正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

LeVERB is a VLA framework for humanoid whole-body control, combining a vision-language model and a low-level controller via a shared latent action space, trained entirely in sim, deployed zero shot.

The Humanoid Hub

57,783 subscribers

10,233 次观看 • 1 年前 •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

2 条评论

The Humanoid Hub 的头像

The Humanoid Hub1 年前

More details in this thread:

Brian Bellia 的头像

Brian Bellia1 年前

I want to see one of these things get in and out of a regular car. 🧐

相关视频

UK-based startup 'Humanoid' announced KinetIQ, an AI framework with a Vision-Language-Action (VLA) model at its core. It uses a four-layer architecture: fleet orchestration, task decomposition, VLA, and RL for whole-body control. It works on both bipedal and wheeled robots.

UK-based startup 'Humanoid' announced KinetIQ, an AI framework with a Vision-Language-Action (VLA) model at its core. It uses a four-layer architecture: fleet orchestration, task decomposition, VLA, and RL for whole-body control. It works on both bipedal and wheeled robots.

The Humanoid Hub

21,954 次观看 • 6 个月前

New paper introduces NaVILA, a vision-language-action (VLA) model that integrates high-level visual-language understanding and low-level locomotion control. It enables humanoid or quadruped robots to navigate unseen environments with natural language instructions.

New paper introduces NaVILA, a vision-language-action (VLA) model that integrates high-level visual-language understanding and low-level locomotion control. It enables humanoid or quadruped robots to navigate unseen environments with natural language instructions.

The Humanoid Hub

20,462 次观看 • 1 年前

Big news from the TeleAI embodied intelligence team! They unveiled TextOp, a general cerebellar framework for real-time, text-driven humanoid control. TextOp lets humans control the robot via natural language, dynamically modifying instructions during runtime to instantly generate smooth, whole-body actions. This enables precise and highly versatile control. The framework uses a two-layer architecture: an action diffusion model (High-Level) and a general motion tracking policy (Low-Level). It’s a new paradigm that eliminates the need for pre-recorded scripts or manual programming.

Big news from the TeleAI embodied intelligence team! They unveiled TextOp, a general cerebellar framework for real-time, text-driven humanoid control. TextOp lets humans control the robot via natural language, dynamically modifying instructions during runtime to instantly generate smooth, whole-body actions. This enables precise and highly versatile control. The framework uses a two-layer architecture: an action diffusion model (High-Level) and a general motion tracking policy (Low-Level). It’s a new paradigm that eliminates the need for pre-recorded scripts or manual programming.

RoboHub🤖

24,297 次观看 • 8 个月前

X-Humanoid just dropped TG-VLA — the first full-size, whole-body VLA framework for humanoids. 🤖 Most VLA demos today still look arm-centric: see, plan, reach, grasp. The legs are mostly there to carry the arms. TG-VLA pushes action into the whole body: → HEX: task context & cross-embodiment learning → HAF-VLA: high-DoF motion → structured action flows → DSRL-DCT: online RL through a compressed latent space The real shift isn't a smarter hand — it's locomotion, torso control, balance, and manipulation inside one control loop. That's the move: from mobile dual-arm machines to full-body agents.

X-Humanoid just dropped TG-VLA — the first full-size, whole-body VLA framework for humanoids. 🤖 Most VLA demos today still look arm-centric: see, plan, reach, grasp. The legs are mostly there to carry the arms. TG-VLA pushes action into the whole body: → HEX: task context & cross-embodiment learning → HAF-VLA: high-DoF motion → structured action flows → DSRL-DCT: online RL through a compressed latent space The real shift isn't a smarter hand — it's locomotion, torso control, balance, and manipulation inside one control loop. That's the move: from mobile dual-arm machines to full-body agents.

RoboHub🤖

41,598 次观看 • 1 个月前

X-Humanoid unveiled TG-VLA, which it calls the world's first whole-body VLA framework for full-size humanoid robots. The goal: move humanoids past "mobile dual-arm systems" to human-like, whole-body coordinated operation. Built on three technologies: - HEX: an open-source full-size humanoid VLA that learns across embodiments and coordinates the whole body. Claimed SOTA on real-world whole-body manipulation - HAF-VLA: hierarchical action flow that decomposes whole-body motion into subtasks. Best or joint-best on 6 benchmarks - DSRL-DCT: online RL for high-DoF humanoids in a compressed latent space. 100% success on mobile manipulation HEX is open-source.

X-Humanoid unveiled TG-VLA, which it calls the world's first whole-body VLA framework for full-size humanoid robots. The goal: move humanoids past "mobile dual-arm systems" to human-like, whole-body coordinated operation. Built on three technologies: - HEX: an open-source full-size humanoid VLA that learns across embodiments and coordinates the whole body. Claimed SOTA on real-world whole-body manipulation - HAF-VLA: hierarchical action flow that decomposes whole-body motion into subtasks. Best or joint-best on 6 benchmarks - DSRL-DCT: online RL for high-DoF humanoids in a compressed latent space. 100% success on mobile manipulation HEX is open-source.

The Humanoid Hub

19,563 次观看 • 1 个月前

We introduce W.A.L.T, a diffusion model for photorealistic video generation. Our model is a transformer trained on image and video generation in a shared latent space. 🧵👇

We introduce W.A.L.T, a diffusion model for photorealistic video generation. Our model is a transformer trained on image and video generation in a shared latent space. 🧵👇

Agrim Gupta

431,190 次观看 • 2 年前

Remarkably lifelike motion and fluidity. BeyondMimic is a framework for training humanoid whole-body control from large mocap datasets. First, an open-source motion-tracking pipeline to reproduce diverse, highly dynamic human skills on real hardware, then distilling them into a guided state-action diffusion model for zero-shot, task-specific control. Project page:

Remarkably lifelike motion and fluidity. BeyondMimic is a framework for training humanoid whole-body control from large mocap datasets. First, an open-source motion-tracking pipeline to reproduce diverse, highly dynamic human skills on real hardware, then distilling them into a guided state-action diffusion model for zero-shot, task-specific control. Project page:

The Humanoid Hub

58,081 次观看 • 11 个月前

🔥Character AI in VR Space🔥 We present #SOLAMI, a social vision-language-action (VLA) model that enables 3D autonomous characters with *speech and body language* interaction - Project: - Paper Hugging Face : . Thanks AK !

🔥Character AI in VR Space🔥 We present #SOLAMI, a social vision-language-action (VLA) model that enables 3D autonomous characters with speech and body language interaction - Project: - Paper Hugging Face : . Thanks AK !

Ziwei Liu

27,957 次观看 • 1 年前

Boston Dynamics taught Atlas a Rabona kick. Learned from human mocap, retargeted to Atlas, trained in sim via RL, deployed zero-shot to the real robot. Soccer skills demand whole-body coordination, and similar recipe transfers to warehouse work.

Boston Dynamics taught Atlas a Rabona kick. Learned from human mocap, retargeted to Atlas, trained in sim via RL, deployed zero-shot to the real robot. Soccer skills demand whole-body coordination, and similar recipe transfers to warehouse work.

The Humanoid Hub

11,268 次观看 • 2 个月前

Another day, another humanoid robot from china AGIBOT introduces GO-1, a generalist foundation model that integrates a vision-language model with a latent planner for enhanced long-horizon and dexterous manipulation.

Another day, another humanoid robot from china AGIBOT introduces GO-1, a generalist foundation model that integrates a vision-language model with a latent planner for enhanced long-horizon and dexterous manipulation.

Chubby♨️

23,513 次观看 • 1 年前

Ego-VCP: a learned ego-vision world model trained offline on demonstration-free random data that predicts dynamics in latent space for humanoid robots. Achieved robust real-time contact-rich planning on a real Unitree G1: bracing against walls, blocking flying objects, traversing low arches. Paper:

Ego-VCP: a learned ego-vision world model trained offline on demonstration-free random data that predicts dynamics in latent space for humanoid robots. Achieved robust real-time contact-rich planning on a real Unitree G1: bracing against walls, blocking flying objects, traversing low arches. Paper:

The Humanoid Hub

24,742 次观看 • 8 个月前

Whether teleoperated or autonomous, whole body movements like picking objects from the ground are challenging for humanoid robots. A UC San Diego paper introduces a framework that combines sim-to-real RL and trajectory optimization for adaptive, real-time whole body control.

Whether teleoperated or autonomous, whole body movements like picking objects from the ground are challenging for humanoid robots. A UC San Diego paper introduces a framework that combines sim-to-real RL and trajectory optimization for adaptive, real-time whole body control.

The Humanoid Hub

27,879 次观看 • 1 年前

How can we build a general-purpose “foundation model” for robot motion? Zhengyi “Zen” Luo joins us to talk about SONIC, which uses motion tracking as a foundational task for humanoid robot control, and scales humanoid control training to 9k GPU hours and 100 million frames worth of data. The result: a model with a generally-useful embedding space that can be controlled by a VLA, or from human video, to perform a wide variety of humanoid whole-body-control tasks, including with zero-shot transfer to previously unseen motions. Watch episode 72 of RoboPapers, with Michael Cho - Rbt/Acc and Jiafei Duan, now!

How can we build a general-purpose “foundation model” for robot motion? Zhengyi “Zen” Luo joins us to talk about SONIC, which uses motion tracking as a foundational task for humanoid robot control, and scales humanoid control training to 9k GPU hours and 100 million frames worth of data. The result: a model with a generally-useful embedding space that can be controlled by a VLA, or from human video, to perform a wide variety of humanoid whole-body-control tasks, including with zero-shot transfer to previously unseen motions. Watch episode 72 of RoboPapers, with Michael Cho - Rbt/Acc and Jiafei Duan, now!

RoboPapers

24,802 次观看 • 3 个月前

3D-VLA A 3D Vision-Language-Action Generative World Model Recent vision-language-action (VLA) models rely on 2D inputs, lacking integration with the broader realm of the 3D physical world. Furthermore, they perform action prediction by learning a direct mapping from

3D-VLA A 3D Vision-Language-Action Generative World Model Recent vision-language-action (VLA) models rely on 2D inputs, lacking integration with the broader realm of the 3D physical world. Furthermore, they perform action prediction by learning a direct mapping from

AK

85,570 次观看 • 2 年前

Today, a step forward in open robotics - our results show that sim-to-real zero shot transfer for manipulation is possible. MolmoBot is our open model suite for robotics, trained entirely in simulation on MolmoSpaces.🧵

Today, a step forward in open robotics - our results show that sim-to-real zero shot transfer for manipulation is possible. MolmoBot is our open model suite for robotics, trained entirely in simulation on MolmoSpaces.🧵

Ai2

64,816 次观看 • 4 个月前

Meet VLA-JEPA, the first world model policy in LeRobot 🌍 Most VLAs just learn observation → action. VLA-JEPA also learns action-relevant dynamics: during training, a JEPA world model has to predict upcoming frames in latent space from the model's own actions. Then, at inference, the world model disappears entirely, leaving a standard, fast VLA: Qwen backbone, action head, nothing extra. In our demo it was fine-tuned on just 13 examples and ran in real time on an NVIDIA DGX Spark. On a consumer RTX 3080, it hits 10Hz using under 6GB of VRAM. World-model supervision during training, zero extra cost at inference. That's the whole trick.

Meet VLA-JEPA, the first world model policy in LeRobot 🌍 Most VLAs just learn observation → action. VLA-JEPA also learns action-relevant dynamics: during training, a JEPA world model has to predict upcoming frames in latent space from the model's own actions. Then, at inference, the world model disappears entirely, leaving a standard, fast VLA: Qwen backbone, action head, nothing extra. In our demo it was fine-tuned on just 13 examples and ran in real time on an NVIDIA DGX Spark. On a consumer RTX 3080, it hits 10Hz using under 6GB of VRAM. World-model supervision during training, zero extra cost at inference. That's the whole trick.

LeRobot

42,303 次观看 • 29 天前

How do you give a humanoid the general motion capability? Not just single motions, but all motion? Introducing SONIC, our new work on supersizing motion tracking for natural humanoid control. We argue that motion tracking is the scalable foundation task for humanoids. So we "supersized" it: 9k+ GPU hours and 100M+ motion frames. But tracking alone is not enough; we show how to make a useful control system out of it: - Universal Kinematic Planner: Enables game-like gamepad control and high-level teleoperation, just like controlling a character in a game. - VR Full-Body Teleop: Direct, real-time whole-body control by a human wearing a VR headset. - VR Keypoint Teleop: Control the upper body (hands/head) while our planner handles robust locomotion automatically. - VLA Integration: We connect this motion tracker to autonomous Visual-Language-Action (VLA) models for autonomous task execution! We use a Universal Token Space to UNIFY this command space, turning our robust tracker into a general-purpose, programmable humanoid brain. This is the generalist "System 1" for humanoids. 🚀 Project: #Humanoids #Robotics #AI #FoundationModels #NVIDIAResearch 🧠🔥

How do you give a humanoid the general motion capability? Not just single motions, but all motion? Introducing SONIC, our new work on supersizing motion tracking for natural humanoid control. We argue that motion tracking is the scalable foundation task for humanoids. So we "supersized" it: 9k+ GPU hours and 100M+ motion frames. But tracking alone is not enough; we show how to make a useful control system out of it: - Universal Kinematic Planner: Enables game-like gamepad control and high-level teleoperation, just like controlling a character in a game. - VR Full-Body Teleop: Direct, real-time whole-body control by a human wearing a VR headset. - VR Keypoint Teleop: Control the upper body (hands/head) while our planner handles robust locomotion automatically. - VLA Integration: We connect this motion tracker to autonomous Visual-Language-Action (VLA) models for autonomous task execution! We use a Universal Token Space to UNIFY this command space, turning our robust tracker into a general-purpose, programmable humanoid brain. This is the generalist "System 1" for humanoids. 🚀 Project: #Humanoids #Robotics #AI #FoundationModels #NVIDIAResearch 🧠🔥

Zhengyi “Zen” Luo

62,208 次观看 • 8 个月前

Meet BFM-Zero: A Promptable Humanoid Behavioral Foundation Model w/ Unsupervised RL👉 🧩ONE latent space for ALL tasks ⚡Zero-shot goal reaching, tracking, and reward optimization (any reward at test time), from ONE policy 🤖Natural recovery & transition

Meet BFM-Zero: A Promptable Humanoid Behavioral Foundation Model w/ Unsupervised RL👉 🧩ONE latent space for ALL tasks ⚡Zero-shot goal reaching, tracking, and reward optimization (any reward at test time), from ONE policy 🤖Natural recovery & transition

Yitang Li

82,014 次观看 • 9 个月前

Chinese robotics company Astribot released their latest World-Action Model (WAM), Lumo-2. Technical breakdown: - based on a frozen 🥶 Qwen-3.5 4B VLM - trained in 3 progressive stages: 1. Action is aligned with latent world dynamics (an abstract representation of action). Real-world actions are anchored to physical constraints, while the latent space is guided to focus on motion-relevant changes. This bidirectional relationship makes the model physically grounded -> critical for a world model. 2. Action is aligned with vision and language. Reusing the vision backbone and action encoder from the frozen VLM, the authors add a custom vocabulary (for new actions), a semantic module, an action decoder, and an action projector. This aligns the (new) action representations with the (existing) vision-language semantic space. Most importantly: it builds a direct mapping from natural-language instructions to motor execution. 3. End-to-end training on language, video, and robot data. Only the new modules (everything outside the frozen backbone) are trained end-to-end across temporal reasoning, physical understanding, long-horizon, and dexterous manipulation. At the end of the day, Lumo-2 is not the best on benchmarks, but that's not the point. What's genuinely new: - a way to combine latent world modeling and action generation through progressive alignment - a physically-grounded latent dynamics space - it lifts performance on unseen objects using un-annotated human egocentric video + Vision Pro captures, no special transfer algorithm needed Why it matters: - the whole model is thin trainable adapters (semantic module, action decoder/projector) on a frozen 4B backbone (cheap) - that scale is suited for real-time embedded inference (~2.71× decode speedup, no accuracy loss) - its real moat is long-horizon execution, where the added temporal memory pays off far more than on any other task As a result, this robot can now make your latte (5x sped up video):

Chinese robotics company Astribot released their latest World-Action Model (WAM), Lumo-2. Technical breakdown: - based on a frozen 🥶 Qwen-3.5 4B VLM - trained in 3 progressive stages: 1. Action is aligned with latent world dynamics (an abstract representation of action). Real-world actions are anchored to physical constraints, while the latent space is guided to focus on motion-relevant changes. This bidirectional relationship makes the model physically grounded -> critical for a world model. 2. Action is aligned with vision and language. Reusing the vision backbone and action encoder from the frozen VLM, the authors add a custom vocabulary (for new actions), a semantic module, an action decoder, and an action projector. This aligns the (new) action representations with the (existing) vision-language semantic space. Most importantly: it builds a direct mapping from natural-language instructions to motor execution. 3. End-to-end training on language, video, and robot data. Only the new modules (everything outside the frozen backbone) are trained end-to-end across temporal reasoning, physical understanding, long-horizon, and dexterous manipulation. At the end of the day, Lumo-2 is not the best on benchmarks, but that's not the point. What's genuinely new: - a way to combine latent world modeling and action generation through progressive alignment - a physically-grounded latent dynamics space - it lifts performance on unseen objects using un-annotated human egocentric video + Vision Pro captures, no special transfer algorithm needed Why it matters: - the whole model is thin trainable adapters (semantic module, action decoder/projector) on a frozen 4B backbone (cheap) - that scale is suited for real-time embedded inference (~2.71× decode speedup, no accuracy loss) - its real moat is long-horizon execution, where the added temporal memory pays off far more than on any other task As a result, this robot can now make your latte (5x sped up video):

Léo

32,044 次观看 • 14 天前

🎾Your humanoid tennis player is here!🤖 Introducing LATENT (Learning Athletic Humanoid Tennis Skills from Imperfect Human Motion Data) — the world’s first real-time whole-body planning and control algorithm for athletic humanoid tennis. For the first time, a humanoid robot can sustain high-dynamic, long-horizon tennis rallies with millisecond-level reactions, precise ball striking, and natural whole-body motion. This marks a leap from mechanical motion imitation to intelligent, decision-driven athletic interaction. #Galbot #Robotics #Innovation #AI #Technology #Humanoid

🎾Your humanoid tennis player is here!🤖 Introducing LATENT (Learning Athletic Humanoid Tennis Skills from Imperfect Human Motion Data) — the world’s first real-time whole-body planning and control algorithm for athletic humanoid tennis. For the first time, a humanoid robot can sustain high-dynamic, long-horizon tennis rallies with millisecond-level reactions, precise ball striking, and natural whole-body motion. This marks a leap from mechanical motion imitation to intelligent, decision-driven athletic interaction. #Galbot #Robotics #Innovation #AI #Technology #Humanoid

Galbot

45,801 次观看 • 4 个月前