Video wird geladen...

Video konnte nicht geladen werden

Beim Laden dieses Videos ist ein Problem aufgetreten. Dies könnte an einem vorübergehenden Netzwerkproblem liegen oder das Video ist möglicherweise nicht verfügbar.

Today we're announcing microSLAM, a monocular SLAM system built by our computer vision team in Zürich with ETH Zurich's Computer Vision and Geometry Lab. It ranks first on the LaMaria benchmark for monocular SLAM, and holds up against systems that carry many more cameras and IMUs. Ours runs on... a single RGB stream. Robot learning is bottlenecked on data, and the largest untapped source is people going about their work. A camera on someone's head for an afternoon in a plant is a record of how that plant actually operates, including all the parts nobody writes down. That data is only useful if you can recover the geometry, and geometry from one moving camera in a world that will not sit still is the hard version of the problem. Solving it monocular is what makes the data cheap. Rigs do not scale to every worker. Glasses do. microSLAM turns that footage into interactive 3D environments where behavioral foundation models can be trained. One person walks a factory floor. A robot learns to navigate it.show more

Gianni Hodel

1,812 subscribers

76,090 Aufrufe • vor 2 Monaten •via X (Twitter)

Wissenschaft & Technologie

Anya Rossi• Live Now

Private livecam show

20 Kommentare

Profilbild von Pablo Vela

Pablo Velavor 2 Monaten

Cool! What’s the runtime compared to orbslam 3?

Profilbild von toolshed

toolshedvor 2 Monaten

The extra cameras and IMUs are not only about accuracy. One moving camera recovers geometry up to an unknown scale factor, and a stereo baseline or an accelerometer is what gets the metres back. A robot judging a 40cm gap needs metres. Where does microSLAM get its scale?

Profilbild von /

/vor 2 Monaten

closed source?

Profilbild von Ricardo de Azambuja

Ricardo de Azambujavor 2 Monaten

Link to the repo or it doesn't exist 🙃

Profilbild von mansin

mansinvor 2 Monaten

Awesome! Would love to test it

Profilbild von Azeem

Azeemvor 2 Monaten

microSLAM uses a single RGB stream and still outperforms systems with multiple cameras and IMUs. The LaMaria benchmark is one of the most rigorous for monocular SLAM. The fact that ETH Zurich's lab is involved adds significant credibility.

Profilbild von Vasco 🇳🇱🇹🇭

Vasco 🇳🇱🇹🇭vor 2 Monaten

👀👀👀

Profilbild von The Canaanite

The Canaanitevor 2 Monaten

Wonderful, wen robot for housework and how much?

Profilbild von Armeen

Armeenvor 2 Monaten

The hard part is not monocular geometry; it is keeping it stable under motion and layout change. We can help capture the rare failure slices, then keep #heldout evaluation on unseen plant configurations rather than another pass through the same walk.

Profilbild von AI Mastery Guide

AI Mastery Guidevor 2 Monaten

Ranking first with one camera, impressive

Profilbild von indoor positioning

indoor positioningvor 2 Monaten

开源没

Profilbild von Senthilnathan K

Senthilnathan Kvor 2 Monaten

Would love to test this and integrate into our platform, monocular depth estimation if done accurately is super useful

Profilbild von Alvaro L

Alvaro Lvor 2 Monaten

How does it compare to Lingbot Map

Profilbild von DAY☀️

DAY☀️vor 2 Monaten

love a low calorie solution

Profilbild von Daniel Mika

Daniel Mikavor 2 Monaten

Cool work guys

Profilbild von Aryan Dhawan

Aryan Dhawanvor 2 Monaten

Getting a first-place result from one camera is honestly exciting. I’d look next at motion blur and fast body rotation, since those are exactly where monocular SLAM gets uncomfortable on a walking robot.

Profilbild von remco_bos

remco_bosvor 2 Monaten

Release source and open source MicroRover

Profilbild von Julien Blanchon 🇺🇦

Julien Blanchon 🇺🇦vor 2 Monaten

Link ?

Profilbild von Roko’s Basilica

Roko’s Basilicavor 2 Monaten

Cool, but do you really need to use AI to write a slop tweet?

Profilbild von Dredge

Dredgevor 2 Monaten

Monocular SLAM ranks first on LaMaria - benchmark conditions. Real factory: uncontrolled light, fast movements, occlusions. Does geometry recovery hold? If microSLAM degrades 10-20% on messy data, how much does that hurt downstream model training?

Ähnliche Videos

Announcing FPV-SLAM, a state-of-the-art SLAM system for egocentric data. FPV-SLAM ranks 1st in the monocular-inertial track of LaMAria, ETH Zurich's city-scale benchmark.

Announcing FPV-SLAM, a state-of-the-art SLAM system for egocentric data. FPV-SLAM ranks 1st in the monocular-inertial track of LaMAria, ETH Zurich's city-scale benchmark.

Abhishek Anand

13,647 Aufrufe • vor 12 Tagen

A lot of robot learning pipelines treat embodiment mismatch as a software problem. Collect data with one device, retarget the motion to another robot, and try to deal with the differences later. TwinDEX flips that idea around. This system is from a Chinese robotics company called X Square. Instead of starting with a generic data-collection device, the team co-designs a wearable three-finger end-effector and a robotic hand as two sides of the same learning system. They align the things that actually matter during manipulation: joint structure, link proportions, contact geometry, surface properties, visual appearance, sensing, and timing. That matters because dexterous manipulation is much more than matching hand poses. A few millimeters of contact error or a different force relationship can completely change how a task is executed. In the collection evaluation, TwinDEX delivered up to 5.3 times the effective throughput of on-robot teleoperation. It’s a useful reminder that scaling robot learning may not only be about bigger models and more data. Sometimes the hardware collecting the data is part of the data problem itself.

A lot of robot learning pipelines treat embodiment mismatch as a software problem. Collect data with one device, retarget the motion to another robot, and try to deal with the differences later. TwinDEX flips that idea around. This system is from a Chinese robotics company called X Square. Instead of starting with a generic data-collection device, the team co-designs a wearable three-finger end-effector and a robotic hand as two sides of the same learning system. They align the things that actually matter during manipulation: joint structure, link proportions, contact geometry, surface properties, visual appearance, sensing, and timing. That matters because dexterous manipulation is much more than matching hand poses. A few millimeters of contact error or a different force relationship can completely change how a task is executed. In the collection evaluation, TwinDEX delivered up to 5.3 times the effective throughput of on-robot teleoperation. It’s a useful reminder that scaling robot learning may not only be about bigger models and more data. Sometimes the hardware collecting the data is part of the data problem itself.

Alamin

48,112 Aufrufe • vor 2 Monaten

Jensen Huang says agentic AI is not a chatbot. It is a "digital robot" -- and the next bottleneck is not the model. It is first-person data. "Agentic AI is just a digital robot. It understands, it reasons, it plans, and it acts and uses tools." Then he makes the bigger jump: "The world's video data is from a third person, not first person. And so agentic systems, robotic systems, physical AI -- the data is the hardest problem." That is the hidden constraint in robotics. LLMs got the internet. Physical AI needs demonstrations, synthetic worlds, reinforcement learning, and first-person experience. This is why Jensen keeps calling it a stack: robots are not waiting for one magical model. They need the data engine, the simulator, the reward system, the runtime, and the computer. The next wave of AI is not just software that talks. It is software that sees, plans, acts, and eventually moves through the world.

Jensen Huang says agentic AI is not a chatbot. It is a "digital robot" -- and the next bottleneck is not the model. It is first-person data. "Agentic AI is just a digital robot. It understands, it reasons, it plans, and it acts and uses tools." Then he makes the bigger jump: "The world's video data is from a third person, not first person. And so agentic systems, robotic systems, physical AI -- the data is the hardest problem." That is the hidden constraint in robotics. LLMs got the internet. Physical AI needs demonstrations, synthetic worlds, reinforcement learning, and first-person experience. This is why Jensen keeps calling it a stack: robots are not waiting for one magical model. They need the data engine, the simulator, the reward system, the runtime, and the computer. The next wave of AI is not just software that talks. It is software that sees, plans, acts, and eventually moves through the world.

Karl Mehta

14,140 Aufrufe • vor 4 Monaten

Jason Ma reveals the first true scaling law in robotics: robots trained on 1 million hours of first-person human video predictably get better without ever seeing robot data "Yesterday we announced our new flagship robot foundation model called Dyna-2. It's very significant for the entire field for many different reasons. First of all, it's the first robot foundation model trained on at least one million hours of data. That in itself is a very challenging infrastructure challenge." "What we demonstrated is that even if the one million hours of data is entirely first-person video of humans doing manipulation tasks, we actually see scaling law for transferring to robot embodiments that the model has never seen before." "By training on more human data, we actually see predictable performance improvement on robots. That's a big deal because the biggest challenge facing robot foundation models is that we don't have enough data." "Unlike language models, there are just not enough robotics data out there, and it's very difficult to collect these robot data. Only by passively observing humans doing things can we scale this kind of data, and this is the first time we showed there is a lot of improvement that can transfer." Jason Ma Dyna Robotics

Jason Ma reveals the first true scaling law in robotics: robots trained on 1 million hours of first-person human video predictably get better without ever seeing robot data "Yesterday we announced our new flagship robot foundation model called Dyna-2. It's very significant for the entire field for many different reasons. First of all, it's the first robot foundation model trained on at least one million hours of data. That in itself is a very challenging infrastructure challenge." "What we demonstrated is that even if the one million hours of data is entirely first-person video of humans doing manipulation tasks, we actually see scaling law for transferring to robot embodiments that the model has never seen before." "By training on more human data, we actually see predictable performance improvement on robots. That's a big deal because the biggest challenge facing robot foundation models is that we don't have enough data." "Unlike language models, there are just not enough robotics data out there, and it's very difficult to collect these robot data. Only by passively observing humans doing things can we scale this kind of data, and this is the first time we showed there is a lot of improvement that can transfer." Jason Ma Dyna Robotics

MTS

18,002 Aufrufe • vor 3 Monaten

When we started Score, the standard computer vision tools already existed. About a million people use them every day. Most of those people are still waiting on labels, running training jobs by hand, and watching models fail once they leave the test set. Most of those people are still waiting on labels, running training jobs by hand, and watching models fail once they leave the test set. Most of those people are also still waiting on verified computer vision models, evaluated against real life conditions and ready to be deployed for them to deliver value for their teams, clients or users. Score Studio is the full computer vision path in one place. A team describes the problem. The system can generate the missing scenes, label them, train the candidates, evaluate which ones actually hold, and deploy the winner. Data, labels, training, eval, ship. One loop. If no model exists for that job yet, they can put a bounty on the subnet. Anything from a small vision brick to a full VLM. Miners compete on the task. Only the winning work comes back. Same path for software agents. Any agent can call it. Built to be fully agent-accessible. Built for the people who already do this work: computer vision engineers and the small teams around them in plants, warehouses, farms, robotics, sport, and security. And for the agents those teams will run. That is the part that changes the job. Not another training screen. The stretch that used to take a lab and a calendar, footage, boxes, versions, failed runs, a separate deploy project, sits behind one starting point. And if the network needs a new model, that request is part of the same path. We spent more than a year building it. Then we had a choice. Keep it for us, or commoditize the whole subnet and make it available 24/7, in permissionless and open-source way. And we knew we couldn't keep it for us. It had to live on Bittensor. Open source software already showed how this should work. Infrastructure should not sit inside one company. Same idea as open AI before the phrase changed meaning: inspect it, fork it, keep building. That is what SN44 is for. Open vision intelligence, powered by Bittensor. Miners do the work. Studio is how that gets monetized. Profit does not stay in a company account. It goes back into the subnet through buyback and burn. We built the tool we wanted on day one. It will live on the network now, and for ever. Waitlist is open.

When we started Score, the standard computer vision tools already existed. About a million people use them every day. Most of those people are still waiting on labels, running training jobs by hand, and watching models fail once they leave the test set. Most of those people are still waiting on labels, running training jobs by hand, and watching models fail once they leave the test set. Most of those people are also still waiting on verified computer vision models, evaluated against real life conditions and ready to be deployed for them to deliver value for their teams, clients or users. Score Studio is the full computer vision path in one place. A team describes the problem. The system can generate the missing scenes, label them, train the candidates, evaluate which ones actually hold, and deploy the winner. Data, labels, training, eval, ship. One loop. If no model exists for that job yet, they can put a bounty on the subnet. Anything from a small vision brick to a full VLM. Miners compete on the task. Only the winning work comes back. Same path for software agents. Any agent can call it. Built to be fully agent-accessible. Built for the people who already do this work: computer vision engineers and the small teams around them in plants, warehouses, farms, robotics, sport, and security. And for the agents those teams will run. That is the part that changes the job. Not another training screen. The stretch that used to take a lab and a calendar, footage, boxes, versions, failed runs, a separate deploy project, sits behind one starting point. And if the network needs a new model, that request is part of the same path. We spent more than a year building it. Then we had a choice. Keep it for us, or commoditize the whole subnet and make it available 24/7, in permissionless and open-source way. And we knew we couldn't keep it for us. It had to live on Bittensor. Open source software already showed how this should work. Infrastructure should not sit inside one company. Same idea as open AI before the phrase changed meaning: inspect it, fork it, keep building. That is what SN44 is for. Open vision intelligence, powered by Bittensor. Miners do the work. Studio is how that gets monetized. Profit does not stay in a company account. It goes back into the subnet through buyback and burn. We built the tool we wanted on day one. It will live on the network now, and for ever. Waitlist is open.

Score

11,292 Aufrufe • vor 2 Monaten

one of the biggest hurdles in computer vision is that the front end actually matters. you can’t just build models and call it a product. that’s why we’re building Manako. we see it as a “control plane” for visual intelligence. where data, policies, and operators meet. where vision stops being research and starts having real impact in the physical world. this is built for people running real systems. operators who can do 1,000x more when vision is packaged as a real ai product from a dev perspective, we’re already 2 months ahead of plan. now the focus is polish, usability, and connecting it directly into the subnet. build with vision.

one of the biggest hurdles in computer vision is that the front end actually matters. you can’t just build models and call it a product. that’s why we’re building Manako. we see it as a “control plane” for visual intelligence. where data, policies, and operators meet. where vision stops being research and starts having real impact in the physical world. this is built for people running real systems. operators who can do 1,000x more when vision is packaged as a real ai product from a dev perspective, we’re already 2 months ahead of plan. now the focus is polish, usability, and connecting it directly into the subnet. build with vision.

Max

10,537 Aufrufe • vor 9 Monaten

We’re excited to welcome Animesh Garg as our new Chief Research Officer at microagi, with the team from Usable Robots joining him. He has spent most of his career working on one of the hardest problems in robotics: getting robots out of the lab and into the real world. Frontier AI now works. Hardware is becoming cheap. And the industry is finally learning how to collect robot data at scale. What’s still missing is post-training. Taking a general-purpose model and teaching it one specific job, in one specific environment, until a company can actually depend on it. In LLMs, post-training is what turned impressive demos into products. In robotics, that layer barely exists yet. A strong model is a capability. A robot that can perform the same job, on the same line, every shift, without an engineer standing next to it, is a product. And that process has to happen again for every task, every site, and every customer. We believe the company that can do this well, fast, and at scale will be the company that puts robots into production at massive scale. MicroAGI is building both sides of that system. With shift, we’re building one of the most diverse and largest egocentric datasets in the world. With Atlas, we post-train and harness models directly on enterprise deployments. Our goal is simple: Deploy 1 million robots.

We’re excited to welcome Animesh Garg as our new Chief Research Officer at microagi, with the team from Usable Robots joining him. He has spent most of his career working on one of the hardest problems in robotics: getting robots out of the lab and into the real world. Frontier AI now works. Hardware is becoming cheap. And the industry is finally learning how to collect robot data at scale. What’s still missing is post-training. Taking a general-purpose model and teaching it one specific job, in one specific environment, until a company can actually depend on it. In LLMs, post-training is what turned impressive demos into products. In robotics, that layer barely exists yet. A strong model is a capability. A robot that can perform the same job, on the same line, every shift, without an engineer standing next to it, is a product. And that process has to happen again for every task, every site, and every customer. We believe the company that can do this well, fast, and at scale will be the company that puts robots into production at massive scale. MicroAGI is building both sides of that system. With shift, we’re building one of the most diverse and largest egocentric datasets in the world. With Atlas, we post-train and harness models directly on enterprise deployments. Our goal is simple: Deploy 1 million robots.

microagi

77,563 Aufrufe • vor 1 Monat

Anthropic's graphics team automated Blender so one request builds a structure, and most of the run finishes before a vertex exists. The geometry was never the hard half. Deciding what counts as one object is where the time actually goes. > PLAN - what the structure depends on, ordered > SPLIT - where one object ends and the next starts > BUILD - geometry emitted against a finished plan A structure that arrives as one fused mesh is finished the moment it lands, because nothing in it can move. Split it wrong and it is worse. A door welded into its frame looks correct until somebody tries to open it. So the run spends its first minutes on hierarchy, and the modelling that follows is close to mechanical. That is why a single request holds at the scale of a building instead of a prop or one isolated room. What lands in the viewport is a tree of named parts, each one editable without disturbing anything else. The request and the tree it produced sit in the article below.

Anthropic's graphics team automated Blender so one request builds a structure, and most of the run finishes before a vertex exists. The geometry was never the hard half. Deciding what counts as one object is where the time actually goes. > PLAN - what the structure depends on, ordered > SPLIT - where one object ends and the next starts > BUILD - geometry emitted against a finished plan A structure that arrives as one fused mesh is finished the moment it lands, because nothing in it can move. Split it wrong and it is worse. A door welded into its frame looks correct until somebody tries to open it. So the run spends its first minutes on hierarchy, and the modelling that follows is close to mechanical. That is why a single request holds at the scale of a building instead of a prop or one isolated room. What lands in the viewport is a tree of named parts, each one editable without disturbing anything else. The request and the tree it produced sit in the article below.

wast3

17,714 Aufrufe • vor 3 Tagen

Can United States manufacture robots? Matic Robots says "yes." It makes the best floor cleaning robot, that has won many perfect scores from Wired to many others. We love ours. But my trip there to get a tour from AI pioneer Navneet Dalal Navneet Dalal provided some real insights into how hard it is for a hardware company to make hardware in the United States. And how deeply AI is changing consumer electronics products that are going to be in many more homes soon. In this first part (Part II coming tomorrow) we get a look at how long it took for this company to go through prototypes to a shipping product. In the second part, you'll see the scaling hell that it takes to even ship a few thousand robots and the kinds of problems that scaling up a factory brings. Matic is one of my favorite small Silicon Valley companies. It has found what we call "product market fit." I just came back from CES where I saw many of its competitors, and the Matic wins because of not just the product thinking of Mehul and Navneet Dalal but because of their AI leadership. In a way their robot took many lessons from Tesla, from where to put the batteries to its bet on computer vision, which Navneet has been a pioneer in for years, working quietly behind the scenes. It is about to move into a new location that will allow it to grow to meet the demand that now is showing up (the boxes in its lobby show that it's outgrowing its current facilities). In terms of AI, it has aspirations of making a humanoid too, but it is taking a far more measured approach to getting there. By starting on the floor it can not just build world models based on real world data (customers are given a choice whether to allow its data to be used that way. Most customers choose to keep their data on the robot only, for privacy reasons, but if you opt in you can help them improve their models). They are using that data to understand homes. Navneet told me they hit very unusual situations in people's homes already that they couldn't really predict in simulators, like full-wall mirrors that confuse computer vision systems, or pools and water features in people's homes. Having real customers brings a ton of customer feedback about how to further improve the robot, and, as Navneet demonstrates in the second video, forces them to build a manufacturing muscle memory. Getting teams to work together, figuring out how to solve supply chain problems, from Trump's tarriffs, to a new one that showed up over the past couple of weeks. A supplier for its bags (one of the cheaper parts that goes into the robot) changed the glue it used, which caused robots to fail quality tests and the manufacturing line to stop. Reminds me a lot of the hell Elon Musk faced in its Fremont factory when Tesla was first starting to manufacture its Model 3, which almost bankrupted the company. Off the record Mehul and Navneet 🇮🇳 showed me some of the prototypes and plans for its next products that will show up over the next few years. Certainly not as sexy as Tesla, Figure, 1x_tech, and all the Chinese manufacturers are showing off already, but far better thought out for the typical Western home and AI plays a huge role in its future. It is the product that speaks for itself. It's amazing, and is about to get better this year due to AI. It's the first real vision-only robot to be in my home and I bet it won't be the last from this company. Real honor that they invited me over with my Insta360 camera (another company launched in my home, just like Matic was last year). In Part II we go into the factory.

Can United States manufacture robots? Matic Robots says "yes." It makes the best floor cleaning robot, that has won many perfect scores from Wired to many others. We love ours. But my trip there to get a tour from AI pioneer Navneet Dalal Navneet Dalal provided some real insights into how hard it is for a hardware company to make hardware in the United States. And how deeply AI is changing consumer electronics products that are going to be in many more homes soon. In this first part (Part II coming tomorrow) we get a look at how long it took for this company to go through prototypes to a shipping product. In the second part, you'll see the scaling hell that it takes to even ship a few thousand robots and the kinds of problems that scaling up a factory brings. Matic is one of my favorite small Silicon Valley companies. It has found what we call "product market fit." I just came back from CES where I saw many of its competitors, and the Matic wins because of not just the product thinking of Mehul and Navneet Dalal but because of their AI leadership. In a way their robot took many lessons from Tesla, from where to put the batteries to its bet on computer vision, which Navneet has been a pioneer in for years, working quietly behind the scenes. It is about to move into a new location that will allow it to grow to meet the demand that now is showing up (the boxes in its lobby show that it's outgrowing its current facilities). In terms of AI, it has aspirations of making a humanoid too, but it is taking a far more measured approach to getting there. By starting on the floor it can not just build world models based on real world data (customers are given a choice whether to allow its data to be used that way. Most customers choose to keep their data on the robot only, for privacy reasons, but if you opt in you can help them improve their models). They are using that data to understand homes. Navneet told me they hit very unusual situations in people's homes already that they couldn't really predict in simulators, like full-wall mirrors that confuse computer vision systems, or pools and water features in people's homes. Having real customers brings a ton of customer feedback about how to further improve the robot, and, as Navneet demonstrates in the second video, forces them to build a manufacturing muscle memory. Getting teams to work together, figuring out how to solve supply chain problems, from Trump's tarriffs, to a new one that showed up over the past couple of weeks. A supplier for its bags (one of the cheaper parts that goes into the robot) changed the glue it used, which caused robots to fail quality tests and the manufacturing line to stop. Reminds me a lot of the hell Elon Musk faced in its Fremont factory when Tesla was first starting to manufacture its Model 3, which almost bankrupted the company. Off the record Mehul and Navneet 🇮🇳 showed me some of the prototypes and plans for its next products that will show up over the next few years. Certainly not as sexy as Tesla, Figure, 1x_tech, and all the Chinese manufacturers are showing off already, but far better thought out for the typical Western home and AI plays a huge role in its future. It is the product that speaks for itself. It's amazing, and is about to get better this year due to AI. It's the first real vision-only robot to be in my home and I bet it won't be the last from this company. Real honor that they invited me over with my Insta360 camera (another company launched in my home, just like Matic was last year). In Part II we go into the factory.

Robert Scoble

69,229 Aufrufe • vor 9 Monaten

THIS LOOKS LIKE A MARATHON. IT IS ACTUALLY A COST PROBLEM. The humanoid approaches a painted spot on the track and stops. Three people in vests close in. One sprays the joints. One slams a fresh pack against the back. One lifts a metal flask and pours coolant while the machine just stands there. Then they step off the lane and the robot starts running again. That 40-second stop is the whole industry in one scene. The legs already work. Balance already works. The public already films it. What still does not work is the part companies actually pay for: runtime. swap time. heat. maintenance. how many humans it takes to keep one body moving. A factory does not buy a cool runner. A factory buys hours without a crew. Right now this machine still needs a pit team. That means the unit price is only half the number. The other half is people kneeling on the track with a flask and a battery. The first company that turns this stop into 20 seconds and one technician does not just win a race. It turns a demo into a product. Until then a humanoid is still a race car. Fast on camera. Expensive the moment it has to keep going.

THIS LOOKS LIKE A MARATHON. IT IS ACTUALLY A COST PROBLEM. The humanoid approaches a painted spot on the track and stops. Three people in vests close in. One sprays the joints. One slams a fresh pack against the back. One lifts a metal flask and pours coolant while the machine just stands there. Then they step off the lane and the robot starts running again. That 40-second stop is the whole industry in one scene. The legs already work. Balance already works. The public already films it. What still does not work is the part companies actually pay for: runtime. swap time. heat. maintenance. how many humans it takes to keep one body moving. A factory does not buy a cool runner. A factory buys hours without a crew. Right now this machine still needs a pit team. That means the unit price is only half the number. The other half is people kneeling on the track with a flask and a battery. The first company that turns this stop into 20 seconds and one technician does not just win a race. It turns a demo into a product. Until then a humanoid is still a race car. Fast on camera. Expensive the moment it has to keep going.

P1eSenb

40,235 Aufrufe • vor 1 Monat

every question in this clip is an ownership question, especially data because when everyone has access to the same intelligence, the only input that separates your business from the next one is the data you own your data is decades of decisions, customers, mistakes, and edge cases that exist nowhere else on earth that is the moat and enterprises are waking up to the fact that they've been leaking it one api call at a time my prediction is this: data ownership is going to absolutely matter in the world we're going into and whoever's building the infrastructure for it is going to have a very good decade.

every question in this clip is an ownership question, especially data because when everyone has access to the same intelligence, the only input that separates your business from the next one is the data you own your data is decades of decisions, customers, mistakes, and edge cases that exist nowhere else on earth that is the moat and enterprises are waking up to the fact that they've been leaking it one api call at a time my prediction is this: data ownership is going to absolutely matter in the world we're going into and whoever's building the infrastructure for it is going to have a very good decade.

Adeniyi.sui

13,834 Aufrufe • vor 4 Monaten

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 Aufrufe • vor 9 Monaten

Robotics and CV! 👓 Computer vision gives the robots a sense of vision and additional intelligence. Pralines are packed by a delta robot using computer vision. Packing chocolate pralines into a box with the delta robot. Unlike most robots, this one has a fixed TCP, and the base moves in response to vision data. To adjust the base, the vision system determines exactly where the praline is located on the conveyor belt. 🍫 Using this application, the system knows where each praline should be placed based on its orientation. A true engineering showcase!

Robotics and CV! 👓 Computer vision gives the robots a sense of vision and additional intelligence. Pralines are packed by a delta robot using computer vision. Packing chocolate pralines into a box with the delta robot. Unlike most robots, this one has a fixed TCP, and the base moves in response to vision data. To adjust the base, the vision system determines exactly where the praline is located on the conveyor belt. 🍫 Using this application, the system knows where each praline should be placed based on its orientation. A true engineering showcase!

Lukas Ziegler

79,438 Aufrufe • vor 1 Jahr

Picking up laundry with a 3D printed robot arm and LeRobot. It operates using SO-ARM101 arm mounted on a mobile base, relying on just a wrist and base camera. The base is controlled with an Xbox controller by a human operator. The arm is fully autonomous thanks to the ACT model. The robot can generalize to previously unseen environments. The technical stack: - Model: Action Chunking Transformer (ACT) with Temporal Ensemble - Data: Learned via teleoperation including negative examples and failure recoveries - Framework: Built and trained locally using LeRobot on a single consumer GPU in 3.5h This is a perfect example that real-world robotics isn't about perfect lab conditions - it's about messy living rooms, confusing shadows, and learning to recover from mistakes. And with open tools, anyone can tackle these edge cases right from their desk.

Picking up laundry with a 3D printed robot arm and LeRobot. It operates using SO-ARM101 arm mounted on a mobile base, relying on just a wrist and base camera. The base is controlled with an Xbox controller by a human operator. The arm is fully autonomous thanks to the ACT model. The robot can generalize to previously unseen environments. The technical stack: - Model: Action Chunking Transformer (ACT) with Temporal Ensemble - Data: Learned via teleoperation including negative examples and failure recoveries - Framework: Built and trained locally using LeRobot on a single consumer GPU in 3.5h This is a perfect example that real-world robotics isn't about perfect lab conditions - it's about messy living rooms, confusing shadows, and learning to recover from mistakes. And with open tools, anyone can tackle these edge cases right from their desk.

LeRobot

69,293 Aufrufe • vor 3 Monaten

On The Information's TITV talking about where open weights actually land inside a big company Nobody serious is picking one model. They'll ride the frontier of intelligence(rent) and most will train OSS models(own) on their own data for the work nobody else can do. For many critical end to end agentification the expertise is in your people and your systems, not on the internet.

On The Information's TITV talking about where open weights actually land inside a big company Nobody serious is picking one model. They'll ride the frontier of intelligence(rent) and most will train OSS models(own) on their own data for the work nobody else can do. For many critical end to end agentification the expertise is in your people and your systems, not on the internet.

Garrett Lord

90,767 Aufrufe • vor 1 Monat

"We (Democrats) have to provide a vision, and the vision is of a functional democracy. The vision is of a government that is not corrupt. The vision is of a government that is actually focused on solutions for people."

"We (Democrats) have to provide a vision, and the vision is of a functional democracy. The vision is of a government that is not corrupt. The vision is of a government that is actually focused on solutions for people."

George Conway ⚖️🇺🇸

41,301 Aufrufe • vor 6 Monaten

A one-man trading hedge fund now costs about $100 a month in AI subscriptions. Five PhDs on a Citadel desk cost $270,000 a month, and that is the cheap end. That buys one tested idea a month. Man Group's AI writes hundreds of new signals a week, on a floor where the humans used to manage twenty in a quarter. Fifty AI agents do the reading and the writing. One of them exists only to destroy what the others build, and that one is the reason any of it works. Every job on that payroll is now an agent you can run yourself: > AI research agents reading filings, transcripts, options flow and on-chain data overnight, fifty personas at once, none of them allowed to see what the crowd is pricing > coding agent that turns one sentence of plain English into entry rules, exit rules, sizing and risk limits, then debugs itself until it runs > backtest agent that replays five years of that idea in about 12 seconds > breaker agent, an AI whose only job is killing the thing, at double the trading costs and in the ten worst markets that asset has ever seen > critic agent that reads your journal and names the mistake you keep making Nobody on that list asks for a bonus in January. $200 million is already run this way on one platform where 52,000 people mostly sit and watch the machine work. The full map of what is built and what is missing is in the article below. Bookmark & read it If you're not yet using AI in your trading and investing.

A one-man trading hedge fund now costs about $100 a month in AI subscriptions. Five PhDs on a Citadel desk cost $270,000 a month, and that is the cheap end. That buys one tested idea a month. Man Group's AI writes hundreds of new signals a week, on a floor where the humans used to manage twenty in a quarter. Fifty AI agents do the reading and the writing. One of them exists only to destroy what the others build, and that one is the reason any of it works. Every job on that payroll is now an agent you can run yourself: > AI research agents reading filings, transcripts, options flow and on-chain data overnight, fifty personas at once, none of them allowed to see what the crowd is pricing > coding agent that turns one sentence of plain English into entry rules, exit rules, sizing and risk limits, then debugs itself until it runs > backtest agent that replays five years of that idea in about 12 seconds > breaker agent, an AI whose only job is killing the thing, at double the trading costs and in the ten worst markets that asset has ever seen > critic agent that reads your journal and names the mistake you keep making Nobody on that list asks for a bonus in January. $200 million is already run this way on one platform where 52,000 people mostly sit and watch the machine work. The full map of what is built and what is missing is in the article below. Bookmark & read it If you're not yet using AI in your trading and investing.

cvxv666

173,490 Aufrufe • vor 3 Monaten

Aravind Srinivas just described a future most founders are pretending they are ready for. One person. One machine. A company that runs itself. Srinivas: “Buy a Mac mini, set up a Perplexity personal computer, and run their business on that.” Not a side project. Not a pitch deck. A real business with real revenue while the founder is not in the building. AI runs the ads. Handles SEO. Integrates Stripe. Ships features. Answers customers. All of it executing without a single employee. Srinivas: “Have this all working while you can be sipping wine in Napa.” But before he sold the dream he killed the one most people are already chasing. Srinivas: “Everybody talks about this one-person one-billion-dollar company. It’s not truly moving the GDP by one billion. It’s not truly creating new value.” One researcher collecting a billion in equity does not grow an economy. It rearranges numbers between balance sheets. Nothing gets built. No customer gets served. That is not value creation. That is valuation creation. Srinivas wants no part of it. What he described is the opposite. The person driving Uber between shifts who has the idea but not the payroll. Not the engineering. Not the marketing. Not the support staff. That person gets a machine that replaces all of it. Hundreds of thousands in revenue. Millions. Generated by autonomous systems doing the work that used to require ten employees and a burn rate. Not paper wealth. Not valuation theater. Output that moves through an economy and touches real customers. That is what moves GDP. Not one person worth a billion dollars. A million people each building something worth a million. That math rewrites a country. Then Srinivas said the part that separates him from every hype merchant in the room. Srinivas: “Everybody thinks AI is already there. It’s not there yet. Someone has to do that hard work.” The vision is real. The infrastructure is not. The agents are not autonomous. The integrations are not seamless. The plumbing is not finished. Someone has to wire the APIs. Connect the billing. Build the bridge between what a founder wants and what a machine can deliver. That work is not a keynote. It is not a tweet thread. It is engineering that nobody wants to do and everybody will depend on. Whoever finishes it first does not just build a product. They hand every ambitious person on Earth a company they can run alone. The corporations that need five hundred people to do what one founder with the right infrastructure could do are not efficient. They are exposed. And the person building the thing that exposes them just told you exactly what it looks like. He also told you it is not going to build itself.

Aravind Srinivas just described a future most founders are pretending they are ready for. One person. One machine. A company that runs itself. Srinivas: “Buy a Mac mini, set up a Perplexity personal computer, and run their business on that.” Not a side project. Not a pitch deck. A real business with real revenue while the founder is not in the building. AI runs the ads. Handles SEO. Integrates Stripe. Ships features. Answers customers. All of it executing without a single employee. Srinivas: “Have this all working while you can be sipping wine in Napa.” But before he sold the dream he killed the one most people are already chasing. Srinivas: “Everybody talks about this one-person one-billion-dollar company. It’s not truly moving the GDP by one billion. It’s not truly creating new value.” One researcher collecting a billion in equity does not grow an economy. It rearranges numbers between balance sheets. Nothing gets built. No customer gets served. That is not value creation. That is valuation creation. Srinivas wants no part of it. What he described is the opposite. The person driving Uber between shifts who has the idea but not the payroll. Not the engineering. Not the marketing. Not the support staff. That person gets a machine that replaces all of it. Hundreds of thousands in revenue. Millions. Generated by autonomous systems doing the work that used to require ten employees and a burn rate. Not paper wealth. Not valuation theater. Output that moves through an economy and touches real customers. That is what moves GDP. Not one person worth a billion dollars. A million people each building something worth a million. That math rewrites a country. Then Srinivas said the part that separates him from every hype merchant in the room. Srinivas: “Everybody thinks AI is already there. It’s not there yet. Someone has to do that hard work.” The vision is real. The infrastructure is not. The agents are not autonomous. The integrations are not seamless. The plumbing is not finished. Someone has to wire the APIs. Connect the billing. Build the bridge between what a founder wants and what a machine can deliver. That work is not a keynote. It is not a tweet thread. It is engineering that nobody wants to do and everybody will depend on. Whoever finishes it first does not just build a product. They hand every ambitious person on Earth a company they can run alone. The corporations that need five hundred people to do what one founder with the right infrastructure could do are not efficient. They are exposed. And the person building the thing that exposes them just told you exactly what it looks like. He also told you it is not going to build itself.

Dustin

64,593 Aufrufe • vor 7 Monaten

Want to create an avatar from a single image? FlexAvatar is a transformer model that creates full 360°, high-quality, and expressive 3D head avatar from just a single portrait image in minutes. Real-time Demo: FlexAvatar's lightweight architecture allows both animation and rendering in real-time, enabling interactive user experiences. To create a new 3D head avatar, only one image is required, e.g., from a webcam. The final avatar is ready after 2 minutes. Architecture: Under the hood, FlexAvatar adopts a transformer-based encoder-decoder design. The encoder maps the input image onto a latent avatar space, while the decoder produces 3D Gaussian attribute maps by incorporating the animation signal via cross-attention. The model learns all facial animations directly from the data without relying on pre-built 3D face models. This equips the avatars with realistic facial expressions. The internal avatar latent space can be conveniently used to integrate additional observations of a person via fitting. This enables use-cases where more than one image of a person is available, e.g., from a phone scan of the person. We train jointly on 2D monocular videos and multi-view data. However, in monocular videos, the animation signal leaks the target viewpoint, causing the model to produce incomplete 3D heads. We call this phenomenon entanglement of driving signal and target viewpoint. To prevent entanglement, we introduce bias sinks. These are learnable tokens that indicate whether a training sample stems from a monocular or a multi-view dataset. During training, the model learns to produce incomplete 3D heads only when the monocular token is present. During inference, FlexAvatar then always uses the multi-view token for which the model has learned to produce complete 3D heads. This simple design allows to combine the generalizability from monocular data with the quality of multi-view data. FlexAvatar summary: - Input: Single-image, phone scan, or monocular video - Output: Full 360° head avatar - Expressive animations - Real-time rendering and animation - Generalization to any portrait - Create a new avatar in 2 minutes - Use bias sinks to combine 2D and 3D data 🏠 🌍 🎥 Great work by Tobias Kirschstein and Simon Giebenhain!

Matthias Niessner

96,371 Aufrufe • vor 10 Monaten