Video yükleniyor...

Video Yüklenemedi

Ana Sayfaya Dön

We developed RECAP Physical Intelligence to apply RL and interventions to π0.6, achieving high success rates and throughput on several challenging tasks! Watching these policies operate successfully for hours gives an appreciation for what the method can do

michael_equi's profile picture

Michael Equi

1,331 subscribers

14,241 görüntüleme • 8 ay önce •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

0 Yorum

Yorum bulunmuyor

Orijinal gönderinin yorumları burada görünecek

Benzer Videolar

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.
2:15

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

438,403 görüntüleme • 4 ay önce

A Surat-based startup has developed high-tech attack drones for Indian Army. These Trikal drones are designed to monitor and strike enemy targets in the most challenging environments. It can fly for up to two hours and carry a payload of around 11 kilograms.
2:13

A Surat-based startup has developed high-tech attack drones for Indian Army. These Trikal drones are designed to monitor and strike enemy targets in the most challenging environments. It can fly for up to two hours and carry a payload of around 11 kilograms.

News Arena India

55,015 görüntüleme • 1 yıl önce

Good News : A Surat-based startup has developed high-tech attack drones for Indian Army. These Trikal drones are designed to monitor and strike enemy targets in the most challenging environments. It can fly for up to two hours and carry a payload of around 11 kilograms.
2:14

Good News : A Surat-based startup has developed high-tech attack drones for Indian Army. These Trikal drones are designed to monitor and strike enemy targets in the most challenging environments. It can fly for up to two hours and carry a payload of around 11 kilograms.

Baba Banaras™

44,703 görüntüleme • 1 yıl önce

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.
1:41

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

26,198 görüntüleme • 1 yıl önce

Learning dexterous policies from human videos is challenging due to differences between human and robot hands. We present HuDOR, a method that learns dexterous policies within the robot's physical constraints using just one human video and an hour of online interactions! [1/n]
1:48

Learning dexterous policies from human videos is challenging due to differences between human and robot hands. We present HuDOR, a method that learns dexterous policies within the robot's physical constraints using just one human video and an hour of online interactions! [1/n]

Irmak Guzey

65,121 görüntüleme • 1 yıl önce

[1/16] The real world is large, and we want our AI models to operate on the scale of reality. Over the past two years, my colleagues and I have developed fVDB, a deep learning framework for large-scale, high performance spatial intelligence. We finally announced this work at SIGGRAPH and have released the framework in early access. Here’s a small tour of what fVDB is, and what we’ve used it to do.
3:19

[1/16] The real world is large, and we want our AI models to operate on the scale of reality. Over the past two years, my colleagues and I have developed fVDB, a deep learning framework for large-scale, high performance spatial intelligence. We finally announced this work at SIGGRAPH and have released the framework in early access. Here’s a small tour of what fVDB is, and what we’ve used it to do.

Francis Williams

33,898 görüntüleme • 2 yıl önce

Claude Code /simplify is now /code-review Now accepts an effort parameter: - low: short, scoped, latency-sensitive tasks that aren't intelligence-sensitive - medium: cost-sensitive work that can trade off some intelligence for fewer tokens - high: balances tokens and intelligence. Minimum for intelligence-sensitive work, or to cut spend vs xhigh - xhigh: best results for most coding and agentic tasks. Recommended default on Opus 4.7 - max: can improve performance on demanding tasks but shows diminishing returns and tends to overthink. Test before adopting broadly
0:24

Claude Code /simplify is now /code-review Now accepts an effort parameter: - low: short, scoped, latency-sensitive tasks that aren't intelligence-sensitive - medium: cost-sensitive work that can trade off some intelligence for fewer tokens - high: balances tokens and intelligence. Minimum for intelligence-sensitive work, or to cut spend vs xhigh - xhigh: best results for most coding and agentic tasks. Recommended default on Opus 4.7 - max: can improve performance on demanding tasks but shows diminishing returns and tends to overthink. Test before adopting broadly

Daniel San

85,822 görüntüleme • 2 ay önce

I’m really hoping there is an appreciation for what we are watching Ohio State and Ryan Day do in real time, and the effects it’s having on opposing coaching staffs…
0:57

I’m really hoping there is an appreciation for what we are watching Ohio State and Ryan Day do in real time, and the effects it’s having on opposing coaching staffs…

Kris Drew

40,806 görüntüleme • 8 ay önce

Uganda's long journey to its current development is strategically based on the available resources over time, which is why the government has steadily managed to achieve real development. Now, we need to address the issue of free education. We are at risk due to the high dropout rates among our children, right from primary school. While several strategies may make developmental sense, I strongly believe that free education for all, PDM, and the Emyooga are critical programs for achieving socio-economic transformation. These initiatives involve everyone and can drive progress for our society.
1:45

Uganda's long journey to its current development is strategically based on the available resources over time, which is why the government has steadily managed to achieve real development. Now, we need to address the issue of free education. We are at risk due to the high dropout rates among our children, right from primary school. While several strategies may make developmental sense, I strongly believe that free education for all, PDM, and the Emyooga are critical programs for achieving socio-economic transformation. These initiatives involve everyone and can drive progress for our society.

Yoweri K Museveni

14,869 görüntüleme • 1 yıl önce

Super impressive, this AI agent can use the web browser like a human. Just describe what you want it to do, and it will automatically operate Chrome for you to achieve your task. Apply for early access to HyperWrite:
0:37

Super impressive, this AI agent can use the web browser like a human. Just describe what you want it to do, and it will automatically operate Chrome for you to achieve your task. Apply for early access to HyperWrite:

Lior Alexander

217,712 görüntüleme • 3 yıl önce

We have news! We created a new robotics model called Loop Model 1. On the zip-tie insertion task, it achieves 20x more throughput per unit of data than "Pi06 + RLT" from Physical Intelligence, a top model for such tasks. It’s the missing piece that makes MicroFactory work, because now deployment becomes so simple and fast that our users can do it themselves.
3:35

We have news! We created a new robotics model called Loop Model 1. On the zip-tie insertion task, it achieves 20x more throughput per unit of data than "Pi06 + RLT" from Physical Intelligence, a top model for such tasks. It’s the missing piece that makes MicroFactory work, because now deployment becomes so simple and fast that our users can do it themselves.

Igor Kulakov (MicroFactory)

76,738 görüntüleme • 2 ay önce

National Truck Driver Appreciation Week is such an important time for us at U.S. Department of Transportation to talk to truckers about what we can do to support them. These men and women keep our store shelves stocked and America moving day and night, rain or shine. We thank them for their work! 🚚🇺🇸
0:40

National Truck Driver Appreciation Week is such an important time for us at U.S. Department of Transportation to talk to truckers about what we can do to support them. These men and women keep our store shelves stocked and America moving day and night, rain or shine. We thank them for their work! 🚚🇺🇸

Secretary Sean Duffy

131,607 görüntüleme • 10 ay önce

Knights we’ve 10 hours before voting lines closes Have you voted for kola? Do you think the vote is enough or better to apply more pressure? It’s the last hours of voting and we need to apply more pressure and vote for kola!! VOTE FOR KOLA #KolaOmotoso #BBNaija
0:31

Knights we’ve 10 hours before voting lines closes Have you voted for kola? Do you think the vote is enough or better to apply more pressure? It’s the last hours of voting and we need to apply more pressure and vote for kola!! VOTE FOR KOLA #KolaOmotoso #BBNaija

Kola Omotoso

42,705 görüntüleme • 11 ay önce

I attended school for 7 hours today and I accomplished 5 tasks within the first 30 minutes. If a high school senior can do this, federal government employees have no excuse to not do the same!
0:21

I attended school for 7 hours today and I accomplished 5 tasks within the first 30 minutes. If a high school senior can do this, federal government employees have no excuse to not do the same!

Brilyn Hollyhand

1,781,736 görüntüleme • 1 yıl önce

18-18 Hours of Work.....What a Dedication: From showing Green Flags to Buses to This.....Such Important tasks for the Nation!!! Only a True Nationalist and Patriot can do such Jobs...
0:25

18-18 Hours of Work.....What a Dedication: From showing Green Flags to Buses to This.....Such Important tasks for the Nation!!! Only a True Nationalist and Patriot can do such Jobs...

𝐒𝐢𝐝𝐝

78,174 görüntüleme • 9 ay önce

RL is a powerful mechanism for training company-specific models on their unique work and data. This is what we do at Applied Compute. A key challenge is how to make RL efficient, because we need runs to be fast (delivered in days), cheap (scalable unit economics), and predictable (not just fast, but reliably fast). Here are some takeaways: • Synchronous RL is wasteful with time and compute. • Asynchronous RL is more efficient but introduces staleness, which causes learning instabilities. • Modeling and simulations can help analytically solve for what configuration leads to optimal efficiency. This allows us to rapidly prototype training configurations, without burning expensive compute cycles on trial runs. Two of our co-founders, Rhythm Garg and Linden Li, discussed some of this research at AI Engineer recently, with a focus on the following subproblem: what is the highest throughput way to do RL given a maximum staleness and compute budget?
20:12

RL is a powerful mechanism for training company-specific models on their unique work and data. This is what we do at Applied Compute. A key challenge is how to make RL efficient, because we need runs to be fast (delivered in days), cheap (scalable unit economics), and predictable (not just fast, but reliably fast). Here are some takeaways: • Synchronous RL is wasteful with time and compute. • Asynchronous RL is more efficient but introduces staleness, which causes learning instabilities. • Modeling and simulations can help analytically solve for what configuration leads to optimal efficiency. This allows us to rapidly prototype training configurations, without burning expensive compute cycles on trial runs. Two of our co-founders, Rhythm Garg and Linden Li, discussed some of this research at AI Engineer recently, with a focus on the following subproblem: what is the highest throughput way to do RL given a maximum staleness and compute budget?

Applied Compute

45,555 görüntüleme • 8 ay önce

Today I’m excited to introduce micro1 Intelligence, the world’s most advanced platform for training frontier AI models. Achieving AGI is bottlenecked by one main thing: high-quality data. Data based on real-world environments that capture human expert workflows, complex decision-making, and reward signals models need to learn. With micro1 Intelligence, frontier labs can train on RL environments across every subject matter all in one place.
1:33

Today I’m excited to introduce micro1 Intelligence, the world’s most advanced platform for training frontier AI models. Achieving AGI is bottlenecked by one main thing: high-quality data. Data based on real-world environments that capture human expert workflows, complex decision-making, and reward signals models need to learn. With micro1 Intelligence, frontier labs can train on RL environments across every subject matter all in one place.

Ali Ansari

332,794 görüntüleme • 8 ay önce

Sim2Real RL for Vision-Based Dexterous Manipulation on Humanoids TLDR - we train a humanoid robot with two multifingered hands to perform a range of dexterous manipulation tasks robust generalization and high performance without human demonstration :D
0:20

Sim2Real RL for Vision-Based Dexterous Manipulation on Humanoids TLDR - we train a humanoid robot with two multifingered hands to perform a range of dexterous manipulation tasks robust generalization and high performance without human demonstration :D

Toru

49,561 görüntüleme • 1 yıl önce

Historically, RL policies for robots have been trained in synthetic, untextured environments, limiting perceptive policies to depth images where the sim-to-real gap is manageable. RGB has always had more potential, but leveraging it to train policies in simulation remained an open problem. Partnering with Niantic Spatial 🌎 and NVIDIA Robotics, we built a pipeline that addresses exactly that. We can now scan a real deployment site with off-the-shelf hardware, reconstruct it into a photorealistic Gaussian splat, and run massively parallel RL training. The policies trained in our Gym environment then transfer zero-shot to the real robot and environments they were trained for. This enables faster deployment of more capable and robust policies for the end user. The new resulting capabilities are a big step towards solving sim-to-real and also apply well beyond navigation. Read the full technical breakdown on our blog; link in the comments. #HumanoidRobots #Flexion #NianticSpatial #NVIDIA
1:21

Historically, RL policies for robots have been trained in synthetic, untextured environments, limiting perceptive policies to depth images where the sim-to-real gap is manageable. RGB has always had more potential, but leveraging it to train policies in simulation remained an open problem. Partnering with Niantic Spatial 🌎 and NVIDIA Robotics, we built a pipeline that addresses exactly that. We can now scan a real deployment site with off-the-shelf hardware, reconstruct it into a photorealistic Gaussian splat, and run massively parallel RL training. The policies trained in our Gym environment then transfer zero-shot to the real robot and environments they were trained for. This enables faster deployment of more capable and robust policies for the end user. The new resulting capabilities are a big step towards solving sim-to-real and also apply well beyond navigation. Read the full technical breakdown on our blog; link in the comments. #HumanoidRobots #Flexion #NianticSpatial #NVIDIA

Flexion

70,564 görüntüleme • 17 gün önce