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.

First look at our collaboration with Audi on bringing AI-driven robotics into industrial production. Our end-to-end pixel-to-action model, running on our bi-manual platform, is capable of performing a complex, dexterous and long-horizon insertion task.

mimic

4,241 subscribers

66,186 views • 7 months ago •via X (Twitter)

Science & Technology

Anya Rossi• Live Now

Private livecam show

16 Comments

atharva ☆7 months ago

@AudiOfficial crazy

Nurvai - The Data Layer for Physical AI7 months ago

@AudiOfficial Complex tasks require a lot of dexterity and control. Your platform and and model combination seems like a really good deployment tool for such tasks to be automatized . Congrats

Kun Tao7 months ago

@AudiOfficial This is one of the most difficult tasks for dexterous hands. Great work! 👍

Sanskar Pandey7 months ago

@AudiOfficial Cool

Kalash7 months ago

@AudiOfficial cute hands

Gustav Adelhorst7 months ago

@AudiOfficial 👌 Cool!

avi7 months ago

@AudiOfficial wow

R2rule7 months ago

@AudiOfficial People only use three fingers for 99.9% of their daily tasks. Building five-fingered robotic hands is stupid. In the video, the robot never needs to use its ring or little finger.

Maxym Sergiyovych 🐲7 months ago

@AudiOfficial But it does not finish process correctly 😳

Luděk Čižinský7 months ago

@AudiOfficial Is that mimic video based policy?

Aivean ➛7 months ago

@AudiOfficial why do they need human to pull it out and reset? can't they automate that too?

Rue Mohr🇨🇦7 months ago

@AudiOfficial hahah, you just spent HOW MUCH to have a robot do that?... needs to find a better market application....

Paru7 months ago

@AudiOfficial that pixel-to-action model on a bi-manual platform is impressive the dexterity and long-horizon capabilities could redefine industrial automation

Martin Němec7 months ago

@AudiOfficial @bratricek

feel2buy7 months ago

@AudiOfficial

LumiPad7 months ago

@AudiOfficial Need to make them fast now

Related Videos

Today we're excited to share a glimpse of what we're building at Generalist. As a first step towards our mission of making general-purpose robots a reality, we're pushing the frontiers of what end-to-end AI models can achieve in the real world. Here's a preview of our early results in autonomous general-purpose dexterous capabilities – fast, reactive, smooth, precise, bi-manual coordinated sensorimotor control.

Today we're excited to share a glimpse of what we're building at Generalist. As a first step towards our mission of making general-purpose robots a reality, we're pushing the frontiers of what end-to-end AI models can achieve in the real world. Here's a preview of our early results in autonomous general-purpose dexterous capabilities – fast, reactive, smooth, precise, bi-manual coordinated sensorimotor control.

Generalist

278,988 views • 1 year 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.

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

386,618 views • 1 year ago

📢 First contact between a frontier model and robots! Gemini Robotics is a SOTA generalist Vision-Language-Action model bringing frontier model intelligence to the physical world. It's an extremely capable model enabling dexterous, steerable, and general robot control. 🧵⬇️

📢 First contact between a frontier model and robots! Gemini Robotics is a SOTA generalist Vision-Language-Action model bringing frontier model intelligence to the physical world. It's an extremely capable model enabling dexterous, steerable, and general robot control. 🧵⬇️

Ted Xiao

152,554 views • 1 year ago

Our military-industrial complex thrives on the profits of war. Defense contractors influence our foreign policy through relentless lobbying and generous campaign contributions, pushing us from one conflict into the next. This cycle of profit-driven warfare must end.

Our military-industrial complex thrives on the profits of war. Defense contractors influence our foreign policy through relentless lobbying and generous campaign contributions, pushing us from one conflict into the next. This cycle of profit-driven warfare must end.

Dr. Jill Stein🌻

352,435 views • 2 years ago

At Physical Intelligence, we teamed up with Weave Robotics and Ultra to stress-test our models in real-world deployments. This was a really fun collaboration that saw our latest pi06 model running in production at Sea Breeze Cleaners and a real warehouse! More below.

At Physical Intelligence, we teamed up with Weave Robotics and Ultra to stress-test our models in real-world deployments. This was a really fun collaboration that saw our latest pi06 model running in production at Sea Breeze Cleaners and a real warehouse! More below.

Sergey Levine

32,333 views • 7 months ago

We’re bringing powerful AI directly onto robots with Gemini Robotics On-Device. 🤖 It’s our first vision-language-action model to help make robots faster, highly efficient, and adaptable to new tasks and environments - without needing a constant internet connection. 🧵

We’re bringing powerful AI directly onto robots with Gemini Robotics On-Device. 🤖 It’s our first vision-language-action model to help make robots faster, highly efficient, and adaptable to new tasks and environments - without needing a constant internet connection. 🧵

Google DeepMind

820,137 views • 1 year ago

How to learn dexterous manipulation for any robot hand from a single human demonstration? Check out DexMachina, our new RL algorithm that learns long-horizon, bimanual dexterous policies for a variety of dexterous hands, articulated objects, and complex motions.

How to learn dexterous manipulation for any robot hand from a single human demonstration? Check out DexMachina, our new RL algorithm that learns long-horizon, bimanual dexterous policies for a variety of dexterous hands, articulated objects, and complex motions.

Mandi Zhao

121,807 views • 1 year ago

We took a short break from robotics to build a human-level agent to play Competitive Pokémon. Partially observed. Stochastic. Long-horizon. Now mastered with Offline RL + Transformers. Our agent, trained on 475k+ human battles, hits the top 10% on Pokémon Showdown leaderboards. No search or heuristics, just sequence modeling. Today, we're open-sourcing our Metamon platform with our algorithms, data, and environments: 🌐 We are excited to see how our work accelerates research on building generally capable AI agents, and more importantly, inspires the next generation of Pokémon trainers!

We took a short break from robotics to build a human-level agent to play Competitive Pokémon. Partially observed. Stochastic. Long-horizon. Now mastered with Offline RL + Transformers. Our agent, trained on 475k+ human battles, hits the top 10% on Pokémon Showdown leaderboards. No search or heuristics, just sequence modeling. Today, we're open-sourcing our Metamon platform with our algorithms, data, and environments: 🌐 We are excited to see how our work accelerates research on building generally capable AI agents, and more importantly, inspires the next generation of Pokémon trainers!

Yuke Zhu

50,783 views • 1 year ago

Introducing FLUX-mimic, a next-generation Video-Action Model for general purpose dexterity, developed in partnership with Black Forest Labs. Late last year we published mimic-video and introduced Video-Action Models (VAM): a new family of robotics foundation models built on top of video generation models. We showed that robot control reduces to visual prediction, and that robot capability is downstream of improvements in video modeling accuracy. The obvious implication was that advances in the video modeling frontier would directly translate to increased capabilities in end-to-end robot learning. FLUX-mimic is that thesis at frontier scale: We've applied our VAM architecture to the strongest video backbone available today, FLUX 3 from Black Forest Labs, and trained it on data from our own robots and wearables. General-purpose dexterity, running on a single GPU on premises. Because the model already understands world dynamics, it needs far fewer demonstrations to learn a new task. This is game-changing for our mission to deploy robots to factory floors, where industrial robot data is scarce and expensive to collect. We're now testing and deploying FLUX-mimic with manufacturing leaders like Audi USA, on complex, multi-step manipulation long considered impossible for conventional automation.

Introducing FLUX-mimic, a next-generation Video-Action Model for general purpose dexterity, developed in partnership with Black Forest Labs. Late last year we published mimic-video and introduced Video-Action Models (VAM): a new family of robotics foundation models built on top of video generation models. We showed that robot control reduces to visual prediction, and that robot capability is downstream of improvements in video modeling accuracy. The obvious implication was that advances in the video modeling frontier would directly translate to increased capabilities in end-to-end robot learning. FLUX-mimic is that thesis at frontier scale: We've applied our VAM architecture to the strongest video backbone available today, FLUX 3 from Black Forest Labs, and trained it on data from our own robots and wearables. General-purpose dexterity, running on a single GPU on premises. Because the model already understands world dynamics, it needs far fewer demonstrations to learn a new task. This is game-changing for our mission to deploy robots to factory floors, where industrial robot data is scarce and expensive to collect. We're now testing and deploying FLUX-mimic with manufacturing leaders like Audi USA, on complex, multi-step manipulation long considered impossible for conventional automation.

mimic

119,063 views • 2 months ago

1/ We are speed running industrial robotics. It took us just 19 days from the first day of data collection to filming a 2.5-hour continuous run of our model autonomously breaking down industrial containers — zero human intervention. The data efficiency of our DVA model is fundamentally changing how fast we bring robots out of the lab and into the factory. Autonomous operation with 3 hours of data collection at a customer factory.

1/ We are speed running industrial robotics. It took us just 19 days from the first day of data collection to filming a 2.5-hour continuous run of our model autonomously breaking down industrial containers — zero human intervention. The data efficiency of our DVA model is fundamentally changing how fast we bring robots out of the lab and into the factory. Autonomous operation with 3 hours of data collection at a customer factory.

Rhoda AI

26,442 views • 6 months ago

Elon Musk’s farewell to Model S/X Production, which will be ending in Q2 2026: “It's time to basically bring the Model S and X programs to an end with an honorable discharge. We're moving into a future that is based on autonomy. We're going to take the Model S and X production space in our Fremont Factory, and convert that into an Optimus factory with the long-term goal of 1M/year. It's part of our overall shift to an autonomous future.” 😢

Elon Musk’s farewell to Model S/X Production, which will be ending in Q2 2026: “It's time to basically bring the Model S and X programs to an end with an honorable discharge. We're moving into a future that is based on autonomy. We're going to take the Model S and X production space in our Fremont Factory, and convert that into an Optimus factory with the long-term goal of 1M/year. It's part of our overall shift to an autonomous future.” 😢

Nic Cruz Patane

516,776 views • 8 months ago

Today we’re releasing K2 Think V2, our most capable open-source reasoning model to date. This is a fully sovereign model: trained end-to-end on IFM-curated and synthesized data, with complete transparency from pre-training through final reasoning alignment.

Today we’re releasing K2 Think V2, our most capable open-source reasoning model to date. This is a fully sovereign model: trained end-to-end on IFM-curated and synthesized data, with complete transparency from pre-training through final reasoning alignment.

MBZUAI

287,728 views • 8 months ago

From first components to final assemble, Atlas production is taking flight! Want to build the future of robotics? Check out open roles on our ProtoOps team and more on our careers page.

From first components to final assemble, Atlas production is taking flight! Want to build the future of robotics? Check out open roles on our ProtoOps team and more on our careers page.

Boston Dynamics

37,681 views • 15 days ago

Very excited to share what our research team at Covariant has been working on: RFM-1, our latest Robotics Foundation Model. Built on top of high-quality multimodal data the Covariant robotics fleet has collected over the years, this project embodies our commitment to pushing the boundaries of how AI can interact with and understand the physical world. We're eager to share this milestone with the community and invite feedback and collaboration. Read more at

Very excited to share what our research team at Covariant has been working on: RFM-1, our latest Robotics Foundation Model. Built on top of high-quality multimodal data the Covariant robotics fleet has collected over the years, this project embodies our commitment to pushing the boundaries of how AI can interact with and understand the physical world. We're eager to share this milestone with the community and invite feedback and collaboration. Read more at

Rocky Duan

31,901 views • 2 years ago

Today we’re thrilled to announce #SharpaWave — our first dexterous robotic hand — now officially in mass production and delivery! Robotic dexterity just took a leap forward. #Sharpa #Robotics #AI #DexterousHand #Robot #Humanoid #TactileSensing

Today we’re thrilled to announce #SharpaWave — our first dexterous robotic hand — now officially in mass production and delivery! Robotic dexterity just took a leap forward. #Sharpa #Robotics #AI #DexterousHand #Robot #Humanoid #TactileSensing

Sharpa

135,238 views • 1 year ago

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."

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 views • 1 year ago

We introduced our first story-driven experience in our end-of-year update. Join Plort and SAGE on a journey across Galia and learn how to play Star Atlas along the way. 🌌

We introduced our first story-driven experience in our end-of-year update. Join Plort and SAGE on a journey across Galia and learn how to play Star Atlas along the way. 🌌

Star Atlas

21,733 views • 9 months ago

Today, we’re introducing KinetIQ, our own AI framework for end-to-end orchestration of humanoid robot fleets. One system, multiple robot embodiments. Industrial, service and home environments coordinated in real time. The framework consists of 4 cognitive layers: from high-level task allocation and workflow optimisation down to VLA-based task execution and RL-trained whole-body control. Watch how KinetIQ runs both our wheeled and bipedal robots. Read more on our blog:

Today, we’re introducing KinetIQ, our own AI framework for end-to-end orchestration of humanoid robot fleets. One system, multiple robot embodiments. Industrial, service and home environments coordinated in real time. The framework consists of 4 cognitive layers: from high-level task allocation and workflow optimisation down to VLA-based task execution and RL-trained whole-body control. Watch how KinetIQ runs both our wheeled and bipedal robots. Read more on our blog:

Humanoid

23,975 views • 8 months ago

Aion 1.0 Plan represents an evolution of what the Windows on-device AI platform is capable of at scale! Thrilled to partner with Unsloth AI on optimization across our silicon ecosystem. More #MSBuild news here:

Aion 1.0 Plan represents an evolution of what the Windows on-device AI platform is capable of at scale! Thrilled to partner with Unsloth AI on optimization across our silicon ecosystem. More #MSBuild news here:

Windows Developer

87,624 views • 4 months ago

We’re redefining what’s possible with AI. With the release of our latest model, Command A, optimized for real-world agentic and multilingual tasks, we’re demonstrating our commitment to bringing enterprises AI that goes beyond the ordinary, and offers security & efficiency. Our team has developed highly capable and efficient models that can be run on just 2 GPUs. Check out our tech report to learn more:

We’re redefining what’s possible with AI. With the release of our latest model, Command A, optimized for real-world agentic and multilingual tasks, we’re demonstrating our commitment to bringing enterprises AI that goes beyond the ordinary, and offers security & efficiency. Our team has developed highly capable and efficient models that can be run on just 2 GPUs. Check out our tech report to learn more:

Cohere

16,426 views • 1 year ago