may be the connective tissue between all of them. This video teaches viewers that the next wave of AI agents will not just operate inside apps, browsers, calendars, and spreadsheets. The real frontier is agents that can understand, coordinate, and act in the physical world. Iddris explains a vision for “agentic infrastructure for atoms”: systems that let AI agents manage physical objects, deliveries, storage, location, identity, logistics, robots, vehicles, and real-world context.

The coming merger of AI agents with the physical world. iddris, founder/CEO of Open Matter and I have a wide-ranging conversation about how the next platform shift may not be just AI chat, robotics, smart glasses, or autonomous cars separately. It may be the connective tissue between all of them. This video teaches viewers that the next wave of AI agents will not just operate inside apps, browsers, calendars, and spreadsheets. The real frontier is agents that can understand, coordinate, and act in the physical world. Iddris explains a vision for “agentic infrastructure for atoms”: systems that let AI agents manage physical objects, deliveries, storage, location, identity, logistics, robots, vehicles, and real-world context.

Robert Scoble

17,261 views • 1 month ago

Do what you do best. Let agents do the rest. Introducing Agentforce, a suite of limitlessly buildable and customizable autonomous AI agents that augment employees and handle tasks across your business. The future of AI is agents. And it's here: #DF24

Do what you do best. Let agents do the rest. Introducing Agentforce, a suite of limitlessly buildable and customizable autonomous AI agents that augment employees and handle tasks across your business. The future of AI is agents. And it's here: #DF24

Salesforce

2,744,326 views • 1 year ago

Humanoid Robots can Think, Move, and Adapt in Real Time. LimX COSA (Cognitive OS of Agents), the first physical-world-native agentic OS, unifies cognitive reasoning and whole-body control, enabling robots to complete long-horizon, multi-step tasks.

Humanoid Robots can Think, Move, and Adapt in Real Time. LimX COSA (Cognitive OS of Agents), the first physical-world-native agentic OS, unifies cognitive reasoning and whole-body control, enabling robots to complete long-horizon, multi-step tasks.

LimX Dynamics

1,631,725 views • 5 months ago

How can robots autonomously handle ambiguous situations that require commonsense reasoning? *VLM-PC* provides adaptive high-level planning, so robots can get unstuck by exploring multiple strategies. Paper:

How can robots autonomously handle ambiguous situations that require commonsense reasoning? VLM-PC provides adaptive high-level planning, so robots can get unstuck by exploring multiple strategies. Paper:

Annie Chen

24,112 views • 1 year ago

Unboxing Alert. 🚨 Robots just got a lot smarter thanks to #NVIDIAJetson Thor. 🧠 It's the ultimate brain for physical AI agents and general robotics, accelerating their ability to reason in real time. Learn more ➡️ #NVIDIARobotics

Unboxing Alert. 🚨 Robots just got a lot smarter thanks to #NVIDIAJetson Thor. 🧠 It's the ultimate brain for physical AI agents and general robotics, accelerating their ability to reason in real time. Learn more ➡️ #NVIDIARobotics

NVIDIA Robotics

90,712 views • 10 months ago

Everywhere you turned at #NVIDIAGTC, physical AI was in the mix. 🦾 From robots and autonomous vehicles to industrial AI, it was incredible to see it all in one place, alongside an amazing community of developers. See you at the next GTC. 🤗

Everywhere you turned at #NVIDIAGTC, physical AI was in the mix. 🦾 From robots and autonomous vehicles to industrial AI, it was incredible to see it all in one place, alongside an amazing community of developers. See you at the next GTC. 🤗

NVIDIA Robotics

25,334 views • 3 months ago

NEWS: NVIDIA just announced Alpamayo, what CEO Jensen Huang calls the world’s first thinking, reasoning autonomous vehicle AI, launching on U.S. roads later this year, starting with the Mercedes CLA. Jensen: "It's trained end-to-end. Literally from camera in to actuation out; It reasons what action it is about to take, the reason by which is came about that action, and the trajectory." Alpamayo introduces Vision-Language-Action (VLA) models, which enable self-driving systems to interpret what they see, reason about complex driving scenarios, and generate driving actions. The platform includes large reasoning models, simulation tools for testing rare and edge-case scenarios, and open datasets for training and validation. NVIDIA says the approach improves transparency, safety, and robustness in autonomous systems, particularly in complex real-world environments, and supports progress toward higher levels of vehicle autonomy: "With a 10-billion-parameter architecture, Alpamayo 1 uses video input to generate trajectories alongside reasoning traces, showing the logic behind each decision. Developers can adapt Alpamayo 1 into smaller runtime models for vehicle development, or use it as a foundation for AV development tools such as reasoning-based evaluators and auto-labeling systems. Alpamayo 1 provides open model weights and open-source inferencing scripts. Future models in the family will feature larger parameter counts, more detailed reasoning capabilities, more input and output flexibility, and options for commercial usage."

NEWS: NVIDIA just announced Alpamayo, what CEO Jensen Huang calls the world’s first thinking, reasoning autonomous vehicle AI, launching on U.S. roads later this year, starting with the Mercedes CLA. Jensen: "It's trained end-to-end. Literally from camera in to actuation out; It reasons what action it is about to take, the reason by which is came about that action, and the trajectory." Alpamayo introduces Vision-Language-Action (VLA) models, which enable self-driving systems to interpret what they see, reason about complex driving scenarios, and generate driving actions. The platform includes large reasoning models, simulation tools for testing rare and edge-case scenarios, and open datasets for training and validation. NVIDIA says the approach improves transparency, safety, and robustness in autonomous systems, particularly in complex real-world environments, and supports progress toward higher levels of vehicle autonomy: "With a 10-billion-parameter architecture, Alpamayo 1 uses video input to generate trajectories alongside reasoning traces, showing the logic behind each decision. Developers can adapt Alpamayo 1 into smaller runtime models for vehicle development, or use it as a foundation for AV development tools such as reasoning-based evaluators and auto-labeling systems. Alpamayo 1 provides open model weights and open-source inferencing scripts. Future models in the family will feature larger parameter counts, more detailed reasoning capabilities, more input and output flexibility, and options for commercial usage."

Sawyer Merritt

1,603,262 views • 6 months ago

💨 How fast can an autonomous vehicle think? With Alpamayo 1, NVIDIA's 10B-parameter chain-of-thought reasoning model, the distilled version can reason in real time. Hear Marco Pavone (Marco Pavone), Yan Wang, Yurong You, and Wenhao Ding from our AV Research team break down Alpamayo 1 and what's next for reasoning in autonomous driving. 🔁 Watch the replay:

💨 How fast can an autonomous vehicle think? With Alpamayo 1, NVIDIA's 10B-parameter chain-of-thought reasoning model, the distilled version can reason in real time. Hear Marco Pavone (Marco Pavone), Yan Wang, Yurong You, and Wenhao Ding from our AV Research team break down Alpamayo 1 and what's next for reasoning in autonomous driving. 🔁 Watch the replay:

NVIDIA DRIVE

13,606 views • 4 months ago

🚨🚨Can agents earn money, run a business, or even self-organize a society in the physical social world? 🤖🤖 Can agents learn continually to survive and thrive in embodied environments, like how human babies grow? 👶 Super excited to introduce SimWorld, an open-ended simulator of LLM agents in infinite, realistic embodied worlds. SimWorld features 3 key designs: 1⃣Open-ended realistic world simulation - built on Unreal Engine 5, with accurate physical social dynamics - 100+ built-in environments (city, island, wilderness ...) - language-controllable procedural generation - text-to-3D asset generation 2⃣Native interface for LLM/VLM agents - Gym-like agent-environment interaction APIs - plug in any LLMs/VLMs (GPTs, Gemini, Qwen ...) - rich multi-modal perception - open-vocabulary natural-language action outputs 3⃣Diverse physical and social reasoning scenarios - long-horizon embodied reasoning - multi-agent collaboration / competition - easily customizable for any reasoning tasks SimWorld is fully open-sourced, with a hope to become a foundational infrastructure for real-world agent research across disciplines: robotics, economy, public health, education, etc. Project website + more details in the thread👇 ...1/

🚨🚨Can agents earn money, run a business, or even self-organize a society in the physical social world? 🤖🤖 Can agents learn continually to survive and thrive in embodied environments, like how human babies grow? 👶 Super excited to introduce SimWorld, an open-ended simulator of LLM agents in infinite, realistic embodied worlds. SimWorld features 3 key designs: 1⃣Open-ended realistic world simulation - built on Unreal Engine 5, with accurate physical social dynamics - 100+ built-in environments (city, island, wilderness ...) - language-controllable procedural generation - text-to-3D asset generation 2⃣Native interface for LLM/VLM agents - Gym-like agent-environment interaction APIs - plug in any LLMs/VLMs (GPTs, Gemini, Qwen ...) - rich multi-modal perception - open-vocabulary natural-language action outputs 3⃣Diverse physical and social reasoning scenarios - long-horizon embodied reasoning - multi-agent collaboration / competition - easily customizable for any reasoning tasks SimWorld is fully open-sourced, with a hope to become a foundational infrastructure for real-world agent research across disciplines: robotics, economy, public health, education, etc. Project website + more details in the thread👇 ...1/

Lianhui Qin

64,864 views • 7 months ago

At #NVIDIAGTC, Jensen announced a major open source collection of physical AI agent skills and tools, available now on GitHub. The new collection helps agents tap into NVIDIA technologies including Omniverse libraries, Cosmos world foundation models, Isaac simulation frameworks, Metropolis, Alpamayo and Jetson, with skills spanning autonomous vehicles, robotics, vision AI, industrial digital twins and healthcare. Read the release ➡️

At #NVIDIAGTC, Jensen announced a major open source collection of physical AI agent skills and tools, available now on GitHub. The new collection helps agents tap into NVIDIA technologies including Omniverse libraries, Cosmos world foundation models, Isaac simulation frameworks, Metropolis, Alpamayo and Jetson, with skills spanning autonomous vehicles, robotics, vision AI, industrial digital twins and healthcare. Read the release ➡️

NVIDIA Newsroom

65,736 views • 1 month ago

Spatial reasoning is a major challenge for the foundation models today, even in simple tasks like arranging objects in 3D space. #CVPR2025 Introducing LayoutVLM, a differentiable optimization framework that uses VLM to spatially reason about diverse scene layouts from unlabeled assets and open-ended language instructions 1/n

Spatial reasoning is a major challenge for the foundation models today, even in simple tasks like arranging objects in 3D space. #CVPR2025 Introducing LayoutVLM, a differentiable optimization framework that uses VLM to spatially reason about diverse scene layouts from unlabeled assets and open-ended language instructions 1/n

Fan-Yun Sun

92,545 views • 1 year ago

How do AI agents move from simple actions to true reasoning? In Episode 6 of Making a Mind, Dr. Danielle Perszyk and Amazon AI researcher Meiqi Sun explore how reinforcement learning helps AI handle more complex, multistep challenges.

How do AI agents move from simple actions to true reasoning? In Episode 6 of Making a Mind, Dr. Danielle Perszyk and Amazon AI researcher Meiqi Sun explore how reinforcement learning helps AI handle more complex, multistep challenges.

Amazon News

25,876 views • 4 months ago