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.

What comes after vision-language-action models in robotics? 🤖 Join NVIDIA researchers live to explore World Action Models (WAMs), Vision-Language-Action models (VLAs), and hybrid robot foundation models, and see how NVIDIA Cosmos 3 natively represents action alongside video. 🕑 Thursday, Aug. 13 • 9:00–10:00 a.m. PT 📅Add calendar:

NVIDIA Robotics

146,752 subscribers

12,659 views • 2 months ago •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

Working on a new topic and hardware for a while: Feet Language Action models. VLAs teach robots to act through vision and language FLAs teach legged robots to act through contact Given a task, terrain, body state, and instruction - decide where, when, and how to make contact

Working on a new topic and hardware for a while: Feet Language Action models. VLAs teach robots to act through vision and language FLAs teach legged robots to act through contact Given a task, terrain, body state, and instruction - decide where, when, and how to make contact

Irvin (in Japan 🇯🇵)

14,015 views • 3 months ago

MolmoAct2 is landing in LeRobot! Ai2's open Action Reasoning Model combines a Molmo2-ER vision-language backbone with a flow-matching continuous action expert to predict robot action chunks from images, language instructions, and proprioceptive state. An open robot foundation model built for real-world control, with strong out-of-the-box performance and easy fine-tuning in LeRobot. Pick-and-place inference running on NVIDIA DGX Spark! Blog: Paper: Thanks to Ai2 Jiafei Duan Haoquan Fang

MolmoAct2 is landing in LeRobot! Ai2's open Action Reasoning Model combines a Molmo2-ER vision-language backbone with a flow-matching continuous action expert to predict robot action chunks from images, language instructions, and proprioceptive state. An open robot foundation model built for real-world control, with strong out-of-the-box performance and easy fine-tuning in LeRobot. Pick-and-place inference running on NVIDIA DGX Spark! Blog: Paper: Thanks to Ai2 Jiafei Duan Haoquan Fang

LeRobot

25,163 views • 4 months ago

Vision AI agents are becoming a practical way to automatically turn video data from the physical world into operational intelligence in factories, cities, warehouses and transportation systems. See how Roboflow, DeepHow, and Linker Vision use NVIDIA Cosmos and NVIDIA Metropolis to generate synthetic data, fine-tune vision models faster, and deploy vision agents at scale. 📰 Read the blog:

Vision AI agents are becoming a practical way to automatically turn video data from the physical world into operational intelligence in factories, cities, warehouses and transportation systems. See how Roboflow, DeepHow, and Linker Vision use NVIDIA Cosmos and NVIDIA Metropolis to generate synthetic data, fine-tune vision models faster, and deploy vision agents at scale. 📰 Read the blog:

NVIDIA Omniverse

21,412 views • 3 months ago

🤖 NVIDIA’s Gr00t N1.5 is now available in LeRobot! This is the result of a great collaboration between the Hugging Face LeRobot team and NVIDIA Robotics ! Gr00t N1.5 highlights: 🦾 Cross-embodiment foundation model for robots 🧠 Multimodal inputs: vision, language, and proprioception 🪛Tested on the Libero benchmark and real-world hardware tasks 🌍Trained on real robot, synthetic, and internet-scale video data ⚙️ Flow matching action transformer for action prediction

🤖 NVIDIA’s Gr00t N1.5 is now available in LeRobot! This is the result of a great collaboration between the Hugging Face LeRobot team and NVIDIA Robotics ! Gr00t N1.5 highlights: 🦾 Cross-embodiment foundation model for robots 🧠 Multimodal inputs: vision, language, and proprioception 🪛Tested on the Libero benchmark and real-world hardware tasks 🌍Trained on real robot, synthetic, and internet-scale video data ⚙️ Flow matching action transformer for action prediction

LeRobot

115,194 views • 11 months ago

See how Gemini 3 Flash and Vision-Language-Action (VLA) models work together to teach a robot how to play the board game First Orchard. This project shows how to use Gemini as the “brain” for tracking game rules and state, while the VLA handles complex physical manipulations like picking and placing fruit 🍎

See how Gemini 3 Flash and Vision-Language-Action (VLA) models work together to teach a robot how to play the board game First Orchard. This project shows how to use Gemini as the “brain” for tracking game rules and state, while the VLA handles complex physical manipulations like picking and placing fruit 🍎

Google AI Developers

26,640 views • 7 months ago

Ready to bring AI into the physical world? 🤖 Join our livestream on Tuesday, August 11th at 9:00am PT to learn how to: 🧠 Run and fine-tune NVIDIA GR00T 1.7 🔗 Connect models, sensors, and actuators with ROS 2 🦾 Deploy a model on the SO-101 robot arm to execute a real-world task 🎙️Guest speaker Nikodem Bartnik will also share the latest advances and highlights from the open-source robotics community. Add to calendar:

Ready to bring AI into the physical world? 🤖 Join our livestream on Tuesday, August 11th at 9:00am PT to learn how to: 🧠 Run and fine-tune NVIDIA GR00T 1.7 🔗 Connect models, sensors, and actuators with ROS 2 🦾 Deploy a model on the SO-101 robot arm to execute a real-world task 🎙️Guest speaker Nikodem Bartnik will also share the latest advances and highlights from the open-source robotics community. Add to calendar:

NVIDIA Robotics

23,709 views • 2 months ago

Building robots that can effectively operate alongside human workers is difficult. 🛠️ Advances in open-source physics, open foundation models, and frameworks are helping accelerate physical #AI deployment. ✔️ Newton Physics Engine, an open-source GPU-powered simulation built on OpenUSD, speeds up robot learning for advanced manipulation and mobility. ✔️ NVIDIA Cosmos Reason, an open reasoning vision language model, gives robots the ability to think like humans using prior knowledge, common sense and physics ✔️NVIDIA Isaac GR00T N1.6, an open robot foundation model, enables humanoids to understand ambiguous instructions Leading robotics developers including Agility Robotics, Lightwheel, Mentee Robotics, UniversalRobots, and Wandelbots are adopting simulation technologies and libraries to accelerate physical AI development and deployment. Omniverse Ambassador Dylan Tobin built an AI chatbot trained on Isaac Sim workflows, helping devs navigate Omniverse faster. Read the full blog 👉

Building robots that can effectively operate alongside human workers is difficult. 🛠️ Advances in open-source physics, open foundation models, and frameworks are helping accelerate physical #AI deployment. ✔️ Newton Physics Engine, an open-source GPU-powered simulation built on OpenUSD, speeds up robot learning for advanced manipulation and mobility. ✔️ NVIDIA Cosmos Reason, an open reasoning vision language model, gives robots the ability to think like humans using prior knowledge, common sense and physics ✔️NVIDIA Isaac GR00T N1.6, an open robot foundation model, enables humanoids to understand ambiguous instructions Leading robotics developers including Agility Robotics, Lightwheel, Mentee Robotics, UniversalRobots, and Wandelbots are adopting simulation technologies and libraries to accelerate physical AI development and deployment. Omniverse Ambassador Dylan Tobin built an AI chatbot trained on Isaac Sim workflows, helping devs navigate Omniverse faster. Read the full blog 👉

NVIDIA

48,500 views • 1 year ago

Current Vision-Language-Action (VLA) paradigms in autonomous driving primarily rely on Imitation Learning (IL), which introduces inherent challenges such as distribution shift and causal confusion. Online Reinforcement Learning offers a promising pathway to address these issues through trial-and-error learning. However, applying online reinforcement learning to VLA models in autonomous driving is hindered by inefficient exploration in continuous action spaces. MindDrive, a VLA framework comprising a large language model (LLM) with two distinct sets of LoRA parameters. The one LLM serves as a Decision Expert for scenario reasoning and driving decision-making, while the other acts as an Action Expert that dynamically maps linguistic decisions into feasible trajectories. Paper Title: MindDrive: A Vision-Language-Action Model for Autonomous Driving via Project: Link:

Current Vision-Language-Action (VLA) paradigms in autonomous driving primarily rely on Imitation Learning (IL), which introduces inherent challenges such as distribution shift and causal confusion. Online Reinforcement Learning offers a promising pathway to address these issues through trial-and-error learning. However, applying online reinforcement learning to VLA models in autonomous driving is hindered by inefficient exploration in continuous action spaces. MindDrive, a VLA framework comprising a large language model (LLM) with two distinct sets of LoRA parameters. The one LLM serves as a Decision Expert for scenario reasoning and driving decision-making, while the other acts as an Action Expert that dynamically maps linguistic decisions into feasible trajectories. Paper Title: MindDrive: A Vision-Language-Action Model for Autonomous Driving via Project: Link:

AI Bites | YouTube Channel

43,556 views • 8 months ago

In a masterclass at Sequoia Capital AI Ascent, Jim Fan laid out the "Great Parallel": how robotics is speedrunning the LLM playbook. 🔹 VLA → WAM: Moving from language-heavy models to "World Action Models" that dream in physics. 🔹 Teleop → EgoScale: Replacing manual data with human egocentric video. 🔹 Simulation 2.0: Using neural simulators like DreamDojo to turn compute into environments. "Our generation was born too late to explore the earth and too early to explore the stars. But we are born just in time to solve robotics." He believes that robots will pass the Physical Turing Test in the coming 2–3 years.

In a masterclass at Sequoia Capital AI Ascent, Jim Fan laid out the "Great Parallel": how robotics is speedrunning the LLM playbook. 🔹 VLA → WAM: Moving from language-heavy models to "World Action Models" that dream in physics. 🔹 Teleop → EgoScale: Replacing manual data with human egocentric video. 🔹 Simulation 2.0: Using neural simulators like DreamDojo to turn compute into environments. "Our generation was born too late to explore the earth and too early to explore the stars. But we are born just in time to solve robotics." He believes that robots will pass the Physical Turing Test in the coming 2–3 years.

Humanoids daily

12,123 views • 5 months ago

💚🤗💚 Jensen showing Hugging Face during GTC keynote, where NVIDIA AI dropped amazing new open models, datasets and blogs! Some of my favorites, links in comments: 🧠 Nemotron 3 Super 120A12B - Reasoning LLM 🏥 Open-H-Embodiment - Healthcare Robotics Dataset 🩻 Cosmos-H-Surgical-Simulator - World Foundation Model 🚕 Alpamayo 1.5 - Autonomous Vehicle Model and Datasets 🕺 Kimodo v1 - Generate body movement from prompts! And SO MUCH MORE to explore at

💚🤗💚 Jensen showing Hugging Face during GTC keynote, where NVIDIA AI dropped amazing new open models, datasets and blogs! Some of my favorites, links in comments: 🧠 Nemotron 3 Super 120A12B - Reasoning LLM 🏥 Open-H-Embodiment - Healthcare Robotics Dataset 🩻 Cosmos-H-Surgical-Simulator - World Foundation Model 🚕 Alpamayo 1.5 - Autonomous Vehicle Model and Datasets 🕺 Kimodo v1 - Generate body movement from prompts! And SO MUCH MORE to explore at

Jeff Boudier 🤗

19,922 views • 6 months ago

New startup out of stealth in Cambridge MA: Eka Robotics. The company is building intelligence for the physical world in its native language: FORCE. Their core solution to mastering fast, reliable adaptive robots: Vision-Force-Action (VFA) model: - sim-only reinforcement learning - no human teleop data - robot practices thousands of hours in a physics-rich simulator (mass, inertia) and comes up with its own solutions, AlphaZero-style. - custom grippers add touch sensing; the model maps pixels + felt force to actions.

New startup out of stealth in Cambridge MA: Eka Robotics. The company is building intelligence for the physical world in its native language: FORCE. Their core solution to mastering fast, reliable adaptive robots: Vision-Force-Action (VFA) model: - sim-only reinforcement learning - no human teleop data - robot practices thousands of hours in a physics-rich simulator (mass, inertia) and comes up with its own solutions, AlphaZero-style. - custom grippers add touch sensing; the model maps pixels + felt force to actions.

The Humanoid Hub

12,845 views • 5 months ago

Today may be the ImageNet moment for robotics. RT-X: the largest open-source robot dataset ever compiled, across 33 institutes, 22 robot hardware, 527 skills, and 1M episodes. Why is robotics lagging so far behind NLP, vision, and other AI domains? Data scarcity is the main culprit to blame, among other difficulties. Unlike text, images, and videos, you cannot download mass amounts of onboard robot control data from the internet. They simply don't exist in the wild. 11 yrs ago, ImageNet kicked off the deep learning revolution. 3-4 yrs ago, internet-scale data fueled the first GPTs and Diffusions that define this era of foundation models. I think 2023 is finally the year for robotics to scale up. Robot foundation models like VIMA ( my team's work at NVIDIA) and RT-1/2 ( Google DeepMind's effort) are extremely data hungry. While massively parallel simulations like NVIDIA IsaacGym & Omniverse can alleviate the problem to some extent, it's still not quite enough to bridge the gap to the messy, physical world. This new dataset is not just a technical contribution. I also see it as a commendable effort to overcome institutional bureaucracies and unite researchers from around the world to tackle a grand challenge together. Robotics will be the final holy grail that we capture in AI. We are not there yet, but ascending in the right gradient direction. RT-X website: Launch blog:

Today may be the ImageNet moment for robotics. RT-X: the largest open-source robot dataset ever compiled, across 33 institutes, 22 robot hardware, 527 skills, and 1M episodes. Why is robotics lagging so far behind NLP, vision, and other AI domains? Data scarcity is the main culprit to blame, among other difficulties. Unlike text, images, and videos, you cannot download mass amounts of onboard robot control data from the internet. They simply don't exist in the wild. 11 yrs ago, ImageNet kicked off the deep learning revolution. 3-4 yrs ago, internet-scale data fueled the first GPTs and Diffusions that define this era of foundation models. I think 2023 is finally the year for robotics to scale up. Robot foundation models like VIMA ( my team's work at NVIDIA) and RT-1/2 ( Google DeepMind's effort) are extremely data hungry. While massively parallel simulations like NVIDIA IsaacGym & Omniverse can alleviate the problem to some extent, it's still not quite enough to bridge the gap to the messy, physical world. This new dataset is not just a technical contribution. I also see it as a commendable effort to overcome institutional bureaucracies and unite researchers from around the world to tackle a grand challenge together. Robotics will be the final holy grail that we capture in AI. We are not there yet, but ascending in the right gradient direction. RT-X website: Launch blog:

Jim Fan

265,061 views • 3 years ago

We just hit a new huge milestone. 🏆 Thanks to our amazing community, we have now reached 170,000 3D Maps across the world. Here are the numbers that define what we’ve built so far: ↳ 170,000 mapped locations ↳ 767 TB of world data ↳ 85.2M+ images captured ↳ And a steady, unstoppable month over month growth. A single dataset designed to help machines see, understand, and navigate space, also used to train spatial AI and visual models, and to geolocalize robots and experiences with precision through our VPS, in order to interact seamlessly with the real world. And yes... you read that right! We are already in talks with several top AI companies that want access to our dataset to train their AI models and to support what comes next, including robotics and advanced visual and video models. It is all one story, one ecosystem, one vision, and it is called Over the Reality.

We just hit a new huge milestone. 🏆 Thanks to our amazing community, we have now reached 170,000 3D Maps across the world. Here are the numbers that define what we’ve built so far: ↳ 170,000 mapped locations ↳ 767 TB of world data ↳ 85.2M+ images captured ↳ And a steady, unstoppable month over month growth. A single dataset designed to help machines see, understand, and navigate space, also used to train spatial AI and visual models, and to geolocalize robots and experiences with precision through our VPS, in order to interact seamlessly with the real world. And yes... you read that right! We are already in talks with several top AI companies that want access to our dataset to train their AI models and to support what comes next, including robotics and advanced visual and video models. It is all one story, one ecosystem, one vision, and it is called Over the Reality.

Over the Reality 🌐

93,234 views • 10 months ago

𝗗𝗼𝗻'𝘁 𝗳𝗶𝗻𝗲-𝘁𝘂𝗻𝗲 𝗿𝗼𝗯𝗼𝘁 𝗳𝗼𝘂𝗻𝗱𝗮𝘁𝗶𝗼𝗻 𝗺𝗼𝗱𝗲𝗹𝘀. 𝗦𝘁𝗲𝗲𝗿 𝘁𝗵𝗲𝗺 𝘄𝗶𝘁𝗵 𝗵𝘂𝗺𝗮𝗻 𝗰𝗼𝗿𝗿𝗲𝗰𝘁𝗶𝗼𝗻𝘀 𝗶𝗻𝘀𝘁𝗲𝗮𝗱, 𝘄𝗶𝘁𝗵𝗼𝘂𝘁 𝗰𝗵𝗮𝗻𝗴𝗶𝗻𝗴 𝘁𝗵𝗲 𝗯𝗮𝘀𝗲 𝗽𝗼𝗹𝗶𝗰𝘆 Modern VLAs and world-action models can perform impressive manipulation skills, but adapting them reliably to new robots and tasks remains challenging. A natural solution is DAgger-style online imitation learning: deploy the robot, collect human corrections, and update the policy. Yet foundation models are fragile in the low-data regime, fine-tuning on a handful of interventions can improve one behavior while degrading others. Online post-training or reinforcement learning can require costly data collection and exploration, making real-world learning expensive and potentially unsafe. In our new paper, 𝗙𝗹𝗼𝘄𝗗𝗔𝗴𝗴𝗲𝗿, we take a different approach: 𝗜𝗻𝘀𝘁𝗲𝗮𝗱 𝗼𝗳 𝗰𝗵𝗮𝗻𝗴𝗶𝗻𝗴 𝘁𝗵𝗲 𝗳𝗼𝘂𝗻𝗱𝗮𝘁𝗶𝗼𝗻 𝗺𝗼𝗱𝗲𝗹, 𝘄𝗲 𝗹𝗲𝗮𝗿𝗻 𝗵𝗼𝘄 𝘁𝗼 𝘀𝘁𝗲𝗲𝗿 𝗶𝘁 𝗳𝗿𝗼𝗺 𝗵𝘂𝗺𝗮𝗻 𝗰𝗼𝗿𝗿𝗲𝗰𝘁𝗶𝗼𝗻𝘀. The key idea is 𝗮𝗰𝘁𝗶𝗼𝗻 𝗶𝗻𝘃𝗲𝗿𝘀𝗶𝗼𝗻: we map human corrective actions back into the latent noise space of the frozen generative policy. These latent targets train a lightweight controller that adapts the robot while preserving the original model's capabilities. Across simulation and real robots, FlowDAgger: 📈 Learns from only 5–20 human intervention episodes 🏆 Outperforms supervised fine-tuning and latent-space reinforcement learning 🤖 Works across VLAs, diffusion policies, and world-action models ✔️ Provides reliable improvements without modifying the pretrained policy We believe this offers a practical path toward making robot foundation models improve during deployment, learning from the way humans naturally teach: through corrections. 📄 Paper: 🌐 Project: 💻 Code: This project was led by my amazing colleague Michael Murray with help from Daphne Chen, Simran Bagaria, Dean Fortier, Tess Hellebrekers, Harshavardhan Reddy Gajarla, Galen Mullins and Andrey Kolobov at Microsoft Research and Maya Cakmak at University of Washington

𝗗𝗼𝗻'𝘁 𝗳𝗶𝗻𝗲-𝘁𝘂𝗻𝗲 𝗿𝗼𝗯𝗼𝘁 𝗳𝗼𝘂𝗻𝗱𝗮𝘁𝗶𝗼𝗻 𝗺𝗼𝗱𝗲𝗹𝘀. 𝗦𝘁𝗲𝗲𝗿 𝘁𝗵𝗲𝗺 𝘄𝗶𝘁𝗵 𝗵𝘂𝗺𝗮𝗻 𝗰𝗼𝗿𝗿𝗲𝗰𝘁𝗶𝗼𝗻𝘀 𝗶𝗻𝘀𝘁𝗲𝗮𝗱, 𝘄𝗶𝘁𝗵𝗼𝘂𝘁 𝗰𝗵𝗮𝗻𝗴𝗶𝗻𝗴 𝘁𝗵𝗲 𝗯𝗮𝘀𝗲 𝗽𝗼𝗹𝗶𝗰𝘆 Modern VLAs and world-action models can perform impressive manipulation skills, but adapting them reliably to new robots and tasks remains challenging. A natural solution is DAgger-style online imitation learning: deploy the robot, collect human corrections, and update the policy. Yet foundation models are fragile in the low-data regime, fine-tuning on a handful of interventions can improve one behavior while degrading others. Online post-training or reinforcement learning can require costly data collection and exploration, making real-world learning expensive and potentially unsafe. In our new paper, 𝗙𝗹𝗼𝘄𝗗𝗔𝗴𝗴𝗲𝗿, we take a different approach: 𝗜𝗻𝘀𝘁𝗲𝗮𝗱 𝗼𝗳 𝗰𝗵𝗮𝗻𝗴𝗶𝗻𝗴 𝘁𝗵𝗲 𝗳𝗼𝘂𝗻𝗱𝗮𝘁𝗶𝗼𝗻 𝗺𝗼𝗱𝗲𝗹, 𝘄𝗲 𝗹𝗲𝗮𝗿𝗻 𝗵𝗼𝘄 𝘁𝗼 𝘀𝘁𝗲𝗲𝗿 𝗶𝘁 𝗳𝗿𝗼𝗺 𝗵𝘂𝗺𝗮𝗻 𝗰𝗼𝗿𝗿𝗲𝗰𝘁𝗶𝗼𝗻𝘀. The key idea is 𝗮𝗰𝘁𝗶𝗼𝗻 𝗶𝗻𝘃𝗲𝗿𝘀𝗶𝗼𝗻: we map human corrective actions back into the latent noise space of the frozen generative policy. These latent targets train a lightweight controller that adapts the robot while preserving the original model's capabilities. Across simulation and real robots, FlowDAgger: 📈 Learns from only 5–20 human intervention episodes 🏆 Outperforms supervised fine-tuning and latent-space reinforcement learning 🤖 Works across VLAs, diffusion policies, and world-action models ✔️ Provides reliable improvements without modifying the pretrained policy We believe this offers a practical path toward making robot foundation models improve during deployment, learning from the way humans naturally teach: through corrections. 📄 Paper: 🌐 Project: 💻 Code: This project was led by my amazing colleague Michael Murray with help from Daphne Chen, Simran Bagaria, Dean Fortier, Tess Hellebrekers, Harshavardhan Reddy Gajarla, Galen Mullins and Andrey Kolobov at Microsoft Research and Maya Cakmak at University of Washington

Oier Mees

13,469 views • 2 months ago

🚨 BREAKING: NVIDIA just announced the Isaac GR00T Reference Humanoid Robot. The first fully open humanoid robot reference design built on Jetson Thor, and it's going straight to the world's top research institutions. This is Jensen Huang's bet on open physical AI infrastructure. The hardware stack is serious: → Unitree H2 Plus chassis, 6 feet tall, 150 pounds, 31 degrees of freedom → Sharpa Wave tactile five-finger hands, 22 degrees of freedom, bringing total to 75 across the full body → NVIDIA Jetson AGX Thor onboard compute, 2,070 FP4 teraflops of AI performance, 128GB unified memory → Multi-view sensing, stereo head camera, wrist cameras, IMU Alongside this announcement, Unitree also introduced the H2 Plus as a standalone product, a frontier humanoid combining Unitree's own body, Sharpa's five-finger hands and NVIDIA Robotics Jetson Thor compute into one fully integrated research platform. The full Isaac GR00T software stack ships with it, teleoperation for data capture, open foundation models, Isaac Sim for training, Isaac Lab for evaluation, and accelerated ROS middleware for deployment. The complete loop from data to real-world robot in one unified platform. ETH Zürich, Stanford Robotics Center, UC San Diego and Ai2 are already on board as launch research partners. NVIDIA Robotics did to AI what it's now doing to robotics, build the platform, open the ecosystem, let the world build on top of it. Whoever owns the infrastructure layer wins. NVIDIA knows this better than anyone. 👀 Read more here: ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →

🚨 BREAKING: NVIDIA just announced the Isaac GR00T Reference Humanoid Robot. The first fully open humanoid robot reference design built on Jetson Thor, and it's going straight to the world's top research institutions. This is Jensen Huang's bet on open physical AI infrastructure. The hardware stack is serious: → Unitree H2 Plus chassis, 6 feet tall, 150 pounds, 31 degrees of freedom → Sharpa Wave tactile five-finger hands, 22 degrees of freedom, bringing total to 75 across the full body → NVIDIA Jetson AGX Thor onboard compute, 2,070 FP4 teraflops of AI performance, 128GB unified memory → Multi-view sensing, stereo head camera, wrist cameras, IMU Alongside this announcement, Unitree also introduced the H2 Plus as a standalone product, a frontier humanoid combining Unitree's own body, Sharpa's five-finger hands and NVIDIA Robotics Jetson Thor compute into one fully integrated research platform. The full Isaac GR00T software stack ships with it, teleoperation for data capture, open foundation models, Isaac Sim for training, Isaac Lab for evaluation, and accelerated ROS middleware for deployment. The complete loop from data to real-world robot in one unified platform. ETH Zürich, Stanford Robotics Center, UC San Diego and Ai2 are already on board as launch research partners. NVIDIA Robotics did to AI what it's now doing to robotics, build the platform, open the ecosystem, let the world build on top of it. Whoever owns the infrastructure layer wins. NVIDIA knows this better than anyone. 👀 Read more here: ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →

Lukas Ziegler

16,062 views • 4 months ago

1/ World models are getting popular in robotics 🤖✨ But there’s a big problem: most are slow and break physical consistency over long horizons. 2/ Today we’re releasing Interactive World Simulator: An action-conditioned world model that supports stable long-horizon interaction. 3/ Key result: ✅ 10+ minutes of interactive prediction ✅ 15 FPS ✅ on a single RTX 4090🔥 4/ Why this matters: it unlocks two critical robotics applications: 🚀 Scalable data generation for policy training 🧪 Faithful policy evaluation 5/ You can play with our world model NOW at NO git clone, NO pip install, NO python. Just click and play! NOTE ⚠️ ALL videos here are generated purely by our model in pixel space! They are **NOT** from a real camera More details coming 👇 (1/9) #Robotics #AI #MachineLearning #WorldModels #RobotLearning #ImitationLearning

1/ World models are getting popular in robotics 🤖✨ But there’s a big problem: most are slow and break physical consistency over long horizons. 2/ Today we’re releasing Interactive World Simulator: An action-conditioned world model that supports stable long-horizon interaction. 3/ Key result: ✅ 10+ minutes of interactive prediction ✅ 15 FPS ✅ on a single RTX 4090🔥 4/ Why this matters: it unlocks two critical robotics applications: 🚀 Scalable data generation for policy training 🧪 Faithful policy evaluation 5/ You can play with our world model NOW at NO git clone, NO pip install, NO python. Just click and play! NOTE ⚠️ ALL videos here are generated purely by our model in pixel space! They are NOT from a real camera More details coming 👇 (1/9) #Robotics #AI #MachineLearning #WorldModels #RobotLearning #ImitationLearning

Yixuan Wang

130,477 views • 7 months ago

AI Is Moving Beyond “Generating Videos” — Toward “Generating Worlds” Over the past two years, AI video models have advanced at an astonishing pace. From Runway and Pika to Sora and Veo, AI-generated videos have become increasingly realistic and more consistent with the physical laws of the real world. Many people believe the next objective is simply to generate videos that are longer, sharper, and more lifelike. But if we take a step back, we can see that the real transformation is not happening in video itself. It is happening in world models. What Is a World Model? In 1943, psychologist Kenneth Craik proposed an idea that would influence artificial intelligence research for decades. He argued that the human brain does not merely react to the outside world. Instead, it maintains an internal model of how the world works. Because we have this internal model, we can predict the outcome of an action before we actually take it. Before crossing a road, we estimate whether a car will pass by. Before catching a ball, we predict its trajectory. These abilities come from continuously simulating the world in our minds, rather than relying entirely on trial and error. This idea later became known by a more formal term: World Model. A world model does not describe a single image or a fixed video clip. It is an internal representation capable of continuously simulating the rules and dynamics of the real world. Why Is AI Research Turning Toward World Models? Because predicting “what comes next” is becoming increasingly central to how AI systems work. Language models predict the next token. Image models predict the next step in the denoising process. Video models predict the next frame. A world model, however, attempts to predict something broader: What should the world look like in the next moment? In 2018, David Ha and Jürgen Schmidhuber proposed in their paper World Models that an intelligent agent could first learn a model of the world, and then use that internal model to plan its actions. The Dreamer series later demonstrated that many complex tasks could be learned by training agents inside an “imagined world.” At the same time, the development of video models such as Sora and Veo led researchers to another realization: A model capable of continuously generating video has already learned, at least implicitly, many of the rules governing the real world. As a result, these two research directions have gradually begun to converge. But Video Is Not Yet a World This is where the distinction is often misunderstood. For a world model to support meaningful real-time interaction, it must solve several critical problems. Most video models today are essentially answering one question: What should the next frame look like? A true world model needs to answer much more: What happens if I take one step forward? If I walk behind a building and then return, will the building still be there? If I suddenly change the camera angle, will the entire space remain consistent? If I enter a command such as: “Summon a dragon.” Will the world respond immediately? In other words, a world model must do more than generate content. It must understand space. It must understand time. It must understand causality. And it must understand interaction. Moving from watching to participating is where the real difficulty of world models begins. World Models Are Entering the Interactive Era One of the latest attempts in this direction is Alaya World, recently open-sourced by Alaya World, or Alaya Lab. Instead of generating a fixed video clip, it generates a world that users can explore in real time. Users can begin with text, an image, or a video, enter the generated scene, move freely through it, and introduce new prompts at any moment during generation. The world responds immediately. According to the publicly released information, Alaya World provides: Real-time streaming generation at 720p and 24 FPS Stable continuous exploration for more than one minute The ability to switch prompts and trigger skills or events during generation Model weights and inference code released under the Apache 2.0 License Training code and datasets planned for future release What makes these capabilities important is not simply the technical specifications. It is that the generated “world” can now support continuous interaction. The official demo shows that users can genuinely control, transform, and explore the generated environment. AI Is Evolving From a Tool Into an Environment Over the past few years, most discussions around AI have focused on content generation. Generating text. Generating images. Generating videos. But world models raise a fundamentally different question: Can AI generate an environment that people can inhabit, explore, and continuously evolve? If the answer is yes, the impact will extend far beyond video generation. Game development, robotics training, embodied intelligence, digital twins, virtual production, and many other fields could be transformed by the development of world models. World models are still at a very early stage. Yet from Craik’s proposal of an internal mental model more than eighty years ago to the emergence of today’s interactive world-generation systems, a clear evolutionary path is beginning to take shape. Perhaps what AI is ultimately learning has never been limited to images, videos, or language. Perhaps it is learning the world itself. References GitHub: Technical Report:

AI Is Moving Beyond “Generating Videos” — Toward “Generating Worlds” Over the past two years, AI video models have advanced at an astonishing pace. From Runway and Pika to Sora and Veo, AI-generated videos have become increasingly realistic and more consistent with the physical laws of the real world. Many people believe the next objective is simply to generate videos that are longer, sharper, and more lifelike. But if we take a step back, we can see that the real transformation is not happening in video itself. It is happening in world models. What Is a World Model? In 1943, psychologist Kenneth Craik proposed an idea that would influence artificial intelligence research for decades. He argued that the human brain does not merely react to the outside world. Instead, it maintains an internal model of how the world works. Because we have this internal model, we can predict the outcome of an action before we actually take it. Before crossing a road, we estimate whether a car will pass by. Before catching a ball, we predict its trajectory. These abilities come from continuously simulating the world in our minds, rather than relying entirely on trial and error. This idea later became known by a more formal term: World Model. A world model does not describe a single image or a fixed video clip. It is an internal representation capable of continuously simulating the rules and dynamics of the real world. Why Is AI Research Turning Toward World Models? Because predicting “what comes next” is becoming increasingly central to how AI systems work. Language models predict the next token. Image models predict the next step in the denoising process. Video models predict the next frame. A world model, however, attempts to predict something broader: What should the world look like in the next moment? In 2018, David Ha and Jürgen Schmidhuber proposed in their paper World Models that an intelligent agent could first learn a model of the world, and then use that internal model to plan its actions. The Dreamer series later demonstrated that many complex tasks could be learned by training agents inside an “imagined world.” At the same time, the development of video models such as Sora and Veo led researchers to another realization: A model capable of continuously generating video has already learned, at least implicitly, many of the rules governing the real world. As a result, these two research directions have gradually begun to converge. But Video Is Not Yet a World This is where the distinction is often misunderstood. For a world model to support meaningful real-time interaction, it must solve several critical problems. Most video models today are essentially answering one question: What should the next frame look like? A true world model needs to answer much more: What happens if I take one step forward? If I walk behind a building and then return, will the building still be there? If I suddenly change the camera angle, will the entire space remain consistent? If I enter a command such as: “Summon a dragon.” Will the world respond immediately? In other words, a world model must do more than generate content. It must understand space. It must understand time. It must understand causality. And it must understand interaction. Moving from watching to participating is where the real difficulty of world models begins. World Models Are Entering the Interactive Era One of the latest attempts in this direction is Alaya World, recently open-sourced by Alaya World, or Alaya Lab. Instead of generating a fixed video clip, it generates a world that users can explore in real time. Users can begin with text, an image, or a video, enter the generated scene, move freely through it, and introduce new prompts at any moment during generation. The world responds immediately. According to the publicly released information, Alaya World provides: Real-time streaming generation at 720p and 24 FPS Stable continuous exploration for more than one minute The ability to switch prompts and trigger skills or events during generation Model weights and inference code released under the Apache 2.0 License Training code and datasets planned for future release What makes these capabilities important is not simply the technical specifications. It is that the generated “world” can now support continuous interaction. The official demo shows that users can genuinely control, transform, and explore the generated environment. AI Is Evolving From a Tool Into an Environment Over the past few years, most discussions around AI have focused on content generation. Generating text. Generating images. Generating videos. But world models raise a fundamentally different question: Can AI generate an environment that people can inhabit, explore, and continuously evolve? If the answer is yes, the impact will extend far beyond video generation. Game development, robotics training, embodied intelligence, digital twins, virtual production, and many other fields could be transformed by the development of world models. World models are still at a very early stage. Yet from Craik’s proposal of an internal mental model more than eighty years ago to the emergence of today’s interactive world-generation systems, a clear evolutionary path is beginning to take shape. Perhaps what AI is ultimately learning has never been limited to images, videos, or language. Perhaps it is learning the world itself. References GitHub: Technical Report:

雪踏乌云

113,347 views • 2 months ago

🛠️ What if a robot could invent its own tools. And teach itself how to use them? That’s exactly what VLMgineer does: a new framework that lets Vision Language Models (VLMs) design physical tools and the actions to use them, entirely on their own. No templates. No human demonstrations. Just raw, AI-driven creativity. Why it matters ✅ Co-designs tools and actions together using VLMs, ensuring tight coupling between form and function ✅ Uses VLM-guided evolution (not random search) to refine designs intelligently ✅ Outperforms human-designed tools by +64.7% in task success across 12 RoboToolBench challenges ✅ Produces better-than-everyday tools for real manipulation tasks—measured in success rate and elegance It builds on the emerging trend of large-model-guided evolutionary design (like Eureka and AlphaEvolve) and brings it into physical robotics. It opens the door to general-purpose, automated hardware design, no strong priors needed. Code & paper: —- Weekly robotics and AI insights. Subscribe free:

🛠️ What if a robot could invent its own tools. And teach itself how to use them? That’s exactly what VLMgineer does: a new framework that lets Vision Language Models (VLMs) design physical tools and the actions to use them, entirely on their own. No templates. No human demonstrations. Just raw, AI-driven creativity. Why it matters ✅ Co-designs tools and actions together using VLMs, ensuring tight coupling between form and function ✅ Uses VLM-guided evolution (not random search) to refine designs intelligently ✅ Outperforms human-designed tools by +64.7% in task success across 12 RoboToolBench challenges ✅ Produces better-than-everyday tools for real manipulation tasks—measured in success rate and elegance It builds on the emerging trend of large-model-guided evolutionary design (like Eureka and AlphaEvolve) and brings it into physical robotics. It opens the door to general-purpose, automated hardware design, no strong priors needed. Code & paper: —- Weekly robotics and AI insights. Subscribe free:

Ilir Aliu

14,294 views • 9 months ago

🚨 BREAKING: Walden Robotics has just come out of stealth with $300 million in funding and a $1.1 billion valuation. Another unicorn in the robotics space. 🦄 Just 6 months after incubation. The company was spun out of Toyota's robotics research lab by co-founder Russ Tedrake, a former Toyota Research Institute executive and MIT professor who taught a course on robotic legs. The seed round was co-led by Deviation Capital and Toyota, with participation from: NVIDIA, Boeing, Samsung Ventures, CoreWeave Ventures and AE Ventures. The robot is already working. A pilot is live at a North American Toyota factory where a Walden humanoid is pulling eight-hour shifts alongside human workers, loading and unloading car parts, cleaning machinery, kitting for assembly. A shift. Every day. Walden builds its own hardware, software and AI models, designed to continuously learn and improve in real production environments. Tedrake's words on the opportunity are worth noting: "Everyone recognises the magnitude of the opportunity and the technology feels ready, but success is not assured. You have to think through the business case, the unit economics, and how to marry the best of manufacturing and logistics with disruptive AI technology." Rare honesty in a space full of hype. The race to own that market is accelerating every single week. 🤖 Great story by Bloomberg here: ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →

🚨 BREAKING: Walden Robotics has just come out of stealth with $300 million in funding and a $1.1 billion valuation. Another unicorn in the robotics space. 🦄 Just 6 months after incubation. The company was spun out of Toyota's robotics research lab by co-founder Russ Tedrake, a former Toyota Research Institute executive and MIT professor who taught a course on robotic legs. The seed round was co-led by Deviation Capital and Toyota, with participation from: NVIDIA, Boeing, Samsung Ventures, CoreWeave Ventures and AE Ventures. The robot is already working. A pilot is live at a North American Toyota factory where a Walden humanoid is pulling eight-hour shifts alongside human workers, loading and unloading car parts, cleaning machinery, kitting for assembly. A shift. Every day. Walden builds its own hardware, software and AI models, designed to continuously learn and improve in real production environments. Tedrake's words on the opportunity are worth noting: "Everyone recognises the magnitude of the opportunity and the technology feels ready, but success is not assured. You have to think through the business case, the unit economics, and how to marry the best of manufacturing and logistics with disruptive AI technology." Rare honesty in a space full of hype. The race to own that market is accelerating every single week. 🤖 Great story by Bloomberg here: ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →

Lukas Ziegler

76,642 views • 2 months ago