正在加载视频...

视频加载失败

返回首页

Humanoid robots shouldn't just follow pre-defined movements—they should perform! 🤖✨ Introducing UniAct: A unified model for multimodal motion generation and action streaming. Most humanoids are limited to pre-designed moves. UniAct changes the game by allowing robots to generate live action sequences from: 📝 Text instructions 🎶 Music rhythms 📉...

siyuanhuang95's profile picture

Siyuan Huang

5,288 subscribers

10,688 次观看 • 9 个月前 •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

4 条评论

Xiatao Sun 的头像
Xiatao Sun9 个月前

Very cool—unifying text/music/trajectory conditioning with real-time action streaming feels like the right direction for “performative” humanoids, not just canned demos.

WWLTD 的头像
WWLTD9 个月前

Walks like a little old man compared to Atlas

Jithin Palepu 的头像
Jithin Palepu9 个月前

it's wild how much potential open AI has to level the playing field for everyone. just like how First100 is shaking up marketing and making it accessible, these open models are unlocking creativity and innovation on a massive scale. exciting times ahead!

Sar-thak 的头像
Sar-thak9 个月前

Hey, I’m Sarthak. I run Sentientx. We’re solving the data bottleneck that’s keeping robots out of homes/factories. But we’re not just a data collection company, we’re an AI research team first. We collect real world robot data, tele-op data, 24/7 out of India. Our edge? Speed. While others are still hiring, we’ve got an army of trained operators ready to go- massive data campaigns in days, not months. Think of us as your outsourced autonomy team.

相关视频

🤖GET TO KNOW ONE OF THE MOST AFFORDABLE HUMANOID ROBOTS One of the most affordable humanoid robots on the market, the G1 starts at around $16,000 and brings the robot trade closer to the mainstream.
0:45

🤖GET TO KNOW ONE OF THE MOST AFFORDABLE HUMANOID ROBOTS One of the most affordable humanoid robots on the market, the G1 starts at around $16,000 and brings the robot trade closer to the mainstream.

Coin Bureau

86,312 次观看 • 3 个月前

Humanoid robots are now being trained to build other humanoid robots.
0:31

Humanoid robots are now being trained to build other humanoid robots.

Massimo

77,230 次观看 • 3 个月前

From imagination to everyday life. UWORLD Ultra-Bionic Humanoid Robots are designed to enter real-life scenarios and create meaningful connections with people. From intelligent reception and emotional companionship to healthcare support and personalized experiences, we are bringing humanoid robots closer to everyday life. #UBTECH #UWORLD #UltraBionic #HumanoidRobot #ConsumerRobotics #Robotics #AI
1:21

From imagination to everyday life. UWORLD Ultra-Bionic Humanoid Robots are designed to enter real-life scenarios and create meaningful connections with people. From intelligent reception and emotional companionship to healthcare support and personalized experiences, we are bringing humanoid robots closer to everyday life. #UBTECH #UWORLD #UltraBionic #HumanoidRobot #ConsumerRobotics #Robotics #AI

UBTECH Robotics

12,509 次观看 • 3 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.
0:45

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

20,484 次观看 • 1 年前

Humanoid robots are entering people's homes. In the past three months of 2025, these humanoid robots have begun to perform some simple household chores.
3:23

Humanoid robots are entering people's homes. In the past three months of 2025, these humanoid robots have begun to perform some simple household chores.

CyberRobo

30,616 次观看 • 1 年前

The humanoid robot Lingxi X2 can easily dodge thrown balls… powered by AGIBOT’s newly launched AGILE perception-motion foundation model. With this motion intelligence, it can avoid interference and make real-time perceptual adjustments when working in complex environments. I’m curious whether it could dodge a human’s flying kick? (They always seem to kick humanoid robots during testing.)
0:24

The humanoid robot Lingxi X2 can easily dodge thrown balls… powered by AGIBOT’s newly launched AGILE perception-motion foundation model. With this motion intelligence, it can avoid interference and make real-time perceptual adjustments when working in complex environments. I’m curious whether it could dodge a human’s flying kick? (They always seem to kick humanoid robots during testing.)

CyberRobo

32,796 次观看 • 5 个月前

🤖✨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]
2:39

🤖✨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 次观看 • 4 个月前

🤖 China has launched a factory where robots build robots UBTECH Robotics has opened a “smart” factory in Liuzhou for the mass production of humanoid robots. Robots are already being used on the production line to help assemble other robots. The facility is designed to produce more than 10,000 humanoids a year, with a target rate of roughly one finished robot every 10 minutes. For now, it all looks like industrial automation. Skynet, please take a number and wait your turn.
0:32

🤖 China has launched a factory where robots build robots UBTECH Robotics has opened a “smart” factory in Liuzhou for the mass production of humanoid robots. Robots are already being used on the production line to help assemble other robots. The facility is designed to produce more than 10,000 humanoids a year, with a target rate of roughly one finished robot every 10 minutes. For now, it all looks like industrial automation. Skynet, please take a number and wait your turn.

NEXTA

45,655 次观看 • 1 个月前

🤖 New paper: MobileVLA-R1 A unified VLA system that brings real reasoning + continuous control to quadruped robots. CoT dataset, 2-stage training, real-world deployment. 📄paper & code & demo:
3:48

🤖 New paper: MobileVLA-R1 A unified VLA system that brings real reasoning + continuous control to quadruped robots. CoT dataset, 2-stage training, real-world deployment. 📄paper & code & demo:

Hao Tang (hiring postdocs)

27,306 次观看 • 11 个月前

TextOp: A real-time text-to-motion framework for humanoid robots. It allows users to instruct the robot using natural language and to modify commands on the fly, producing smooth, whole-body motions instantly.
1:11

TextOp: A real-time text-to-motion framework for humanoid robots. It allows users to instruct the robot using natural language and to modify commands on the fly, producing smooth, whole-body motions instantly.

The Humanoid Hub

25,125 次观看 • 11 个月前

Turning video into humanoid robot motion! 🤳🏼 Training humanoid robots needs huge amounts of motion data, but real-world capture doesn’t scale. Mocap is expensive, dangerous edge cases are rare, and you can’t ask humans to repeatedly fall or crash. Video2Robot tackles this by converting videos into physics-grounded humanoid simulations. Motion is generated to respect balance, inertia, ground contact, and joint limits, then directly retargeted to robot simulators. One prompt can generate a full humanoid motion sequence, including multi-agent interactions and failure cases like falls or collisions, scenarios that are hard or impossible to capture safely in the real world. The pipeline is model-agnostic and works with existing video generators, making it a practical way to scale data for robots. If robots are going to operate in the real world, they need to be trained on the failures too, not just the perfect demos. Here's the GitHub: ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →
0:26

Turning video into humanoid robot motion! 🤳🏼 Training humanoid robots needs huge amounts of motion data, but real-world capture doesn’t scale. Mocap is expensive, dangerous edge cases are rare, and you can’t ask humans to repeatedly fall or crash. Video2Robot tackles this by converting videos into physics-grounded humanoid simulations. Motion is generated to respect balance, inertia, ground contact, and joint limits, then directly retargeted to robot simulators. One prompt can generate a full humanoid motion sequence, including multi-agent interactions and failure cases like falls or collisions, scenarios that are hard or impossible to capture safely in the real world. The pipeline is model-agnostic and works with existing video generators, making it a practical way to scale data for robots. If robots are going to operate in the real world, they need to be trained on the failures too, not just the perfect demos. Here's the GitHub: ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →

Lukas Ziegler

60,070 次观看 • 10 个月前

🤖 Introducing ExBody2: our most advanced whole-body controller for humanoid robots. 🔊 Sound on to watch it move in perfect rhythm to the beats.
1:54

🤖 Introducing ExBody2: our most advanced whole-body controller for humanoid robots. 🔊 Sound on to watch it move in perfect rhythm to the beats.

Xuxin Cheng

164,077 次观看 • 1 年前

Introducing TraceVLA: a fully open-source Vision-Language-Action model reimagining spatial-temporal awareness: ✨ 3.5x gains on real robots, SOTA in simulation 💡 Fine-tunes on just 150K trajectories ⚡ Compact 4B model = 7B performance
0:29

Introducing TraceVLA: a fully open-source Vision-Language-Action model reimagining spatial-temporal awareness: ✨ 3.5x gains on real robots, SOTA in simulation 💡 Fine-tunes on just 150K trajectories ⚡ Compact 4B model = 7B performance

Yongyuan Liang

39,603 次观看 • 1 年前

While Unitree sells a lot of dumb humanoid robots to developers and researchers, they're also working on their own AI models. Robots making robots: Unitree’s UnifoLM-X1-0 AI model in action, performing assembly tasks in Unitree's own factory.
0:42

While Unitree sells a lot of dumb humanoid robots to developers and researchers, they're also working on their own AI models. Robots making robots: Unitree’s UnifoLM-X1-0 AI model in action, performing assembly tasks in Unitree's own factory.

The Humanoid Hub

26,867 次观看 • 8 个月前