Загрузка видео...

Не удалось загрузить видео

На главную

A while back Benjie Holson described a set of "Robot Olympics" challenge tasks -- washing a pan, making a peanut butter sandwich, and more. We tried to fine-tune our models at PI to these tasks, and found that we could do most of them. A few highlights below.

svlevine's profile picture

Sergey Levine

134,842 subscribers

81,353 просмотров • 8 месяцев назад •via X (Twitter)

ОбразованиеНаука и технологии
LIVE

Anya Rossi• Live Now

Private livecam show

Комментарии: 0

Нет доступных комментариев

Здесь появятся комментарии из оригинального поста

Похожие видео

Evaluation is a critical bottleneck in building robot foundation models. Check out our latest work RoboLab, led by Xuning Yang, which addresses this exact challenge. Its a high-fidelity simulation environment for testing these models. A truly generalist policy should be able to complete these tasks zero-shot, and this benchmark highlights exactly how far we still have to go. More info 👇
0:26

Evaluation is a critical bottleneck in building robot foundation models. Check out our latest work RoboLab, led by Xuning Yang, which addresses this exact challenge. Its a high-fidelity simulation environment for testing these models. A truly generalist policy should be able to complete these tasks zero-shot, and this benchmark highlights exactly how far we still have to go. More info 👇

Ankit Goyal

29,910 просмотров • 4 месяцев назад

Snuggles first birthday. He got sung to a few times that day and we made him a special peanut butter and pumpkin cake #SaveSnuggles
0:25

Snuggles first birthday. He got sung to a few times that day and we made him a special peanut butter and pumpkin cake #SaveSnuggles

Jennifer Evancho

21,588 просмотров • 1 месяц назад

📁 Dario Amodei, CEO of Anthropic, says we are approaching a country of geniuses inside a data center. AI agents could soon surpass most humans at most tasks and coordinate at superhuman speed. That could cure disease and lift billions out of poverty. Or it could amplify misuse, autonomy and economic disruption at a scale we have never faced.
1:00

📁 Dario Amodei, CEO of Anthropic, says we are approaching a country of geniuses inside a data center. AI agents could soon surpass most humans at most tasks and coordinate at superhuman speed. That could cure disease and lift billions out of poverty. Or it could amplify misuse, autonomy and economic disruption at a scale we have never faced.

Jon Hernandez

22,350 просмотров • 6 месяцев назад

Meet Dobb·E: a home robot system that needs just 5 minutes of human teaching to learn new tasks. Dobb·E has visited 10 homes, learned 100+ tasks, and we are just getting started! Dobb·E is fully open-sourced (including hardware, models, and software): 🧵
1:14

Meet Dobb·E: a home robot system that needs just 5 minutes of human teaching to learn new tasks. Dobb·E has visited 10 homes, learned 100+ tasks, and we are just getting started! Dobb·E is fully open-sourced (including hardware, models, and software): 🧵

Lerrel Pinto

211,736 просмотров • 2 лет назад

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

440,982 просмотров • 5 месяцев назад

Vision-language models perform diverse tasks via in-context learning. Time for robots to do the same! Introducing In-Context Robot Transformer (ICRT): a robot policy that learns new tasks by prompting with robot trajectories, without any fine-tuning. [1/N]
0:25

Vision-language models perform diverse tasks via in-context learning. Time for robots to do the same! Introducing In-Context Robot Transformer (ICRT): a robot policy that learns new tasks by prompting with robot trajectories, without any fine-tuning. [1/N]

Max Fu

40,466 просмотров • 2 лет назад

1/ A protein is a nanomachine - moving parts, does real work, changes shape to do its job. A gene editor is one of them: a molecular machine that hunts down a stretch of DNA and cuts it. We still borrow these machines from nature and tune them, because we don't understand them well enough to build our own. We started Mandrake to change that.
1:20

1/ A protein is a nanomachine - moving parts, does real work, changes shape to do its job. A gene editor is one of them: a molecular machine that hunts down a stretch of DNA and cuts it. We still borrow these machines from nature and tune them, because we don't understand them well enough to build our own. We started Mandrake to change that.

Tanay Lohia

47,366 просмотров • 1 месяц назад

Close-up A few years back while with a different streaming service we created close-up versions of a few episodes. Now that we have the space, we are creating a new Catalog for those episodes. We have a few uploaded and a few more to come.
0:51

Close-up A few years back while with a different streaming service we created close-up versions of a few episodes. Now that we have the space, we are creating a new Catalog for those episodes. We have a few uploaded and a few more to come.

Testing4Laughs

21,921 просмотров • 2 лет назад

Claude Tasks are more powerful than I expected. Spent a few hours testing them against Ralph. The difference? When to use each? How to get the most out of them? Here's what I found:
7:30

Claude Tasks are more powerful than I expected. Spent a few hours testing them against Ralph. The difference? When to use each? How to get the most out of them? Here's what I found:

Mac Martine

24,385 просмотров • 7 месяцев назад

Excited to announce RoboCasa, a large-scale simulation framework of everyday tasks! We use generative AI tools to create diverse objects, scenes, and tasks. Simulation plays a pivotal role in our Data Pyramid for training generalist robots. Open-source at
0:34

Excited to announce RoboCasa, a large-scale simulation framework of everyday tasks! We use generative AI tools to create diverse objects, scenes, and tasks. Simulation plays a pivotal role in our Data Pyramid for training generalist robots. Open-source at

Yuke Zhu

141,540 просмотров • 2 лет назад

A new way to fine tune: Preference Fine-Tuning. Customize models by comparing responses, rather than fixed targets—ideal for subjective tasks where tone, style, and creativity matter.
3:41

A new way to fine tune: Preference Fine-Tuning. Customize models by comparing responses, rather than fixed targets—ideal for subjective tasks where tone, style, and creativity matter.

OpenAI Developers

199,296 просмотров • 1 год назад

Prior to release, we shared a version of Cohere North Mini Code with AI engineers and answered some questions. Here's a quick illustrated walkthrough of the model's architecture and training process. Small models fill an important niche. They: 1. run on more widely available hardware 2. handle tasks within a certain range of complexity 3. take on sub-tasks that larger models delegate
4:53

Prior to release, we shared a version of Cohere North Mini Code with AI engineers and answered some questions. Here's a quick illustrated walkthrough of the model's architecture and training process. Small models fill an important niche. They: 1. run on more widely available hardware 2. handle tasks within a certain range of complexity 3. take on sub-tasks that larger models delegate

Jay Alammar

89,074 просмотров • 2 месяцев назад

AI only has pre-schooler level capabilities for visual tasks. "The frontier models—the best of them—still reason around the age of a preschooler, and any elementary school kid in that benchmark was able to beat all the frontier models on these visual tasks." "These are tasks that are not just object recognition. It's about spatial reasoning... tasks like navigating through the maze…” — Andrew M. Dai, CEO of Elorian
0:49

AI only has pre-schooler level capabilities for visual tasks. "The frontier models—the best of them—still reason around the age of a preschooler, and any elementary school kid in that benchmark was able to beat all the frontier models on these visual tasks." "These are tasks that are not just object recognition. It's about spatial reasoning... tasks like navigating through the maze…” — Andrew M. Dai, CEO of Elorian

The Information

25,934 просмотров • 1 месяц назад

A few months back, together with my family, we visited the marginalized Batwa community at Mpeerwa Camp in Nyakabande, Kisoro District. Amongst other problems, their main challenge is access to clean water. I pledged to support them, and yesterday our team delivered the 10,000 litre water-tank to them. While we strive to change our country and have a better governed society, it's important that we do the little we can to improve the lives of our people as we struggle to change their lives fundamentally.
1:22

A few months back, together with my family, we visited the marginalized Batwa community at Mpeerwa Camp in Nyakabande, Kisoro District. Amongst other problems, their main challenge is access to clean water. I pledged to support them, and yesterday our team delivered the 10,000 litre water-tank to them. While we strive to change our country and have a better governed society, it's important that we do the little we can to improve the lives of our people as we struggle to change their lives fundamentally.

BOBI WINE

161,358 просмотров • 2 лет назад

Every home is different. That means that to build a useful home robot, we must be able to perform zero-shot generalization on a wide range of tasks. Humanoid company 1X has a solution: world models. 1X Director of Evaluations Daniel Ho joins us on RoboPapers to talk about: - why world models are the future for scaling robot learning - how to use world models for robot control - what world models unlock for evaluating robot model performance - how we can hill-climb from here to general purpose robots Watch Episode #61 of RoboPapers, with Michael Cho - Rbt/Acc and Chris Paxton, now!
54:52

Every home is different. That means that to build a useful home robot, we must be able to perform zero-shot generalization on a wide range of tasks. Humanoid company 1X has a solution: world models. 1X Director of Evaluations Daniel Ho joins us on RoboPapers to talk about: - why world models are the future for scaling robot learning - how to use world models for robot control - what world models unlock for evaluating robot model performance - how we can hill-climb from here to general purpose robots Watch Episode #61 of RoboPapers, with Michael Cho - Rbt/Acc and Chris Paxton, now!

RoboPapers

27,567 просмотров • 6 месяцев назад

Boston Dynamics has released a new video of their next-generation humanoid robot, Atlas. "We are excited to share some of our progress on developing Large Behavior Models for Atlas. This work is part of a collaboration between AI research teams at Toyota Research Institute (TRI) and Boston Dynamics. We have been building end-to-end language-conditioned policies that enable Atlas to accomplish long-horizon manipulation tasks."
2:02

Boston Dynamics has released a new video of their next-generation humanoid robot, Atlas. "We are excited to share some of our progress on developing Large Behavior Models for Atlas. This work is part of a collaboration between AI research teams at Toyota Research Institute (TRI) and Boston Dynamics. We have been building end-to-end language-conditioned policies that enable Atlas to accomplish long-horizon manipulation tasks."

Sawyer Merritt

200,744 просмотров • 1 год назад

Here is the full run of MicroFactory, that autonomously assembles a photo frame - a real product sold on Amazon. This is a good example of how to deal with complex tasks, while we do not yet have a large set of robotic data to train a big general ai model. Thread:
4:35

Here is the full run of MicroFactory, that autonomously assembles a photo frame - a real product sold on Amazon. This is a good example of how to deal with complex tasks, while we do not yet have a large set of robotic data to train a big general ai model. Thread:

Igor Kulakov (MicroFactory)

209,612 просмотров • 10 месяцев назад

How do we make dexterous hands handle both power and precision tasks with ease? 🫳👌🫰 We introduce Power to Precision (💪➡️🎯), our new paper that optimizes both control and fingertip geometry to unlock robust manipulation from power grasp to fine-grained manipulations. With simplified finger motions and augmented fingertips, the hand can perform diverse motions from pinching a nut🔩 to handling a pan🍳. Check the demos below🎥.
0:37

How do we make dexterous hands handle both power and precision tasks with ease? 🫳👌🫰 We introduce Power to Precision (💪➡️🎯), our new paper that optimizes both control and fingertip geometry to unlock robust manipulation from power grasp to fine-grained manipulations. With simplified finger motions and augmented fingertips, the hand can perform diverse motions from pinching a nut🔩 to handling a pan🍳. Check the demos below🎥.

Jianglong Ye

110,391 просмотров • 9 месяцев назад