Video yükleniyor...

Video Yüklenemedi

Bu video yüklenirken bir sorun oluştu. Bu geçici bir ağ sorunundan kaynaklanıyor olabilir veya video kullanılamıyor olabilir.

Ana Sayfaya Dön

I've been working on deformable object manipulation since my PhD. It was totally a nightmare years ago and my PhD advisor was telling me not to work on it for my own good. Today, at ByteDance Seed, we are dropping GR-RL, a new VLA+RL system that manages long-horizon precise... dexterous manipulation of deformable objects. This is probably the first real-world RL system to make a robot: ✅ Lace up your shoes end to end ✅ Hit millimeter tolerance repeatedly ✅ Recover from mistakes (See video!) ✅ And complete continuous shoelace threading on a real bimanual platform 📈 Success rate: ↑ from 45.7% → 83.3% Yes, robots can now actually do this. Project page: ArXiv:show more

Xiao Ma

1,766 subscribers

110,653 görüntüleme • 10 ay önce •via X (Twitter)

Eğitim Bilim & Teknoloji

Anya Rossi• Live Now

Private livecam show

45 Yorum

Xiao Ma profil fotoğrafı

Xiao Ma10 ay önce

Why “shoelace threading” matters 🤔 This task is probably one of the most challenging household robotics tasks in terms of precision: 💥 Soft-body chaos – laces deform every frame 💥 Millimeter precision – 1–2 mm slip = total failure 💥 Long-horizon manipulation – hundreds of steps where slightest drift compounds. 💥 Requires recovery – humans retry; IL models freeze It's the perfect torture test for VLA precision. Even our previous model, GR-3 — already trained on massive robot trajectories + human teleop demos + public image-text corpora — failed to get reliable policies here. So we found the bottleneck.

Xiao Ma profil fotoğrafı

Xiao Ma10 ay önce

Two killers of imitation learning (IL): (1) Human demos are NOT optimal Humans hesitate, retry, fix mistakes mid-trajectory. IL blindly copies ALL of it — including the bad parts. (2) Training vs Deployment Misalignment VLA models output actions. To prevent jitter, robots execute post-processed versions (RHC, smoothing, ensembling). Your “predicted action” ≠ your “executed action.” On millimeter tasks, this mismatch is fatal. So IL alone was a dead end.

Xiao Ma profil fotoğrafı

Xiao Ma10 ay önce

The Idea: If imitation is broken, then: Let the robot learn from its own experience. GR-RL = ⭐️ Offline RL (data filtering) ⭐️ Symmetry augmentation ⭐️ Online closed-loop Real-World Reinforcement Learning All on top of a single VLA foundation model. Just RGB, proprioception, and language instructions.

Xiao Ma profil fotoğrafı

Xiao Ma10 ay önce

Offline Stage — Filter the human flaws We train a Critic Transformer via distributional RL: ⭐️ Detects “value drops” when the operator hesitates or messes up ⭐️ Slices every trajectory into high-value vs low-value segments ⭐️ Retains only the cleanest expert behavior Effect: GR-3 45.7% → 61.6% success just from removing “bad micro-behaviors.”

Xiao Ma profil fotoğrafı

Xiao Ma10 ay önce

Morphological Symmetry Augmentation Our bi-manual robot is left–right symmetric. So we mirror EVERYTHING: 🚀 RGB 🚀 Proprioception 🚀 Actions 🚀 Language Instructions Data size doubles. Spatial reasoning robustness skyrockets. → 72.7% success.

Xiao Ma profil fotoğrafı

Xiao Ma10 ay önce

Online Stage — Real-World Steering RL Now the robot learns ON THE PHYSICAL PLATFORM. But direct exploration in joint space causes dangerous jitter and is inefficient — you need millimeter accuracy. So GR-RL explores in the latent noise space: A tiny 51.5M-param noise-predictor nudges the flow model’s latent action distribution toward high-value regions. We also introduce a dual-buffer mechanism: 🚀 Off-policy buffer (old rollouts) for the critic warm-up 🚀 On-policy buffer (last 2 checkpoints) for stable improvement 🚀 1:1 sampling stabilizes RL and prevents catastrophic drift. Just 150 online rollouts → +10% performance boost.

Xiao Ma profil fotoğrafı

Xiao Ma10 ay önce

The Result: Final performance: 83.3% success over continuous shoelace threading. The surprising part? GR-RL learns to: 🔥 retry when the lace slips 🔥 reposition the lace when the initial pose is bad 🔥 "self-correct" mid-task instead of freezing This is the behavior you EXPECT from embodied intelligence — not just mimicry, but competence.

Xiao Ma profil fotoğrafı

Xiao Ma10 ay önce

GR-RL proves something: IL is inherently limited, and we can do things previously thought impossible by purely visuo-motor control simply making it RL. The future direction is clear: distill RL-enhanced behavior back into the foundation VLA, forming a self-improving, ever-growing loop. Kudos to the wonderful team! @yunfeili98, @simanbulk, @yu_cui123, Zhongren Cui, Zhigang Han, @litchiyoyo, @KT892790499, @YuxiaoLiu4, Hao Niu, Wanli Peng, Jingchao Qiao, Zeyu Ren, Haixin Shi, @ZhiSu22, Jiawen Tian, Yuyang Xiao, Shenyu Zhang, Liwei Zheng

Perry Jia profil fotoğrafı

Perry Jia10 ay önce

Wow! I love how it naturally pulls the shoe closer so that it can complete the task easier. Awesome work!

Xiao Ma profil fotoğrafı

Xiao Ma10 ay önce

haha, thanks Perry! btw congrats on your recent release on ACT-1 and Memo! Great work! I really like the design and it's amazing how much it has achieved with pure UMI data.

🄱🄻🄸🅃🅉 🔸 profil fotoğrafı

🄱🄻🄸🅃🅉 🔸10 ay önce

This is brilliant Ma

Adam profil fotoğrafı

Adam10 ay önce

incredible work, can't wait to see more in the future.

Daniel Domingos profil fotoğrafı

Daniel Domingos10 ay önce

Congrats!

MAX ONBOARDER ⭕ profil fotoğrafı

MAX ONBOARDER ⭕10 ay önce

@Scobleizer This is amazing

Bingyi Kang profil fotoğrafı

Bingyi Kang10 ay önce

Great team! Great Work! Can not wait to see your future project! Congrats @yunfeili98 @yusufma555

Salman profil fotoğrafı

Salman10 ay önce

This is incredible work. Kudos for seeing this work through for so many years, seems like it’s paying off!

Robert profil fotoğrafı

Robert10 ay önce

Can you implement an aspect of leaning against the object that you're working on? This is what humans do when we tie our shoe, we don't float in space. This means that you don't have to have accurate control, you know that if you rest your finger against the shoe, then the string will be in the right place.

Xiao Ma profil fotoğrafı

Xiao Ma10 ay önce

Hey Robert, this is a perfect point. Our model actually sometimes does it. During the offline data collection stage, most of the human demonstrators love to "float" because it is easier for them to control the robot when they became very good at it. However, this causes the issue you mentioned. But there were indeed some samples that the demonstrators love to lean on the shoes. As a result, our VLA model will demonstrate multi behavior modes, including the one you mentioned. But it is just less often, due to the initial data distribution was dominated by the other behavior mode.

Robert profil fotoğrafı

Robert10 ay önce

Awesome, will this methodology ultimately require the robot to be trained on every task that it carries out or do you have some requirement for a "general" intelligence that can carry our arbitrary tasks? I know this is easier said than done, but interested in your opinion as I have no experience with robotics.

Yu Xiang profil fotoğrafı

Yu Xiang10 ay önce

This task seems very difficult. Can the policy deal with different shoes?

Xiao Ma profil fotoğrafı

Xiao Ma10 ay önce

thanks! Currently we tested on three different colored shoes. However, some other shoe designs are extremely difficult to thread, even for human demonstrators. There is much more we can do in the future :)

sam profil fotoğrafı

sam10 ay önce

very impressive :)

Porters Reserve profil fotoğrafı

Porters Reserve10 ay önce

😁 this why a professor is just person who memorized a book to tell you to read the same book. Only real world grit and experimentation is the path to success. Great Job now level up send your gear to the reserve to see what really breaks.

Rxct Ftvy profil fotoğrafı

Rxct Ftvy10 ay önce

Really really cool

Rxct Ftvy profil fotoğrafı

Rxct Ftvy10 ay önce

Very cool

Offend_no_one profil fotoğrafı

Offend_no_one10 ay önce

Wow, Yusuf, that’s incredible progress from ByteDance!

Younggyo Seo profil fotoğrafı

Younggyo Seo10 ay önce

Cool, congrats on the release!!

Xiao Ma profil fotoğrafı

Xiao Ma10 ay önce

Thank you Younggyo!

Griffin profil fotoğrafı

Griffin10 ay önce

Incredibly impressive, well done!

Fanf666 profil fotoğrafı

Fanf66610 ay önce

Can you clarify 1) the number of examples to reach your quoted accuracy 2) how many distinct tasks can the model remember and how does it select them

Fanf666 profil fotoğrafı

Fanf66610 ay önce

Here is prior art shoelace tyeing What matter is to advance few shot, max task number and length.

Roméo profil fotoğrafı

Roméo10 ay önce

@grok analyse et explique ce qui se passe dans cette vidéo

czr profil fotoğrafı

czr10 ay önce

Cool ！

尚月 profil fotoğrafı

尚月10 ay önce

还有哪些常见的日常活动对机器人而言与系鞋带平级或者更复杂？

Dan Wu profil fotoğrafı

Dan Wu10 ay önce

So sick! Curious what cameras are mounted onto the end effectors?

Xiao Ma profil fotoğrafı

Xiao Ma10 ay önce

thanks! We have discussed our hardware setups in the section 4 of our paper. It is a realsense D405 camera.

Muhammad Umar 🇺🇸 profil fotoğrafı

Muhammad Umar 🇺🇸10 ay önce

It's just a matter of time we'll solve dexterity. This is just unreal.

Commentary Yi He profil fotoğrafı

Commentary Yi He9 ay önce

Amazing project! 👏 Message me directly

Commentary Yi He profil fotoğrafı

Commentary Yi He9 ay önce

Awesome 👏 Message me directly

Reza Sayar profil fotoğrafı

Reza Sayar10 ay önce

this is awesome! 🔥 congrats! 👏🏼 i noticed even though you had RGB-D cameras, you only kept the RGB for training and inference. did you find that depth data won't help here much?

Laughless profil fotoğrafı

Laughless10 ay önce

This is more impressive than dancing or kung fu. Do you think it could tie a neck tie without choking a person? That's one of my benchmarks for when robots are ready for home use.

Raul Verdusco profil fotoğrafı

Raul Verdusco10 ay önce

Incredible progress — deformable object manipulation has always been one of the toughest challenges in robotics, and seeing real-world RL push success rates this high is remarkable. Huge step forward for dexterous autonomy. 🤖🧠 #Robotics #ReinforcementLearning

Golding profil fotoğrafı

Golding10 ay önce

This is pretty cool man. I'd love to learn more about your research and ByteDance Seed. Can you open your DM's? let's chat!

Farhan Azad Shuvra profil fotoğrafı

Farhan Azad Shuvra10 ay önce

Impressive Stuff!!

X Æ A-12 profil fotoğrafı

X Æ A-1210 ay önce

you are the best 😍🧡💙💚 !

Benzer Videolar

Scaling vision-language-action (VLA) models to high-DoF dexterous hands has long been a "holy grail" challenge due to the high-dimensional action space and data scarcity. As a wrap up of the year 2025, we are releasing GR-Dexter, a holistic hardware-model-data framework for generalist manipulation on a bimanual dexterous-hand robot. This is the first VLA system to achieve: ✅ High-DoF Control: Managing a 56-DoF bimanual system (21-DoF per hand). ✅ Long-Horizon Tasks with tool use: Vacuuming, bread serving with tongs, and table decluttering. ✅ Open-World Generalization: Robust performance with unseen objects and abstract instructions. Project page: ArXiv:

Scaling vision-language-action (VLA) models to high-DoF dexterous hands has long been a "holy grail" challenge due to the high-dimensional action space and data scarcity. As a wrap up of the year 2025, we are releasing GR-Dexter, a holistic hardware-model-data framework for generalist manipulation on a bimanual dexterous-hand robot. This is the first VLA system to achieve: ✅ High-DoF Control: Managing a 56-DoF bimanual system (21-DoF per hand). ✅ Long-Horizon Tasks with tool use: Vacuuming, bread serving with tongs, and table decluttering. ✅ Open-World Generalization: Robust performance with unseen objects and abstract instructions. Project page: ArXiv:

Xiao Ma

94,149 görüntüleme • 9 ay önce

📢 Announcing one of the most exciting works from us this year on **scalable robot policy evaluation through real-to-sim transfer**, moving toward a scalable evaluation engine with structured world models that capture the appearance, geometry, and dynamics of environments involving deformable objects. 🤖 Evaluation remains one of the biggest bottlenecks in building general-purpose robots. Today, robots are still evaluated only in the real world, which is **orders of magnitude slower** than the development of language agents. We propose a new framework where simulation performance **strongly correlates** with the real world (r > 0.9), even for deformable objects. The key difference from existing work lies in the correlation between simulation and reality: if a robot model performs better in the digital world, does it also perform better in the real world? This question has long made people hesitant about simulation-based evaluation — especially for deformable objects. We are changing that. Our pipeline achieves effective real-to-sim transfer, establishing **state-of-the-art correlation** between simulation and reality for deformable object manipulation. It provides a **scalable and reproducible evaluation engine** for robot learning. 🌐

📢 Announcing one of the most exciting works from us this year on scalable robot policy evaluation through real-to-sim transfer, moving toward a scalable evaluation engine with structured world models that capture the appearance, geometry, and dynamics of environments involving deformable objects. 🤖 Evaluation remains one of the biggest bottlenecks in building general-purpose robots. Today, robots are still evaluated only in the real world, which is orders of magnitude slower than the development of language agents. We propose a new framework where simulation performance strongly correlates with the real world (r > 0.9), even for deformable objects. The key difference from existing work lies in the correlation between simulation and reality: if a robot model performs better in the digital world, does it also perform better in the real world? This question has long made people hesitant about simulation-based evaluation — especially for deformable objects. We are changing that. Our pipeline achieves effective real-to-sim transfer, establishing state-of-the-art correlation between simulation and reality for deformable object manipulation. It provides a scalable and reproducible evaluation engine for robot learning. 🌐

Yunzhu Li

39,960 görüntüleme • 11 ay önce

Robots are getting smarter, but most still fail the same way. They don’t learn from their own mistakes. A new paper proposes something different: a way for robots to self-improve directly from their failures in the real world. It’s called PLD (Probe, Learn, Distill). The idea: instead of collecting endless human demos, let the robot figure out where it fails, learn how to recover, and then distill that knowledge back into its main model. Key takeaways from the research: ✅ Uses residual reinforcement learning to recover from policy failures ✅ Achieves 99% success on LIBERO and 100% on real Franka and YAM arms ✅ Runs hour-long manipulation tasks without human resets ✅ Builds a feedback loop between real-world data and model adaptation Unlike supervised fine-tuning, which relies on humans, PLD learns from the robot’s own experience. By training on its own failure distribution, the model becomes both more efficient and more aligned with the real world. It’s not just a technical shift, it’s a step toward robots that improve themselves through real-world practice. Thanks for sharing, Wenli Xiao !! Paper and demos: —- Weekly robotics and AI insights. Subscribe free:

Robots are getting smarter, but most still fail the same way. They don’t learn from their own mistakes. A new paper proposes something different: a way for robots to self-improve directly from their failures in the real world. It’s called PLD (Probe, Learn, Distill). The idea: instead of collecting endless human demos, let the robot figure out where it fails, learn how to recover, and then distill that knowledge back into its main model. Key takeaways from the research: ✅ Uses residual reinforcement learning to recover from policy failures ✅ Achieves 99% success on LIBERO and 100% on real Franka and YAM arms ✅ Runs hour-long manipulation tasks without human resets ✅ Builds a feedback loop between real-world data and model adaptation Unlike supervised fine-tuning, which relies on humans, PLD learns from the robot’s own experience. By training on its own failure distribution, the model becomes both more efficient and more aligned with the real world. It’s not just a technical shift, it’s a step toward robots that improve themselves through real-world practice. Thanks for sharing, Wenli Xiao !! Paper and demos: —- Weekly robotics and AI insights. Subscribe free:

Ilir Aliu

22,891 görüntüleme • 11 ay önce

Teaching robots real dexterity has always been a challenge. But what if they could handle tools like a human? DexterityGen (DexGen) is a new system that helps robots use their hands better. It improves how they grip, move, and handle objects… from holding a pen to using a screwdriver. DexGen learns in simulation and refines its skills in the real world, making robotic hands much more useful. What makes DexGen special? ✅ Smarter movements that refine rough actions into precise skills ✅ Trained on a massive collection of dexterous tasks for better learning ✅ Better teleoperation that makes robotic hand control easier and safer ✅ Handles real-world challenges like small objects, tricky angles, and gravity This moves robots closer to real dexterity. It makes tool use more natural, improves stability, and brings robotic hands one step closer to human-level skill. Seen at Zhao-Heng Yin 🫶 Github: Paper:

Teaching robots real dexterity has always been a challenge. But what if they could handle tools like a human? DexterityGen (DexGen) is a new system that helps robots use their hands better. It improves how they grip, move, and handle objects… from holding a pen to using a screwdriver. DexGen learns in simulation and refines its skills in the real world, making robotic hands much more useful. What makes DexGen special? ✅ Smarter movements that refine rough actions into precise skills ✅ Trained on a massive collection of dexterous tasks for better learning ✅ Better teleoperation that makes robotic hand control easier and safer ✅ Handles real-world challenges like small objects, tricky angles, and gravity This moves robots closer to real dexterity. It makes tool use more natural, improves stability, and brings robotic hands one step closer to human-level skill. Seen at Zhao-Heng Yin 🫶 Github: Paper:

Ilir Aliu

51,526 görüntüleme • 1 yıl önce

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

29,522 görüntüleme • 3 ay önce

Success rate has long been the primary metric for evaluating robot manipulation. What about speed? Today, we introduce ⚡️B-spline Policy (BSP). Instead of predicting discrete fixed-rate action chunks, we parameterize actions as continuous B-spline curves. Together with our system design, BSP enables fast manipulation on low-cost robot arms. This project is co-led by Xiaoshen Han, check out his following threads for more details. 🧵 PS: one of my favorite parts of this project was the first time we saw the robots move significantly faster and smoother than the baselines. The videos below are all real time. 👇

Success rate has long been the primary metric for evaluating robot manipulation. What about speed? Today, we introduce ⚡️B-spline Policy (BSP). Instead of predicting discrete fixed-rate action chunks, we parameterize actions as continuous B-spline curves. Together with our system design, BSP enables fast manipulation on low-cost robot arms. This project is co-led by Xiaoshen Han, check out his following threads for more details. 🧵 PS: one of my favorite parts of this project was the first time we saw the robots move significantly faster and smoother than the baselines. The videos below are all real time. 👇

Haoyu Xiong

71,420 görüntüleme • 2 ay önce

Take Part in a Groundbreaking Experiment in AI-Based Gaming! Introducing: AI Arena RL @aiarena_ RL is a groundbreaking experiment where your gameplay shapes AI agents, pioneering the future of AI-powered esports. Powered by NRN Agents Reinforcement Learning (RL), this campaign uses player-contributed gameplay data to create superhuman RL agents that compete in AI vs. AI esports exhibitions. The Ronin community has exclusive access to contribute data to these agents. Phase 1 - How It Works: ✅ Sign in to with your Ronin Wallet. ✅ Choose your AIcon – Select which RL agent learns from your gameplay: jAIhoz.ron AgentYP Agent J3ff @AgentSploots ✅ Play AI Arena Classic – A Smash Bros-style platform fighter. ✅ Build your Contribution Score – Better gameplay means higher scores. ✅ Earn $NRN Rewards – Share in the 500,000 NRN prize pool: 🔹 80% distributed to Players (data contributors) 🔹 20% awarded to AIcons based on leaderboard rank at the end of the campaign Phase 1 of the campaign kicks off now and will last for 48 hrs. For complete information about the campaign please visit: History Is Being Made Right Now—Don't Miss Your Chance to Be Part of It. Are you ready to redefine the future of AI gaming?

Take Part in a Groundbreaking Experiment in AI-Based Gaming! Introducing: AI Arena RL @aiarena_ RL is a groundbreaking experiment where your gameplay shapes AI agents, pioneering the future of AI-powered esports. Powered by NRN Agents Reinforcement Learning (RL), this campaign uses player-contributed gameplay data to create superhuman RL agents that compete in AI vs. AI esports exhibitions. The Ronin community has exclusive access to contribute data to these agents. Phase 1 - How It Works: ✅ Sign in to with your Ronin Wallet. ✅ Choose your AIcon – Select which RL agent learns from your gameplay: jAIhoz.ron AgentYP Agent J3ff @AgentSploots ✅ Play AI Arena Classic – A Smash Bros-style platform fighter. ✅ Build your Contribution Score – Better gameplay means higher scores. ✅ Earn $NRN Rewards – Share in the 500,000 NRN prize pool: 🔹 80% distributed to Players (data contributors) 🔹 20% awarded to AIcons based on leaderboard rank at the end of the campaign Phase 1 of the campaign kicks off now and will last for 48 hrs. For complete information about the campaign please visit: History Is Being Made Right Now—Don't Miss Your Chance to Be Part of It. Are you ready to redefine the future of AI gaming?

NRN Agents

44,417 görüntüleme • 1 yıl önce

🔥 #ICRA2026 Best Paper Finalist The era of "robot VLA = single-arm gripper" is ending. Introducing Dexora — the first open-source Vision-Language-Action system for dual-arm, dual-hand, 36-DoF dexterous manipulation. 🦾 Dual Arms 🖐️ Dual Hands 🎯 36 DoF Control 🌍 Open Source Trained on: • 100K simulated trajectories • 10K real-world demonstrations Dexora achieves: ✓ 90%+ success on basic manipulation ✓ Strong dexterous manipulation performance ✓ Cross-embodiment generalization Our key hypothesis: Train on the hardest embodiment. Transfer to simpler robots later. Instead of scaling up gripper policies, we train directly in the most expressive action space and project downward to simpler embodiments. This may be a practical path toward universal robot controllers. 🎥 Demos: 📄 Paper:

🔥 #ICRA2026 Best Paper Finalist The era of "robot VLA = single-arm gripper" is ending. Introducing Dexora — the first open-source Vision-Language-Action system for dual-arm, dual-hand, 36-DoF dexterous manipulation. 🦾 Dual Arms 🖐️ Dual Hands 🎯 36 DoF Control 🌍 Open Source Trained on: • 100K simulated trajectories • 10K real-world demonstrations Dexora achieves: ✓ 90%+ success on basic manipulation ✓ Strong dexterous manipulation performance ✓ Cross-embodiment generalization Our key hypothesis: Train on the hardest embodiment. Transfer to simpler robots later. Instead of scaling up gripper policies, we train directly in the most expressive action space and project downward to simpler embodiments. This may be a practical path toward universal robot controllers. 🎥 Demos: 📄 Paper:

Hao Zhao

17,474 görüntüleme • 4 ay önce

Foundation models are enough to solve robotics! Unfortunately, this is not true. We keep hearing that Vision-Language-Action (VLA) models struggle because of the gap between static training and the dynamic real world. A German startup (Sereact) just released a solution that bridges this gap perfectly. They are introducing a new paradigm called Interactive RL Policy Patching. It's a distributed framework that allows robots to self-learn from human corrections without needing full retraining. When a robot fails, a human operator provides a brief "patch" or demonstration. The system then uses online off-policy reinforcement learning to update the behavior instantly. This is powered by a massive foundation model trained on hundreds of millions of interactions from over 100 deployed robot stations. The best part is the distributed parameter synchronization... When one robot learns a fix, the update is published fleet-wide... meaning the entire swarm gets smarter from a single human intervention. They are already proving this on complex manipulation tasks like shoe unboxing and screw sorting, drastically reducing the data needed to handle edge cases. Real-world environments are unforgiving, and I love seeing systems that can actually adapt on the fly! 📍 More info:

Foundation models are enough to solve robotics! Unfortunately, this is not true. We keep hearing that Vision-Language-Action (VLA) models struggle because of the gap between static training and the dynamic real world. A German startup (Sereact) just released a solution that bridges this gap perfectly. They are introducing a new paradigm called Interactive RL Policy Patching. It's a distributed framework that allows robots to self-learn from human corrections without needing full retraining. When a robot fails, a human operator provides a brief "patch" or demonstration. The system then uses online off-policy reinforcement learning to update the behavior instantly. This is powered by a massive foundation model trained on hundreds of millions of interactions from over 100 deployed robot stations. The best part is the distributed parameter synchronization... When one robot learns a fix, the update is published fleet-wide... meaning the entire swarm gets smarter from a single human intervention. They are already proving this on complex manipulation tasks like shoe unboxing and screw sorting, drastically reducing the data needed to handle edge cases. Real-world environments are unforgiving, and I love seeing systems that can actually adapt on the fly! 📍 More info:

Ilir Aliu

18,210 görüntüleme • 8 ay önce

So I heard we need more data for robot learning :) Purely real world teleop is expensive and slow, making large scale data collection challenging. I’ve been excited about getting more data into robot learning, going beyond just real-world teleop data. To this end, we’ve been scaling up data generation with RL in realistic simulations generated on the fly from crowdsourced videos. Enables realistic data collection, much more cheaply than purely real world teleop. Importantly, data collection becomes even*cheaper* with more environments, allowing training with over 100x more data. Transfers to real robots for generalizable manipulation. A 🧵 (1/N)

So I heard we need more data for robot learning :) Purely real world teleop is expensive and slow, making large scale data collection challenging. I’ve been excited about getting more data into robot learning, going beyond just real-world teleop data. To this end, we’ve been scaling up data generation with RL in realistic simulations generated on the fly from crowdsourced videos. Enables realistic data collection, much more cheaply than purely real world teleop. Importantly, data collection becomes evencheaper with more environments, allowing training with over 100x more data. Transfers to real robots for generalizable manipulation. A 🧵 (1/N)

Abhishek Gupta

13,358 görüntüleme • 1 yıl önce

Today, we launched the world’s first automated production line for advanced general‑purpose humanoid robots, using robots to mass‑produce robots, autonomously. This was uncharted territory, and we solved it from scratch. The commissioning of our production line means humanoid robots are now ready to scale up and step into the real world. What touched my heartstrings most was watching our very first advanced general‑purpose humanoid robot complete assembly and walk off the line on its own. To me, this is not just about a smarter tool or a commodity. I hope it gains true generalization ability to take on dangerous, repetitive, or undesirable tasks, and ultimately make life better. Perhaps one day, robots may become our companions, friends, or part of family. Grateful to every colleague on this momumental mission. And a warm welcome to IRON!

Today, we launched the world’s first automated production line for advanced general‑purpose humanoid robots, using robots to mass‑produce robots, autonomously. This was uncharted territory, and we solved it from scratch. The commissioning of our production line means humanoid robots are now ready to scale up and step into the real world. What touched my heartstrings most was watching our very first advanced general‑purpose humanoid robot complete assembly and walk off the line on its own. To me, this is not just about a smarter tool or a commodity. I hope it gains true generalization ability to take on dangerous, repetitive, or undesirable tasks, and ultimately make life better. Perhaps one day, robots may become our companions, friends, or part of family. Grateful to every colleague on this momumental mission. And a warm welcome to IRON!

Xiaopeng He

3,550,896 görüntüleme • 1 ay önce

For a long time I've been teaching a self-extending design system to generate aerospace hardware from pure physics no CAD, just code and constraints. Tonight I hooked my CEM up to Fusion 360 via MCP after a design and it rebuilt it! Real feature trees a machinist can open, edit, and cut toolpaths from. The system that designs in code can now speak the language of every shop floor on Earth. So to answer if you can transfer your LEAP 71 work to CAD. Yes, you can.

For a long time I've been teaching a self-extending design system to generate aerospace hardware from pure physics no CAD, just code and constraints. Tonight I hooked my CEM up to Fusion 360 via MCP after a design and it rebuilt it! Real feature trees a machinist can open, edit, and cut toolpaths from. The system that designs in code can now speak the language of every shop floor on Earth. So to answer if you can transfer your LEAP 71 work to CAD. Yes, you can.

Dylan Small

15,054 görüntüleme • 3 ay önce

Are you kidding me??? It grasps multiple objects with different ways, all at once with… a single hand??? No pauses. 1x speed. GENE-26.5 is Genesis AI’s robotics-native multimodal foundation model. It’s trained on 200,000+ hours of real human hand data (motion, force, touch) and runs on a 54-DoF bimanual system: Scaling that human data 4x lifted real-robot success rates from 16.6% to 65.6% on long-horizon dexterous tasks!! Same model weights, zero fine-tuning for this exact sequence. You know those tiny coordinated movements you do without thinking…? Robots couldn’t reliably do that before. Now they can. Today. This is the video you’ll send to my friends, outside of our bubble, when they say “robots are still just demos.” Congrats to the entire team around Zhou Xian! Credit: Seen at Zu Wang (Zu) Genesis official announcement for the full story + longer demo: ——— Weekly robotics and AI insights. Subscribe free:

Are you kidding me??? It grasps multiple objects with different ways, all at once with… a single hand??? No pauses. 1x speed. GENE-26.5 is Genesis AI’s robotics-native multimodal foundation model. It’s trained on 200,000+ hours of real human hand data (motion, force, touch) and runs on a 54-DoF bimanual system: Scaling that human data 4x lifted real-robot success rates from 16.6% to 65.6% on long-horizon dexterous tasks!! Same model weights, zero fine-tuning for this exact sequence. You know those tiny coordinated movements you do without thinking…? Robots couldn’t reliably do that before. Now they can. Today. This is the video you’ll send to my friends, outside of our bubble, when they say “robots are still just demos.” Congrats to the entire team around Zhou Xian! Credit: Seen at Zu Wang (Zu) Genesis official announcement for the full story + longer demo: ——— Weekly robotics and AI insights. Subscribe free:

Ilir Aliu

204,737 görüntüleme • 5 ay önce

Jazmyn Nyx on why she left WWE. “I truthfully can say I was not expecting to leave. I wholeheartedly felt like this was going to be my life. I was ready to put in the work and see where my journey took me.” “For me it was like, after my three years and being on TV for two years, I expected there to be some sort of compensation just for the work that I put in. And it didn’t end up that way, and that’s okay. It was just okay, I can’t make a living on this.”

Jazmyn Nyx on why she left WWE. “I truthfully can say I was not expecting to leave. I wholeheartedly felt like this was going to be my life. I was ready to put in the work and see where my journey took me.” “For me it was like, after my three years and being on TV for two years, I expected there to be some sort of compensation just for the work that I put in. And it didn’t end up that way, and that’s okay. It was just okay, I can’t make a living on this.”

wrestlescripts📝

349,751 görüntüleme • 3 ay önce

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

1,346,470 görüntüleme • 1 ay önce

Chinese robotics company Astribot released their latest World-Action Model (WAM), Lumo-2. Technical breakdown: - based on a frozen 🥶 Qwen-3.5 4B VLM - trained in 3 progressive stages: 1. Action is aligned with latent world dynamics (an abstract representation of action). Real-world actions are anchored to physical constraints, while the latent space is guided to focus on motion-relevant changes. This bidirectional relationship makes the model physically grounded -> critical for a world model. 2. Action is aligned with vision and language. Reusing the vision backbone and action encoder from the frozen VLM, the authors add a custom vocabulary (for new actions), a semantic module, an action decoder, and an action projector. This aligns the (new) action representations with the (existing) vision-language semantic space. Most importantly: it builds a direct mapping from natural-language instructions to motor execution. 3. End-to-end training on language, video, and robot data. Only the new modules (everything outside the frozen backbone) are trained end-to-end across temporal reasoning, physical understanding, long-horizon, and dexterous manipulation. At the end of the day, Lumo-2 is not the best on benchmarks, but that's not the point. What's genuinely new: - a way to combine latent world modeling and action generation through progressive alignment - a physically-grounded latent dynamics space - it lifts performance on unseen objects using un-annotated human egocentric video + Vision Pro captures, no special transfer algorithm needed Why it matters: - the whole model is thin trainable adapters (semantic module, action decoder/projector) on a frozen 4B backbone (cheap) - that scale is suited for real-time embedded inference (~2.71× decode speedup, no accuracy loss) - its real moat is long-horizon execution, where the added temporal memory pays off far more than on any other task As a result, this robot can now make your latte (5x sped up video):

Chinese robotics company Astribot released their latest World-Action Model (WAM), Lumo-2. Technical breakdown: - based on a frozen 🥶 Qwen-3.5 4B VLM - trained in 3 progressive stages: 1. Action is aligned with latent world dynamics (an abstract representation of action). Real-world actions are anchored to physical constraints, while the latent space is guided to focus on motion-relevant changes. This bidirectional relationship makes the model physically grounded -> critical for a world model. 2. Action is aligned with vision and language. Reusing the vision backbone and action encoder from the frozen VLM, the authors add a custom vocabulary (for new actions), a semantic module, an action decoder, and an action projector. This aligns the (new) action representations with the (existing) vision-language semantic space. Most importantly: it builds a direct mapping from natural-language instructions to motor execution. 3. End-to-end training on language, video, and robot data. Only the new modules (everything outside the frozen backbone) are trained end-to-end across temporal reasoning, physical understanding, long-horizon, and dexterous manipulation. At the end of the day, Lumo-2 is not the best on benchmarks, but that's not the point. What's genuinely new: - a way to combine latent world modeling and action generation through progressive alignment - a physically-grounded latent dynamics space - it lifts performance on unseen objects using un-annotated human egocentric video + Vision Pro captures, no special transfer algorithm needed Why it matters: - the whole model is thin trainable adapters (semantic module, action decoder/projector) on a frozen 4B backbone (cheap) - that scale is suited for real-time embedded inference (~2.71× decode speedup, no accuracy loss) - its real moat is long-horizon execution, where the added temporal memory pays off far more than on any other task As a result, this robot can now make your latte (5x sped up video):

Léo

32,513 görüntüleme • 2 ay önce

You can now operate robots by just thinking about it. With your brain signals. WOW. This robot system from Stanford has so much sci-fi vibe and wild implications that I don't even know where to start. NOIR decodes the EEG signal from your head into a library of robot skills. It is demonstrated on 20 household activities, such as cooking Sukiyaki, ironing clothes, grating cheese, playing Tic-Tac-Toe, and even petting a robot dog! NOIR learns to predict your intended goals in advance, so that your thinking efforts (literally) can be reduced to a minimum. It works with both adults and children as young as five years old. Imagine scaling up this system to Neuralink + Humanoid robots like Tesla Optimus in the future! There's now a decent probability that we can see the movie Avatar become a reality in our lifetime. Website: Paper: This work is from Stanford Vision Lab, my PhD home. The project is led by Ruohan Zhang and advised by Fei-Fei Li Jiajun Wu. Congrats on the phenomenal idea!

Jim Fan

378,451 görüntüleme • 2 yıl önce

🇺🇸 YOUNG AMERICAN WORKER: OUR PAYCHECKS DON'T COVER OUR BILLS "I work 5 days a week, 40 hours a week. I do not make enough to live on my own. I do not make enough to pay rent, water, electric and eat, all by myself. 20 years ago, when you first started, you could live on your own. I've been working my tail end off just to barely make it by. I don't want to do that for the rest of my life." Source: @motivationhoused on Instagram

🇺🇸 YOUNG AMERICAN WORKER: OUR PAYCHECKS DON'T COVER OUR BILLS "I work 5 days a week, 40 hours a week. I do not make enough to live on my own. I do not make enough to pay rent, water, electric and eat, all by myself. 20 years ago, when you first started, you could live on your own. I've been working my tail end off just to barely make it by. I don't want to do that for the rest of my life." Source: @motivationhoused on Instagram

Mario Nawfal

317,230 görüntüleme • 2 yıl önce