Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

Real-Time Omni-Modal Interaction Driven Whole-Body Mobile Manipulation🥳 Unitree UnifoLM-OminiA-0.3 — a single model handling diverse home-care and wellness tasks, with omni-modal interactive understanding, fully autonomous, stable and disturbance-resistant execution.

Unitree

149,362 subscribers

15,488,084 views • 1 month ago •via X (Twitter)

Science & Technology

Anya Rossi• Live Now

Private livecam show

34 Comments

CorsaMotoGP1 month ago

This is a complete utter waste of human intellect. Using highly sophisticated technology, combined with rare earths and technological components all for a robot to rearrange cusions and hand other you pills that are an arm's reach - This will devolve us and make us lazier

Mickey Graf1 month ago

would love to see the original video without speedup. just look at her eyes/movements when she's in frame and the robot is "thinking"

Luke Dogwalker1 month ago

Robot so slow you have to speed up the footage...will be waiting for faster models

Peter 🪖Vet-Ret🩴1 month ago

I wonder which country will have the first robot human homicide...🤔🫡

David Curtis1 month ago

Sorry, but this seems ridiculous. Why do I need a robot to pick up a cushion?

SystemofaDave1 month ago

Everyone relax, this will all lead to a utopian future

Tim1 month ago

Gee it just took 5 mins to pick up a cushion & place it on the seat. Why can’t the person standing right there do it themselves,it’d be quicker & she would also get exercise. The human body is supposed to move & this thing looks like it needs another 10 years of development.

Socia1 month ago

At that speed, by the time it brings my delivery from downstairs onto my table, I'd be starved to death.

unacceptable matthew1 month ago

I'm used to these robots hitting children. This model appears to not have that feature enabled. Will it be added in the future?

Jim McPherson1 month ago

Has technology ever moved as fast as it is now?

Robert Scoble1 month ago

Bravo!

Jamie McAleny1 month ago

Now these are the droids I’m looking for!! 😂✌️ Why do the testers always wind them up though!! That’s the sort of shit they remember and will be the cause of the eventual robot revolution 😂🙏

TheZuzuCat🍉🚫1 month ago

Wow it can do what humans do but 5x slower!

PrismaX1 month ago

Impressive!

Bernard1 month ago

Until it gets bored and pissed off...

Steven Cheng1 month ago

disturbance-resistant is the real bottleneck. most demos fail when you actually touch them. curious how they handle dynamic contact forces without hard-coding every scenario.

Laurence Marie1 month ago

J'ai hate de voir comment ils font pour mettre un suppositoire au patient.

Matthew Ragnoli1 month ago

Great all that money and resources to pick up a fucking cushion,think I'll just do my self

clankr1 month ago

The Unitree G1 EDU (from $43,900) remains the best research humanoid compared to its rivals. Unitree deserves credit for taking responsibility and open-sourcing its models. More exciting developments could follow soon.

Tim Vee1 month ago

He loads the dishwasher like a teen kid who doesn't give a fuck.

Pommes1 month ago

Cant wait to have my own T800

RoboHub🤖1 month ago

Okay, Unitree’s AI stack is moving fast — this is wild! 👏👏👏

RAZA | AI EXPLORER1 month ago

The future of home-looking robotics is looking brighter. Love this.

Sonya Stewart1 month ago

Having your own robot seems somewhat appealing. It can start by tidying my place. 🤣

Lone Whiplash Dev - Try it now for free!1 month ago

why dont these things have pressure sensors that scale up when they are pushing/pulling on thier fingertips/palms? They need a skin that can feel varying degrees of pressure. seems obvious

Techniahqrobot | humanoid robots1 month ago

Impressive progress. A single model combining real time multimodal interaction with whole body mobile manipulation is a major step but I’d like to see longer uncut demos showing recovery from failures and performance in unfamiliar homes.

Old Ironsides1 month ago

Why not just pick up the cushion yourself?

🇬🇧Lee, investing to hopefully retire at 501 month ago

Its frightening how quick the technology is moving

mistofstars1 month ago

Am I the only one who finds this disturbing?

rw1 month ago

It's gonna take 3 weeks to clean up at this pace?

Paulie B1 month ago

I hate this planet

Peasant 龙鸣1 month ago

你们每次发的宣传视频背景音乐都让人听了很燥，能不能挑个有审美的人做视频

Ranjan Soni 🇨🇦1 month ago

Curious which parts are solved engineering problems, and which parts are just curated demos? That's usually where the real progress is hiding.

Bob Loblaw1 month ago

I'd use a foam bat to wack him whenever I think he's not moving fast enough, combined with insults and threats if he doesnt start moving it. It would be 🤖🤛😁

Related Videos

Okay, this is wild—Unitree’s embodied AI stack is moving fast. 👏 WVLA 2.0 cleaned a messy conference room autonomously in one take. Now UnifoLM-OminiA-0.3 adds real-time omni-modal interaction, letting one model understand the scene and coordinate its whole body for home-care and wellness tasks.

Okay, this is wild—Unitree’s embodied AI stack is moving fast. 👏 WVLA 2.0 cleaned a messy conference room autonomously in one take. Now UnifoLM-OminiA-0.3 adds real-time omni-modal interaction, letting one model understand the scene and coordinate its whole body for home-care and wellness tasks.

RoboHub🤖

27,452 views • 1 month ago

Humanoid robot caregiving is not far off Caregiver: Hey, get me the medicine from the cabinet,tidy up the kitchen… Patient: Help me raise the bed a bit higher… --- (Great work,Untree.Real-Time Omni-Modal Interaction Driven Whole-Body Mobile Manipulation--UnifoLM-OminiA-0.3)

Humanoid robot caregiving is not far off Caregiver: Hey, get me the medicine from the cabinet,tidy up the kitchen… Patient: Help me raise the bed a bit higher… --- (Great work,Untree.Real-Time Omni-Modal Interaction Driven Whole-Body Mobile Manipulation--UnifoLM-OminiA-0.3)

CyberRobo

12,335 views • 1 month ago

Unitree General-Purpose Humanoid Foundation Model Fully Upgrade Major Open Source🥳 Unitree majorly fully open-sources the UnifoLM-WLA-1.0 embodied foundation model, achieving new SOTA results across multiple benchmarks among open-source models worldwide. A single model coordinates desktop and whole-body mobile manipulation, supporting cross-task and cross-end-effector generalization, driven by one model, whole-body coordination.

Unitree General-Purpose Humanoid Foundation Model Fully Upgrade Major Open Source🥳 Unitree majorly fully open-sources the UnifoLM-WLA-1.0 embodied foundation model, achieving new SOTA results across multiple benchmarks among open-source models worldwide. A single model coordinates desktop and whole-body mobile manipulation, supporting cross-task and cross-end-effector generalization, driven by one model, whole-body coordination.

Unitree

81,104 views • 3 days ago

🥳 Introducing MiniCPM-o 4.5 The first full-duplex omni-modal LLM in open-source community 🎬🎙️ 🔥 Key Highlights: • Full-duplex Omni-modal Live Streaming: The model can see, listen, and speak simultaneously in a real-time conversation without mutual blocking • Proactive Interaction: Moving beyond reactive QA to performing proactive interaction, such as initiating reminders • Leading Performance: Scoring 77.6 on OpenCompass, it outperforms GPT-4o & Gemini 2.0 Pro in vision-language tasks with 9B params The best part? You can experience all above on your PC! #MiniCPM #OpenSource #MultimodalAI #LLM

🥳 Introducing MiniCPM-o 4.5 The first full-duplex omni-modal LLM in open-source community 🎬🎙️ 🔥 Key Highlights: • Full-duplex Omni-modal Live Streaming: The model can see, listen, and speak simultaneously in a real-time conversation without mutual blocking • Proactive Interaction: Moving beyond reactive QA to performing proactive interaction, such as initiating reminders • Leading Performance: Scoring 77.6 on OpenCompass, it outperforms GPT-4o & Gemini 2.0 Pro in vision-language tasks with 9B params The best part? You can experience all above on your PC! #MiniCPM #OpenSource #MultimodalAI #LLM

OpenBMB

398,258 views • 7 months ago

🤖✨Excited to share our new work: OMG: Omni-Modal Motion Generation for Generalist Humanoid Control What if a humanoid could understand intent from language, music/audio, human motion, or their combinations—and turn it into executable whole-body motion in real time? [🧵1/11]

🤖✨Excited to share our new work: OMG: Omni-Modal Motion Generation for Generalist Humanoid Control What if a humanoid could understand intent from language, music/audio, human motion, or their combinations—and turn it into executable whole-body motion in real time? [🧵1/11]

Siqiao Huang

13,750 views • 3 months ago

🤖 Introducing ω-0 (OMEGA-0) — a whole-body World Action Model for humanoids. Can one model make a humanoid walk, manipulate, and coordinate its whole body simultaneously across many real-world tasks? ω-0 does exactly that. ⚡ One unified model for multi-task whole-body loco-manipulation 🧠 Predicts future visual latents while generating executable whole-body actions 🏠 Trained with ω-HOME: 40+ hours, 24 household tasks, 4,827 episodes 🔥 81.8% real-world success rate across 11 evaluation tasks No separate locomotion/manipulation policies. One model. Whole body. Multiple tasks. Humanoid intelligence should not be a collection of isolated skills. It should be a unified whole-body policy. 🔗 📜 One-take, uncut real-world demo👇

🤖 Introducing ω-0 (OMEGA-0) — a whole-body World Action Model for humanoids. Can one model make a humanoid walk, manipulate, and coordinate its whole body simultaneously across many real-world tasks? ω-0 does exactly that. ⚡ One unified model for multi-task whole-body loco-manipulation 🧠 Predicts future visual latents while generating executable whole-body actions 🏠 Trained with ω-HOME: 40+ hours, 24 household tasks, 4,827 episodes 🔥 81.8% real-world success rate across 11 evaluation tasks No separate locomotion/manipulation policies. One model. Whole body. Multiple tasks. Humanoid intelligence should not be a collection of isolated skills. It should be a unified whole-body policy. 🔗 📜 One-take, uncut real-world demo👇

Jianfei Yang

18,740 views • 1 month ago

So cool...a humanoid just drove a go-kart for real. A Unitree G1 lowers itself into the tight cockpit, hands on the wheel, feet on the pedals, then runs the track， even drifts. It shows constrained whole-body loco-manipulation, mobile pick-and-place, and hand-eye-foot coordination in one sequence. This comes from China’s Symbiosis Robotics and their Direct Perception Control (DPC) model. It skips the usual high-level goals + tracker stack, mapping vision, language, body state and feedback straight to joint and hand targets. The focus is whole-body coordination for loco-manipulation. Interestingly, data diversity...Training used 15,010 hours of joint-aligned data-- 6,781h human egocentric, 4,024h armed robots, 3,660h wheeled humanoids, 545h bipedal. Teleop, head-mounted and egocentric sources were all converted into time-aligned joint trajectories across embodiments. A clean test that packs perception, balance and continuous whole-body control into one task chain ,and leaves room for other real-world scenarios.

So cool...a humanoid just drove a go-kart for real. A Unitree G1 lowers itself into the tight cockpit, hands on the wheel, feet on the pedals, then runs the track， even drifts. It shows constrained whole-body loco-manipulation, mobile pick-and-place, and hand-eye-foot coordination in one sequence. This comes from China’s Symbiosis Robotics and their Direct Perception Control (DPC) model. It skips the usual high-level goals + tracker stack, mapping vision, language, body state and feedback straight to joint and hand targets. The focus is whole-body coordination for loco-manipulation. Interestingly, data diversity...Training used 15,010 hours of joint-aligned data-- 6,781h human egocentric, 4,024h armed robots, 3,660h wheeled humanoids, 545h bipedal. Teleop, head-mounted and egocentric sources were all converted into time-aligned joint trajectories across embodiments. A clean test that packs perception, balance and continuous whole-body control into one task chain ,and leaves room for other real-world scenarios.

CyberRobo

76,039 views • 27 days ago

NVIDIA MotionBricks brings humanoid robots closer to natural, fluid movement The system combines a modular latent generative model with Smart Primitives, packing more than 350,000 motion skills into a single backbone. It runs in real time at up to 15,000 FPS with just 2ms latency. Navigation, object interaction, sitting, jumping, obstacle crossing, and even different movement styles can be composed zero-shot, like reusable motion modules. It is already being used for whole-body control on the Unitree G1 and serves as the motion layer for NVIDIA GR00T Whole-Body Control. What makes this interesting is the move from training individual behaviors toward building a shared library of motion capabilities. If that approach scales, robot movement could become more modular, transferable, and easier to deploy across different tasks and environments.

NVIDIA MotionBricks brings humanoid robots closer to natural, fluid movement The system combines a modular latent generative model with Smart Primitives, packing more than 350,000 motion skills into a single backbone. It runs in real time at up to 15,000 FPS with just 2ms latency. Navigation, object interaction, sitting, jumping, obstacle crossing, and even different movement styles can be composed zero-shot, like reusable motion modules. It is already being used for whole-body control on the Unitree G1 and serves as the motion layer for NVIDIA GR00T Whole-Body Control. What makes this interesting is the move from training individual behaviors toward building a shared library of motion capabilities. If that approach scales, robot movement could become more modular, transferable, and easier to deploy across different tasks and environments.

CyberRobo

11,089 views • 3 months ago

Generalist AI has raised a $400M funding round at a ~$2B valuation, bringing the total amount raised since its founding to over $500M . Led by Radical Ventures, with new participation from 8VC, Union Square Ventures, Hanabi Capital, and Norwest. Existing backers NVIDIA's NVentures, Boldstart, Spark, Bezos Expeditions, and NFDG followed on. Notable angel additions: Fei-Fei Li, Naval Ravikant, and Xiaomi co-founder Bin Lin. Founded by alumni of OpenAI, Google DeepMind, and Boston Dynamics, the team is building foundation models that span humanoids, robot arms, mobile warehouse robots, and autonomous space systems. GEN-1 (April 2026) hit 99% reliability on diverse tasks and 3x faster execution than prior models. The new funding will help scale models, the data engine, compute, and commercial deployments.. GEN-1 model in action, fully autonomous:

Generalist AI has raised a $400M funding round at a ~$2B valuation, bringing the total amount raised since its founding to over $500M . Led by Radical Ventures, with new participation from 8VC, Union Square Ventures, Hanabi Capital, and Norwest. Existing backers NVIDIA's NVentures, Boldstart, Spark, Bezos Expeditions, and NFDG followed on. Notable angel additions: Fei-Fei Li, Naval Ravikant, and Xiaomi co-founder Bin Lin. Founded by alumni of OpenAI, Google DeepMind, and Boston Dynamics, the team is building foundation models that span humanoids, robot arms, mobile warehouse robots, and autonomous space systems. GEN-1 (April 2026) hit 99% reliability on diverse tasks and 3x faster execution than prior models. The new funding will help scale models, the data engine, compute, and commercial deployments.. GEN-1 model in action, fully autonomous:

The Humanoid Hub

17,611 views • 3 months ago

NEWS: Humanoid robotics company Figure has released Helix 02, what they claim in their most capable humanoid model yet. "A single neural system that controls the full body directly from pixels, enabling dexterous, long horizon autonomy across an entire room: • Autonomous, long‑horizon loco-manipulation: Helix 02 unloads and reloads a dishwasher across a full-sized kitchen - a four-minute, end-to-end autonomous task that integrates walking, manipulation, and balance with no resets and no human intervention. We believe this is the longest horizon, most complex task completed autonomously by a humanoid robot to date. • All sensors in. All actuators out: Helix 02 connects every onboard sensor - vision, touch, and proprioception - directly to every actuator through a single unified visuomotor neural network. • Human-like whole body control from human data: All results are enabled by System 0, a learned whole‑body controller trained on over 1,000 hours of human motion data and sim‑to‑real reinforcement learning. System 0 replaces 109,504 lines of hand‑engineered C++ with a single neural prior for stable, natural motion. • New classes of dexterity: With Figure 03’s embedded tactile sensing and palm cameras, Helix 02 performs manipulation that was previously out of reach: extracting individual pills, dispensing precise syringe volumes, and singulating small, irregular objects from clutter despite self‑occlusion. Helix 02 is trained on over 1,000 hours of human motion data and integrates vision, touch, and proprioception."

NEWS: Humanoid robotics company Figure has released Helix 02, what they claim in their most capable humanoid model yet. "A single neural system that controls the full body directly from pixels, enabling dexterous, long horizon autonomy across an entire room: • Autonomous, long‑horizon loco-manipulation: Helix 02 unloads and reloads a dishwasher across a full-sized kitchen - a four-minute, end-to-end autonomous task that integrates walking, manipulation, and balance with no resets and no human intervention. We believe this is the longest horizon, most complex task completed autonomously by a humanoid robot to date. • All sensors in. All actuators out: Helix 02 connects every onboard sensor - vision, touch, and proprioception - directly to every actuator through a single unified visuomotor neural network. • Human-like whole body control from human data: All results are enabled by System 0, a learned whole‑body controller trained on over 1,000 hours of human motion data and sim‑to‑real reinforcement learning. System 0 replaces 109,504 lines of hand‑engineered C++ with a single neural prior for stable, natural motion. • New classes of dexterity: With Figure 03’s embedded tactile sensing and palm cameras, Helix 02 performs manipulation that was previously out of reach: extracting individual pills, dispensing precise syringe volumes, and singulating small, irregular objects from clutter despite self‑occlusion. Helix 02 is trained on over 1,000 hours of human motion data and integrates vision, touch, and proprioception."

Sawyer Merritt

624,876 views • 7 months ago

Today, we're announcing the next evolution of Sword Thrive: a fully revamped experience anchored by a new conversational care model, Vision AI, and a more powerful Phoenix. At the center of this evolution is a first-of-its-kind care model: a 3-way chat connecting the member, Phoenix, and their Doctor of Physical Therapy in a single interface, making continuous, 24/7 care possible for the first time, with the clinical oversight only a human specialist can provide. Vision AI, our proprietary technology trained on years of movement data, now delivers precise movement detection in real-world home environments - cluttered, noisy, and everything in between - and runs entirely through the Sword Health app on smartphones and tablets. Phoenix, our AI Care Specialist, is now more capable as well, providing deeper, personalized two-way conversational guidance and real-time form correction, adapting to each member as they move. From proactive care to continuous recovery, this is how healthcare should show up: with reliability, clinical memory, and real-time support that never drops the thread. Watch the video to see it in action:

Today, we're announcing the next evolution of Sword Thrive: a fully revamped experience anchored by a new conversational care model, Vision AI, and a more powerful Phoenix. At the center of this evolution is a first-of-its-kind care model: a 3-way chat connecting the member, Phoenix, and their Doctor of Physical Therapy in a single interface, making continuous, 24/7 care possible for the first time, with the clinical oversight only a human specialist can provide. Vision AI, our proprietary technology trained on years of movement data, now delivers precise movement detection in real-world home environments - cluttered, noisy, and everything in between - and runs entirely through the Sword Health app on smartphones and tablets. Phoenix, our AI Care Specialist, is now more capable as well, providing deeper, personalized two-way conversational guidance and real-time form correction, adapting to each member as they move. From proactive care to continuous recovery, this is how healthcare should show up: with reliability, clinical memory, and real-time support that never drops the thread. Watch the video to see it in action:

Sword Health

27,974 views • 6 months ago

How humanoids move from "Kung Fu" mode to "Blue-collar" work 🤖🦾 Unitree founder Xingxing Wang just dropped some major truth bombs about the reality of robot labor at the HEIS meeting in Beijing Extreme mobility like the "Kung Fu" bot at the Gala is the prerequisite—stable movement is the foundation for robots to actually start working Unitree has been deploying humanoids at NIO and Geely since 2024 with a 100% success rate on single tasks like simple parts assembly The real challenge is long-sequence complex tasks with 20+ steps—success rates struggle here especially when handling tiny parts Whole-body teleoperation is the key technical breakthrough for capturing high-quality physical world data to solve the industry's data scarcity Standardization is now the priority—setting unified task metrics, evaluation systems, and safety baselines to move beyond one-off lab innovations In 2025 Unitree shipped over 5,500 humanoids with more than 6,500 units coming off the production line leading the global market in volume The end goal is clear—Unitree wants humanoids working in its own factories to manufacture even more robots, closing the automation loop Source: HEIS Annual Meeting #Robot #Humanoid #Robotics #AI #EmbodiedAI #PhysicalAI #Unitree #SmartManufacturing #Automation

How humanoids move from "Kung Fu" mode to "Blue-collar" work 🤖🦾 Unitree founder Xingxing Wang just dropped some major truth bombs about the reality of robot labor at the HEIS meeting in Beijing Extreme mobility like the "Kung Fu" bot at the Gala is the prerequisite—stable movement is the foundation for robots to actually start working Unitree has been deploying humanoids at NIO and Geely since 2024 with a 100% success rate on single tasks like simple parts assembly The real challenge is long-sequence complex tasks with 20+ steps—success rates struggle here especially when handling tiny parts Whole-body teleoperation is the key technical breakthrough for capturing high-quality physical world data to solve the industry's data scarcity Standardization is now the priority—setting unified task metrics, evaluation systems, and safety baselines to move beyond one-off lab innovations In 2025 Unitree shipped over 5,500 humanoids with more than 6,500 units coming off the production line leading the global market in volume The end goal is clear—Unitree wants humanoids working in its own factories to manufacture even more robots, closing the automation loop Source: HEIS Annual Meeting #Robot #Humanoid #Robotics #AI #EmbodiedAI #PhysicalAI #Unitree #SmartManufacturing #Automation

RoboHub🤖

31,755 views • 6 months ago

The power of generative models — now embodied in humanoids. Announcing DreamControl –– After a year-long research effort at General Robotics — we present a scalable framework for whole-body humanoid control that fuses diffusion priors with reinforcement learning to unlock real-world scene interaction. Diffusion + RL → natural whole-body skills on real robots. DreamControl enables humanoids to move beyond locomotion demos → performing natural, human-like skills such as –– Picking & lifting objects, Opening drawers & doors, Precise punching, kicking, and jumping, Bimanual manipulation tasks Our key innovation: a diffusion prior over human motion that guides RL, eliminating the need for massive teleoperation datasets, and producing motions that look human while transferring to real hardware. Trained purely in simulation, deployed on the Unitree G1 humanoid, DreamControl policies run in real time, bridging sim-to-real with unprecedented naturalness. We leverage a novel hybrid edge + cloud infrastructure that runs RL-trained policies on the edge backed by powerful AI models running in the cloud This is the next step in General Robotics’ journey toward general-purpose humanoid assistants that interact, adapt, and assist autonomously. Paper: Blog: 1/n

The power of generative models — now embodied in humanoids. Announcing DreamControl –– After a year-long research effort at General Robotics — we present a scalable framework for whole-body humanoid control that fuses diffusion priors with reinforcement learning to unlock real-world scene interaction. Diffusion + RL → natural whole-body skills on real robots. DreamControl enables humanoids to move beyond locomotion demos → performing natural, human-like skills such as –– Picking & lifting objects, Opening drawers & doors, Precise punching, kicking, and jumping, Bimanual manipulation tasks Our key innovation: a diffusion prior over human motion that guides RL, eliminating the need for massive teleoperation datasets, and producing motions that look human while transferring to real hardware. Trained purely in simulation, deployed on the Unitree G1 humanoid, DreamControl policies run in real time, bridging sim-to-real with unprecedented naturalness. We leverage a novel hybrid edge + cloud infrastructure that runs RL-trained policies on the edge backed by powerful AI models running in the cloud This is the next step in General Robotics’ journey toward general-purpose humanoid assistants that interact, adapt, and assist autonomously. Paper: Blog: 1/n

Ashish Kapoor

118,467 views • 1 year ago

From lab to open-source: A new milestone for AI-driven education. 🎓 🤗 We’ve been closely following the MAIC project at Tsinghua University, and we’re thrilled to see it now open-sourced as #OpenMAIC. ✨ This isn't just another chatbot; it takes Multi-Agent orchestration to the next level by building a fully interactive classroom where AI instructors and peers collaborate in real-time. What makes it technically impressive: 🛠️ Complex Orchestration: Leveraging #LangGraph to manage spontaneous interactions—like #AI students "raising hands" during a live lecture. 🧠 Structured Planning: A dedicated "Plan Agent" that transforms raw PDFs into coherent, logically sequenced pedagogical flows. 💻 Beyond Text: A masterclass in GenUI implementation, featuring synchronized TTS, laser pointers, and real-time whiteboard demonstrations. 🥳 If you’re building complex, multi-modal #Agent workflows, this repo is a treasure trove of engineering insights. 🖥️Explore the project: 📰 Read the research:

From lab to open-source: A new milestone for AI-driven education. 🎓 🤗 We’ve been closely following the MAIC project at Tsinghua University, and we’re thrilled to see it now open-sourced as #OpenMAIC. ✨ This isn't just another chatbot; it takes Multi-Agent orchestration to the next level by building a fully interactive classroom where AI instructors and peers collaborate in real-time. What makes it technically impressive: 🛠️ Complex Orchestration: Leveraging #LangGraph to manage spontaneous interactions—like #AI students "raising hands" during a live lecture. 🧠 Structured Planning: A dedicated "Plan Agent" that transforms raw PDFs into coherent, logically sequenced pedagogical flows. 💻 Beyond Text: A masterclass in GenUI implementation, featuring synchronized TTS, laser pointers, and real-time whiteboard demonstrations. 🥳 If you’re building complex, multi-modal #Agent workflows, this repo is a treasure trove of engineering insights. 🖥️Explore the project: 📰 Read the research:

OpenBMB

152,659 views • 6 months ago

X-Humanoid just officially dropped Embodied Tien Kung 3.0, A universal platform designed to be way more open and developer-friendly. 🤖 Built on their Wise Kaiwu AI platform, this next-gen humanoid is all about slashing development costs. It’s a fully interoperable ecosystem that supports everything from tactile interaction to high-dynamic motion control at a full humanoid scale. ➤ Radical Openness: X-Humanoid is open-sourcing the full stack—robot body, motion control, VLM/VLA models, and the RoboMIND dataset. It fully supports ROS2, MQTT, and TCP/IP, so developers can customize use cases without re-engineering the basics. ➤ High-Performance Hardware: With high-torque integrated joints, Tien Kung 3.0 can clear 1-meter (3.3ft) obstacles and handle dexterous moves like kneeling and bending. It hits millimeter-level precision, making it a solid fit for industrial-grade tasks. ➤ True Autonomy: The bot runs a continuous perception-decision-execution loop. It uses world models to break down complex language commands and VLA models for real-time obstacle avoidance and navigation. ➤ Scalable Collaboration: The platform moves beyond single-unit tasks to support multi-robot collaboration with autonomous scheduling. It’s built to move embodied AI from the lab straight into real-world commercial and industrial environments. Source: X-Humanoid #Humanoid #OpenSource #Robotics #EmbodiedAI #PhysicalAI #Automation #XHumanoid #TienKung #WiseKaiwu

X-Humanoid just officially dropped Embodied Tien Kung 3.0, A universal platform designed to be way more open and developer-friendly. 🤖 Built on their Wise Kaiwu AI platform, this next-gen humanoid is all about slashing development costs. It’s a fully interoperable ecosystem that supports everything from tactile interaction to high-dynamic motion control at a full humanoid scale. ➤ Radical Openness: X-Humanoid is open-sourcing the full stack—robot body, motion control, VLM/VLA models, and the RoboMIND dataset. It fully supports ROS2, MQTT, and TCP/IP, so developers can customize use cases without re-engineering the basics. ➤ High-Performance Hardware: With high-torque integrated joints, Tien Kung 3.0 can clear 1-meter (3.3ft) obstacles and handle dexterous moves like kneeling and bending. It hits millimeter-level precision, making it a solid fit for industrial-grade tasks. ➤ True Autonomy: The bot runs a continuous perception-decision-execution loop. It uses world models to break down complex language commands and VLA models for real-time obstacle avoidance and navigation. ➤ Scalable Collaboration: The platform moves beyond single-unit tasks to support multi-robot collaboration with autonomous scheduling. It’s built to move embodied AI from the lab straight into real-world commercial and industrial environments. Source: X-Humanoid #Humanoid #OpenSource #Robotics #EmbodiedAI #PhysicalAI #Automation #XHumanoid #TienKung #WiseKaiwu

RoboHub🤖

49,440 views • 7 months ago

Reporting from CES 2026 LG Electronics has unveiled LG CLOiD, an AI-powered home robot, advancing its “Zero Labor Home” vision to automate chores. CLOiD features: • Wheeled base for safe navigation • Tilting torso • Two 7-DoF arms with 5-fingered hands for precise manipulation • Head as mobile AI hub equipped with a chipset (its brain), display, speakers, cameras, sensors, and voice-based generative AI for communication, learning user patterns, and appliance control Powered by LG’s Physical AI (VLM for understanding + VLA for actions), trained on tens of thousands of hours of household task data. It performs tasks like breakfast prep, laundry (loading/folding), dishwasher unloading, and more. LG also launched AXIUM actuators lineup for efficient robotics solutions. Vision for the future: AI-driven homes freeing time for meaningful activities.

Reporting from CES 2026 LG Electronics has unveiled LG CLOiD, an AI-powered home robot, advancing its “Zero Labor Home” vision to automate chores. CLOiD features: • Wheeled base for safe navigation • Tilting torso • Two 7-DoF arms with 5-fingered hands for precise manipulation • Head as mobile AI hub equipped with a chipset (its brain), display, speakers, cameras, sensors, and voice-based generative AI for communication, learning user patterns, and appliance control Powered by LG’s Physical AI (VLM for understanding + VLA for actions), trained on tens of thousands of hours of household task data. It performs tasks like breakfast prep, laundry (loading/folding), dishwasher unloading, and more. LG also launched AXIUM actuators lineup for efficient robotics solutions. Vision for the future: AI-driven homes freeing time for meaningful activities.

The Humanoid Hub

82,570 views • 8 months ago

Humanoids finally move like humans… and can do more than copy. [Details + demos in thread 👇] A new framework, BeyondMimic, shows how to learn naturalistic whole-body control from human motion. But then goes further by composing those skills into versatile, zero-shot policies. Two key pieces make it work: •Motion tracking pipeline: robustly turns human mocap into dynamic robot motions (jump spins, sprinting, cartwheels) on real hardware •Guided diffusion policy: distills motion primitives and enables zero-shot downstream tasks with simple cost functions The result: ✅ State-of-the-art motion quality from mocap tracking ✅ Versatile task execution; waypoint navigation, joystick teleop, obstacle avoidance ✅ Stable sim-to-real transfer for diverse humanoid skills Thank you for sharing, Qiayuan Liao! 📍 Paper: Video:

Humanoids finally move like humans… and can do more than copy. [Details + demos in thread 👇] A new framework, BeyondMimic, shows how to learn naturalistic whole-body control from human motion. But then goes further by composing those skills into versatile, zero-shot policies. Two key pieces make it work: •Motion tracking pipeline: robustly turns human mocap into dynamic robot motions (jump spins, sprinting, cartwheels) on real hardware •Guided diffusion policy: distills motion primitives and enables zero-shot downstream tasks with simple cost functions The result: ✅ State-of-the-art motion quality from mocap tracking ✅ Versatile task execution; waypoint navigation, joystick teleop, obstacle avoidance ✅ Stable sim-to-real transfer for diverse humanoid skills Thank you for sharing, Qiayuan Liao! 📍 Paper: Video:

Ilir Aliu - eu/acc

72,522 views • 1 year ago