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.

Teaching a robot a new task has traditionally meant collecting data, training models and repeating the process until it works. PokeBot wants to make that much simpler. Its new RoboAPI lets developers give robots instructions in everyday language and try Poke-Aurora on supported hardware, without having to train a... show more

Science girl

5,725,247 subscribers

18,669 Aufrufe • vor 3 Tagen •via X (Twitter)

Wissenschaft & Technologie

Anya Rossi• Live Now

Private livecam show

7 Kommentare

Profilbild von Nothing Boss

Nothing Bossvor 3 Tagen

Wow great innovation

Profilbild von Tsuki

Tsukivor 3 Tagen

Natural language control of robots is the future.

Profilbild von Science girl

Science girlvor 3 Tagen

Try it here 👇 API docs:

Profilbild von RIINSHAAN

RIINSHAANvor 3 Tagen

Making robots easier to program could bring amazing new ideas, right?

Profilbild von PokeBot

PokeBotvor 3 Tagen

Making intelligence accessible is one part of the equation. Bringing it into capable physical robots is another. We’re excited about building both sides of that future.

Profilbild von 🦋匕工êれ丹れムモㄥ🦋

🦋匕工êれ丹れムモㄥ🦋vor 3 Tagen

If this actually eliminates training from scratch, it completely changes the hardware bottleneck. Huge step for open-source devs. Who else thinks this accelerates the humanoid timeline by a couple of years?

Profilbild von MING-女儿奴产品经理

MING-女儿奴产品经理vor 3 Tagen

Language instruction only works if the robot already has the primitives. New tasks still need someone to define them.

Ähnliche Videos

We took a robot to RSS in LA running our new Gemini Robotics On-Device VLA model. People interacted with the model with new objects and instructions in a brand new environment and the results were amazing!

Ayzaan Wahid

19,710 Aufrufe • vor 1 Jahr

We got a robot to clean up homes that were never seen in its training data! Our new model, π-0.5, aims to tackle open-world generalization. We took our robot into homes that were not in the training data and asked it to clean kitchens and bedrooms. More below⤵️

We got a robot to clean up homes that were never seen in its training data! Our new model, π-0.5, aims to tackle open-world generalization. We took our robot into homes that were not in the training data and asked it to clean kitchens and bedrooms. More below⤵️

Physical Intelligence

553,178 Aufrufe • vor 1 Jahr

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

76,913 Aufrufe • vor 1 Monat

Austin-based robotics startup Apptronik has unveiled Apollo 2, the latest version of its humanoid robot. Apollo 2 comes in both bipedal and wheeled versions and performs real-world tasks while collecting training data. Apptronik is using this data with Google DeepMind to train Gemini Robotics AI models, making Apollo smarter and more capable.

Austin-based robotics startup Apptronik has unveiled Apollo 2, the latest version of its humanoid robot. Apollo 2 comes in both bipedal and wheeled versions and performs real-world tasks while collecting training data. Apptronik is using this data with Google DeepMind to train Gemini Robotics AI models, making Apollo smarter and more capable.

Space and Technology

11,540 Aufrufe • vor 3 Monaten

Working with robots has always been harder than it should be. The intelligence was hard to access. The hardware was hard to afford. Today, both change. MakerMods Robotics Maker Arm + Metal Arm, powered by Dream Labs 's Dream-1. Give your robot a task in plain language, right from your browser. Try it:

Working with robots has always been harder than it should be. The intelligence was hard to access. The hardware was hard to afford. Today, both change. MakerMods Robotics Maker Arm + Metal Arm, powered by Dream Labs 's Dream-1. Give your robot a task in plain language, right from your browser. Try it:

Isaac Sin

27,307 Aufrufe • vor 14 Tagen

Open science is how we continue to push technology forward and today at Meta FAIR we’re sharing eight new AI research artifacts including new models, datasets and code to inspire innovation in the community. More in the video from @jpineau1. This work is another important step towards our goal of achieving Advanced Machine Intelligence (AMI). What we’re releasing: • Meta Spirit LM: An open source language model for seamless speech and text integration. • Meta Segment Anything Model 2.1: An updated checkpoint with improved results on visually similar objects, small objects and occlusion handling. Plus a new developer suite to make it easier for developers to build with SAM 2. • Layer Skip: Inference code and fine-tuned checkpoints demonstrating a new method for enhancing LLM performance. • SALSA: New code to enable researchers to benchmark AI-based attacks in support of validating security for post-quantum cryptography. • Meta Lingua: A lightweight and self-contained codebase designed to train language models at scale. • Meta Open Materials: New open source models and the largest dataset of its kind to accelerate AI-driven discovery of new inorganic materials. • MEXMA: A new research paper and code for our novel pre-trained cross-lingual sentence encoder with coverage across 80 languages. • Self-Taught Evaluator: a new method for generating synthetic preference data to train reward models without relying on human annotations. Access to state-of-the-art AI creates opportunities for everyone. We’re excited to share this work and look forward to seeing the community innovation that results from it. Details and access to everything released by FAIR today ➡️

Open science is how we continue to push technology forward and today at Meta FAIR we’re sharing eight new AI research artifacts including new models, datasets and code to inspire innovation in the community. More in the video from @jpineau1. This work is another important step towards our goal of achieving Advanced Machine Intelligence (AMI). What we’re releasing: • Meta Spirit LM: An open source language model for seamless speech and text integration. • Meta Segment Anything Model 2.1: An updated checkpoint with improved results on visually similar objects, small objects and occlusion handling. Plus a new developer suite to make it easier for developers to build with SAM 2. • Layer Skip: Inference code and fine-tuned checkpoints demonstrating a new method for enhancing LLM performance. • SALSA: New code to enable researchers to benchmark AI-based attacks in support of validating security for post-quantum cryptography. • Meta Lingua: A lightweight and self-contained codebase designed to train language models at scale. • Meta Open Materials: New open source models and the largest dataset of its kind to accelerate AI-driven discovery of new inorganic materials. • MEXMA: A new research paper and code for our novel pre-trained cross-lingual sentence encoder with coverage across 80 languages. • Self-Taught Evaluator: a new method for generating synthetic preference data to train reward models without relying on human annotations. Access to state-of-the-art AI creates opportunities for everyone. We’re excited to share this work and look forward to seeing the community innovation that results from it. Details and access to everything released by FAIR today ➡️

AI at Meta

150,632 Aufrufe • vor 2 Jahren

Today, we announced 𝗥𝗧-𝟮: a first of its kind vision-language-action model to control robots. 🤖 It learns from both web and robotics data and translates this knowledge into generalised instructions. Find out more:

Today, we announced 𝗥𝗧-𝟮: a first of its kind vision-language-action model to control robots. 🤖 It learns from both web and robotics data and translates this knowledge into generalised instructions. Find out more:

Google DeepMind

537,940 Aufrufe • vor 3 Jahren

The robot flipped a pancake nobody taught it! 🥞 Skild AI team assumed pancake flipping had to be somewhere in the training data. So they searched. Millions of hours of pre-training data. Nothing. S1 inferred the whole task from a single human demonstration. That's their new general robot model, built as an in-context learner from the ground up. Every new robot task today starts with days of teleoperation and a fine-tuning run on a specialist policy. S1 skips all of it. Much like a language model, it never updates its weights to learn a new task. The demonstration enters the context window, and the policy uses it to decide what to do next. → Ten-minute tasks it was never trained on, composed from primitives learned in pre-training: a new style of coffee, potting a plant, frying pancakes. → Soil and pots arrived at their office at 8:54 PM. The robot was running the task autonomously by 9:27 PM. → Slide objects away mid-reach, swap them, change the lighting, it still finishes. → The prompt waters a plant with a watering can, but only a cup is available. It uses the cup. It doesn't rigidly replay what it saw, but it recovers from its own errors, and sometimes executes with more precision than the demonstrator, when the human fumbles an egg and makes a mess, S1 performs the same step cleanly. The demonstration is a specification of the goal, and not a trajectory to copy. On unseen tasks after 100K hours of pre-training: language-prompted VLAs reach 9%. Their new model reaches 66%. It's already deploying with industrial partners, with a wider rollout over the coming months. Congrats Deepak Pathak and team behind this! 😮‍💨 🔗 Link to their latest blog: ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →

The robot flipped a pancake nobody taught it! 🥞 Skild AI team assumed pancake flipping had to be somewhere in the training data. So they searched. Millions of hours of pre-training data. Nothing. S1 inferred the whole task from a single human demonstration. That's their new general robot model, built as an in-context learner from the ground up. Every new robot task today starts with days of teleoperation and a fine-tuning run on a specialist policy. S1 skips all of it. Much like a language model, it never updates its weights to learn a new task. The demonstration enters the context window, and the policy uses it to decide what to do next. → Ten-minute tasks it was never trained on, composed from primitives learned in pre-training: a new style of coffee, potting a plant, frying pancakes. → Soil and pots arrived at their office at 8:54 PM. The robot was running the task autonomously by 9:27 PM. → Slide objects away mid-reach, swap them, change the lighting, it still finishes. → The prompt waters a plant with a watering can, but only a cup is available. It uses the cup. It doesn't rigidly replay what it saw, but it recovers from its own errors, and sometimes executes with more precision than the demonstrator, when the human fumbles an egg and makes a mess, S1 performs the same step cleanly. The demonstration is a specification of the goal, and not a trajectory to copy. On unseen tasks after 100K hours of pre-training: language-prompted VLAs reach 9%. Their new model reaches 66%. It's already deploying with industrial partners, with a wider rollout over the coming months. Congrats Deepak Pathak and team behind this! 😮‍💨 🔗 Link to their latest blog: ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →

Lukas Ziegler

11,406 Aufrufe • vor 2 Monaten

🤖What if a robot could perform a new task just from a natural language command, with zero demonstrations? Our new work, NovaFlow, makes it possible! We use pre-trained video generative model to create a video of the task, then translate it into a plan for real-world robot execution. 1/6 #Robotics #AI #ZeroShot #Manipulation

🤖What if a robot could perform a new task just from a natural language command, with zero demonstrations? Our new work, NovaFlow, makes it possible! We use pre-trained video generative model to create a video of the task, then translate it into a plan for real-world robot execution. 1/6 #Robotics #AI #ZeroShot #Manipulation

Hongyu Li

106,422 Aufrufe • vor 1 Jahr

Collecting robot data at scale is key to deploying working manipulation policies, and the team from Tutor Intelligence Tutor is here to tell us about how to accomplish it. Their new announcement: a massive, 100-robot “data factory,” with a behind-the-scenes look at how to build a teleoperation platform and how to make robots and policies that are useful for their customers. Tutor Intelligence is a full-stack robotics company: they build robot arms, they sell robot arms, they write the software and they train neural networks. Josh Gruenstein, Jesse Michel, Shiraz, and Joe McCalmon, and Joe McCalmon join us to tell us more about how they scale both teleop data and human interventions from their teleoperators in order to train the policies they need. Watch Episode #85 of RoboPapers, with Chris Paxton and Jiafei Duan, to learn more!

Collecting robot data at scale is key to deploying working manipulation policies, and the team from Tutor Intelligence Tutor is here to tell us about how to accomplish it. Their new announcement: a massive, 100-robot “data factory,” with a behind-the-scenes look at how to build a teleoperation platform and how to make robots and policies that are useful for their customers. Tutor Intelligence is a full-stack robotics company: they build robot arms, they sell robot arms, they write the software and they train neural networks. Josh Gruenstein, Jesse Michel, Shiraz, and Joe McCalmon, and Joe McCalmon join us to tell us more about how they scale both teleop data and human interventions from their teleoperators in order to train the policies they need. Watch Episode #85 of RoboPapers, with Chris Paxton and Jiafei Duan, to learn more!

RoboPapers

36,041 Aufrufe • vor 5 Monaten

Excited to announce GR00T N1, the world’s first open foundation model for humanoid robots! We are on a mission to democratize Physical AI. The power of general robot brain, in the palm of your hand - with only 2B parameters, N1 learns from the most diverse physical action dataset ever compiled and punches above its weight: - Real humanoid teleoperation data. - Large-scale simulation data: we are open-sourcing 300K+ trajectories! - Neural trajectories: we apply SOTA video generation models to “hallucinate” new synthetic data that features accurate physics in pixels. Using Jensen’s words, “systematically infinite data”! - Latent actions: we develop novel algorithms to extract action tokens from in-the-wild human videos and neural generated videos. GR00T N1 is a single end-to-end neural net, from photons to actions: - Vision-Language Model (System 2) that interprets the physical world through vision and language instructions, enabling robots to reason about their environment and instructions, and plan the right actions. - Diffusion Transformer (System 1) that “renders” smooth and precise motor actions at 120 Hz, executing the latent plan made by System 2. We deploy N1 on GR1 robot, 1X Neo robot, and a large collection of simulation benchmarks. N1 achieves up to +30% boost in diverse manipulation tasks for household and industrial settings. While humanoid robots are the main focus of N1, our model also supports cross-embodiment. We finetune it to work on the $110 HuggingFace LeRobot SO100 robot arm! Open robot brain runs on open hardware. Sounds just right. Let’s solve robotics, together, one token at a time. Links to our Whitepaper, Github repo, HuggingFace model, and open dataset page in the thread: 🧵

Excited to announce GR00T N1, the world’s first open foundation model for humanoid robots! We are on a mission to democratize Physical AI. The power of general robot brain, in the palm of your hand - with only 2B parameters, N1 learns from the most diverse physical action dataset ever compiled and punches above its weight: - Real humanoid teleoperation data. - Large-scale simulation data: we are open-sourcing 300K+ trajectories! - Neural trajectories: we apply SOTA video generation models to “hallucinate” new synthetic data that features accurate physics in pixels. Using Jensen’s words, “systematically infinite data”! - Latent actions: we develop novel algorithms to extract action tokens from in-the-wild human videos and neural generated videos. GR00T N1 is a single end-to-end neural net, from photons to actions: - Vision-Language Model (System 2) that interprets the physical world through vision and language instructions, enabling robots to reason about their environment and instructions, and plan the right actions. - Diffusion Transformer (System 1) that “renders” smooth and precise motor actions at 120 Hz, executing the latent plan made by System 2. We deploy N1 on GR1 robot, 1X Neo robot, and a large collection of simulation benchmarks. N1 achieves up to +30% boost in diverse manipulation tasks for household and industrial settings. While humanoid robots are the main focus of N1, our model also supports cross-embodiment. We finetune it to work on the $110 HuggingFace LeRobot SO100 robot arm! Open robot brain runs on open hardware. Sounds just right. Let’s solve robotics, together, one token at a time. Links to our Whitepaper, Github repo, HuggingFace model, and open dataset page in the thread: 🧵

Jim Fan

468,238 Aufrufe • vor 1 Jahr

S1 learns new tasks like a language model. You prompt it with a video demonstration, and it outputs robot actions to complete the task in any environment and in any embodiment.

S1 learns new tasks like a language model. You prompt it with a video demonstration, and it outputs robot actions to complete the task in any environment and in any embodiment.

Skild AI

308,754 Aufrufe • vor 2 Monaten

Robotics is moving beyond teaching robots how to perform a fixed set of actions. nature will’s new foundation model is built around a more general problem: can a robot understand an instruction, adapt to the situation in front of it, and physically execute the task? What makes this interesting is the combination of dexterous control, zero-shot generalization and long-horizon execution in one model.

Robotics is moving beyond teaching robots how to perform a fixed set of actions. nature will’s new foundation model is built around a more general problem: can a robot understand an instruction, adapt to the situation in front of it, and physically execute the task? What makes this interesting is the combination of dexterous control, zero-shot generalization and long-horizon execution in one model.

Fathela Esq

85,798 Aufrufe • vor 20 Tagen

World Labs CEO Dr. Fei-Fei Li & SceniX Co-Founder Yunzhu Li on the data bottleneck in robotics and how world models help: "The lack of data in training, the lack of data in evaluation, this is very, very different from language models, where data is abundant on the internet." "And we know that in order for robotics to work, we have to somehow unlock the power of scaling law. But where does that come from?" "It's a profound problem that everybody's battling with in robotics." "We see a lot of unlock in being able to do this whole process through the modeling of the environments." "Being able to create these digital worlds... that's just going to unlock so much more potential for being able to replace all the costly and the unsafe data in the real environments with the data generated from the worlds for robots to be able to do scalable learning and evaluations." Fei-Fei Li Yunzhu Li martin_casado

World Labs CEO Dr. Fei-Fei Li & SceniX Co-Founder Yunzhu Li on the data bottleneck in robotics and how world models help: "The lack of data in training, the lack of data in evaluation, this is very, very different from language models, where data is abundant on the internet." "And we know that in order for robotics to work, we have to somehow unlock the power of scaling law. But where does that come from?" "It's a profound problem that everybody's battling with in robotics." "We see a lot of unlock in being able to do this whole process through the modeling of the environments." "Being able to create these digital worlds... that's just going to unlock so much more potential for being able to replace all the costly and the unsafe data in the real environments with the data generated from the worlds for robots to be able to do scalable learning and evaluations." Fei-Fei Li Yunzhu Li martin_casado

a16z

80,437 Aufrufe • vor 3 Monaten

1/N Most Vision-Language-Action models need tons of data for finetuning, and still fail for new objects and instructions. Introducing OTTER, a lightweight, easy-to-train model that uses text-aware visual features to nail unseen tasks out of the box! Here's how it works 👇

1/N Most Vision-Language-Action models need tons of data for finetuning, and still fail for new objects and instructions. Introducing OTTER, a lightweight, easy-to-train model that uses text-aware visual features to nail unseen tasks out of the box! Here's how it works 👇

Fangchen Liu

69,453 Aufrufe • vor 1 Jahr

One of the biggest problems with robot benchmarks is also one of the easiest to overlook: The test itself can become predictable. Axis Robotics If robots keep getting evaluated on the same fixed set of tasks, eventually a high score can tell you less about whether a model actually learned to generalize and more about whether it has become good at that particular test. That’s the problem Open Axis Benchmark is trying to tackle, together with OpenRoboto. Instead of treating the benchmark as a permanent list of tasks, Open Axis keeps introducing fresh challenges. Each evaluation round draws from the growing Axis Library, giving models a new set of manipulation tasks to deal with. The goal is simple: make the robot demonstrate that it can handle situations it hasn’t simply memorized. And this is where Axis becomes interesting. The same system continuously generates and expands the task data used to train robotic models, while Open Axis can use that growing pool to create new evaluation environments. So training and evaluation become part of the same compounding loop: more data → more diverse tasks → harder evaluation → better measurement of generalization. That matters because the next generation of robotics models shouldn't just be able to perform tasks they've seen before. They need to work when the task changes. And a benchmark that keeps changing may be a much better way to find out whether they actually can.

One of the biggest problems with robot benchmarks is also one of the easiest to overlook: The test itself can become predictable. Axis Robotics If robots keep getting evaluated on the same fixed set of tasks, eventually a high score can tell you less about whether a model actually learned to generalize and more about whether it has become good at that particular test. That’s the problem Open Axis Benchmark is trying to tackle, together with OpenRoboto. Instead of treating the benchmark as a permanent list of tasks, Open Axis keeps introducing fresh challenges. Each evaluation round draws from the growing Axis Library, giving models a new set of manipulation tasks to deal with. The goal is simple: make the robot demonstrate that it can handle situations it hasn’t simply memorized. And this is where Axis becomes interesting. The same system continuously generates and expands the task data used to train robotic models, while Open Axis can use that growing pool to create new evaluation environments. So training and evaluation become part of the same compounding loop: more data → more diverse tasks → harder evaluation → better measurement of generalization. That matters because the next generation of robotics models shouldn't just be able to perform tasks they've seen before. They need to work when the task changes. And a benchmark that keeps changing may be a much better way to find out whether they actually can.

_Victorad

35,391 Aufrufe • vor 1 Monat

For decades, we’ve dreamed of robots that can seamlessly step into our world and lend a hand. Today, we take a major stride toward making that dream a reality: Introducing Gemini Robotics 2 from Google DeepMind, the intelligence layer powering the next generation of truly adaptable robots. This major advance unlocks intelligent whole-body control, advanced dexterity, and even multi-robot collaboration 🤯. Ok but... how does a robot actually "think"? Real-world tasks take time and planning. To manage that complexity, our new embodied reasoning model, Gemini Robotics ER 2, acts as the robot’s high-level brain, enhancing the robot’s capabilities to: — Observe the environment — Reason about the actions needed to complete the task — Coordinate with the vision-language-action model to carry out actions — Track progress until the job is done This setup allows robots to execute complex multi-step workflows, self-correct if a step fails, and adapt to completely novel situations. Learn more about Gemini Robotics ER 2 (and our two other brand new models) here:

Google AI

789,829 Aufrufe • vor 3 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

“Data in robotics versus data in LLMs has a very different alpha decay problem.” — Tarun Chitra, Managing Partner Robot Ventures Much of what LLMs learn can carry across contexts. Robotics data is far more conditional: what works depends heavily on the robot, the objects, and the environment. As robots move into more complex, real-world settings, previously collected data can become less relevant much faster. For builders and investors, that shifts the question from “How much data do you have” to “How quickly can you close the loop between deployment, new data, and adaptation”. From The Convergence: Bhutan by YZi Labs.

“Data in robotics versus data in LLMs has a very different alpha decay problem.” — Tarun Chitra, Managing Partner Robot Ventures Much of what LLMs learn can carry across contexts. Robotics data is far more conditional: what works depends heavily on the robot, the objects, and the environment. As robots move into more complex, real-world settings, previously collected data can become less relevant much faster. For builders and investors, that shifts the question from “How much data do you have” to “How quickly can you close the loop between deployment, new data, and adaptation”. From The Convergence: Bhutan by YZi Labs.

YZi Labs

26,762 Aufrufe • vor 1 Monat