Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

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... show more

Ankit Goyal

3,013 subscribers

29,731 views • 2 months ago •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

Scalable, reproducible, and reliable robotic evaluation remains an open challenge, especially in the age of generalist robot foundation models. Can *simulation* effectively predict *real-world* robot policy performance & behavior? Presenting SIMPLER!👇

Scalable, reproducible, and reliable robotic evaluation remains an open challenge, especially in the age of generalist robot foundation models. Can simulation effectively predict real-world robot policy performance & behavior? Presenting SIMPLER!👇

Xuanlin Li (Simon)

86,338 views • 2 years ago

It’s been a massive week for embodied AI foundation models: the pace of this field is truly staggering. Throwing it back to the SimToolReal work by Kushal and Tyler Lum (Cornell & Stanford labs). In February, they achieved zero-shot tool manipulation across 24 tasks using a single RL policy and a robotic arm fitted with the SharpaWave hand. Watching the robot nail these high-speed in-hand rotations is incredible. The precision is especially impressive when you consider the policy was never trained on these specific objects or tasks. This is what solving the manipulation bottleneck looks like. ⚡️

It’s been a massive week for embodied AI foundation models: the pace of this field is truly staggering. Throwing it back to the SimToolReal work by Kushal and Tyler Lum (Cornell & Stanford labs). In February, they achieved zero-shot tool manipulation across 24 tasks using a single RL policy and a robotic arm fitted with the SharpaWave hand. Watching the robot nail these high-speed in-hand rotations is incredible. The precision is especially impressive when you consider the policy was never trained on these specific objects or tasks. This is what solving the manipulation bottleneck looks like. ⚡️

Sharpa

868,162 views • 2 months ago

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.

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.

Sergey Levine

81,265 views • 6 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!

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

98,090 views • 1 year ago

Robot foundation models are limited by costly real data, while simulation data is plentiful but visually mismatched to reality. We present Point Bridge, a method that enables zero-shot sim-to-real transfer for robot learning with minimal visual alignment.

Robot foundation models are limited by costly real data, while simulation data is plentiful but visually mismatched to reality. We present Point Bridge, a method that enables zero-shot sim-to-real transfer for robot learning with minimal visual alignment.

Siddhant Haldar

19,818 views • 4 months ago

Developing general-purpose robot models is costly due to the need for extensive real-world data. 🤖 #NVIDIAIsaac GR00T addresses these challenges by providing #humanoidrobot developers with robot foundation models & more. #CES2025 📹

Developing general-purpose robot models is costly due to the need for extensive real-world data. 🤖 #NVIDIAIsaac GR00T addresses these challenges by providing #humanoidrobot developers with robot foundation models & more. #CES2025 📹

NVIDIA Robotics

19,055 views • 1 year ago

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!

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 views • 4 months ago

Testing robot policies on hardware is slow, expensive and hard to scale. World models offer a promising path to accelerating robot policy development. We're sharing new research from the Runway Robotics team, in which we simulated 8 robot policies inside our General World Model and found 0.95 correlation with real-world results. Those early results point to world model simulation as a practical substitute for hardware evaluation, comparing favorably to existing real-to-sim approaches. Learn more at the link below.

Testing robot policies on hardware is slow, expensive and hard to scale. World models offer a promising path to accelerating robot policy development. We're sharing new research from the Runway Robotics team, in which we simulated 8 robot policies inside our General World Model and found 0.95 correlation with real-world results. Those early results point to world model simulation as a practical substitute for hardware evaluation, comparing favorably to existing real-to-sim approaches. Learn more at the link below.

Runway

13,464 views • 3 months ago

We’re organizing the RoboArena Challenge at CoRL this year! Show the performance of your best generalist policy, in a fair, open benchmark for the robotics community! 🤖 Sign up, even if you don’t have a robot! More details in 🧵👇

We’re organizing the RoboArena Challenge at CoRL this year! Show the performance of your best generalist policy, in a fair, open benchmark for the robotics community! 🤖 Sign up, even if you don’t have a robot! More details in 🧵👇

Karl Pertsch

26,775 views • 11 months ago

Building for the Apple ecosystem? You will soon be able to securely call cloud-hosted Gemini models directly from Apple’s Foundation Models framework 🔥 This integration, powered by Firebase AI Logic, will allow you to use both Apple’s Foundation Models and Gemini models via a shared API surface.

Building for the Apple ecosystem? You will soon be able to securely call cloud-hosted Gemini models directly from Apple’s Foundation Models framework 🔥 This integration, powered by Firebase AI Logic, will allow you to use both Apple’s Foundation Models and Gemini models via a shared API surface.

Firebase

13,476 views • 15 days ago

Given the strong community adoption and real-world deployment of MolmoAct2 on YAM, we're introducing zero-shot evaluation of MolmoAct2 Bimanual YAM in simulation. Now you can test out our models without a real-world robot and build on them! Code: Simulation built on Maniskill!

Given the strong community adoption and real-world deployment of MolmoAct2 on YAM, we're introducing zero-shot evaluation of MolmoAct2 Bimanual YAM in simulation. Now you can test out our models without a real-world robot and build on them! Code: Simulation built on Maniskill!

Jiafei Duan

35,927 views • 14 days ago

It’s long been a dream of roboticists to be able to teach a robot in simulation so as to skip the long and expensive process of collecting large amounts of real-world training data. However, building simulations for robot tasks is extremely hard. Ideally, we could go from real data to a useful simulation. This is exactly what Guangqi Jiang and his co-authors do. they use 3d Gaussian splatting to reconstructed scenes which let them create interactive environments that, when combined with a physcs engine, allow for training robot policies that show zero-shot sim-to-real transfer (i.e., using no real-world demonstrations). To learn more, watch Episode 56 of Robopapers with Michael Cho - Rbt/Acc and Chris Paxton now!

It’s long been a dream of roboticists to be able to teach a robot in simulation so as to skip the long and expensive process of collecting large amounts of real-world training data. However, building simulations for robot tasks is extremely hard. Ideally, we could go from real data to a useful simulation. This is exactly what Guangqi Jiang and his co-authors do. they use 3d Gaussian splatting to reconstructed scenes which let them create interactive environments that, when combined with a physcs engine, allow for training robot policies that show zero-shot sim-to-real transfer (i.e., using no real-world demonstrations). To learn more, watch Episode 56 of Robopapers with Michael Cho - Rbt/Acc and Chris Paxton now!

RoboPapers

20,434 views • 6 months ago

How to harness foundation models for *generalization in the wild* in robot manipulation? Introducing VoxPoser: use LLM+VLM to label affordances and constraints directly in 3D perceptual space for zero-shot robot manipulation in the real world! 🌐 🧵👇

How to harness foundation models for generalization in the wild in robot manipulation? Introducing VoxPoser: use LLM+VLM to label affordances and constraints directly in 3D perceptual space for zero-shot robot manipulation in the real world! 🌐 🧵👇

Wenlong Huang

293,876 views • 3 years ago

Today, we publicly released RoboCasa365, a large-scale simulation benchmark for training and systematically evaluating generalist robot models. Built upon our original RoboCasa framework, it offers: • 2,500 realistic kitchen environments; • 365 everyday tasks (basic skills + long-horizon mobile manipulation); • Over 3,200 objects with many articulated fixtures/appliances. All are designed for fully controlled, reproducible benchmarking of robotic policies. Progress in robotic foundation models is real. But it’s still hard to answer basic questions like: How close are we to general-purpose autonomy? What factors drive generalization? What are the model/data scaling curves like? Real-world eval is slow and noisy, and existing sims (like LIBERO, which we built 3 years ago) often lack sufficient task and scene diversity. This benchmark comes with 2,200+ hours of demonstrations and 500K+ trajectories to support studies of multi-task training, pretraining, and continual learning at scale. Check it out at

Today, we publicly released RoboCasa365, a large-scale simulation benchmark for training and systematically evaluating generalist robot models. Built upon our original RoboCasa framework, it offers: • 2,500 realistic kitchen environments; • 365 everyday tasks (basic skills + long-horizon mobile manipulation); • Over 3,200 objects with many articulated fixtures/appliances. All are designed for fully controlled, reproducible benchmarking of robotic policies. Progress in robotic foundation models is real. But it’s still hard to answer basic questions like: How close are we to general-purpose autonomy? What factors drive generalization? What are the model/data scaling curves like? Real-world eval is slow and noisy, and existing sims (like LIBERO, which we built 3 years ago) often lack sufficient task and scene diversity. This benchmark comes with 2,200+ hours of demonstrations and 500K+ trajectories to support studies of multi-task training, pretraining, and continual learning at scale. Check it out at

Yuke Zhu

23,745 views • 3 months ago

How well do today’s frontier models handle long-horizon, multi-step web agent tasks, such as identifying the top 25 U.S. CS PhD programs with ML/AI faculty likely accepting students and compiling the results into a structured sheet? Check out our new work on Odysseys: Benchmarking Web Agents on Realistic Long Horizon Tasks Paper: Leaderboard: We introduce Odysseys, a benchmark of 200 long-horizon tasks derived from real browsing sessions and evaluated on the live Internet. We show that binary pass/fail is inadequate in this setting and propose rubric-based evaluation, which better aligns with human judgment and provides more informative signals. Across leading models, the best achieves only 44.5% success, leaving substantial headroom. We further introduce a Trajectory Efficiency metric (rubric score per step) and find efficiency remains extremely low (1.15%), highlighting a key bottleneck. Odysseys provides a realistic benchmark for measuring progress toward web agents capable of sustained, efficient, real-world operation. See a more detailed thread by Jing Yu Koh.

How well do today’s frontier models handle long-horizon, multi-step web agent tasks, such as identifying the top 25 U.S. CS PhD programs with ML/AI faculty likely accepting students and compiling the results into a structured sheet? Check out our new work on Odysseys: Benchmarking Web Agents on Realistic Long Horizon Tasks Paper: Leaderboard: We introduce Odysseys, a benchmark of 200 long-horizon tasks derived from real browsing sessions and evaluated on the live Internet. We show that binary pass/fail is inadequate in this setting and propose rubric-based evaluation, which better aligns with human judgment and provides more informative signals. Across leading models, the best achieves only 44.5% success, leaving substantial headroom. We further introduce a Trajectory Efficiency metric (rubric score per step) and find efficiency remains extremely low (1.15%), highlighting a key bottleneck. Odysseys provides a realistic benchmark for measuring progress toward web agents capable of sustained, efficient, real-world operation. See a more detailed thread by Jing Yu Koh.

Russ Salakhutdinov

22,518 views • 1 month ago

Meta PARTNR is a benchmark for planning and reasoning in embodied multi-agent tasks. This large-scale human and robot collaboration benchmark was core to our recent demos and also informs our work as scientists and engineers pushing this field of study forward.

Meta PARTNR is a benchmark for planning and reasoning in embodied multi-agent tasks. This large-scale human and robot collaboration benchmark was core to our recent demos and also informs our work as scientists and engineers pushing this field of study forward.

AI at Meta

33,607 views • 1 year ago

Earlier this week at GTC, we announced our partnership with Nvidia. We will work with Nvidia to build strong, American open-source models that are at the frontier of scientific reasoning. These models will be essential for the US to compete with China on science in the coming decades. Jensen is committing to spend tens of billions of dollars developing open-source models, and we are excited to be a partner with them in figuring out how to benchmark, train and use those agents to accelerate scientific research. We have already open-sourced some of the work we have done with them, and are looking forward to open-sourcing more. There are few things today that are more important. See our blog post below, and watch the video to learn more, narrated by the man himself.

Earlier this week at GTC, we announced our partnership with Nvidia. We will work with Nvidia to build strong, American open-source models that are at the frontier of scientific reasoning. These models will be essential for the US to compete with China on science in the coming decades. Jensen is committing to spend tens of billions of dollars developing open-source models, and we are excited to be a partner with them in figuring out how to benchmark, train and use those agents to accelerate scientific research. We have already open-sourced some of the work we have done with them, and are looking forward to open-sourcing more. There are few things today that are more important. See our blog post below, and watch the video to learn more, narrated by the man himself.

Sam Rodriques

22,201 views • 3 months ago

This is a single uncut video, showing a robot learning several tasks instantly, after just one demonstration each ... This is possible because we've now been able to achieve in-context learning for everyday robotics tasks, and I'm very excited to announce our latest paper: 🎆 Instant Policy: In-Context Imitation Learning via Graph Diffusion 🎆 (1/6) 🧵👇

This is a single uncut video, showing a robot learning several tasks instantly, after just one demonstration each ... This is possible because we've now been able to achieve in-context learning for everyday robotics tasks, and I'm very excited to announce our latest paper: 🎆 Instant Policy: In-Context Imitation Learning via Graph Diffusion 🎆 (1/6) 🧵👇

Edward Johns

74,663 views • 1 year ago

🔬 What is a humanized mouse, and why is it essential for medical research? Watch our video to learn how these models help fight diseases like cancer and HIV. 🎥👇 📄 More info: #AnimalResearch #MedicalBreakthroughs

🔬 What is a humanized mouse, and why is it essential for medical research? Watch our video to learn how these models help fight diseases like cancer and HIV. 🎥👇 📄 More info: #AnimalResearch #MedicalBreakthroughs

Foundation for Biomedical Research

28,325 views • 1 year ago

We have 6 different models of CNC machines already designed and validated for production but we would need crores to scale up production and offer it to other manufacturers. Hence, we only build machines for our own production facility. Capital is a bottleneck for us. Currently we just have a tiny space within our own factory which is our R&D lab. We are a team of mere three people. Scaling hardware isn’t easy but it’s something that must be done for us to truly be self-reliant. Really appreciate your efforts Sridhar Vembu to build these hardware tools here. We must build more factories and hardware products in the country. Long way to go before I sleep.

We have 6 different models of CNC machines already designed and validated for production but we would need crores to scale up production and offer it to other manufacturers. Hence, we only build machines for our own production facility. Capital is a bottleneck for us. Currently we just have a tiny space within our own factory which is our R&D lab. We are a team of mere three people. Scaling hardware isn’t easy but it’s something that must be done for us to truly be self-reliant. Really appreciate your efforts Sridhar Vembu to build these hardware tools here. We must build more factories and hardware products in the country. Long way to go before I sleep.

Vishakh Ranotra

12,511 views • 21 days ago