Video yükleniyor...

Video Yüklenemedi

Ana Sayfaya Dön

At Cobot, we've been trying Real-Time Action Chunking from Physical Intelligence, which keeps robot rollouts smooth even with slow inference. Our blog shares a tweak for even slicker control. Check it out:

asoare159's profile picture

Alexander Soare

1,100 subscribers

23,196 görüntüleme • 1 yıl önce •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

0 Yorum

Yorum bulunmuyor

Orijinal gönderinin yorumları burada görünecek

Benzer Videolar

Real-time inference is a big challenge for VLAs. We’ve been working on a way to amortize inference delays in π0.5. Our new Real-Time Chunking (RTC) method speeds up π0.5 by allowing the robot to “think” while it’s moving, which makes it quite a bit faster! 🧵👇
0:29

Real-time inference is a big challenge for VLAs. We’ve been working on a way to amortize inference delays in π0.5. Our new Real-Time Chunking (RTC) method speeds up π0.5 by allowing the robot to “think” while it’s moving, which makes it quite a bit faster! 🧵👇

Sergey Levine

73,688 görüntüleme • 1 yıl önce

I'm extremely excited to announce that we've successfully inferenced π0.5 on our excavator! We've collected a massive corpus of real-world data with natural language labels from operators in the industry and are using it to create some really cool policies. Here's our first demo of it successfully completing a task with just 200 trajectories. More on the way :) Read our blog post: Physical Intelligence
1:04

I'm extremely excited to announce that we've successfully inferenced π0.5 on our excavator! We've collected a massive corpus of real-world data with natural language labels from operators in the industry and are using it to create some really cool policies. Here's our first demo of it successfully completing a task with just 200 trajectories. More on the way :) Read our blog post: Physical Intelligence

Lane Burgett

121,422 görüntüleme • 5 ay önce

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. 🧵👇
5:10

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 görüntüleme • 1 yıl önce

Last week I presented real-time chunking (RTC) at NeurIPS, and we did a live coffee demo the very same evening. To celebrate, we're releasing a (very short) follow-up paper describing a training-time variant of RTC, which is what we've actually been using in our demos!
2:16

Last week I presented real-time chunking (RTC) at NeurIPS, and we did a live coffee demo the very same evening. To celebrate, we're releasing a (very short) follow-up paper describing a training-time variant of RTC, which is what we've actually been using in our demos!

Kevin Black

33,659 görüntüleme • 8 ay önce

Check out this Circulus Pion robot at Computex 2026. It’s running on a Panther Lake processor, using P-cores for real-time control, E-cores to collect sensor data, the GPU for vision-language-action models, and the NPU for continuous perception.
2:12

Check out this Circulus Pion robot at Computex 2026. It’s running on a Panther Lake processor, using P-cores for real-time control, E-cores to collect sensor data, the GPU for vision-language-action models, and the NPU for continuous perception.

Intel Technology

10,752 görüntüleme • 2 ay önce

Everyday for the past 2 weeks, we've been sharing something new from GEN-1, our latest milestone in scaling robot learning. This has never been done before. Going from ideas to skills in days (or faster) is what physical AI models should deliver. More coming. Stay tuned. Read more about it in our blog post in the comments below ↓
0:42

Everyday for the past 2 weeks, we've been sharing something new from GEN-1, our latest milestone in scaling robot learning. This has never been done before. Going from ideas to skills in days (or faster) is what physical AI models should deliver. More coming. Stay tuned. Read more about it in our blog post in the comments below ↓

Generalist

39,593 görüntüleme • 3 ay önce

We’ve been collaborating with Physical Intelligence to deploy their models on our robots to automate order packing in real warehouses. With a sufficiently scoped and repetitive task, we have achieved a high level of reliable autonomy. This is an uncut, 1 minute time-lapse of a full 8-hour shift during which our robot ran autonomously 96.4% of the time. Thread below features some of our favorite moments [1/7]
1:00

We’ve been collaborating with Physical Intelligence to deploy their models on our robots to automate order packing in real warehouses. With a sufficiently scoped and repetitive task, we have achieved a high level of reliable autonomy. This is an uncut, 1 minute time-lapse of a full 8-hour shift during which our robot ran autonomously 96.4% of the time. Thread below features some of our favorite moments [1/7]

Ultra

56,053 görüntüleme • 5 ay önce

We’ve just stepped into the future. Our AI, CERE, no longer just talks… It walks, moves, and interacts with you in real time! Cere Thanks to our integration with Robot TEMI, CERE is now embodied as a physical being: Meet Robot CERE! And with its GenAI integration, it can now talk to you on the spot. We’ve brought artificial intelligence into the physical world. Unveiled today at the expo — Tomorrow, it might be in your home, your office, or even on the street. Get ready: Technology is no longer just code — Cerebrum Tech #CERE #RobotCERE #ArtificialIntelligence #Robotics #CerebrumTech #AI #FutureTech
0:49

We’ve just stepped into the future. Our AI, CERE, no longer just talks… It walks, moves, and interacts with you in real time! Cere Thanks to our integration with Robot TEMI, CERE is now embodied as a physical being: Meet Robot CERE! And with its GenAI integration, it can now talk to you on the spot. We’ve brought artificial intelligence into the physical world. Unveiled today at the expo — Tomorrow, it might be in your home, your office, or even on the street. Get ready: Technology is no longer just code — Cerebrum Tech #CERE #RobotCERE #ArtificialIntelligence #Robotics #CerebrumTech #AI #FutureTech

Dr. R.Erdem ERKUL

367,264 görüntüleme • 1 yıl önce

The showcase: a simulated workflow for a Serve Robotics delivery robot navigating Seoul on NAVER Maps, settling onchain through WDK on Solana A robot accessing a real-world digital service, making a real-time decision, and getting paid for it No human in the loop All verifiable onchain — check out the blog for links to transactions and wallets, with a video for illustration
1:43

The showcase: a simulated workflow for a Serve Robotics delivery robot navigating Seoul on NAVER Maps, settling onchain through WDK on Solana A robot accessing a real-world digital service, making a real-time decision, and getting paid for it No human in the loop All verifiable onchain — check out the blog for links to transactions and wallets, with a video for illustration

peaq

97,654 görüntüleme • 2 ay önce

🚀 We’re excited to announce LingBot-VA, a new state-of-the-art robot policy model from Robbyant ! LingBot-VA is built on a causal, autoregressive video-action world model for generalist robot control. Highlights: (1) First unified autoregressive video-action world model for robot control (2) Low-latency inference with a new asynchronous execution pipeline (3) SOTA on RoboTwin (92.9%, firstever > 90%) and LIBERO (98.5%) (4) +20% over π0.5 on challenging real-world long-horizon & high-precision tasks
1:51

🚀 We’re excited to announce LingBot-VA, a new state-of-the-art robot policy model from Robbyant ! LingBot-VA is built on a causal, autoregressive video-action world model for generalist robot control. Highlights: (1) First unified autoregressive video-action world model for robot control (2) Low-latency inference with a new asynchronous execution pipeline (3) SOTA on RoboTwin (92.9%, firstever > 90%) and LIBERO (98.5%) (4) +20% over π0.5 on challenging real-world long-horizon & high-precision tasks

Yinghao Xu

46,962 görüntüleme • 6 ay önce

I. Alright, mate! Check it out, we've got the ultimate deal for ya - the moveable version of our lovely Reimu with a built-in skeleton. And wait for it, you can even rock her with some fly outfits! It's time to get your hands on it! Don't miss this wicked opportunity, my friends!
1:12

I. Alright, mate! Check it out, we've got the ultimate deal for ya - the moveable version of our lovely Reimu with a built-in skeleton. And wait for it, you can even rock her with some fly outfits! It's time to get your hands on it! Don't miss this wicked opportunity, my friends!

Fumo Fumo

35,772 görüntüleme • 3 yıl önce

As you've seen all over our social media channels this week, we've been having fun creating content with the teams. And who doesn't love a good BLOOPER REEL from all the behind-the-scenes action?! Check it out ⤵️ #Brier2023
1:16

As you've seen all over our social media channels this week, we've been having fun creating content with the teams. And who doesn't love a good BLOOPER REEL from all the behind-the-scenes action?! Check it out ⤵️ #Brier2023

Curling Canada

15,852 görüntüleme • 3 yıl önce

Instantly tweak your web3 app style with Live Editing!🛠️ Change colours, text, or upload a new logo—just click, type, and save. Everything updates in real time. Check out how smooth and easy it is to use the "Edit" feature on #AgenticIDE👇
0:37

Instantly tweak your web3 app style with Live Editing!🛠️ Change colours, text, or upload a new logo—just click, type, and save. Everything updates in real time. Check out how smooth and easy it is to use the "Edit" feature on #AgenticIDE👇

IG Intern

51,874 görüntüleme • 1 yıl önce

The next generation of models won't just generate images - they'll understand worlds, motion, interaction, and action. We've been building toward this for a while. Visual intelligence is becoming real-time. Stephen spoke about where we're headed at AI Engineer:
2:12

The next generation of models won't just generate images - they'll understand worlds, motion, interaction, and action. We've been building toward this for a while. Visual intelligence is becoming real-time. Stephen spoke about where we're headed at AI Engineer:

Black Forest Labs

33,180 görüntüleme • 2 ay önce

This AI-powered robot dog from the U.S. Army’s C5ISR Center uses artificial intelligence to detect mines and threats, keeping our soldiers out of harms way. Come see it in action at the Great American State Fair for military appreciation day 🇺🇸
0:33

This AI-powered robot dog from the U.S. Army’s C5ISR Center uses artificial intelligence to detect mines and threats, keeping our soldiers out of harms way. Come see it in action at the Great American State Fair for military appreciation day 🇺🇸

Freedom 250

24,426 görüntüleme • 1 ay önce

With Pixel VIPs, you can stay even closer to the people you’re closest with¹ 🫶 💬See the last time you talked, including from WhatsApp 🎉Keep tabs on birthdays & important details 📍Check in with shared locations Head to our #PixelDrop blog for more:²
0:59

With Pixel VIPs, you can stay even closer to the people you’re closest with¹ 🫶 💬See the last time you talked, including from WhatsApp 🎉Keep tabs on birthdays & important details 📍Check in with shared locations Head to our #PixelDrop blog for more:²

Made by Google

22,411 görüntüleme • 1 yıl önce

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.
1:20

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 görüntüleme • 8 ay önce

Ten Years In The Making: Our Colony Sim Space Haven has Been Released as 1.0 Today! This game has been a true labor of love for us, and with our small team we've put everything we've got into it. Check out Space Haven on Steam:
1:15

Ten Years In The Making: Our Colony Sim Space Haven has Been Released as 1.0 Today! This game has been a true labor of love for us, and with our small team we've put everything we've got into it. Check out Space Haven on Steam:

Space Haven - 1.0 Full Release May 13th

50,474 görüntüleme • 2 ay önce

Excited to share our latest progress on legged manipulation with humanoids. We created a VR interface to remote control the Draco-3 robot 🤖, which cooks ramen for hungry graduate students at night. We can't wait for the day it will help us at home in the real world! #humanoid
1:24

Excited to share our latest progress on legged manipulation with humanoids. We created a VR interface to remote control the Draco-3 robot 🤖, which cooks ramen for hungry graduate students at night. We can't wait for the day it will help us at home in the real world! #humanoid

Yuke Zhu

68,317 görüntüleme • 3 yıl önce

(1/N) Content creators have been stuck with costly and slow video generation APIs for far too long. We couldn’t take it anymore.😅😭 FastVideo’s new real-time inference stack has the fastest 1080p TI2AV pipeline ever.😍🚀🚀 Our optimized LTX-2.3 pipeline creates 5-second 1080p videos with audio in 4.55 s, on a single GPU! 3.9x faster than the next fastest option. 🕹️Live demo: 📜Blog:
0:20

(1/N) Content creators have been stuck with costly and slow video generation APIs for far too long. We couldn’t take it anymore.😅😭 FastVideo’s new real-time inference stack has the fastest 1080p TI2AV pipeline ever.😍🚀🚀 Our optimized LTX-2.3 pipeline creates 5-second 1080p videos with audio in 4.55 s, on a single GPU! 3.9x faster than the next fastest option. 🕹️Live demo: 📜Blog:

Hao AI Lab

29,900 görüntüleme • 4 ay önce