Загрузка видео...

Не удалось загрузить видео

Возникла проблема при загрузке этого видео. Это может быть связано с временными проблемами сети или видео может быть недоступно.

На главную

Traditional tokenization methods for robotic actions struggle with high-frequency, dexterous tasks due to redundancy and inefficiency. Inspired by JPEG compression, Physical Intelligence has developed a compressed action representation that accelerates VLA model training 5x.

The Humanoid Hub

108,094 subscribers

26,198 просмотров • 1 год назад •via X (Twitter)

Образование Здоровье и велнес Наука и технологии

Anya Rossi• Live Now

Private livecam show

Комментарии: 7

Фото профиля The Humanoid Hub

The Humanoid Hub1 год назад

More details in this thread:

Фото профиля UserInterface

UserInterface2 лет назад

Unveiling the Future of Prompt Engineering for Better AI Interactions #tech

Фото профиля navuud

navuud1 год назад

How does one build a laundry robot like this at home 😁

Фото профиля Brian Bellia

Brian Bellia1 год назад

So, does this mean the end of teleoperation as a means of training humanoids? I hope it spells the end of teleoperation, period. At this stage, it should be autonomous or nothing - except in rare cases like Optimus catching a ball.

Фото профиля The Humanoid Hub

The Humanoid Hub1 год назад

The DROID dataset they using for training is generated with teleop

Фото профиля Disarm.AGI.UBI

Disarm.AGI.UBI1 год назад

Give'm some practice. They will get better.

Фото профиля Rethynk AI

Rethynk AI1 год назад

Really like the way it put the 2nd on the top of the first. After intellectual capital, machines are getting better understanding of physical environment.

Похожие видео

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

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

Xiao Ma

93,908 просмотров • 7 месяцев назад

🚀 First step to unlocking Generalist Robots! Introducing 🤖LAPA🤖, a new SOTA open-sourced 7B VLA pretrained without using action labels. 💪SOTA VLA trained with Open X (outperforming OpenVLA on cross and multi embodiment) 😯LAPA enables learning from human videos, unlocking potential for robotic foundation model ❗Over 30x pretraining efficiency for VLA training 🤗Code and checkpoints are all open-sourced!

🚀 First step to unlocking Generalist Robots! Introducing 🤖LAPA🤖, a new SOTA open-sourced 7B VLA pretrained without using action labels. 💪SOTA VLA trained with Open X (outperforming OpenVLA on cross and multi embodiment) 😯LAPA enables learning from human videos, unlocking potential for robotic foundation model ❗Over 30x pretraining efficiency for VLA training 🤗Code and checkpoints are all open-sourced!

Seonghyeon Ye

33,296 просмотров • 1 год назад

Really excited to share what I've been working on with my colleagues at Physical Intelligence! We've developed a prototype robotic foundation model that can fold laundry, assemble a box, bus a table, and many other things. We've written a paper and blog post about it. 🧵👇

Really excited to share what I've been working on with my colleagues at Physical Intelligence! We've developed a prototype robotic foundation model that can fold laundry, assemble a box, bus a table, and many other things. We've written a paper and blog post about it. 🧵👇

Sergey Levine

114,997 просмотров • 1 год назад

🚀 MiniCPM enters the physical world — enabling robots to understand, remember, and act. We open-source MiniCPM-Robot, our first embodied AI model series, including: 🤖 MiniCPM-RobotManip — a 1.5B general-purpose Vision-Language-Action (VLA) model for robotic manipulation. 🐕 MiniCPM-RobotTrack — a compact model for real-world target tracking. ⚡ PhyAI — a high-performance inference framework built for embodied models. Together, they bring efficient, practical, and open embodied intelligence closer to real-world robots. ⭐ GitHub: 🤗 MiniCPM-RobotManip: 🤗 MiniCPM-RobotTrack:

🚀 MiniCPM enters the physical world — enabling robots to understand, remember, and act. We open-source MiniCPM-Robot, our first embodied AI model series, including: 🤖 MiniCPM-RobotManip — a 1.5B general-purpose Vision-Language-Action (VLA) model for robotic manipulation. 🐕 MiniCPM-RobotTrack — a compact model for real-world target tracking. ⚡ PhyAI — a high-performance inference framework built for embodied models. Together, they bring efficient, practical, and open embodied intelligence closer to real-world robots. ⭐ GitHub: 🤗 MiniCPM-RobotManip: 🤗 MiniCPM-RobotTrack:

OpenBMB

327,983 просмотров • 16 дней назад

Thrilled to announce my company Scout AI has officially emerged from stealth At Scout, we’re building the robotic foundation model for defense, bringing Silicon Valley physical intelligence to the U.S. military Several updates to share: → We raised an oversubscribed $15M seed round led by Align Ventures and Booz Allen Ventures → We’re unveiling Fury – the first Vision-Language-Action (VLA) foundation model purpose built for defense robotics → We have been selected for two DoD contracts to deploy Fury Giddy up 🫡🇺🇸

Thrilled to announce my company Scout AI has officially emerged from stealth At Scout, we’re building the robotic foundation model for defense, bringing Silicon Valley physical intelligence to the U.S. military Several updates to share: → We raised an oversubscribed $15M seed round led by Align Ventures and Booz Allen Ventures → We’re unveiling Fury – the first Vision-Language-Action (VLA) foundation model purpose built for defense robotics → We have been selected for two DoD contracts to deploy Fury Giddy up 🫡🇺🇸

Colby Adcock

131,585 просмотров • 1 год назад

An interactive world model developed by NVIDIA in collaboration with academic partners. - DreamDojo turns egocentric human video data into physical intelligence. - Human data is more scalable than robotics data but lacks action labels. - To solve this, a dedicated action model extracts latent actions by identifying physics and motion deltas between frames. Training - A massive 44k hours of video data are used for pre-training. - Post-training on small-scale robot datasets maps human physics to specific robot embodiments. - An additional distillation stage converts the model into an autoregressive, few-step diffusion model, enabling real-time, action-controllable simulation. Primary Use Cases - Live Teleoperation: Controlling a robot inside a world simulation in real-time. - Model-based Planning: Previewing and curating the best actions for improved success. - Policy Evaluation: Testing robot policies in realistic, out-of-distribution scenarios. Everything that's open-sourced: weights, code, post-training dataset, eval set, and details to reproduce.

An interactive world model developed by NVIDIA in collaboration with academic partners. - DreamDojo turns egocentric human video data into physical intelligence. - Human data is more scalable than robotics data but lacks action labels. - To solve this, a dedicated action model extracts latent actions by identifying physics and motion deltas between frames. Training - A massive 44k hours of video data are used for pre-training. - Post-training on small-scale robot datasets maps human physics to specific robot embodiments. - An additional distillation stage converts the model into an autoregressive, few-step diffusion model, enabling real-time, action-controllable simulation. Primary Use Cases - Live Teleoperation: Controlling a robot inside a world simulation in real-time. - Model-based Planning: Previewing and curating the best actions for improved success. - Policy Evaluation: Testing robot policies in realistic, out-of-distribution scenarios. Everything that's open-sourced: weights, code, post-training dataset, eval set, and details to reproduce.

The Humanoid Hub

11,575 просмотров • 5 месяцев назад

A major physical painting that was initiated with A.I was acquired today by the forward thinking and innovative Blondie. I recently posted a WIP and Blondie, without hesitation, commented ‘dibs’. She didn’t know yet that the WIP was 100% A.I. and she didn’t know it also inspired a physical. The A.I. work was made by training a MidJourney Model on some of my works. The image that emerged inspired me to create a version with the traditional medium of oil paint on canvas. I am super thrilled to announce that the visionary collector Blondie acquired “Drive-by Diagnosis”, 48” X 60”, for 9.45 eth. 🙏🙏🙏 LFG

A major physical painting that was initiated with A.I was acquired today by the forward thinking and innovative Blondie. I recently posted a WIP and Blondie, without hesitation, commented ‘dibs’. She didn’t know yet that the WIP was 100% A.I. and she didn’t know it also inspired a physical. The A.I. work was made by training a MidJourney Model on some of my works. The image that emerged inspired me to create a version with the traditional medium of oil paint on canvas. I am super thrilled to announce that the visionary collector Blondie acquired “Drive-by Diagnosis”, 48” X 60”, for 9.45 eth. 🙏🙏🙏 LFG

hafftka

24,740 просмотров • 2 лет назад

We developed an RL method for fine-tuning our models for precise tasks in just a few hours or even minutes. Instead of training the whole model, we add an “RL token” output to π-0.6, our latest model, which is used by a tiny actor and critic to learn quickly with RL.

We developed an RL method for fine-tuning our models for precise tasks in just a few hours or even minutes. Instead of training the whole model, we add an “RL token” output to π-0.6, our latest model, which is used by a tiny actor and critic to learn quickly with RL.

Physical Intelligence

438,164 просмотров • 4 месяцев назад

AgiBot has launched its OmniHand 2025 series, breaking the cost barrier for dexterous hands. The new 'Agile' model is the first high-DOF hand priced under 10,000 RMB! ► 'Agile' Model: 16 DOF for interactive services. Priced at just 9,800 RMB. ► 'Pro' Model: 19 DOF with 0.1N multi-modal sensing for precise industrial tasks. This is a major step toward making robot hands accessible for wider use, thanks to innovations like their self-developed joint modules.

AgiBot has launched its OmniHand 2025 series, breaking the cost barrier for dexterous hands. The new 'Agile' model is the first high-DOF hand priced under 10,000 RMB! ► 'Agile' Model: 16 DOF for interactive services. Priced at just 9,800 RMB. ► 'Pro' Model: 19 DOF with 0.1N multi-modal sensing for precise industrial tasks. This is a major step toward making robot hands accessible for wider use, thanks to innovations like their self-developed joint modules.

RoboHub🤖

34,084 просмотров • 11 месяцев назад

Not the flashiest demos, but what’s under the hood represents a foundational shift for general-purpose robotics. World models are the next-gen foundation of Physical AI, not the VLM backbones found in typical VLAs. DreamZero is a 14B-parameter World Action Model (WAM) by NVIDIA that treats robotics as a joint video-and-action prediction task. Unlike traditional Vision-Language-Action (VLA) models that map images directly to motor commands, DreamZero leverages a pretrained video diffusion backbone to predict future world states and actions simultaneously. - achieves 2× better zero-shot generalization to unseen tasks and environments compared to state-of-the-art VLAs. - learns effectively from heterogeneous, non-repetitive data (500 hours), breaking the need for thousands of repeated demonstrations. - adapts to new robot embodiments with just 30 minutes of play data. - enables 7Hz closed-loop control via system optimizations and "DreamZero-Flash," making high-capacity diffusion models viable for real-time use.

Not the flashiest demos, but what’s under the hood represents a foundational shift for general-purpose robotics. World models are the next-gen foundation of Physical AI, not the VLM backbones found in typical VLAs. DreamZero is a 14B-parameter World Action Model (WAM) by NVIDIA that treats robotics as a joint video-and-action prediction task. Unlike traditional Vision-Language-Action (VLA) models that map images directly to motor commands, DreamZero leverages a pretrained video diffusion backbone to predict future world states and actions simultaneously. - achieves 2× better zero-shot generalization to unseen tasks and environments compared to state-of-the-art VLAs. - learns effectively from heterogeneous, non-repetitive data (500 hours), breaking the need for thousands of repeated demonstrations. - adapts to new robot embodiments with just 30 minutes of play data. - enables 7Hz closed-loop control via system optimizations and "DreamZero-Flash," making high-capacity diffusion models viable for real-time use.

The Humanoid Hub

35,204 просмотров • 6 месяцев назад

Building upon SimpleVLA-RL, we have implemented real-world RL on long-horizon dexterous tasks and witnessed a non-trivial (~relatively 300%) performance improvement over the SFT model, along with surprising capabilities on auto-recovery. Blog coming soon. The entire process uses very little data and training compute—basically costing no more than a single robotic arm—hinting that real-world generality for machines is actually within sight.

Building upon SimpleVLA-RL, we have implemented real-world RL on long-horizon dexterous tasks and witnessed a non-trivial (~relatively 300%) performance improvement over the SFT model, along with surprising capabilities on auto-recovery. Blog coming soon. The entire process uses very little data and training compute—basically costing no more than a single robotic arm—hinting that real-world generality for machines is actually within sight.

Ning Ding

93,278 просмотров • 7 месяцев назад

🚀 Meta FAIR is releasing several new research artifacts on our road to advanced machine intelligence (AMI). These latest advancements are transforming our understanding of perception. 1️⃣ Meta Perception Encoder: A large-scale vision encoder that excels across several image & video tasks. 2️⃣ Meta Perception Language Model: A fully open & reproducible vision-language model designed to tackle visual recognition tasks. 3️⃣ Meta Locate 3D: An end-to-end model for accurate object localization in 3D environments. 4️⃣ Releasing model weights for our 8B-parameter Dynamic Byte Latent Transformer, an alternative to traditional tokenization methods with the potential to redefine the standards for language model efficiency and reliability. 5️⃣Collaborative Reasoner: A framework for evaluating & improving collaborative reasoning skills in language models. Download the code, datasets, and research papers and learn more about how these artifacts are paving the way for more efficient and accurate AI systems.➡️

🚀 Meta FAIR is releasing several new research artifacts on our road to advanced machine intelligence (AMI). These latest advancements are transforming our understanding of perception. 1️⃣ Meta Perception Encoder: A large-scale vision encoder that excels across several image & video tasks. 2️⃣ Meta Perception Language Model: A fully open & reproducible vision-language model designed to tackle visual recognition tasks. 3️⃣ Meta Locate 3D: An end-to-end model for accurate object localization in 3D environments. 4️⃣ Releasing model weights for our 8B-parameter Dynamic Byte Latent Transformer, an alternative to traditional tokenization methods with the potential to redefine the standards for language model efficiency and reliability. 5️⃣Collaborative Reasoner: A framework for evaluating & improving collaborative reasoning skills in language models. Download the code, datasets, and research papers and learn more about how these artifacts are paving the way for more efficient and accurate AI systems.➡️

AI at Meta

163,313 просмотров • 1 год назад

We are open-sourcing Wall-OSS-0.5. Pretrain Once, Act Anywhere. Wall-OSS-0.5 is a VLA model for real-world robotic manipulation, exploring whether pretraining alone can produce robot capabilities directly testable on physical hardware before task-specific fine-tuning. Key technical highlights: • Gradient-bridged co-training • Vision-Aligned RVQ Action Tokenizer • Action-Space Supervision • DMuon distributed optimizer In zero-shot real-robot evaluation, the pretrained checkpoint achieved task-progress scores above 80 on multiple tasks, including Block Sorting, Fruit Sorting, Ring Stacking, and Rope Tightening. Paper, code, blog, and uncut videos:

We are open-sourcing Wall-OSS-0.5. Pretrain Once, Act Anywhere. Wall-OSS-0.5 is a VLA model for real-world robotic manipulation, exploring whether pretraining alone can produce robot capabilities directly testable on physical hardware before task-specific fine-tuning. Key technical highlights: • Gradient-bridged co-training • Vision-Aligned RVQ Action Tokenizer • Action-Space Supervision • DMuon distributed optimizer In zero-shot real-robot evaluation, the pretrained checkpoint achieved task-progress scores above 80 on multiple tasks, including Block Sorting, Fruit Sorting, Ring Stacking, and Rope Tightening. Paper, code, blog, and uncut videos:

X Square Robot

24,659 просмотров • 2 месяцев назад

EnvGS: Modeling View-Dependent Appearance with Environment Gaussian Contributions: • We propose a novel scene representation for accurately modeling complex near-field and high-frequency reflections in real-world environments. • We developed a real-time ray-tracing renderer for 2DGS, enabling joint optimization of our representation for accurate scene reconstruction while achieving real-time rendering speeds. • Extensive experiments show that EnvGS significantly outperforms previous methods. To the best of our knowledge, EnvGS is the first method to achieve real-time photorealistic specular reflections synthesis in real-world scenes.

EnvGS: Modeling View-Dependent Appearance with Environment Gaussian Contributions: • We propose a novel scene representation for accurately modeling complex near-field and high-frequency reflections in real-world environments. • We developed a real-time ray-tracing renderer for 2DGS, enabling joint optimization of our representation for accurate scene reconstruction while achieving real-time rendering speeds. • Extensive experiments show that EnvGS significantly outperforms previous methods. To the best of our knowledge, EnvGS is the first method to achieve real-time photorealistic specular reflections synthesis in real-world scenes.

MrNeRF

44,650 просмотров • 1 год назад

Can vision-language-action (VLA) models generalize to diverse OOD tasks and align with customized objectives? 🤔 🚀 We introduce GRAPE, a plug-and-play algorithm to generalize robot policies via preference alignment. GRAPE unfolds three benefits to boost the generalizability of VLAs: 👉1. GRAPE aligns VLAs on a trajectory level and endows the model with the ability for global decision-making, instead of merely cloning behavior; 👉2. GRAPE implicitly models reward from both successful and failed trials to boost generalizability to diverse tasks; 👉3. GRAPE adopts a scalable preference synthesis algorithm to rank trajectories with preferences that align with arbitrary objectives. Our experiments on a diverse array of real-world and simulated robotic tasks reveal: 1⃣GRAPE enhances the performance of state-of-the-art VLA models, increasing success rates on in-domain and unseen manipulation tasks by 51.79% and 60.36%; 2⃣GRAPE is versatile to be aligned with diverse objectives and reduce collision rates by 44.31% or rollout length by 11.15% when aligning towards safer or more efficient manipulation policy, respectively. Check out our full project for more details: 🔥 Paper: 🔥 Project: 🔥 Code:

Can vision-language-action (VLA) models generalize to diverse OOD tasks and align with customized objectives? 🤔 🚀 We introduce GRAPE, a plug-and-play algorithm to generalize robot policies via preference alignment. GRAPE unfolds three benefits to boost the generalizability of VLAs: 👉1. GRAPE aligns VLAs on a trajectory level and endows the model with the ability for global decision-making, instead of merely cloning behavior; 👉2. GRAPE implicitly models reward from both successful and failed trials to boost generalizability to diverse tasks; 👉3. GRAPE adopts a scalable preference synthesis algorithm to rank trajectories with preferences that align with arbitrary objectives. Our experiments on a diverse array of real-world and simulated robotic tasks reveal: 1⃣GRAPE enhances the performance of state-of-the-art VLA models, increasing success rates on in-domain and unseen manipulation tasks by 51.79% and 60.36%; 2⃣GRAPE is versatile to be aligned with diverse objectives and reduce collision rates by 44.31% or rollout length by 11.15% when aligning towards safer or more efficient manipulation policy, respectively. Check out our full project for more details: 🔥 Paper: 🔥 Project: 🔥 Code:

Huaxiu Yao

19,988 просмотров • 1 год назад

Open-source dexterous hands with fingertip sensors! 🪬 ORCA Dexterity just released three dexterous hand models. Their mission: is to democratize robotic hand dexterity. They're sharing progress on exceptional, low-cost hardware and a software layer from low-level control to robotic hand learning. This is the open-source approach to dexterous manipulation. It has 83 taxels per finger with 0.1 N force detection which pretty is impressive for an open-source design. Tactile sensing is critical for dexterous manipulation, knowing contact forces enables gentle grasping, slip detection, and force-controlled assembly. Also 700g weight for the lite version makes it practical for mounting on robot arms without exceeding payload limits. Lower weight means faster movements and lower torque requirements. Open hardware accelerates robotics by letting researchers and builders modify designs for their specific needs without starting from scratch! ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →

Open-source dexterous hands with fingertip sensors! 🪬 ORCA Dexterity just released three dexterous hand models. Their mission: is to democratize robotic hand dexterity. They're sharing progress on exceptional, low-cost hardware and a software layer from low-level control to robotic hand learning. This is the open-source approach to dexterous manipulation. It has 83 taxels per finger with 0.1 N force detection which pretty is impressive for an open-source design. Tactile sensing is critical for dexterous manipulation, knowing contact forces enables gentle grasping, slip detection, and force-controlled assembly. Also 700g weight for the lite version makes it practical for mounting on robot arms without exceeding payload limits. Lower weight means faster movements and lower torque requirements. Open hardware accelerates robotics by letting researchers and builders modify designs for their specific needs without starting from scratch! ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →

Lukas Ziegler

38,094 просмотров • 4 месяцев назад

Robotic vascular anastomosis demands precision. Training should reflect that. We developed a perfused simulation model with pulsatile flow that recreates physiologic hemodynamics, allowing residents and surgeons to practice before entering high-stakes surgeries. Structured. Measurable. Reproducible. Scalable. #RoboticSurgery #Robotics #SurgicalEducation #MedEd #Simulation #Transplant #TransplantSurgery #AcademicSurgery #SurgicalInnovation #MinimallyInvasive #RoboticTraining #FutureOfSurgery ASTS AHPBA IHPBA BIDMC Department of Surgery Harvard Medical School BIDMCTransplant Intuitive

Robotic vascular anastomosis demands precision. Training should reflect that. We developed a perfused simulation model with pulsatile flow that recreates physiologic hemodynamics, allowing residents and surgeons to practice before entering high-stakes surgeries. Structured. Measurable. Reproducible. Scalable. #RoboticSurgery #Robotics #SurgicalEducation #MedEd #Simulation #Transplant #TransplantSurgery #AcademicSurgery #SurgicalInnovation #MinimallyInvasive #RoboticTraining #FutureOfSurgery ASTS AHPBA IHPBA BIDMC Department of Surgery Harvard Medical School BIDMCTransplant Intuitive

Martin Dib

72,922 просмотров • 5 месяцев назад

General Intuition CEO Pim de Witte, who's building foundation models trained on video game controller input data ("action-labeled gameplay clips"), says general intelligence won't "taste like an LLM": "We have a scale of data that's going to allow us to jump to the frontier in one capability — which is any system that can be controlled with a game controller (which is most robots) — and then, you can use that to create a sufficiently general intelligence." "As humans, the decision to talk or type is a very, very small subset of the actions that we can actually take." "So in order to create a sufficiently general intelligence to play 10,000+ video games, the model has to be able to predict across the entire action space of human cognition when they're interacting with these environments. Which are 2D and 3D environments, interfaces, long-horizon tasks, short-horizon tasks, [etc.]." "It has to be a sufficiently general intelligence in order to predict actions. Therefore, the type of model you get out is not going to taste like an LLM. This model is going to be incredibly good at navigating unforeseen environments. It's going to be incredibly good at zero-shotting any task that can be done with a game controller."

General Intuition CEO Pim de Witte, who's building foundation models trained on video game controller input data ("action-labeled gameplay clips"), says general intelligence won't "taste like an LLM": "We have a scale of data that's going to allow us to jump to the frontier in one capability — which is any system that can be controlled with a game controller (which is most robots) — and then, you can use that to create a sufficiently general intelligence." "As humans, the decision to talk or type is a very, very small subset of the actions that we can actually take." "So in order to create a sufficiently general intelligence to play 10,000+ video games, the model has to be able to predict across the entire action space of human cognition when they're interacting with these environments. Which are 2D and 3D environments, interfaces, long-horizon tasks, short-horizon tasks, [etc.]." "It has to be a sufficiently general intelligence in order to predict actions. Therefore, the type of model you get out is not going to taste like an LLM. This model is going to be incredibly good at navigating unforeseen environments. It's going to be incredibly good at zero-shotting any task that can be done with a game controller."

TBPN

80,199 просмотров • 1 месяц назад