Video yükleniyor...

Video Yüklenemedi

Ana Sayfaya Dön

Why create robot intelligence for just one hand, when we could have it learn from many? GEN-1, our latest embodied foundation model, now supports a broad range of end effectors from 5-finger hands, to specialized tools, and everything in between.

GeneralistAI's profile picture

Generalist

11,068 subscribers

265,603 görüntüleme • 4 gün önce •via X (Twitter)

Bilim & Teknoloji
LIVE

Anya Rossi• Live Now

Private livecam show

0 Yorum

Yorum bulunmuyor

Orijinal gönderinin yorumları burada görünecek

Benzer Videolar

We brought Dynasaur to The Clean Show and ran it live, 8 hours a day. Each deployment fuels our robotics foundation model — scaling data, accelerating iteration, and enabling real-world generalization. Embodied intelligence won’t come from lab demos, but from deployment-first robotics running continuously in the wild.
1:50

We brought Dynasaur to The Clean Show and ran it live, 8 hours a day. Each deployment fuels our robotics foundation model — scaling data, accelerating iteration, and enabling real-world generalization. Embodied intelligence won’t come from lab demos, but from deployment-first robotics running continuously in the wild.

Dyna Robotics

24,680 görüntüleme • 11 ay önce

Two-thirds of secondary state schools in England teach just one #ModernForeignLanguage according to our latest Language Trends report. We went to a school in Leeds, where pupils learn a range of languages, to ask why they're beneficial. And we did it #WesAnderson style. #MFL
2:12

Two-thirds of secondary state schools in England teach just one #ModernForeignLanguage according to our latest Language Trends report. We went to a school in Leeds, where pupils learn a range of languages, to ask why they're beneficial. And we did it #WesAnderson style. #MFL

British Council

81,769 görüntüleme • 3 yıl önce

🤖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
0:27

🤖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

105,613 görüntüleme • 9 ay önce

AI excels in the virtual world, but acting in the physical world is a whole different challenge. Why is it so hard to get a robot to fetch an egg without freezing? 🤔 Check out our new explainer video on Embodied Intelligence. We discuss the gap between robot "Thinking" and "Acting,"
2:54

AI excels in the virtual world, but acting in the physical world is a whole different challenge. Why is it so hard to get a robot to fetch an egg without freezing? 🤔 Check out our new explainer video on Embodied Intelligence. We discuss the gap between robot "Thinking" and "Acting,"

Tongyi Lab

5,630,641 görüntüleme • 1 ay önce

1/ Big day — Nim is now publicly available to all at You can now use 15+ AI video creation tools in one easy-to-learn interface. Start for free and create unlimited images/videos for just $10/mo Here's the demo and why we are building Nim 👇
1:27

1/ Big day — Nim is now publicly available to all at You can now use 15+ AI video creation tools in one easy-to-learn interface. Start for free and create unlimited images/videos for just $10/mo Here's the demo and why we are building Nim 👇

Yury Lifshits

12,909 görüntüleme • 1 yıl önce

A humanoid robot is now climbing vertical industrial tanks to weld, grind, inspect, and remove rust. 🧲🤖 This is RobotPlusPlus’ embodied-intelligence wall-climbing robot, now deployed in high-risk scenes across chemical plants, shipyards, and energy facilities. The upper body uses dual humanoid arms. The lower body uses a wheeled magnetic-adhesion chassis that lets the robot work on steel walls instead of flat factory floors. The reported specs are industrial, not demo-stage: 90 kg body weight, 15 degrees of freedom, 12 active arm joints, millisecond-level remote response, and tethered power for long-duration operation. The real advantage is tool switching. Swap the end effectors, and the same platform can move between welding, grinding, flaw detection, rust removal, spraying, and surface treatment. For operators, the workflow changes from climbing scaffolds or hanging in baskets to controlling the robot through a remote interface and VR glasses. RobotPlusPlus says its special-operation model has learned from 100,000+ hours of field work, 22,500 km of operating distance, and 5,000 km² of covered work area. This is where embodied AI starts to look useful: not dancing onstage, but taking tools into places humans should not have to enter.
3:18

A humanoid robot is now climbing vertical industrial tanks to weld, grind, inspect, and remove rust. 🧲🤖 This is RobotPlusPlus’ embodied-intelligence wall-climbing robot, now deployed in high-risk scenes across chemical plants, shipyards, and energy facilities. The upper body uses dual humanoid arms. The lower body uses a wheeled magnetic-adhesion chassis that lets the robot work on steel walls instead of flat factory floors. The reported specs are industrial, not demo-stage: 90 kg body weight, 15 degrees of freedom, 12 active arm joints, millisecond-level remote response, and tethered power for long-duration operation. The real advantage is tool switching. Swap the end effectors, and the same platform can move between welding, grinding, flaw detection, rust removal, spraying, and surface treatment. For operators, the workflow changes from climbing scaffolds or hanging in baskets to controlling the robot through a remote interface and VR glasses. RobotPlusPlus says its special-operation model has learned from 100,000+ hours of field work, 22,500 km of operating distance, and 5,000 km² of covered work area. This is where embodied AI starts to look useful: not dancing onstage, but taking tools into places humans should not have to enter.

RoboHub🤖

79,853 görüntüleme • 2 ay önce

Codex for (almost) everything. It can now use apps on your Mac, connect to more of your tools, create images, learn from previous actions, remember how you like to work, and take on ongoing and repeatable tasks.
1:39

Codex for (almost) everything. It can now use apps on your Mac, connect to more of your tools, create images, learn from previous actions, remember how you like to work, and take on ongoing and repeatable tasks.

OpenAI

3,406,733 görüntüleme • 3 ay önce

How to learn dexterous manipulation for any robot hand from a single human demonstration? Check out DexMachina, our new RL algorithm that learns long-horizon, bimanual dexterous policies for a variety of dexterous hands, articulated objects, and complex motions.
0:43

How to learn dexterous manipulation for any robot hand from a single human demonstration? Check out DexMachina, our new RL algorithm that learns long-horizon, bimanual dexterous policies for a variety of dexterous hands, articulated objects, and complex motions.

Mandi Zhao

120,954 görüntüleme • 1 yıl önce

We just released HaMeR, our latest work for Hand Mesh Recovery! We reconstruct hands in 3D from a single image with big improvements in accuracy and robustness. Code and models are available. Also colab and Hugging Face demo!
0:52

We just released HaMeR, our latest work for Hand Mesh Recovery! We reconstruct hands in 3D from a single image with big improvements in accuracy and robustness. Code and models are available. Also colab and Hugging Face demo!

Georgios Pavlakos

38,336 görüntüleme • 2 yıl önce

Google's Jeff Dean says current pre-training is passive: initialize a model, stream the internet past it, let it observe But models need to learn not just from data, but by acting, predicting, and choosing what to learn from next "we have this artificial distinction now between pre and post-training, and it shouldn't exist long term"
1:20

Google's Jeff Dean says current pre-training is passive: initialize a model, stream the internet past it, let it observe But models need to learn not just from data, but by acting, predicting, and choosing what to learn from next "we have this artificial distinction now between pre and post-training, and it shouldn't exist long term"

Haider.

55,694 görüntüleme • 3 ay önce

Introducing INTELLECT-3: Scaling RL to a 100B+ MoE model on our end-to-end stack Achieving state-of-the-art performance for its size across math, code and reasoning Built using the same tools we put in your hands, from environments & evals, RL frameworks, sandboxes & more
0:41

Introducing INTELLECT-3: Scaling RL to a 100B+ MoE model on our end-to-end stack Achieving state-of-the-art performance for its size across math, code and reasoning Built using the same tools we put in your hands, from environments & evals, RL frameworks, sandboxes & more

Prime Intellect

1,142,730 görüntüleme • 8 ay önce

We trained a humanoid with 22-DoF dexterous hands to assemble model cars, operate syringes, sort poker cards, fold/roll shirts, all learned primarily from 20,000+ hours of egocentric human video with no robot in the loop. Humans are the most scalable embodiment on the planet. We discovered a near-perfect log-linear scaling law (R² = 0.998) between human video volume and action prediction loss, and this loss directly predicts real-robot success rate. Humanoid robots will be the end game, because they are the practical form factor with minimal embodiment gap from humans. Call it the Bitter Lesson of robot hardware: the kinematic similarity lets us simply retarget human finger motion onto dexterous robot hand joints. No learned embeddings, no fancy transfer algorithms needed. Relative wrist motion + retargeted 22-DoF finger actions serve as a unified action space that carries through from pre-training to robot execution. Our recipe is called "EgoScale": - Pre-train GR00T N1.5 on 20K hours of human video, mid-train with only 4 hours (!) of robot play data with Sharpa hands. 54% gains over training from scratch across 5 highly dexterous tasks. - Most surprising result: a *single* teleop demo is sufficient to learn a never-before-seen task. Our recipe enables extreme data efficiency. - Although we pre-train in 22-DoF hand joint space, the policy transfers to a Unitree G1 with 7-DoF tri-finger hands. 30%+ gains over training on G1 data alone. The scalable path to robot dexterity was never more robots. It was always us. Deep dives in thread:
1:17

We trained a humanoid with 22-DoF dexterous hands to assemble model cars, operate syringes, sort poker cards, fold/roll shirts, all learned primarily from 20,000+ hours of egocentric human video with no robot in the loop. Humans are the most scalable embodiment on the planet. We discovered a near-perfect log-linear scaling law (R² = 0.998) between human video volume and action prediction loss, and this loss directly predicts real-robot success rate. Humanoid robots will be the end game, because they are the practical form factor with minimal embodiment gap from humans. Call it the Bitter Lesson of robot hardware: the kinematic similarity lets us simply retarget human finger motion onto dexterous robot hand joints. No learned embeddings, no fancy transfer algorithms needed. Relative wrist motion + retargeted 22-DoF finger actions serve as a unified action space that carries through from pre-training to robot execution. Our recipe is called "EgoScale": - Pre-train GR00T N1.5 on 20K hours of human video, mid-train with only 4 hours (!) of robot play data with Sharpa hands. 54% gains over training from scratch across 5 highly dexterous tasks. - Most surprising result: a *single* teleop demo is sufficient to learn a never-before-seen task. Our recipe enables extreme data efficiency. - Although we pre-train in 22-DoF hand joint space, the policy transfers to a Unitree G1 with 7-DoF tri-finger hands. 30%+ gains over training on G1 data alone. The scalable path to robot dexterity was never more robots. It was always us. Deep dives in thread:

Jim Fan

293,585 görüntüleme • 5 ay önce

How can we build robotic hands with truly superhuman dexterity? Daxo Robotics is developing a unique tendon-driven soft robot hand, which aims to be tougher and more capable than a traditional humanoid hand. Each finger consists of many different tendons, which act in concert to move or manipulate. This is a special episode of RoboPapers where, instead of talking about a scientific paper, we talk to Tom Zhang, founder of Daxo Robotics, in order to learn both about his background and about how this one-of-a-kind robot hand design works. Watch Episode #40 of RoboPapers with Michael Cho - Rbt/Acc and Chris Paxton now!
1:01:15

How can we build robotic hands with truly superhuman dexterity? Daxo Robotics is developing a unique tendon-driven soft robot hand, which aims to be tougher and more capable than a traditional humanoid hand. Each finger consists of many different tendons, which act in concert to move or manipulate. This is a special episode of RoboPapers where, instead of talking about a scientific paper, we talk to Tom Zhang, founder of Daxo Robotics, in order to learn both about his background and about how this one-of-a-kind robot hand design works. Watch Episode #40 of RoboPapers with Michael Cho - Rbt/Acc and Chris Paxton now!

RoboPapers

16,171 görüntüleme • 8 ay önce

This is a portion of the force info we get from the hand, both when it's actively controlled and passively wiggled. We damaged some motors (black hexagons) from shipping the robot. But the fingers still have their full range of motion, thanks to the robustness of complexity.
0:31

This is a portion of the force info we get from the hand, both when it's actively controlled and passively wiggled. We damaged some motors (black hexagons) from shipping the robot. But the fingers still have their full range of motion, thanks to the robustness of complexity.

Tom Zhang

48,030 görüntüleme • 8 ay önce

🚨Dr. John Mack on alien abductions: Many experiencers don’t just encounter the “other” — they discover a double alien identity. “Why do these aliens look so humanoid? ... we both began separated from a common source.” “They have a whole other identity as an alien... they are seen as emissaries from the Source.” Dr. Mack reveals these encounters force a sometimes traumatic but necessary reunion between our densely embodied humanity and a far less embodied intelligence.
2:12

🚨Dr. John Mack on alien abductions: Many experiencers don’t just encounter the “other” — they discover a double alien identity. “Why do these aliens look so humanoid? ... we both began separated from a common source.” “They have a whole other identity as an alien... they are seen as emissaries from the Source.” Dr. Mack reveals these encounters force a sometimes traumatic but necessary reunion between our densely embodied humanity and a far less embodied intelligence.

High Strangeness

39,658 görüntüleme • 1 ay önce

💎 ICT Private Mentorship Complete Masterclass 💎 • Questions and Answers session from the ICT private charter forum about model 5. Model 5 is ICT's preferred model when it comes to forex. This is just one example of the hundreds of private videos we have available.
1:08:06

💎 ICT Private Mentorship Complete Masterclass 💎 • Questions and Answers session from the ICT private charter forum about model 5. Model 5 is ICT's preferred model when it comes to forex. This is just one example of the hundreds of private videos we have available.

ICT private mentorship videos & forum discussions

18,450 görüntüleme • 2 yıl önce

For the first time in human history, we are teaching a Foundation Model to master the diverse tasks of medicinal chemists, biologists, and computational scientists all in one place. In our latest collaboration with Liquid AI, we are moving away from fragmented, specialized tools toward a single, super-intelligent model. What surprised me most? This model isn't just performing at reasonable levels—it has started outperforming specialist models across physics-based tasks, imaging, and longitudinal data. Why this changes everything: -Synergy over Specialization: Fine-tuning on specific tasks has unlocked unexpected capabilities in synergetic areas, opening a new frontier in multimodal AI research. -Zero-Shot Potential: We are building a model that can perform out-of-scope tasks, moving us closer to an "AI deity" for drug discovery. -Quality First: The goal isn't just to bypass regulations to save time; it’s about using these synergies to develop better, more effective drugs. We are no longer just looking at linear regression or simple text; we are looking at the future of how humanity fights disease. #LiquidAI #InsilicoMedicine #GenerativeAI #DrugDiscovery #DeepTech #BiotechInnovation
1:53

For the first time in human history, we are teaching a Foundation Model to master the diverse tasks of medicinal chemists, biologists, and computational scientists all in one place. In our latest collaboration with Liquid AI, we are moving away from fragmented, specialized tools toward a single, super-intelligent model. What surprised me most? This model isn't just performing at reasonable levels—it has started outperforming specialist models across physics-based tasks, imaging, and longitudinal data. Why this changes everything: -Synergy over Specialization: Fine-tuning on specific tasks has unlocked unexpected capabilities in synergetic areas, opening a new frontier in multimodal AI research. -Zero-Shot Potential: We are building a model that can perform out-of-scope tasks, moving us closer to an "AI deity" for drug discovery. -Quality First: The goal isn't just to bypass regulations to save time; it’s about using these synergies to develop better, more effective drugs. We are no longer just looking at linear regression or simple text; we are looking at the future of how humanity fights disease. #LiquidAI #InsilicoMedicine #GenerativeAI #DrugDiscovery #DeepTech #BiotechInnovation

Alex Zhavoronkov, PhD (aka Aleksandrs Zavoronkovs)

10,544 görüntüleme • 3 ay önce

What happens when robot world models learn from human experience at scale? 🤔 DreamDojo from NVIDIA Research is a generalist robot world model pretrained on 44K hours of egocentric human videos and then post-trained on robot data to generalize across new objects and environments. After distillation, it runs at 10 FPS for live teleoperation, policy evaluation, and model-based planning. Read the ICML paper to learn more 📄
0:32

What happens when robot world models learn from human experience at scale? 🤔 DreamDojo from NVIDIA Research is a generalist robot world model pretrained on 44K hours of egocentric human videos and then post-trained on robot data to generalize across new objects and environments. After distillation, it runs at 10 FPS for live teleoperation, policy evaluation, and model-based planning. Read the ICML paper to learn more 📄

NVIDIA Robotics

22,413 görüntüleme • 21 gün önce

"This is going to be a big part of our identity." 🇪🇸 Mikel Arteta’s transformation of Arsenal is just one example of the Basque coaching revolution. From Guardiola to Emery, Xabi Alonso to Andoni Iraola, why are so many top managers emerging from this region? 🤔 In our latest It Was What It Was episode, we explore how Basque coaches have risen to dominate elite football. 🎙️
1:15

"This is going to be a big part of our identity." 🇪🇸 Mikel Arteta’s transformation of Arsenal is just one example of the Basque coaching revolution. From Guardiola to Emery, Xabi Alonso to Andoni Iraola, why are so many top managers emerging from this region? 🤔 In our latest It Was What It Was episode, we explore how Basque coaches have risen to dominate elite football. 🎙️

The Overlap

25,141 görüntüleme • 1 yıl önce