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.

We’ve seen humanoid robots walk around for a while, but when will they actually help with useful tasks in daily life? The challenge here is the diversity and complexity of real-world scenes. Our new work tackles this problem via 3D visuomotor policy learning. Using data from only 1 scene,... show more

Yanjie Ze

5,826 subscribers

75,515 views • 2 years ago •via X (Twitter)

Science & Technology Arts Education

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

Elon Musk: "There are no useful humanoid robots at this point. There are sort of gimmicks, but there are no actually useful humanoid robots. And I think Tesla's going to make the first actually useful humanoid robots."

Elon Musk: "There are no useful humanoid robots at this point. There are sort of gimmicks, but there are no actually useful humanoid robots. And I think Tesla's going to make the first actually useful humanoid robots."

Joe Rogan Podcast News

88,521 views • 4 months ago

Predicting what a robot will feel as it moves. Our 3D World Simulator learns to predict touch as 3D particles alongside scene geometry, keeping tactile signals aligned with contact surfaces as interactions unfold. Learning from these predicted visual and tactile observations helps robots perform contact-rich manipulation in the real world. Glad to see a world model learning from FlexiTac data. The tactile predictions look really impressive!

Predicting what a robot will feel as it moves. Our 3D World Simulator learns to predict touch as 3D particles alongside scene geometry, keeping tactile signals aligned with contact surfaces as interactions unfold. Learning from these predicted visual and tactile observations helps robots perform contact-rich manipulation in the real world. Glad to see a world model learning from FlexiTac data. The tactile predictions look really impressive!

Binghao Huang ✈️ CoRL

17,116 views • 10 days ago

What does a real humanoid robotics dataset actually look like? Humanoid robots are expensive and complex, which makes their data unusually difficult to collect - and difficult for most people to get hands-on experience with. We previously shared a post on conversion code for the new Human in the Wild dataset by BitRobot 🦾, Hugging Face, and Unitree. Now we’re publishing the full HIW-500 data converted to RRD, so you can explore that data directly with Rerun. Watch the robot move. Inspect cameras and robot states together. Zoom in on a moment and query episodes through Rerun catalog! If you’re curious about a real-world humanoid dataset, HIW-500 is now a lot easier to explore. We share the conversion code along with our previous abc-130k dataset conversion example.

What does a real humanoid robotics dataset actually look like? Humanoid robots are expensive and complex, which makes their data unusually difficult to collect - and difficult for most people to get hands-on experience with. We previously shared a post on conversion code for the new Human in the Wild dataset by BitRobot 🦾, Hugging Face, and Unitree. Now we’re publishing the full HIW-500 data converted to RRD, so you can explore that data directly with Rerun. Watch the robot move. Inspect cameras and robot states together. Zoom in on a moment and query episodes through Rerun catalog! If you’re curious about a real-world humanoid dataset, HIW-500 is now a lot easier to explore. We share the conversion code along with our previous abc-130k dataset conversion example.

Rerun

11,355 views • 2 months ago

DimensionX: Create Any 3D and 4D Scenes from a Single Image with Controllable Video Diffusion TL;DR: Create 3/4DGS from Video Diffusion Note: Some first inference code released (not all yet). Contributions (cited): • We present DimensionX, a novel framework for generating photorealistic 3D and 4D scenes from only a single image using controllable video diffusion. • We propose ST-Director, which decouples the spatial and temporal priors in video diffusion models by learning (spatial and temporal) dimension-aware modules with our curated datasets. We further enhance the hybriddimension control with a training-free composition approach according to the essence of video diffusion denoising process. • To bridge the gap between video diffusion and real-world scenes, we design a trajectory-aware mechanism for 3D generation and an identity-preserving denoising approach for 4D generation, enabling more realistic and controllable scene synthesis. • Extensive experiments manifest that our DimensionX delivers superior performance in video, 3D, and 4D generation compared with baseline methods.

DimensionX: Create Any 3D and 4D Scenes from a Single Image with Controllable Video Diffusion TL;DR: Create 3/4DGS from Video Diffusion Note: Some first inference code released (not all yet). Contributions (cited): • We present DimensionX, a novel framework for generating photorealistic 3D and 4D scenes from only a single image using controllable video diffusion. • We propose ST-Director, which decouples the spatial and temporal priors in video diffusion models by learning (spatial and temporal) dimension-aware modules with our curated datasets. We further enhance the hybriddimension control with a training-free composition approach according to the essence of video diffusion denoising process. • To bridge the gap between video diffusion and real-world scenes, we design a trajectory-aware mechanism for 3D generation and an identity-preserving denoising approach for 4D generation, enabling more realistic and controllable scene synthesis. • Extensive experiments manifest that our DimensionX delivers superior performance in video, 3D, and 4D generation compared with baseline methods.

MrNeRF

17,062 views • 2 years ago

Static 3D generation isn't enough. We need assets ready for animation. Our new #SIGGRAPH work, AniGen, takes a single image and generates the 3D shape, skeleton, and skinning weights all at once. Code is fully open-sourced! Kudos to Yihua and VAST AI Research 🧵(1/4)

Static 3D generation isn't enough. We need assets ready for animation. Our new #SIGGRAPH work, AniGen, takes a single image and generates the 3D shape, skeleton, and skinning weights all at once. Code is fully open-sourced! Kudos to Yihua and VAST AI Research 🧵(1/4)

Yanpei Cao

145,891 views • 7 months ago

Excited to announce Gemini Robotics 2.5 for real-world general dexterity! 🦾 ✨ For robots to help people even more in the real-world, they need to be able to take on any task skillfully, reliably and safely. Gemini Robotics 2.5 is our most capable vision-language-action model to date - increasing both the breadth of skills a robot can learn and the speed at which it can master them. It marks a leap forward in three key areas: 🔧Dexterity: mastering precise, fiddly tasks with delicate, flexible objects, from using everyday tools like tongs to tying a bow. 🤝Reliability: With Apptronik and Mercedes-Benz, we put 2.5 to the test our models helped Apptronik’s Apollo 2 humanoid pick and pack automotive parts with a 96% success rate. 🛑Safety: We developed new features to help robots better spot hazards and people and steer around them in real time. We’re also releasing a new open-source benchmark to test against jailbreaks. We’re rolling out Gemini Robotics 2.5 to our partners now! Learn more: Google DeepMind Robotics

Excited to announce Gemini Robotics 2.5 for real-world general dexterity! 🦾 ✨ For robots to help people even more in the real-world, they need to be able to take on any task skillfully, reliably and safely. Gemini Robotics 2.5 is our most capable vision-language-action model to date - increasing both the breadth of skills a robot can learn and the speed at which it can master them. It marks a leap forward in three key areas: 🔧Dexterity: mastering precise, fiddly tasks with delicate, flexible objects, from using everyday tools like tongs to tying a bow. 🤝Reliability: With Apptronik and Mercedes-Benz, we put 2.5 to the test our models helped Apptronik’s Apollo 2 humanoid pick and pack automotive parts with a 96% success rate. 🛑Safety: We developed new features to help robots better spot hazards and people and steer around them in real time. We’re also releasing a new open-source benchmark to test against jailbreaks. We’re rolling out Gemini Robotics 2.5 to our partners now! Learn more: Google DeepMind Robotics

Carolina Parada

46,899 views • 2 days ago

Elon Musk today on Optimus robot: "You’ve probably seen a lot of impressive demos of robots on the internet, but those demonstrations are pre-programmed or remote-controlled. There is no humanoid robot that can actually do generalized tasks. Optimus will be the first one that will be capable of doing that, in just a demo, it’s generally useful in day-to-day life."

Elon Musk today on Optimus robot: "You’ve probably seen a lot of impressive demos of robots on the internet, but those demonstrations are pre-programmed or remote-controlled. There is no humanoid robot that can actually do generalized tasks. Optimus will be the first one that will be capable of doing that, in just a demo, it’s generally useful in day-to-day life."

Nic Cruz Patane

120,482 views • 3 months ago

(1/6) X-Humanoid 🤖: Scaling up data for Humanoid Robots. We convert human daily activity videos (from Ego-Exo4D) into humanoid videos (i.e., Tesla Optimus) performing tasks like cooking or fixing a bike. This data can be potentially used to train robot policies and world models. 🔥 Project page: Paper link:

(1/6) X-Humanoid 🤖: Scaling up data for Humanoid Robots. We convert human daily activity videos (from Ego-Exo4D) into humanoid videos (i.e., Tesla Optimus) performing tasks like cooking or fixing a bike. This data can be potentially used to train robot policies and world models. 🔥 Project page: Paper link:

Mike Shou

88,752 views • 11 months ago

We are excited to announce our company to the world - We are working on affordable humanoid robots for the world, designed and made in India.

We are excited to announce our company to the world - We are working on affordable humanoid robots for the world, designed and made in India.

Cosine Robots

30,304 views • 2 years ago

At Humanoids Summit Seoul 2026, ROBOTIS CEO Byoung-soo Kim shared the company’s vision for an open-source humanoid platform. ⠀ He described a future where humanoids evolve into platforms - much like smartphones - supporting a wide range of applications, services, and new possibilities. ⠀ To make that future possible, ROBOTIS believes both hardware and software need to be more open and accessible, lowering the barriers to humanoid development and real-world deployment. ⠀ ROBOTIS is building this ecosystem around AI Sapiens, working with university students through the OH! GYM! project and collaborating with global partners such as NVIDIA to connect simulation, AI training, and real-world deployment. ⠀ Our goal is simple: Make humanoid development more accessible and bring robots closer to real-world applications. ⠀ Stay tuned as ROBOTIS continues to build the open ecosystem for the next generation of humanoids. 🚀 ⠀ #ROBOTIS #NVIDIA #HumanoidsSummit #AISapiens #Humanoid #Robot #PhysicalAI #Robotics #OpenSource

At Humanoids Summit Seoul 2026, ROBOTIS CEO Byoung-soo Kim shared the company’s vision for an open-source humanoid platform. ⠀ He described a future where humanoids evolve into platforms - much like smartphones - supporting a wide range of applications, services, and new possibilities. ⠀ To make that future possible, ROBOTIS believes both hardware and software need to be more open and accessible, lowering the barriers to humanoid development and real-world deployment. ⠀ ROBOTIS is building this ecosystem around AI Sapiens, working with university students through the OH! GYM! project and collaborating with global partners such as NVIDIA to connect simulation, AI training, and real-world deployment. ⠀ Our goal is simple: Make humanoid development more accessible and bring robots closer to real-world applications. ⠀ Stay tuned as ROBOTIS continues to build the open ecosystem for the next generation of humanoids. 🚀 ⠀ #ROBOTIS #NVIDIA #HumanoidsSummit #AISapiens #Humanoid #Robot #PhysicalAI #Robotics #OpenSource

ROBOTIS

12,464 views • 1 month ago

Announcing our commercial partnership with Booster Robotics Booster builds humanoid robot hardware, OS, and developer tools to make humanoid robots more affordable, reliable, and practical. The partnership centers on using simulation to multiply the value of real-robot data—expanding teleoperation demonstrations into scalable training data across diverse tasks and scenes. This joint effort powers sim-real co-training and foundation-model development, accelerating progress from hardware iteration to deployable robot policies. Together, we're building simulation‑powered data infrastructure for Physical AI — making scalable training data accessible to model developers and the broader robotics ecosystem.

Announcing our commercial partnership with Booster Robotics Booster builds humanoid robot hardware, OS, and developer tools to make humanoid robots more affordable, reliable, and practical. The partnership centers on using simulation to multiply the value of real-robot data—expanding teleoperation demonstrations into scalable training data across diverse tasks and scenes. This joint effort powers sim-real co-training and foundation-model development, accelerating progress from hardware iteration to deployable robot policies. Together, we're building simulation‑powered data infrastructure for Physical AI — making scalable training data accessible to model developers and the broader robotics ecosystem.

Axis Robotics

72,960 views • 3 months ago

Humanoid's humanoid robots are undergoing training at Schaeffler, Siemens, and Ford factories. By 2026, the value of humanoid robots will no longer be judged by data or models, but by their real-world reliability and usefulness at the customer's site.

Humanoid's humanoid robots are undergoing training at Schaeffler, Siemens, and Ford factories. By 2026, the value of humanoid robots will no longer be judged by data or models, but by their real-world reliability and usefulness at the customer's site.

CyberRobo

16,294 views • 9 months ago

NVIDIA DROPPED A MOTION DIFFUSION MODEL FOR HUMANOID ROBOTS trained on 700 hours of mocap data kimodo generates high-quality 3D human and robot motions from text prompts you control it with: → full-body pose keyframes → end-effector positions/rotations → 2D paths and waypoints works on human skeletons and unitree G1 robot plug the outputs directly into mujoco or retarget to other robots using GMR has a web-based interactive demo with a timeline editor. runs locally needs ~17GB VRAM to run inference open source under apache 2.0

NVIDIA DROPPED A MOTION DIFFUSION MODEL FOR HUMANOID ROBOTS trained on 700 hours of mocap data kimodo generates high-quality 3D human and robot motions from text prompts you control it with: → full-body pose keyframes → end-effector positions/rotations → 2D paths and waypoints works on human skeletons and unitree G1 robot plug the outputs directly into mujoco or retarget to other robots using GMR has a web-based interactive demo with a timeline editor. runs locally needs ~17GB VRAM to run inference open source under apache 2.0

Vaishnavi

17,572 views • 6 months ago

HUMANOID ROBOTS ARE STARTING TO WALK AMONG US At first, this looks like a completely normal street video. A woman is walking down the sidewalk on a sunny day, with people, stores and traffic around her. Then you notice who’s walking beside her. A humanoid robot. There’s no robotics conference, no laboratory and no team of engineers around it. The robot is simply walking through the city next to her as if this is already part of everyday life. Until recently, humanoid robots were mostly something we saw in controlled demonstrations, factories and tech presentations. Now they’re beginning to appear in ordinary public spaces, walking alongside people without looking completely out of place. The biggest shift isn’t just how advanced these machines are becoming. It’s how quickly they’re starting to blend into the real world. At this pace, seeing a humanoid robot walking next to you in public might soon stop feeling unusual at all

HUMANOID ROBOTS ARE STARTING TO WALK AMONG US At first, this looks like a completely normal street video. A woman is walking down the sidewalk on a sunny day, with people, stores and traffic around her. Then you notice who’s walking beside her. A humanoid robot. There’s no robotics conference, no laboratory and no team of engineers around it. The robot is simply walking through the city next to her as if this is already part of everyday life. Until recently, humanoid robots were mostly something we saw in controlled demonstrations, factories and tech presentations. Now they’re beginning to appear in ordinary public spaces, walking alongside people without looking completely out of place. The biggest shift isn’t just how advanced these machines are becoming. It’s how quickly they’re starting to blend into the real world. At this pace, seeing a humanoid robot walking next to you in public might soon stop feeling unusual at all

Inspector

73,410 views • 2 months ago

What was in the movies is now happening in the real world. The robot squadron. Actually, they are rehearsing the opening ceremony of the 2nd World Humanoid Robot Games to be held this weekend. Welcome to the future!

What was in the movies is now happening in the real world. The robot squadron. Actually, they are rehearsing the opening ceremony of the 2nd World Humanoid Robot Games to be held this weekend. Welcome to the future!

Li Zexin 李泽欣

25,274 views • 2 months ago

A Gaussian Splat can become a world where Robots and AI agents can act. In our latest OVER Research experiment, we placed a robot inside a real-world 3D capture, with a VLM making decisions based on what it sees. At every step, the robot holds a pose in the reconstruction, gets a newly rendered view of the environment, takes an action, moves, and sees the world again from its new position. Why does this matter? Because 3D captures can become more than reconstructions to explore. They can become environments where embodied AI and robots can navigate, act, be evaluated and eventually train across real-world spaces at scale. Capture a place once. Then turn it into a world where AI and Robots can act. The full experiment, including what we discovered once we actually put the loop to the test:

A Gaussian Splat can become a world where Robots and AI agents can act. In our latest OVER Research experiment, we placed a robot inside a real-world 3D capture, with a VLM making decisions based on what it sees. At every step, the robot holds a pose in the reconstruction, gets a newly rendered view of the environment, takes an action, moves, and sees the world again from its new position. Why does this matter? Because 3D captures can become more than reconstructions to explore. They can become environments where embodied AI and robots can navigate, act, be evaluated and eventually train across real-world spaces at scale. Capture a place once. Then turn it into a world where AI and Robots can act. The full experiment, including what we discovered once we actually put the loop to the test:

Over the Reality 🌐

15,316 views • 2 months ago

Another humanoid robot (Tienkung) is running at high speed, navigating corners like an Formula 1 race car. The World Humanoid Robot Games haven't even started yet, but the humanoid robots' warm-up is already in full swing.

Another humanoid robot (Tienkung) is running at high speed, navigating corners like an Formula 1 race car. The World Humanoid Robot Games haven't even started yet, but the humanoid robots' warm-up is already in full swing.

CyberRobo

12,452 views • 2 months ago