正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

Having humans annotate data to pre-train robots is expensive and time-consuming! Introducing SPRINT: A pre-training approach using LLMs and offline RL to equip robots w/ many language-annotated skills while minimizing human annotation effort! URL: 🧵👇

Jesse Zhang

2,065 subscribers

24,725 次观看 • 3 年前 •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

7 条评论

Jesse Zhang 的头像

Jesse Zhang3 年前

Labeling demonstrations with natural language instructions in hindsight is standard, but it is tedious and expensive to scale. We propose automatically (1) **relabeling** language instructions and (2) **chaining** trajectories together to generate more training data.

Jesse Zhang 的头像

Jesse Zhang3 年前

(1) Relabeling: If we have two skills, "Put mug in coffee machine" and "Press brew button," we could call this "Make Coffee." In SPRINT, we do this relabeling **automatically** by prompting an LLM to summarize nearby instructions. This gives us 2-2.5X more pre-training data!

Jesse Zhang 的头像

Jesse Zhang3 年前

(2) Chaining: Offline RL can "stitch" trajectories to learn new behaviors. We carefully relabel rewards with offline RL and modified language instructions to allow stitching even with language conditioning!

Jesse Zhang 的头像

Jesse Zhang3 年前

Results Overall, this allows us to achieve 2-8X better zero-shot long horizon task execution in ALFRED, a realistic household simulator, and on a real robot setup! SPRINT agents also fine-tune more efficiently to new tasks in unseen environments! ALFRED results:

Jesse Zhang 的头像

Jesse Zhang3 年前

Real Robot Results With offline fine-tuning, SPRINT achieves superior performance on new, long-horizon manipulation tasks in previously unseen environments!

Jesse Zhang 的头像

Jesse Zhang3 年前

For more details about SPRINT and experiment results, please see our paper or website. Paper: Website: Work done in collaboration with @KarlPertsch, @JiahuiZhang_32, @JosephLim_AI. @JiahuiZhang_32 is applying for PhD this year!

OliviaLi 的头像

OliviaLi3 年前

It sounds great, so that humans don't have to complete such a large amount of work every day, just let the robot do it

相关视频

How to teach robots to perform long-horizon tasks efficiently and robustly🦾? Introducing MimicPlay - an imitation learning algorithm that uses "cheap human play data". Our approach unlocks both real-time planning through raw perception and strong robustness to disturbances!🧵👇

How to teach robots to perform long-horizon tasks efficiently and robustly🦾? Introducing MimicPlay - an imitation learning algorithm that uses "cheap human play data". Our approach unlocks both real-time planning through raw perception and strong robustness to disturbances!🧵👇

Chen Wang

288,817 次观看 • 3 年前

Wouldn't it be great if we could train robots without any teleoperation! In our latest paper, we train robots to mimic a human video of the task by simply matching the object features using RL. We only need one video and under an hour of robot training.

Wouldn't it be great if we could train robots without any teleoperation! In our latest paper, we train robots to mimic a human video of the task by simply matching the object features using RL. We only need one video and under an hour of robot training.

Lerrel Pinto

46,221 次观看 • 1 年前

HDMI (HumanoiD iMitation for Interaction) is a framework enabling humanoid robots to learn whole-body object interaction skills from monocular RGB human videos. It extracts and retargets human poses and object trajectories using GVHMR and LocoMujoco, building reference datasets with contact annotations. The data is used to train an RL policy via robot-object co-tracking. HDMI achieved 67 consecutive door traversals.

HDMI (HumanoiD iMitation for Interaction) is a framework enabling humanoid robots to learn whole-body object interaction skills from monocular RGB human videos. It extracts and retargets human poses and object trajectories using GVHMR and LocoMujoco, building reference datasets with contact annotations. The data is used to train an RL policy via robot-object co-tracking. HDMI achieved 67 consecutive door traversals.

The Humanoid Hub

17,395 次观看 • 1 年前

Amazon is training humanoids to move boxes. Makes sense! OmniRetarget is a data generation engine that enables complex loco-manipulation for humanoids. It uses offline retargeting from human MoCap datasets and augments data from single demos to produce 8 hours of trajectories that train RL policies in simulation, transferred zero-shot to real robots. Amazon FAR is the primary affiliation for the paper:

Amazon is training humanoids to move boxes. Makes sense! OmniRetarget is a data generation engine that enables complex loco-manipulation for humanoids. It uses offline retargeting from human MoCap datasets and augments data from single demos to produce 8 hours of trajectories that train RL policies in simulation, transferred zero-shot to real robots. Amazon FAR is the primary affiliation for the paper:

The Humanoid Hub

106,447 次观看 • 1 年前

One of the biggest bottlenecks in deploying visual AI and computer vision is annotation, which can be both costly and time-consuming. Today, we’re introducing Verified Auto Labeling, a new approach to AI-assisted annotation that achieves up to 95% of human-level performance while cutting labeling costs by up to 100,000x and time by 5,000x. Read the full paper:

One of the biggest bottlenecks in deploying visual AI and computer vision is annotation, which can be both costly and time-consuming. Today, we’re introducing Verified Auto Labeling, a new approach to AI-assisted annotation that achieves up to 95% of human-level performance while cutting labeling costs by up to 100,000x and time by 5,000x. Read the full paper:

Voxel51

12,851 次观看 • 1 年前

Introducing PointZero—a 3D world model pre-trained without robots. Dexterous manipulation requires understanding diverse 3D dynamics, but current approaches rely on expensive robot data. So how can we pre-train a 3D dynamics model without it? PointZero introduces a simple idea: learning to complete 3D point tracks yields transferable 3D dynamics! Our model achieves SOTA results on: 🔥 Zero-shot 3D dynamics 🔥 Action-conditioned 3D dynamics (post-training) 🔥 Imitation learning (post-training) Details and links 👇 1/6

Introducing PointZero—a 3D world model pre-trained without robots. Dexterous manipulation requires understanding diverse 3D dynamics, but current approaches rely on expensive robot data. So how can we pre-train a 3D dynamics model without it? PointZero introduces a simple idea: learning to complete 3D point tracks yields transferable 3D dynamics! Our model achieves SOTA results on: 🔥 Zero-shot 3D dynamics 🔥 Action-conditioned 3D dynamics (post-training) 🔥 Imitation learning (post-training) Details and links 👇 1/6

Bardienus Duisterhof

28,818 次观看 • 27 天前

Brain-controlled exoskeletons to train humanoid robots! 🧠 Fourier just presented human tele-operators using brain control interfaces and exoskeletal arms to train humanoid robots on home tasks. The brain control interface is the interesting part. Instead of using a controller or joystick to teleoperate, the operator's movements and intentions are captured more naturally through the exoskeleton and BCI. This means the demonstrations are more fluid, more human-like, and better suited for training robots to perform delicate home tasks. Multiple tele-operators are simultaneously generating training data across multiple robots. This is how you build the dataset needed for eventual full autonomy, without waiting years for it to arrive. This might be the bridge between "robots that work in controlled environments" and "robots that work in homes." Not full autonomy right away, but trusted human intelligence operating through a robot body, getting better with every task completed. ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →

Brain-controlled exoskeletons to train humanoid robots! 🧠 Fourier just presented human tele-operators using brain control interfaces and exoskeletal arms to train humanoid robots on home tasks. The brain control interface is the interesting part. Instead of using a controller or joystick to teleoperate, the operator's movements and intentions are captured more naturally through the exoskeleton and BCI. This means the demonstrations are more fluid, more human-like, and better suited for training robots to perform delicate home tasks. Multiple tele-operators are simultaneously generating training data across multiple robots. This is how you build the dataset needed for eventual full autonomy, without waiting years for it to arrive. This might be the bridge between "robots that work in controlled environments" and "robots that work in homes." Not full autonomy right away, but trusted human intelligence operating through a robot body, getting better with every task completed. ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →

Lukas Ziegler

21,042 次观看 • 8 个月前

We discovered an emergent property of VLAs like π0/π0.5/π0.6: as we scale up pre-training, the model learns to align human videos and robot data! This gives us a simple way to leverage human videos. Once π0.5 knows how to control robots, it can naturally learn from human video.

We discovered an emergent property of VLAs like π0/π0.5/π0.6: as we scale up pre-training, the model learns to align human videos and robot data! This gives us a simple way to leverage human videos. Once π0.5 knows how to control robots, it can naturally learn from human video.

Physical Intelligence

1,188,389 次观看 • 10 个月前

𝗛𝘂𝗺𝘆𝗻𝗹𝗮𝗯𝘀 𝗶𝘀 𝗰𝗿𝗲𝗮𝘁𝗶𝗻𝗴 𝗮 𝗱𝗮𝘁𝗮 𝗽𝗹𝗮𝘁𝗳𝗼𝗿𝗺 𝗳𝗼𝗿 𝗽𝗵𝘆𝘀𝗶𝗰𝗮𝗹 𝗔𝗜. They collect thousands of hours of real human activities like what people see, hear, move, and feel and turn it into clean training data for robots. Unlike language models that learn from the internet, robots need real world experience for messy everyday tasks such as ironing while a child runs past, restocking shelves in a crowded store, or assembling parts on a busy factory floor. Humyn Labs' approach uses four sensory streams captured in actual environments so robots can learn practical skills from human experience.

𝗛𝘂𝗺𝘆𝗻𝗹𝗮𝗯𝘀 𝗶𝘀 𝗰𝗿𝗲𝗮𝘁𝗶𝗻𝗴 𝗮 𝗱𝗮𝘁𝗮 𝗽𝗹𝗮𝘁𝗳𝗼𝗿𝗺 𝗳𝗼𝗿 𝗽𝗵𝘆𝘀𝗶𝗰𝗮𝗹 𝗔𝗜. They collect thousands of hours of real human activities like what people see, hear, move, and feel and turn it into clean training data for robots. Unlike language models that learn from the internet, robots need real world experience for messy everyday tasks such as ironing while a child runs past, restocking shelves in a crowded store, or assembling parts on a busy factory floor. Humyn Labs' approach uses four sensory streams captured in actual environments so robots can learn practical skills from human experience.

𝐓𝐡𝐞𝐎𝐧𝐥𝐲𝟏𝐇𝐞𝐫𝐨👑

18,514 次观看 • 1 个月前

Introducing LDA, a latent world action foundation model that, for the first time, unifies the utilization of heterogeneous embodied data across simulation and reality, humans and robots, and varying levels of action quality and annotation. By breaking long-standing data silos in embodied intelligence, LDA enables the field, much like GPT did for language, to benefit continuously from scaling data, marking the transition into a new era of scalable learning. #Galbot #Robotics #Innovation #AI #Technology #Humanoid #WorldModel

Introducing LDA, a latent world action foundation model that, for the first time, unifies the utilization of heterogeneous embodied data across simulation and reality, humans and robots, and varying levels of action quality and annotation. By breaking long-standing data silos in embodied intelligence, LDA enables the field, much like GPT did for language, to benefit continuously from scaling data, marking the transition into a new era of scalable learning. #Galbot #Robotics #Innovation #AI #Technology #Humanoid #WorldModel

Galbot

40,883 次观看 • 5 个月前

🤖 Robotics often faces a chicken and egg problem: no web-scale robot data for training (unlike CV or NLP) b/c robots aren't deployed yet & vice-versa. Introducing VRB: Use large-scale human videos to train a *general-purpose* affordance model to jumpstart any robotics paradigm!

🤖 Robotics often faces a chicken and egg problem: no web-scale robot data for training (unlike CV or NLP) b/c robots aren't deployed yet & vice-versa. Introducing VRB: Use large-scale human videos to train a general-purpose affordance model to jumpstart any robotics paradigm!

Deepak Pathak

70,743 次观看 • 3 年前

NEWS: DeepMind teaches robots to play soccer. In a paper released today Google's DeepMind details how they used Deep Reinforcement Learning (Deep RL) to train low-cost, miniature humanoid robots in dynamic environments, allowing them to play a simplified one-versus-one (1v1) soccer game. The robots, equipped with 20 actuated joints, were initially trained in simulation using the MuJoCo physics engine. Through this training, they learned robust and dynamic movement skills like rapid fall recovery, walking, turning, and kicking. The robots seamlessly transitioned between these skills, even surpassing expectations, and developed a basic strategic understanding of the game. During matches, the trained robots demonstrated agile skills such as turning, kicking moving balls, and dynamic defensive blocking. They quickly combined these skills, showcasing their adaptability and outperforming scripted baselines. The robots walked faster, got up quicker, and kicked faster than their counterparts. Individual skills were first trained in isolation within the simulation environment, and then composed in a self-play setting. The robots successfully transferred these skills to real-world scenarios. Full paper can be found here:

NEWS: DeepMind teaches robots to play soccer. In a paper released today Google's DeepMind details how they used Deep Reinforcement Learning (Deep RL) to train low-cost, miniature humanoid robots in dynamic environments, allowing them to play a simplified one-versus-one (1v1) soccer game. The robots, equipped with 20 actuated joints, were initially trained in simulation using the MuJoCo physics engine. Through this training, they learned robust and dynamic movement skills like rapid fall recovery, walking, turning, and kicking. The robots seamlessly transitioned between these skills, even surpassing expectations, and developed a basic strategic understanding of the game. During matches, the trained robots demonstrated agile skills such as turning, kicking moving balls, and dynamic defensive blocking. They quickly combined these skills, showcasing their adaptability and outperforming scripted baselines. The robots walked faster, got up quicker, and kicked faster than their counterparts. Individual skills were first trained in isolation within the simulation environment, and then composed in a self-play setting. The robots successfully transferred these skills to real-world scenarios. Full paper can be found here:

Dave Lee

372,039 次观看 • 3 年前

TWIST: a real-time teleoperation system for humanoid robots to mimic whole-body motions. Reference motion data is generated by retargeting human motion-capture data to the robot. Then, the controller is trained in simulation using reinforcement learning and behavior cloning.

TWIST: a real-time teleoperation system for humanoid robots to mimic whole-body motions. Reference motion data is generated by retargeting human motion-capture data to the robot. Then, the controller is trained in simulation using reinforcement learning and behavior cloning.

The Humanoid Hub

46,715 次观看 • 1 年前

Introducing Yell At Your Robot (YAY Robot!) 🗣️- a fun collaboration b/w Stanford University and UC Berkeley 🤖 We enable robots to improve on-the-fly from language corrections: robots rapidly adapt in real-time and continuously improve from human verbal feedback. YAY Robot enables long-horizon, dexterous manipulation tasks like preparing trail-mix, packing a ziploc bag, and cleaning dishes:

Introducing Yell At Your Robot (YAY Robot!) 🗣️- a fun collaboration b/w Stanford University and UC Berkeley 🤖 We enable robots to improve on-the-fly from language corrections: robots rapidly adapt in real-time and continuously improve from human verbal feedback. YAY Robot enables long-horizon, dexterous manipulation tasks like preparing trail-mix, packing a ziploc bag, and cleaning dishes:

Lucy Shi

122,827 次观看 • 2 年前

New Course: Post-training of LLMs Learn to post-train and customize an LLM in this short course, taught by Banghua Zhu, Assistant Professor at the University of Washington University of Washington, and co-founder of @NexusflowX. Training an LLM to follow instructions or answer questions has two key stages: pre-training and post-training. In pre-training, it learns to predict the next word or token from large amounts of unlabeled text. In post-training, it learns useful behaviors such as following instructions, tool use, and reasoning. Post-training transforms a general-purpose token predictor—trained on trillions of unlabeled text tokens—into an assistant that follows instructions and performs specific tasks. Because it is much cheaper than pre-training, it is practical for many more teams to incorporate post-training methods into their workflows than pre-training. In this course, you’ll learn three common post-training methods—Supervised Fine-Tuning (SFT), Direct Preference Optimization (DPO), and Online Reinforcement Learning (RL)—and how to use each one effectively. With SFT, you train the model on pairs of input and ideal output responses. With DPO, you provide both a preferred (chosen) and a less preferred (rejected) response and train the model to favor the preferred output. With RL, the model generates an output, receives a reward score based on human or automated feedback, and updates the model to improve performance. You’ll learn the basic concepts, common use cases, and principles for curating high-quality data for effective training. Through hands-on labs, you’ll download a pre-trained model from Hugging Face and post-train it using SFT, DPO, and RL to see how each technique shapes model behavior. In detail, you’ll: - Understand what post-training is, when to use it, and how it differs from pre-training. - Build an SFT pipeline to turn a base model into an instruct model. - Explore how DPO reshapes behavior by minimizing contrastive loss—penalizing poor responses and reinforcing preferred ones. - Implement a DPO pipeline to change the identity of a chat assistant. - Learn online RL methods such as Proximal Policy Optimization (PPO) and Group Relative Policy Optimization (GRPO), and how to design reward functions. - Train a model with GRPO to improve its math capabilities using a verifiable reward. Post-training is one of the most rapidly developing areas of LLM training. Whether you’re building a high-accuracy context-specific assistant, fine-tuning a model's tone, or improving task-specific accuracy, this course will give you experience with the most important techniques shaping how LLMs are post-trained today. Please sign up here:

New Course: Post-training of LLMs Learn to post-train and customize an LLM in this short course, taught by Banghua Zhu, Assistant Professor at the University of Washington University of Washington, and co-founder of @NexusflowX. Training an LLM to follow instructions or answer questions has two key stages: pre-training and post-training. In pre-training, it learns to predict the next word or token from large amounts of unlabeled text. In post-training, it learns useful behaviors such as following instructions, tool use, and reasoning. Post-training transforms a general-purpose token predictor—trained on trillions of unlabeled text tokens—into an assistant that follows instructions and performs specific tasks. Because it is much cheaper than pre-training, it is practical for many more teams to incorporate post-training methods into their workflows than pre-training. In this course, you’ll learn three common post-training methods—Supervised Fine-Tuning (SFT), Direct Preference Optimization (DPO), and Online Reinforcement Learning (RL)—and how to use each one effectively. With SFT, you train the model on pairs of input and ideal output responses. With DPO, you provide both a preferred (chosen) and a less preferred (rejected) response and train the model to favor the preferred output. With RL, the model generates an output, receives a reward score based on human or automated feedback, and updates the model to improve performance. You’ll learn the basic concepts, common use cases, and principles for curating high-quality data for effective training. Through hands-on labs, you’ll download a pre-trained model from Hugging Face and post-train it using SFT, DPO, and RL to see how each technique shapes model behavior. In detail, you’ll: - Understand what post-training is, when to use it, and how it differs from pre-training. - Build an SFT pipeline to turn a base model into an instruct model. - Explore how DPO reshapes behavior by minimizing contrastive loss—penalizing poor responses and reinforcing preferred ones. - Implement a DPO pipeline to change the identity of a chat assistant. - Learn online RL methods such as Proximal Policy Optimization (PPO) and Group Relative Policy Optimization (GRPO), and how to design reward functions. - Train a model with GRPO to improve its math capabilities using a verifiable reward. Post-training is one of the most rapidly developing areas of LLM training. Whether you’re building a high-accuracy context-specific assistant, fine-tuning a model's tone, or improving task-specific accuracy, this course will give you experience with the most important techniques shaping how LLMs are post-trained today. Please sign up here:

Andrew Ng

125,146 次观看 • 1 年前

How well do egocentric human videos scale? Apparently, really well. Dyna Robotics has introduced Dyna-2, a world-action model (WAM) pre-trained on more than 1 million hours of real egocentric human video. It learns by jointly predicting the next video frames and the actions, and that video prediction (world modeling) is what carries learning from humans to robots. • More human video predictably improves action prediction. • Task accuracy improves across embodiments (bimanual arms and a humanoid) with zero robot data in pre-training. • Post-trained on just a few hours of robot data, mean task performance rose 20% to 53% as human pre-training scaled 1k to 1M hours. WAM vs VLA, matched apple-to-apple: the WAM hit 1.55x the VLA's success rate and won 65% of head-to-heads. Deployed zero-shot at unseen customer sites, it passed 87% vs the VLA's 46%.

How well do egocentric human videos scale? Apparently, really well. Dyna Robotics has introduced Dyna-2, a world-action model (WAM) pre-trained on more than 1 million hours of real egocentric human video. It learns by jointly predicting the next video frames and the actions, and that video prediction (world modeling) is what carries learning from humans to robots. • More human video predictably improves action prediction. • Task accuracy improves across embodiments (bimanual arms and a humanoid) with zero robot data in pre-training. • Post-trained on just a few hours of robot data, mean task performance rose 20% to 53% as human pre-training scaled 1k to 1M hours. WAM vs VLA, matched apple-to-apple: the WAM hit 1.55x the VLA's success rate and won 65% of head-to-heads. Deployed zero-shot at unseen customer sites, it passed 87% vs the VLA's 46%.

The Humanoid Hub

15,988 次观看 • 2 个月前

🤖 Introducing H2O (Human2HumanOid): - 🧠 An RL-based human-to-humanoid real-time whole-body teleoperation framework - 💃 Scalable retargeting and training using large human motion dataset - 🎥 With just an RGB camera, everyone can teleoperate a full-sized humanoid to perform actions like pick and place, walking, kicking, boxing, etc - 💡Unleash the potential of humanoids with human cognitive skills and adaptability 🔗:

🤖 Introducing H2O (Human2HumanOid): - 🧠 An RL-based human-to-humanoid real-time whole-body teleoperation framework - 💃 Scalable retargeting and training using large human motion dataset - 🎥 With just an RGB camera, everyone can teleoperate a full-sized humanoid to perform actions like pick and place, walking, kicking, boxing, etc - 💡Unleash the potential of humanoids with human cognitive skills and adaptability 🔗:

Tairan He

97,008 次观看 • 2 年前

Still following your human intuition to mix corpora from different sources for language model pre-training 🧠? Everyone says that data mixture has a big impact on model performance, but how - and why🕵️? Did you know that web corpora are actually highly impactful for downstream tasks 🏆? Let's check out our preprint "RegMix: Data Mixture as Regression for Language Model Pre-training" 📄 🔬In this paper, we've proposed an automatic data mixture method RegMix that achieves a 6.3% improvement over human selection on the widely used HellaSwag benchmark - and it only needs a 2% extra training FLOPs! 📈 Details in the thread 🧵

Still following your human intuition to mix corpora from different sources for language model pre-training 🧠? Everyone says that data mixture has a big impact on model performance, but how - and why🕵️? Did you know that web corpora are actually highly impactful for downstream tasks 🏆? Let's check out our preprint "RegMix: Data Mixture as Regression for Language Model Pre-training" 📄 🔬In this paper, we've proposed an automatic data mixture method RegMix that achieves a 6.3% improvement over human selection on the widely used HellaSwag benchmark - and it only needs a 2% extra training FLOPs! 📈 Details in the thread 🧵

Qian Liu

54,961 次观看 • 2 年前

New short course on Fine-tuning LLMs! Many developers are moving beyond only prompting, to also fine-tuning LLMs - that is, taking a pre-trained model and training it further on your own data, which can deliver superior results inexpensively. In this course, Sharon Zhou, CEO of Lamini (disclosure: I’m a minor shareholder) shows you how to recognize when fine-tuning can be help, and how to train an open-source LLM on your own data. I hope you enjoy the course!

New short course on Fine-tuning LLMs! Many developers are moving beyond only prompting, to also fine-tuning LLMs - that is, taking a pre-trained model and training it further on your own data, which can deliver superior results inexpensively. In this course, Sharon Zhou, CEO of Lamini (disclosure: I’m a minor shareholder) shows you how to recognize when fine-tuning can be help, and how to train an open-source LLM on your own data. I hope you enjoy the course!

Andrew Ng

502,962 次观看 • 3 年前