THIS CHANGES EVERYTHING it's not another robot model. it's... not another polished demo. it's the infrastructure nobody had built. LLMs scaled because they had the entire internet to train on. massive evaluation. RL at scale. robotics never had either. midcentury just came out of stealth with $15M to solve exactly that. they built the world's largest egocentric dataset. recorded from the human point of view. 3D hand pose supervision, depth and tactile information. → 2M+ hours of real-world data → 50+ environments → 20,000+ tasks → hands visible in 90% of frames and Matrix cloud-scale simulation where policies run across thousands of closed-loop scenarios in parallel. failures don't break hardware, they become training. nobody debugs a policy on an expensive robot. nobody generalizes from one clean room. → team from Stanford AI Lab, Scale AI, DeepMind, NVIDIA, OpenAI → already working with frontier labs demos were the easy part. this is what comes next.show more

liam.
36,524 次观看 • 1 个月前
Humanoid robots have a truly insatiable appetite for data.... Midcentury, another New York-based physical AI company, claims to have surpassed the milestone of 2 million hours of human first-person behavioral data: > It covers over 50 environments and 20,000+ tasks, with hands clearly visible in more than 90% of the footage. > It offers more than just raw video; the dataset includes 3D hand tracking, depth maps, and task annotations, and even bundles in 50,000 hours of gameplay data and 69,000 hours of multilingual dialogue. > Beyond selling data, they have developed a cloud-based simulation platform called "Matrix," enabling humanoid robots to train directly in the cloud using this data. --- Companies like Dyna Robotics have demonstrated that if you feed AI enough egocentric/human-centric data, it can independently grasp the objective laws of the physical world, yielding astonishing model performance. It is fair to say that human behavioral data is becoming the "new oil" of the physical AI era. This achievement has helped Midcentury secure $15 million in seed funding.show more

CyberRobo
10,495 次观看 • 1 个月前
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

Chris Yoo
13,641 次观看 • 1 个月前
Generalist robot policies need a benchmark that works across... any robot and any policy. 🦾 Introducing RoboLab, a high‑fidelity simulation benchmark built on NVIDIA Isaac and Omniverse to evaluate generalist robot policies in diverse, photoreal, physics‑based environments. Coming soon to the NVIDIA Isaac Lab‑Arena roadmap for large‑scale, robotic policy evaluation. 📖 #NationalRoboticsWeekshow more

NVIDIA Robotics
24,097 次观看 • 7 个月前
GROK DOMINATES AI AT SCALE, REDEFINING WHAT’S POSSIBLE IN... REAL TIME Most AI models stall at the prototype phase. Grok advances beyond limits where others fail to perform. • Built for real-time decisioning across vast data landscapes • Optimized to process, synthesize, and respond with human-like fluidity • Deploys intelligence at the edge, not just in the cloud • Powers robotics, research, and infrastructure in live environments • Infrastructure built to evolve, not collapse, under scale Grok delivers high-performance AI built for deployment and real-world use. Source: xAI, Grok, Elon Muskshow more

Mario Nawfal
28,837 次观看 • 10 个月前
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

The Daily Ai
33,468 次观看 • 2 个月前
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.show more

Axis Robotics
72,960 次观看 • 3 个月前
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:show more

Over the Reality 🌐
15,316 次观看 • 2 个月前
🚨 BREAKING: NVIDIA just announced the Isaac GR00T Reference... Humanoid Robot. The first fully open humanoid robot reference design built on Jetson Thor, and it's going straight to the world's top research institutions. This is Jensen Huang's bet on open physical AI infrastructure. The hardware stack is serious: → Unitree H2 Plus chassis, 6 feet tall, 150 pounds, 31 degrees of freedom → Sharpa Wave tactile five-finger hands, 22 degrees of freedom, bringing total to 75 across the full body → NVIDIA Jetson AGX Thor onboard compute, 2,070 FP4 teraflops of AI performance, 128GB unified memory → Multi-view sensing, stereo head camera, wrist cameras, IMU Alongside this announcement, Unitree also introduced the H2 Plus as a standalone product, a frontier humanoid combining Unitree's own body, Sharpa's five-finger hands and NVIDIA Robotics Jetson Thor compute into one fully integrated research platform. The full Isaac GR00T software stack ships with it, teleoperation for data capture, open foundation models, Isaac Sim for training, Isaac Lab for evaluation, and accelerated ROS middleware for deployment. The complete loop from data to real-world robot in one unified platform. ETH Zürich, Stanford Robotics Center, UC San Diego and Ai2 are already on board as launch research partners. NVIDIA Robotics did to AI what it's now doing to robotics, build the platform, open the ecosystem, let the world build on top of it. Whoever owns the infrastructure layer wins. NVIDIA knows this better than anyone. 👀 Read more here: ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →show more

Lukas Ziegler
16,062 次观看 • 5 个月前
JUST IN: Reimagine Robotics has just emerged from stealth!... 🥷🏻 Its approach to robot training is one of the most human-centric I've seen. The founder is Jonathan Scholz, the person who built and led Google DeepMind's Applied Robotics team in London for seven years. This is not a first-time founder taking a swing at robotics. He has spent a decade at the frontier of the field. The philosophy is powerful. He calls it "monkey-see, monkey-do." 🐒 A worker shows the robot what to do. Watches it attempt the task. Corrects it on the spot. The robot learns. No specialist programmers. No months of integration. And it's already working in the real world: → A made-to-order plastics business trained robots to tend 3D printers overnight, removing print beds, operating latches, pressing controls → A hard drive disassembly facility built a three-robot cell combining robots and people to recover critical materials → Time to prototype and test a new robot behaviour reduced from one day to 10 MINUTES That last number is the one that changes everything. When testing a new behaviour takes 10 minutes instead of a day, the entire pace of deployment transforms. Scholz's framing of the human-robot relationship is worth reading carefully: "A robot that learns on the job depends on people. The worker identifies the bottleneck, shows the robot how to help, and corrects it until it is useful." It's August, and we keep getting robotics bangers week in week. ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →show more

Lukas Ziegler
23,404 次观看 • 3 个月前
There's an engineer on YouTube building his own room-scale... laundry-picking UFO catcher robot out of QR codes and string, it's one of the most compelling robotics demos I've seen in a while.show more

Jon Barron
513,683 次观看 • 8 个月前
Trained on zero real-world data. Learned to walk, pick... up boxes, and follow multi-step instructions... in the REAL world. ( 📌 Paper below) Researchers from Amazon FAR, Berkeley, Stanford, and CMU scanned real rooms with an iPhone, rebuilt them as 3D Gaussian Splatting scenes, then generated 48,000 synthetic trajectories of a Unitree G1 walking, grasping, and placing objects inside those virtual replicas. They rendered the robot's first-person camera view from each run and paired it with the matching language instruction and motion data. That's the dataset every humanoid team needs and nobody has: synced egocentric video + language + kinematics, at scale. Instead of collecting it in the real world, they manufactured it. They trained a vision-language-kinematics policy on that synthetic data alone, then deployed it on the physical G1 across five task types: navigation to a named object, lifting boxes of three different sizes with no per-size tuning, chained multi-step tasks, robustness to mid-task layout changes and flickering lights, and multi-minute long-horizon runs. No real-world fine-tuning at any point. Real-world interaction data has been the hard limit on humanoid learning... slow, expensive, and small. If scanning a room once and synthesizing thousands of labeled interactions holds up as a general recipe, that limit moves. Data stops being the bottleneck robotics teams have to solve for. 📌 Paper: Project: ——- Weekly robotics and AI insights. Subscribe free:show more

Ilir Aliu
12,950 次观看 • 3 个月前
Today may be the ImageNet moment for robotics. RT-X:... the largest open-source robot dataset ever compiled, across 33 institutes, 22 robot hardware, 527 skills, and 1M episodes. Why is robotics lagging so far behind NLP, vision, and other AI domains? Data scarcity is the main culprit to blame, among other difficulties. Unlike text, images, and videos, you cannot download mass amounts of onboard robot control data from the internet. They simply don't exist in the wild. 11 yrs ago, ImageNet kicked off the deep learning revolution. 3-4 yrs ago, internet-scale data fueled the first GPTs and Diffusions that define this era of foundation models. I think 2023 is finally the year for robotics to scale up. Robot foundation models like VIMA ( my team's work at NVIDIA) and RT-1/2 ( Google DeepMind's effort) are extremely data hungry. While massively parallel simulations like NVIDIA IsaacGym & Omniverse can alleviate the problem to some extent, it's still not quite enough to bridge the gap to the messy, physical world. This new dataset is not just a technical contribution. I also see it as a commendable effort to overcome institutional bureaucracies and unite researchers from around the world to tackle a grand challenge together. Robotics will be the final holy grail that we capture in AI. We are not there yet, but ascending in the right gradient direction. RT-X website: Launch blog:show more

Jim Fan
265,061 次观看 • 3 年前
Holy sh!t ! OpenAI will have their custom inference... chips ready in just a few months and deployed at scale by the end of the year! 🤯 Training chip = The heavy lifters that require massive amounts of data and power to build and teach the AI models from scratch. Inference chip = The specialized, highly efficient chips that actually run the AI and generate the answers in real-time when you use it. This is going to help OpenAI drastically cut down their massive compute costs, speed up model reasoning times, and finally break free from relying entirely on Nvidia to scale their operations.show more

Chris
60,278 次观看 • 8 个月前
Furniture assembly is the task everyone name-drops and nobody... actually attempts at real scale. Every demo I have seen is a scaled down IKEA leg or a single arm on a toy chair. This paper does it properly, real scale, bimanual, up to 7 subtasks and 1,550 control steps per episode, and it is validated on a real Kinova Gen3, not just in sim. That real-robot number is the one that matters: only a 16 percent drop on the hardest task going from simulation to hardware. That is a small enough gap to take seriously, and it did not happen by accident. They built a VR teleoperation rig specifically for coordinated dual-arm collection, because generic single-arm teleop setups do not capture the coordination real assembly needs, and the model predicts a continuous progress signal alongside the action chunk rather than a discrete subtask label, letting it auto-transition and catch drift before it compounds into total failure. The simulation ablation is what got them there, 48 to 80 percent over baselines, with another 21 points from their perception and control design study alone, but that is groundwork, not the headline. Watch the video, there is a clip of the robot misgrasping the seat panel, reopening the gripper, and regrasping on its own. That is not scripted recovery behaviour, it emerged from training, and it emerged on hardware. Excellent work from the team from Mitsubishi Electric Research Laboratories, with Oxford and UNC Chapel Hill Clinical Laboratory Science. Video and project page in comments. #Robotics #Manipulation #VLAshow more

Stephen James
14,952 次观看 • 4 个月前
The next big AI breakthrough might not come from... a bigger model. It might come from data no model has ever seen before. Most AI labs have already trained extensively on publicly available data. But private codebases, real-world tasks, and RL environments are still largely inaccessible. DataVendor is changing that. A marketplace where AI labs can discover, evaluate, and license private training data. This is a pretty interesting direction for AI infrastructure.show more

Aakash Kanojiya
49,715 次观看 • 25 天前
You can't 3D reconstruct glass from images... ...WRONG! Thanks... for video diffusion, now just about anything is possible! Introducing...Diffusion Knows Transparency (DKT) Transparent and reflective objects usually break robot vision and photogrammetry pipelines because they don't follow the "solid object" rules standard cameras expect. DKT is a new AI model that repurposes the "internal physics engine" found in video generation models to solve this problem. Researchers took a massive video diffusion model (WAN) and fine-tuned it using a custom-built synthetic dataset to turn it into a high-precision depth sensor. To train the AI, they built the first massive synthetic video library of transparent objects, 1.32 million frames of perfectly labeled glass and metal objects in motion. Without ever seeing a "real" labeled video of glass during training, the model (DKT) outperformed all previous specialized systems on real-world benchmarks (ClearPose, DREDS). They created a "lightweight" 1.3B parameter version that runs fast enough (0.17s per frame) to be used on actual robot hardware. Two reasons I find this project important: 1. It further proves that synthetic data will be essential for training the next generation vision models. 2. In real-world robotic tests, using DKT's depth maps nearly doubled the success rate of robot arms trying to pick up objects on tricky reflective or translucent surfaces. At home robots will need to interact with these types of objects on a daily basis. Check out the project page here: Code is LIVE! #Computervision #Robotics #AIshow more

Jonathan Stephens
17,712 次观看 • 10 个月前
What if the next big leap in AI comes... from data that’s never been on the internet? Most AI models learn from publicly available information, but companies hold enormous amounts of valuable private data. DataVendor is changing that with a marketplace where companies can sell access to their data to AI labs, helping train smarter AI. With 4,000+ vendors and 50K+ assets already listed, this could be huge.show more

Science girl
27,169 次观看 • 24 天前
A ROBOT WENT ROGUE IN AUSTIN, TEXAS AND ANOTHER... ROBOT HAD TO TAKE IT DOWN During a routine test at a robotics facility in Austin, one of the robots suddenly malfunctioned, escaped its base, and attacked a man nearby. But here's the crazy part. A second robot immediately stepped in, intercepted the rogue machine, and neutralized it before things got worse. One robot attacked a human. Another robot saved him. We're entering an era where robots might need to protect us from other robots. Is this the future of AI security?show more

Andrey
19,843 次观看 • 21 天前
Spatial AI ( is building large real-world datasets to... teach robots how to navigate the world and complete tasks. Their first open source dataset, SEA (Spatial Everyday Activities), is the largest curated egocentric dataset of people carrying out real tasks, with 10,000 hours of data.show more

Y Combinator
21,461 次观看 • 1 年前