Sharpa Robotics Sharpa observed that teleoperating a dual hand... robot offering a combined 63 DoF is a nightmare, even for an experienced operator. They offer a two fold solution: - a VLA that handles "in hand rotation" (like the apple in video below), that the operator can trigger using a foot pedal. - a Mixture-of-Dexterous-Experts that fuses tactile sensing data. Interestingly enough, the first model handles the apple peeling end-to-end, tactile data does not help here. However, it greatly enhances the insertion and grasping of the apple. This research makes use of the SharpaWave 22-DoF dexterous hand, with force and tactile feedback on all ten fingertips. I find it interesting that is now possible to delegate complex low-level finger coordination tasks to RL-trained atomic skills. Optimizing such steps that are difficult to reproduce in teleoperation significantly helps overcoming the data acquisition bottleneck.show more

Pretty human-like hand Beijing-based SynapX will unveil its tendon-driven... OctoH-Hand at WRC. Human-scale in size, the hand uses a hybrid architecture combining fully tendon-driven actuation with direct-drive motors in the forearm. It integrates 28 independently controllable actuators and 23 active DoF, along with tactile sensors embedded in the palm. Interestingly…SynapX is building more than just a dexterous hand. It has also developed a World model(SYNWorld), and a data collection system(OctoSense), creating a loop from data collection to world understanding and policy generation, and finally to real-world execution and feedback. Another physical AI bridge for humanoid robots.show more

Interestingly, Xynova’s technological approach shares the same origins as... the dexterous hand technology used in Optimus v3 (though Elon has noted that this design still needs further refinement). The Flex2 is an upgraded version built on the Flex1: v1 featured 25 DOF and used a cable-driven system; the v2 introduces direct drive, which reduces the DOF to 23 but also sheds 400g in weight. It seems a hybrid drive mechanism may be the more practical solution. In March this year, following the successful completion of its Series A funding round (with investors including Xiaomi and others), this robotics company--founded in 2024--began construction of a large-scale production facility. Spanning over 5,000 square meters, the base is designed to achieve an annual output of 200,000 miniature electric cylinders and 10,000 dexterous hands. However, hardware alone is far from enough. A truly capable dexterous hand must be the result of the co-evolution of data, models, and the physical hardware. In other words, in addition to mass production, Xynova is simultaneously developing a complete integrated system that combines perception capabilities, robotic manipulation intelligence, and hand-specific coordination. This is essentially a foundational robotic module. Yet its applications go far beyond that. It can be directly adapted to industrial robotic arms on production lines, as well as integrated into the bodies of humanoid robots. That said, what I’m most eager to see is its use in advanced bionic prosthetics for humans. If it can successfully demonstrate this expanded capability, its impact will reach well beyond the realm of humanoid robots. (Cyborg)show more

Tactile interaction in the wild can unlock fine-grained manipulation!... 🌿🤖✋ We built a portable handheld tactile gripper that enables large-scale visuo-tactile data collection in real-world settings. By pretraining on this data, we bridge vision and touch—allowing robots to: ✅ Perform robust in-hand reorientation ✅ Control contact and force with precision 🔗 Project page: (1/6)show more

New robot hands just dropped! But it seems to... be missing a couple fingers. Tacta Systems Tacta Systems is a Palo Alto robotics startup that just came out of stealth, and raised with $75M and a dexterity platform, TactaBot, aimed at high-value manufacturing. TactaBot has three parts: - the Tacta Hand -> a human-scale robotic hand with 15 independently actuated joints, proprietary "Fluidic Tendon" actuation, pitched as reliable for millions of factory cycles. - the Tacta Sensor -> a tiny tactile sensor reading force from 250 Pa to 700,000 Pa, sampling at 400 Hz, resolving temperature to 0.1 °C. - Skill Capture -> a data system built around the Tacta Glove. It contains the same sensor embedded in a glove that factory workers wear. Sounds similar to what mimic is doing! Except with 3 fingers instead of 5. Tacta's vision sees 3 fingers as more than enough to complete all tasks, and less complex to simulate than 5. My opinion: Tacta is very strong at semiconductor/MEMS, their moat lies in their ability to manufacture their touch sensor as large as a grain of sand, not the hand or the model. One caveat though: there is no detail nor explanation of how the 5 finger data acquisition glove maps to the 3 finger hand -> I would love to learn more about it! This is where the interesting part of the tech is imho. If this does not work, then nothing does. Still, I have to admit it looks very cool, slick, and minimal, I love it:show more

Robots don’t just need better brains. They need WAY... more real-world data. 🤖 And collecting high-quality dexterous robot data at scale is one of the hardest problems in physical AI. A fascinating approach is emerging: Wearable human demonstrations + structurally matched dexterous robots. Instead of humans directly teleoperating a robot, Chinese embodied AI startup X Square Robot's TwinDEX system captures the motion, contact, and visual information needed to train the robot — while keeping the data closer to the hardware that will actually execute the task. Early results show promising performance on tool use, fine manipulation, and complex contact-rich tasks. If this approach scales, it could change how we build real-world robotics datasets. The next frontier of physical AI might not be bigger models. It might be better data.show more

GPT-6 Astra test 4/n Prompt: "Implement pen spinning with... a dexterous hand. Use Isaac Lab for RL training, use the Sharpa hand, and create the pen mesh yourself. Give me a trained RL policy and a visualization video. You are free to search the web and download papers or anything else you need." After running autonomously for a day and a half (including training the policy), this is what we got: Credit: my student Chengyang Lishow more

Funny enough there is a legitimate argument that this... is clean and not a travel Putting your hand under the ball does not itself end your dribble. You have also bring the ball to a pause. That is the key. So the question is, did he bring the ball to a pause before left foot is down. I think its extremely close and difficult to tell, especially calling it in real timeshow more

Apple has just launched a fresh legal fight against... a secret UK government order that demands access to encrypted iCloud backups. Here is the part most people missed. Rather than build the backdoor the UK asked for, Apple switched off its strongest encryption, called Advanced Data Protection, for British users. So people in the UK no longer have the option where not even Apple can see their data. Not because of a hack, but because their government demanded a key. The whole case is secret by law. Neither side is even allowed to confirm the order exists. Apple has said only that it has never built a backdoor into anything, and it never will.show more

Robot hands got serious. Here are four dexterous hands:... 🔵 Tesla Optimus V3: 22 DOF, motors in the forearm. 🔵 BrainCo Revo 3: 21 DOF, full-palm touch sensing. 🔵 Wuji Hand: 20 DOF, motors inside each finger. 🔵 1X NEO: 22 DOF, force sensing at every joint. Which grip wins?show more

It's 2030 and you are reviewing humanoid robots. A... Tesla. A Google. An Apple. An OpenAI. A Meta. A Figure. And a bunch of Chinese-made ones. Which one is best, and why? I think the Tesla understands the world much better. Why? There were eight Teslas around me on the freeway today. Start there. No other robot company has that data. But my robot is parked at the local high school twice a day. Its cameras see humans in all of our weirdness. How we move. Where we go. Where we walk. Who we talk with. What you are wearing. Whether your hair was combed this morning. That data will lead to robotics breakthroughs. Apple might keep up with its Vision Pro data, but it is too freaked out by the privacy implications of using said data. (On the front are six cameras and a couple of TOF -- Time Of Flight -- sensors that can see everything in your home in great detail). Google has a lot of data, for sure. All my: 1. Email. 2. Calendars. 3. Photos. 4. TV watching behavior. 5. Contacts. 6. Documents and spreadsheets. 7. Files. 8. Location data. So I expect Google's robot will be attractive to many. But how do you see the others shake out over the next five years? Make some guesses. But remember what an AI pioneer told me years ago about AI: it's all about the data. The Chinese ones have huge advantages: the Chinese have more data on their citizens, and many more citizens to boot AND they can make robots cheaper than we can. But now that you know OpenAI is building its own robot you have caught wind of what I've heard from many in San Francisco and Silicon Valley: that humanoid robots are the real prize of AI and will be highly profitable for those that can make them and find customers willing to buy them. Here, too, I learned long ago never to bet against Elon Musk. Will you?show more

We just ran one of the largest robot models... that exists today, all without a local GPU. And it’s running real-time at <50 ms overhead. Scaling laws are becoming real for physical AI. Perceptron’s Isaac 0.5 is one of the largest open-source models, sitting at 36B total parameters. Perceptron AI joins other frontier robotics labs like Dyna Robotics and Generalist in showing the need to massively scale pre-training data, from a 1000s to millions of hours of video. Specifically, they show that the more egocentric video the model is trained on, the less teleop data that it needs to achieve the same loss. At Dreamscale Labs (YC F26) (YC F26), we’ve noticed an important truth here: data and training compute do not just scale in isolation. The model sizes must increase too, and GPT-6 Astra has given a glimpse into what a trillion-parameter robotics model could do. We’re building to serve that future - one that is not constrained by the bottlenecks of on-board compute, but rather, allowing large models to run fast over the cloud. Reach out if you’re interested in our work.show more

OpenAI's Deep Research is getting a run for its... money. Deep Lake was just released, and it's a different take on an AI system that can do deep research on your own data. You can use Deep Lake to build AI search with reasoning on your private and public data. (Look at the attached videos to get an idea of how it works.) If you want to research proprietary and sensitive data, Deep Research won't help you because it's limited to public data. Deep Lake, however, will allow you to use your private data. On top of that, Deep Lake supports multi-modal retrieval from the ground up. It uses vision language models for data ingestion and retrieval so that you can connect any data (PDFs, images, videos, structured data, etc.) You can even use mixed-data queries! Deep Lake can search your data from S3, Dropbox, and GCP. It learns from your queries over time, making the results as relevant to your work as possible!show more

what gets me here is that jungkook just wouldn’t... let go of jimin’s hand 😭 i mean, isn’t that a bit too long for a handshake? even jimin literally had to pull his hand away in the endshow more

Predicting the next word "only" is sufficient for language... models to learn a large body of knowledge that enables then to code, answer questions, understand many topics, chat, and so on. This is clear to many researchers now, and there are nice tutorials on why this works by Ilya Sutskever resorting to compression ( ) and by Geoffrey Hinton ( ). However, the emergence of types of understanding is not unique to language models. In by Misha Denil and Brandon Amos the authors trained models to predict the next few time stems of over a hundred robot hand sensors (Touch, Gyro, Accelerometer, Joint Info, Actuator Info, etc.). They ten found out that they could regress the shape of the thing the hand was touching from the activations of the neural networks using probes. That is, the model developed an internal representation of shapes even though it was simply used to predict "only" the next few senses. Awareness follows from simple predictions and interaction with the world.show more

Its not every day you wake up to find... that the Pope has made your lifes work the central focus of his papacy: “Disarming AI means freeing it from the mentality of “armed” competition [..] This entails a race for ever more powerful algorithms and larger datasets, driven by the desire to secure geopolitical or commercial dominance." - POPE LEO XIV, May 2026 Here, “disarmed” means “neutralised” in the sense that this should not be a differentiator The Innovation Game (TIG) was created to keep data and algorithms open, in order to prevent monopolistic control It's not just an aspiration, it's an economic mechanism that makes open data and open algorithms the rational economic choice • All algorithms are published openly by TIG • If you are willing to make the data you process with an algorithm open, you can use it free-of-charge • Alternatively, if you would like to keep this data private, there is a fee to pay for using the algorithm • All fees are used to fund more open innovation Its an elegant, global, self-reinforcing engine The logical end point of monopoly is that innovation stops We cannot allow that to happen Pope Leo XIV I would be grateful for your thoughts on The Innovation Gameshow more

Odyssey-3 is live. One world model trained on visual... data that can drive cars, fly drones, control robots, and even play video games. The basic premise is that it's better to train a single model across different systems instead of a new model for each system. It's sort of like how a gamer can use their skills in CounterStrike to play Call of Duty or GTA 5.show more

So much of the complexity for multimodal/robotics data is... just getting the right format that's both flexible and performant. I dig into it here in the context of 3d reconstruction. I'm hoping to build an opensource arkit like pipeline and explain the first bit for the data pipeline here! Heres a video of what the final data looks like in a registered catalogshow more