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.

No teleoperation. No simulation. No RL. Multi-fingered robot manipulation policies directly by watching videos of humans with Aria glasses on. It was super fun working on this with Irmak Guzey's lead!! 1/n

Homanga Bharadhwaj

3,566 subscribers

55,045 views • 9 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

Three demos showing SharpaWave’s fine manipulation under high-fidelity teleoperation. Task No.1: putting on a trash bag. With teleoperation and tactile feedback, it finds the rim, opens it, and wraps it neatly — even on a slippery, deformable object. #Sharpa #SharpaWave #Teleoperation #Tactile #DexterousHand

Three demos showing SharpaWave’s fine manipulation under high-fidelity teleoperation. Task No.1: putting on a trash bag. With teleoperation and tactile feedback, it finds the rim, opens it, and wraps it neatly — even on a slippery, deformable object. #Sharpa #SharpaWave #Teleoperation #Tactile #DexterousHand

Sharpa

80,348 views • 9 months ago

Tired of teleoperation? One human video → 1,000s of robot demos. (📍GitHub ) Scaling Robot Data Without Dynamics Simulation or Robot Hardware Real2Render2Real (R2R2R) is a new way to scale robot data without physics simulation or hardware. You take a phone scan + a single monocular human demo. It tracks the motion, renders photorealistic scenes, and generates diverse, robot-agnostic trajectories ready for training. > No teleop, no sim, no robot, just a phone and a video > Train VLA models and diffusion policies directly on the output > Supports multiple robot embodiments with kinematic consistency > 1000s of demos in 1/27 the time of real-world collection Thank you, Max Fu, for sharing!! Project: Paper: Code coming soon: It shows that with the right pipeline, you can scale robot learning data without touching a robot. One of the most interesting directions in scalable robotics today. —— Weekly robotics and AI insights. Subscribe free:

Tired of teleoperation? One human video → 1,000s of robot demos. (📍GitHub ) Scaling Robot Data Without Dynamics Simulation or Robot Hardware Real2Render2Real (R2R2R) is a new way to scale robot data without physics simulation or hardware. You take a phone scan + a single monocular human demo. It tracks the motion, renders photorealistic scenes, and generates diverse, robot-agnostic trajectories ready for training. > No teleop, no sim, no robot, just a phone and a video > Train VLA models and diffusion policies directly on the output > Supports multiple robot embodiments with kinematic consistency > 1000s of demos in 1/27 the time of real-world collection Thank you, Max Fu, for sharing!! Project: Paper: Code coming soon: It shows that with the right pipeline, you can scale robot learning data without touching a robot. One of the most interesting directions in scalable robotics today. —— Weekly robotics and AI insights. Subscribe free:

Ilir Aliu

42,864 views • 7 months ago

Teaching robots to perform dexterous manipulation tasks currently requires teleoperation, which limits demonstration quality, speed, and scalability. Instead, why not use human videos? The problem is that a human hand isn’t a robot hand, so data must be retargeted using simulation to resolve issues like collisions and interpenetration when controlling the hand. In VideoManip, Hongyi Chen and co-authors built a system to solve this problem, taking in RGB videos of humans performing manipulation tasks and using them to create accurate simulations with which to learn robot policies. Watch episode #73 of RoboPapers, hosted by Michael Cho - Rbt/Acc and Chris Paxton, now to learn more!

Teaching robots to perform dexterous manipulation tasks currently requires teleoperation, which limits demonstration quality, speed, and scalability. Instead, why not use human videos? The problem is that a human hand isn’t a robot hand, so data must be retargeted using simulation to resolve issues like collisions and interpenetration when controlling the hand. In VideoManip, Hongyi Chen and co-authors built a system to solve this problem, taking in RGB videos of humans performing manipulation tasks and using them to create accurate simulations with which to learn robot policies. Watch episode #73 of RoboPapers, hosted by Michael Cho - Rbt/Acc and Chris Paxton, now to learn more!

RoboPapers

27,360 views • 4 months ago

We might be solving the wrong problem in robotics. That’s what this makes clear. UMI → Universal Manipulation Interface A simple $400 gripper that lets you teach robots by demonstration. You hold it like a tool. Show the task. The robot learns. No teleoperation. No expensive hardware. No robot-specific data. Stanford open-sourced everything → hardware, code, datasets. What stands out to me is the bottleneck. Not algorithms. Data. Teleoperation → ~35 demos/hour UMI → ~111 demos/hour And the data transfers across robots → UR5, Franka, others. The design is surprisingly practical: → GoPro fisheye lens (155° FOV) + mirrors for depth → SLAM + IMU for precise 6DoF tracking → latency matching for dynamic tasks → diffusion policies for multimodal actions Then it scales. Cheng Chi takes this further with Sunday Robotics (with Tony Zhao). A $200 glove → deployed in 500+ homes → ~10 million real-world interactions. Not lab data. Real human behavior. Their robot learns dishes, laundry, espresso → with zero robot-specific data. This is where the shift becomes obvious. From training robots in controlled environments → to learning directly from humans at scale So here’s the real question: Will robotics be unlocked by better models… or by unlocking data? #ArtificialIntelligence #Robotics #AI #Innovation #FutureOfWork

We might be solving the wrong problem in robotics. That’s what this makes clear. UMI → Universal Manipulation Interface A simple $400 gripper that lets you teach robots by demonstration. You hold it like a tool. Show the task. The robot learns. No teleoperation. No expensive hardware. No robot-specific data. Stanford open-sourced everything → hardware, code, datasets. What stands out to me is the bottleneck. Not algorithms. Data. Teleoperation → ~35 demos/hour UMI → ~111 demos/hour And the data transfers across robots → UR5, Franka, others. The design is surprisingly practical: → GoPro fisheye lens (155° FOV) + mirrors for depth → SLAM + IMU for precise 6DoF tracking → latency matching for dynamic tasks → diffusion policies for multimodal actions Then it scales. Cheng Chi takes this further with Sunday Robotics (with Tony Zhao). A $200 glove → deployed in 500+ homes → ~10 million real-world interactions. Not lab data. Real human behavior. Their robot learns dishes, laundry, espresso → with zero robot-specific data. This is where the shift becomes obvious. From training robots in controlled environments → to learning directly from humans at scale So here’s the real question: Will robotics be unlocked by better models… or by unlocking data? #ArtificialIntelligence #Robotics #AI #Innovation #FutureOfWork

Pascal Bornet

186,712 views • 5 months ago

Making fun of a man working hard while he sits on a bench with no weight on it… Leave people ALONE at the gym or stay home.

Making fun of a man working hard while he sits on a bench with no weight on it… Leave people ALONE at the gym or stay home.

Joey Swoll

772,573 views • 2 years ago

🎉Excited to share a fun little hardware project we’ve been working on. GELLO is an intuitive and low cost teleoperation device for robot arms that costs less than $300. We've seen the importance of data quality in imitation learning. Our goal is to make this more accessible 1/n

🎉Excited to share a fun little hardware project we’ve been working on. GELLO is an intuitive and low cost teleoperation device for robot arms that costs less than $300. We've seen the importance of data quality in imitation learning. Our goal is to make this more accessible 1/n

Philipp Wu

163,101 views • 3 years ago

Build a humanoid robot yourself! 🪚 OpenArm is an open-source humanoid robot. It comes with full CAD, control code, firmware, and simulation tools, everything needed to build, modify, and operate it. The arms are designed to be compliant and backdrivable. Teleoperation is supported, with force feedback and real-time gravity compensation so operators can guide the arm naturally. Super important, on the simulation side, OpenArm works with platforms like MuJoCo and Isaac Sim, letting developers test policies in virtual environments before running on hardware. Assemble it yourself from a kit or get it prebuilt, the goal is accessibility for research labs, small teams, and enthusiasts. The project is run by Enactic in Tokyo, Japan, and aims to lower the barrier for experimenting with dexterous manipulation. Let's put robotics in mainstream! 🔥🔥 P.S. I put the project page in the comments!

Build a humanoid robot yourself! 🪚 OpenArm is an open-source humanoid robot. It comes with full CAD, control code, firmware, and simulation tools, everything needed to build, modify, and operate it. The arms are designed to be compliant and backdrivable. Teleoperation is supported, with force feedback and real-time gravity compensation so operators can guide the arm naturally. Super important, on the simulation side, OpenArm works with platforms like MuJoCo and Isaac Sim, letting developers test policies in virtual environments before running on hardware. Assemble it yourself from a kit or get it prebuilt, the goal is accessibility for research labs, small teams, and enthusiasts. The project is run by Enactic in Tokyo, Japan, and aims to lower the barrier for experimenting with dexterous manipulation. Let's put robotics in mainstream! 🔥🔥 P.S. I put the project page in the comments!

Lukas Ziegler

233,153 views • 11 months ago

Fun fact kim petras is no longer working with dr Luke and has her own production credits on this song

Fun fact kim petras is no longer working with dr Luke and has her own production credits on this song

Kim Petras Crave

160,010 views • 10 months ago

The stories of parents persecuted by cruel No Job No Pay policies are seared on my conscience. I'm no doctor but I am an elected representative in this nation - with a responsibility to raise the alarm on any laws that hurt Australians, especially families with young children.

The stories of parents persecuted by cruel No Job No Pay policies are seared on my conscience. I'm no doctor but I am an elected representative in this nation - with a responsibility to raise the alarm on any laws that hurt Australians, especially families with young children.

Russell Broadbent

11,740 views • 2 years ago

Martha Karua says this was “an election like no other,” accusing leaders of bribing voters with household items instead of policies. Video by Mary Imenza.

Martha Karua says this was “an election like no other,” accusing leaders of bribing voters with household items instead of policies. Video by Mary Imenza.

The Standard Digital

29,631 views • 9 months ago

I placed 🥈 2nd in the LeHome Challenge (at IEEE ICRA 2026) earlier this month, and before that I was 🥇 1st of 62 teams in the simulation round. Now I am sharing my solution — with a detailed logic walkthrough and open-source code. The task was to teach a cheap two-armed robot to fold different garments in simulation and on a real robot. I trained a VLA policy with an RL loop to make it work. Let's break it down 👇

I placed 🥈 2nd in the LeHome Challenge (at IEEE ICRA 2026) earlier this month, and before that I was 🥇 1st of 62 teams in the simulation round. Now I am sharing my solution — with a detailed logic walkthrough and open-source code. The task was to teach a cheap two-armed robot to fold different garments in simulation and on a real robot. I trained a VLA policy with an RL loop to make it work. Let's break it down 👇

Ilia

21,948 views • 2 months ago

Pretrained ViTs see the world in rich, dense detail. Most policies pool it to a single vector before acting, discarding most of it. We introduce Patch Policy: a minimal architectural extension that enables transformer-based policies to consume dense tokens directly, no billion-param VLM required. It outperforms a fine-tuned 7B VLA by 18% with ~0.7% of its parameters, enabling robust, precise manipulation.

Pretrained ViTs see the world in rich, dense detail. Most policies pool it to a single vector before acting, discarding most of it. We introduce Patch Policy: a minimal architectural extension that enables transformer-based policies to consume dense tokens directly, no billion-param VLM required. It outperforms a fine-tuned 7B VLA by 18% with ~0.7% of its parameters, enabling robust, precise manipulation.

Gaoyue Zhou

54,878 views • 1 month ago

Matt Gaetz says government is involved in intergalactic breeding with kidnapped humans. And no. We're not surprised a bunch of these people aren't human. Just come out with it so we can move on to the Hybrid Alien / AI Robot war.

Sensitive content

Matt Gaetz says government is involved in intergalactic breeding with kidnapped humans. And no. We're not surprised a bunch of these people aren't human. Just come out with it so we can move on to the Hybrid Alien / AI Robot war.

Shipwreck

59,527 views • 5 months ago

What if you could build a fully native iOS app… using only PHP? Checkout this first demo of the new Super Native architecture behind NativePHP on iOS — where PHP runs directly alongside native code with no WebView, no JavaScript bridge, and no hybrid layer.

What if you could build a fully native iOS app… using only PHP? Checkout this first demo of the new Super Native architecture behind NativePHP on iOS — where PHP runs directly alongside native code with no WebView, no JavaScript bridge, and no hybrid layer.

NativePHP

11,753 views • 6 months ago

What if a dexterous robot could learn a 20+ step chemistry experiment without a single on-robot training demo? Meet TwinDEX: a pair of co-designed, three-finger, nine-DoF dexterous manipulation interface: one wearable for data collection, one for robot deployment. The twinned design shares identical kinematics, contact surfaces, visual appearance, and sensors across collection and deployment — keeping observations and actions aligned end to end. Trained from scratch on only a few hundred wearable demonstrations - with zero on-robot training or intervention data - TwinDEX completed a standardized chemistry experiment involving tool switches, fine force control, and bimanual coordination. Robot-free data showed comparable learning efficiency on the multi-task evaluation, TwinDEX delivered 5.3 times effective throughput than on-robot teleoperation. TwinDEX demonstrates that high-quality robot-free data can fully substitute for on-robot teleoperation data on challenging dexterous tasks — removing the dependency on real-robot hardware that has been the central bottleneck to scaling dexterous manipulation data. This was the proof-it phase. Now comes scale: what emerges at tens of thousands, or millions, of episodes? Watch the demo and read the technical blog: #TwinDEX #Robotics #EmbodiedAI #DexterousManipulation

What if a dexterous robot could learn a 20+ step chemistry experiment without a single on-robot training demo? Meet TwinDEX: a pair of co-designed, three-finger, nine-DoF dexterous manipulation interface: one wearable for data collection, one for robot deployment. The twinned design shares identical kinematics, contact surfaces, visual appearance, and sensors across collection and deployment — keeping observations and actions aligned end to end. Trained from scratch on only a few hundred wearable demonstrations - with zero on-robot training or intervention data - TwinDEX completed a standardized chemistry experiment involving tool switches, fine force control, and bimanual coordination. Robot-free data showed comparable learning efficiency on the multi-task evaluation, TwinDEX delivered 5.3 times effective throughput than on-robot teleoperation. TwinDEX demonstrates that high-quality robot-free data can fully substitute for on-robot teleoperation data on challenging dexterous tasks — removing the dependency on real-robot hardware that has been the central bottleneck to scaling dexterous manipulation data. This was the proof-it phase. Now comes scale: what emerges at tens of thousands, or millions, of episodes? Watch the demo and read the technical blog: #TwinDEX #Robotics #EmbodiedAI #DexterousManipulation

X Square Robot

1,341,211 views • 9 days ago

Cyclops dissed humans on national TV with no ounce of a fuck given. Had to put the "Like That" beat to it #XMen97

Cyclops dissed humans on national TV with no ounce of a fuck given. Had to put the "Like That" beat to it #XMen97

Ghost in the HTML

1,466,372 views • 2 years ago