Loading video...

Video Failed to Load

Go Home

We present ClutterGen that tackles two important research problems in robotics: 1) how to generate physically compliant cluttered scene for robot learning? 2) how to stably place objects instead of the current "pick and drop" paradigm? Our key idea is to formulate physically compliant cluttered scene generation as a...

Boyuan__Chen's profile picture

Boyuan Chen

2,185 subscribers

20,715 views • 2 years ago •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

Control a robot in simulation with the Gemini Robotics Embodied Reasoning model 🤖 Direct tasks like object localization and placement by simply prompting a robotic arm to pick up and place objects.
0:20

Control a robot in simulation with the Gemini Robotics Embodied Reasoning model 🤖 Direct tasks like object localization and placement by simply prompting a robotic arm to pick up and place objects.

Google AI Developers

1,297,082 views • 9 months ago

Train your avatars to interact with 3D scenes. We use adversarial imitation learning and reinforcement learning to train physically-simulated characters that perform scene interaction tasks in a natural and life-like manner. Today at #SIGGRAPH2023.
0:21

Train your avatars to interact with 3D scenes. We use adversarial imitation learning and reinforcement learning to train physically-simulated characters that perform scene interaction tasks in a natural and life-like manner. Today at #SIGGRAPH2023.

Michael Black

46,237 views • 3 years ago

Robot AI brains, aka Vision-Language-Action models, cannot adapt to new tasks as easily as LLMs like Gemini, ChatGPT, or Grok. LLMs can adapt quickly with their in-context learning (ICL) capabilities. But can we inject ICL abilities into a pre-trained VLA like pi0? Yes! Introducing RICL (Retraining for In-Context Learning), our Conference on Robot Learning (CoRL) 2025 paper. Our RICL-pi0 model can adapt to unseen objects, novel motions, and new scenes with just ICL and RAG (retrieval-augmented generation). RICL-pi0 also boosts performance on the long-tail of tasks. A quick 1 minute video summary:
1:03

Robot AI brains, aka Vision-Language-Action models, cannot adapt to new tasks as easily as LLMs like Gemini, ChatGPT, or Grok. LLMs can adapt quickly with their in-context learning (ICL) capabilities. But can we inject ICL abilities into a pre-trained VLA like pi0? Yes! Introducing RICL (Retraining for In-Context Learning), our Conference on Robot Learning (CoRL) 2025 paper. Our RICL-pi0 model can adapt to unseen objects, novel motions, and new scenes with just ICL and RAG (retrieval-augmented generation). RICL-pi0 also boosts performance on the long-tail of tasks. A quick 1 minute video summary:

Kaustubh Sridhar

52,897 views • 1 year ago

🤖 How can robot policies zero-shot generalize to any new environment and any new object? Introducing our new project: 🚀Data Scaling Laws in Imitation Learning for Robotic Manipulation🚀—bringing us closer to the dream of having robots work as waiters in hot pot restaurants! 🍲
0:29

🤖 How can robot policies zero-shot generalize to any new environment and any new object? Introducing our new project: 🚀Data Scaling Laws in Imitation Learning for Robotic Manipulation🚀—bringing us closer to the dream of having robots work as waiters in hot pot restaurants! 🍲

Yang Gao

125,747 views • 2 years ago

Very cool breakthrough by our physical AI and robotics teams-- Vulcan is the first robot that combines sight and touch, and can feel its way through cluttered spaces the way humans do. Vulcan is helping make work safer by handling ergonomically challenging tasks, while creating opportunities for our teammates to grow their skills in robotics maintenance.
0:28

Very cool breakthrough by our physical AI and robotics teams-- Vulcan is the first robot that combines sight and touch, and can feel its way through cluttered spaces the way humans do. Vulcan is helping make work safer by handling ergonomically challenging tasks, while creating opportunities for our teammates to grow their skills in robotics maintenance.

Andy Jassy

143,985 views • 1 year ago

Alert🚨 This could be by far the most impressive video about 4D human motion generation! 🔥🔥🔥 We present TRUMANS, a pioneering and solid effort that scales up 4D human-scene interactions with both static and dynamic objects. With our model, we could eventually generate diverse and physically plausible human motions of any length in the physical 3D world. Cannot stop to wonder how TRUMANS could be adapted to the humanoid robot. Let me know if you are interested! Our paper has been accepted by CVPR24; check our code, demo, and more details in
5:27

Alert🚨 This could be by far the most impressive video about 4D human motion generation! 🔥🔥🔥 We present TRUMANS, a pioneering and solid effort that scales up 4D human-scene interactions with both static and dynamic objects. With our model, we could eventually generate diverse and physically plausible human motions of any length in the physical 3D world. Cannot stop to wonder how TRUMANS could be adapted to the humanoid robot. Let me know if you are interested! Our paper has been accepted by CVPR24; check our code, demo, and more details in

Siyuan Huang

13,692 views • 2 years ago

We open-source Action Images — a new representation that translates 7-DoF robot actions into interpretable images. Video models are emerging as powerful robotic foundation models, but a key challenge remains: how can we seamlessly integrate robot policies into video models? Instead of representing actions as low-dimensional control tokens, Action Images provide a pixel-grounded action representation, reframing policy learning as a visual tracking problem! By unifying observations and actions in the same video space, Action Images enable a unified robotics world model that supports video-action joint generation, action-conditioned video generation, and action labeling! Code: Paper:
0:51

We open-source Action Images — a new representation that translates 7-DoF robot actions into interpretable images. Video models are emerging as powerful robotic foundation models, but a key challenge remains: how can we seamlessly integrate robot policies into video models? Instead of representing actions as low-dimensional control tokens, Action Images provide a pixel-grounded action representation, reframing policy learning as a visual tracking problem! By unifying observations and actions in the same video space, Action Images enable a unified robotics world model that supports video-action joint generation, action-conditioned video generation, and action labeling! Code: Paper:

Chuang Gan

21,317 views • 4 months ago

In-hand object manipulation is a dexterity litmus test for robot hands. Our new system in Science Robotics Science Robotics can dynamically reorient many different objects in hand in the air. 📚Project website: 🧑‍💻Code: 🧵1/n
0:49

In-hand object manipulation is a dexterity litmus test for robot hands. Our new system in Science Robotics Science Robotics can dynamically reorient many different objects in hand in the air. 📚Project website: 🧑‍💻Code: 🧵1/n

Tao Chen

30,724 views • 2 years ago

Excitement about world-action models and robot learning has never been higher — they promise a way to use human egocentric data to train massive robotics models which can provide the “GPT” moment for robotics and unlock general-purpose embodied intelligence. And yet there’s been little concrete demonstration of scaling in robot learning. Dyna Robotics aims to change that, with an in-depth look at how scaling works as they approach 1 million hours of training data. Jason Ma Tianyu Li Anh-Quan Pham and Chet Bhateja joined us to tell us more. They show that as the amount of data they use in pretraining increased, they saw predictable, statistically significant gains on accuracy metrics on held-out data (data not seen during training). They go on to talk about what they learned, and show how this can be applied to many different problems. Watch Episode #99 of RoboPapers, with Michael Cho - Rbt/Acc Chris Paxton Jiafei Duan✈️CoRL2026 today to learn more!
1:07:18

Excitement about world-action models and robot learning has never been higher — they promise a way to use human egocentric data to train massive robotics models which can provide the “GPT” moment for robotics and unlock general-purpose embodied intelligence. And yet there’s been little concrete demonstration of scaling in robot learning. Dyna Robotics aims to change that, with an in-depth look at how scaling works as they approach 1 million hours of training data. Jason Ma Tianyu Li Anh-Quan Pham and Chet Bhateja joined us to tell us more. They show that as the amount of data they use in pretraining increased, they saw predictable, statistically significant gains on accuracy metrics on held-out data (data not seen during training). They go on to talk about what they learned, and show how this can be applied to many different problems. Watch Episode #99 of RoboPapers, with Michael Cho - Rbt/Acc Chris Paxton Jiafei Duan✈️CoRL2026 today to learn more!

RoboPapers

26,279 views • 2 months ago

A few months ago we set out to understand exactly how our models can be used to accelerate progress in robotics and other AI systems that don’t just represent the world, but are actually able to interact with it. We’ve been collaborating with leading companies in the space and we’ve developed an initial approach that we're now opening up to accelerate development across the industry. Our fifth announcement is GWM Robotics. GWM Robotics is a learned simulator that generates synthetic data for scalable robot training and policy evaluation, removing the bottlenecks of physical hardware.
1:14

A few months ago we set out to understand exactly how our models can be used to accelerate progress in robotics and other AI systems that don’t just represent the world, but are actually able to interact with it. We’ve been collaborating with leading companies in the space and we’ve developed an initial approach that we're now opening up to accelerate development across the industry. Our fifth announcement is GWM Robotics. GWM Robotics is a learned simulator that generates synthetic data for scalable robot training and policy evaluation, removing the bottlenecks of physical hardware.

Runway

35,040 views • 10 months ago

Excited to finally share Generative Value Learning (GVL), my Google DeepMind project on extracting universal value functions from long-context VLMs via in-context learning! We discovered a simple method to generate zero-shot and few-shot values for 300+ robot tasks and 50+ datasets using SOTA VLMs like Gemini (Try out the demo on our website on your robot video today!) I worked a lot on leveraging foundation models as guidance for robots in my PhD, and to me, this result forges a new frontier in how we can use foundation models for robot learning, given its broad applicability independent of embodiment and task types. Quite excited about how we can build on this work as a community!
0:32

Excited to finally share Generative Value Learning (GVL), my Google DeepMind project on extracting universal value functions from long-context VLMs via in-context learning! We discovered a simple method to generate zero-shot and few-shot values for 300+ robot tasks and 50+ datasets using SOTA VLMs like Gemini (Try out the demo on our website on your robot video today!) I worked a lot on leveraging foundation models as guidance for robots in my PhD, and to me, this result forges a new frontier in how we can use foundation models for robot learning, given its broad applicability independent of embodiment and task types. Quite excited about how we can build on this work as a community!

Jason Ma

98,270 views • 2 years ago

Modern AI is confined to the digital world. At Skild AI, we are building towards AGI for the real world, unconstrained by robot type or task — a single, omni-bodied brain. Today, we are sharing our journey, starting with early milestones, with more to come in the weeks ahead. Our Mission: Artificial General Intelligence grounded in the physical world. We believe AGI that can truly understand and reason in the real world can only be built through grounding in the physical world. Our Vision: Any robot, Any task, One brain. We tackle robotics in its full generality – building a continually improving, omni-bodied brain that can control any hardware for any task. Who are we? A passionate group of scientists & engineers driven by our shared vision. We have been researching AI and robotics for more than a decade. Our team includes pioneers of self-supervised learning, curiosity-driven exploration, end-to-end sim2real for visual locomotion, dexterous manipulation, learning from human videos, robot parkour, and many more. Many of these works have won awards at top-tier AI and Robotics conferences. Our team has also built production-ready systems at Anduril, Tesla, Nvidia, Meta, Kitty Hawk, Google, Everyday Robotics, and Amazon. Join us in our mission to build the robot brains of tomorrow.
2:48

Modern AI is confined to the digital world. At Skild AI, we are building towards AGI for the real world, unconstrained by robot type or task — a single, omni-bodied brain. Today, we are sharing our journey, starting with early milestones, with more to come in the weeks ahead. Our Mission: Artificial General Intelligence grounded in the physical world. We believe AGI that can truly understand and reason in the real world can only be built through grounding in the physical world. Our Vision: Any robot, Any task, One brain. We tackle robotics in its full generality – building a continually improving, omni-bodied brain that can control any hardware for any task. Who are we? A passionate group of scientists & engineers driven by our shared vision. We have been researching AI and robotics for more than a decade. Our team includes pioneers of self-supervised learning, curiosity-driven exploration, end-to-end sim2real for visual locomotion, dexterous manipulation, learning from human videos, robot parkour, and many more. Many of these works have won awards at top-tier AI and Robotics conferences. Our team has also built production-ready systems at Anduril, Tesla, Nvidia, Meta, Kitty Hawk, Google, Everyday Robotics, and Amazon. Join us in our mission to build the robot brains of tomorrow.

Skild AI

386,992 views • 1 year ago

The holy grail of robotics is to be able to perform previously-unseen, out-of-distribution manipulation tasks “zero shot” in a new environment. NovaFlow proposes an approach which (1) generates a video, (2) computes predicted flow — how points move through the scene — and (3) uses this flow as an objective to generate a motion. Using this procedure, NovaFlow generates motions in unseen scenes, for unseen tasks, and can transfer across embodiments. To learn more, we are joined by Hongyu Li and Jiahui Fu from RAI. Watch Episode #63 of RoboPapers with Chris Paxton and Michael Cho - Rbt/Acc now to learn more!
1:08:49

The holy grail of robotics is to be able to perform previously-unseen, out-of-distribution manipulation tasks “zero shot” in a new environment. NovaFlow proposes an approach which (1) generates a video, (2) computes predicted flow — how points move through the scene — and (3) uses this flow as an objective to generate a motion. Using this procedure, NovaFlow generates motions in unseen scenes, for unseen tasks, and can transfer across embodiments. To learn more, we are joined by Hongyu Li and Jiahui Fu from RAI. Watch Episode #63 of RoboPapers with Chris Paxton and Michael Cho - Rbt/Acc now to learn more!

RoboPapers

21,543 views • 8 months ago

Reinforcement learning has unlocked tremendous gains in broader AI and humanoid robot whole body control, but still has yet to deliver strong results for robot manipulation due to the difficulty of capturing tasks in an accurate simulation; one way to fix this is to create complex environments with learned world models. But learning fully within world models is often intractable as powerful world models are computationally too expensive. Instead, Joseph Amigo and Rooholla Khorrambakht propose to break the problem down: into a large-scale world model that can generate forward trajectories, and a lightweight, low-dimensional latent-space model which can approximate local dynamics of a problem, without needing to back-propagate through a heavy global model. What this means: you can do reinforcement learning in this coupled local-global world model, and learn contact rich skills for a robot. To learn more, watch Episode #101 of RoboPapers, with Michael Cho - Rbt/Acc and Jiafei Duan!
51:25

Reinforcement learning has unlocked tremendous gains in broader AI and humanoid robot whole body control, but still has yet to deliver strong results for robot manipulation due to the difficulty of capturing tasks in an accurate simulation; one way to fix this is to create complex environments with learned world models. But learning fully within world models is often intractable as powerful world models are computationally too expensive. Instead, Joseph Amigo and Rooholla Khorrambakht propose to break the problem down: into a large-scale world model that can generate forward trajectories, and a lightweight, low-dimensional latent-space model which can approximate local dynamics of a problem, without needing to back-propagate through a heavy global model. What this means: you can do reinforcement learning in this coupled local-global world model, and learn contact rich skills for a robot. To learn more, watch Episode #101 of RoboPapers, with Michael Cho - Rbt/Acc and Jiafei Duan!

RoboPapers

16,866 views • 1 month ago

What can we learn from demonstrations of long-horizon tasks? I am presenting our #CoRL2024 paper "Learning Compositional Behaviors from Demonstration and Language" today, showing we can learn a library of behaviors that can be composed to solve new tasks.
0:20

What can we learn from demonstrations of long-horizon tasks? I am presenting our #CoRL2024 paper "Learning Compositional Behaviors from Demonstration and Language" today, showing we can learn a library of behaviors that can be composed to solve new tasks.

Weiyu Liu

10,091 views • 2 years ago

🇪🇸Spain is the place to be. ➡️Our country is emerging from decades of low productivity and wages to become a truly modern economy. We are building an environment where a highly skilled new generation can have the best life possible and the best work possible.
1:17

🇪🇸Spain is the place to be. ➡️Our country is emerging from decades of low productivity and wages to become a truly modern economy. We are building an environment where a highly skilled new generation can have the best life possible and the best work possible.

Carlos Cuerpo

32,071 views • 11 months ago

Education is one of the most crucial pillars of our THEMES+ agenda. It is not just a priority for our administration, it is a passion of mine. Education lays the foundation for the future of our children and, ultimately, the growth and development of our society. That’s why we are committed to renovating and reconstructing our schools to meet global standards. We want our educational institutions to be places where children can thrive, learn, and be inspired. Every child deserves access to a conducive learning environment, equipped with the necessary resources to help them excel academically and personally. Together, we are building a brighter future for the next generation, and I am excited to see our children flourish in an environment that encourages learning and innovation.
1:51

Education is one of the most crucial pillars of our THEMES+ agenda. It is not just a priority for our administration, it is a passion of mine. Education lays the foundation for the future of our children and, ultimately, the growth and development of our society. That’s why we are committed to renovating and reconstructing our schools to meet global standards. We want our educational institutions to be places where children can thrive, learn, and be inspired. Every child deserves access to a conducive learning environment, equipped with the necessary resources to help them excel academically and personally. Together, we are building a brighter future for the next generation, and I am excited to see our children flourish in an environment that encourages learning and innovation.

Babajide Sanwo-Olu

20,595 views • 1 year ago

After two years in stealth mode, we're thrilled to unveil Mentee Robotics and our humanoid robot, Mentee Robotics! With AI integration at every layer, from Sim2Real machine learning to NeRF-based algorithms and LLMs, we've achieved a complete end-to-end cycle for tasks. This is just the beginning and we can’t wait to share more
2:26

After two years in stealth mode, we're thrilled to unveil Mentee Robotics and our humanoid robot, Mentee Robotics! With AI integration at every layer, from Sim2Real machine learning to NeRF-based algorithms and LLMs, we've achieved a complete end-to-end cycle for tasks. This is just the beginning and we can’t wait to share more

Amnon Shashua

223,942 views • 2 years ago

For decades, we’ve dreamed of robots that can seamlessly step into our world and lend a hand. Today, we take a major stride toward making that dream a reality: Introducing Gemini Robotics 2 from Google DeepMind, the intelligence layer powering the next generation of truly adaptable robots. This major advance unlocks intelligent whole-body control, advanced dexterity, and even multi-robot collaboration 🤯. Ok but... how does a robot actually "think"? Real-world tasks take time and planning. To manage that complexity, our new embodied reasoning model, Gemini Robotics ER 2, acts as the robot’s high-level brain, enhancing the robot’s capabilities to: — Observe the environment — Reason about the actions needed to complete the task — Coordinate with the vision-language-action model to carry out actions — Track progress until the job is done This setup allows robots to execute complex multi-step workflows, self-correct if a step fails, and adapt to completely novel situations. Learn more about Gemini Robotics ER 2 (and our two other brand new models) here:
2:16

For decades, we’ve dreamed of robots that can seamlessly step into our world and lend a hand. Today, we take a major stride toward making that dream a reality: Introducing Gemini Robotics 2 from Google DeepMind, the intelligence layer powering the next generation of truly adaptable robots. This major advance unlocks intelligent whole-body control, advanced dexterity, and even multi-robot collaboration 🤯. Ok but... how does a robot actually "think"? Real-world tasks take time and planning. To manage that complexity, our new embodied reasoning model, Gemini Robotics ER 2, acts as the robot’s high-level brain, enhancing the robot’s capabilities to: — Observe the environment — Reason about the actions needed to complete the task — Coordinate with the vision-language-action model to carry out actions — Track progress until the job is done This setup allows robots to execute complex multi-step workflows, self-correct if a step fails, and adapt to completely novel situations. Learn more about Gemini Robotics ER 2 (and our two other brand new models) here:

Google AI

789,829 views • 3 months ago

New Gemini Robotics 1.5 models will enable robots to better reason, plan ahead, use digital tools like Search, and transfer learning from one kind of robot to another. Our next big step towards general-purpose robots that are truly helpful — you can see how the robot reasons as it sorts laundry in the video below.
0:29

New Gemini Robotics 1.5 models will enable robots to better reason, plan ahead, use digital tools like Search, and transfer learning from one kind of robot to another. Our next big step towards general-purpose robots that are truly helpful — you can see how the robot reasons as it sorts laundry in the video below.

Sundar Pichai

496,947 views • 1 year ago