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.

A few weeks ago, we shared our progress on articulated objects and long-horizon tasks. Here are two representative examples: - We've been steadily expanding our asset library to cover more articulated objects. Articulated objects have always been a challenging asset class to handle in simulation. Interacting with them requires... robots to master atomic skills such as pushing, pulling, opening, and closing, and to understand part structure, interaction constraints, and how the object moves. - Long-horizon tasks can now be generated at scale. Long-horizon tasks are the other hard category: they require chaining multiple sub-goals in sequence. A failure early in the task can cascade and make the rest unrecoverable. Axis is scaling along three dimensions at once: data volume, data quality, and task difficulty.show more

Axis Robotics

29,450 subscribers

13,700 views • 1 month 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

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

24,027 views • 5 months ago

How to chain multiple dexterous skills to tackle complex long-horizon manipulation tasks? Imagine retrieving a LEGO block from a pile, rotating it in-hand, and inserting it at the desired location to build a structure. Introducing our new work - Sequential Dexterity 🧵👇

How to chain multiple dexterous skills to tackle complex long-horizon manipulation tasks? Imagine retrieving a LEGO block from a pile, rotating it in-hand, and inserting it at the desired location to build a structure. Introducing our new work - Sequential Dexterity 🧵👇

Chen Wang

159,809 views • 2 years ago

We’ve been working with OpenAI for the past few weeks to test their latest Computer-using Agent model. On our evals, CUA has set a new SOTA. Once integrated with an agent, it can complete long-horizon tasks previously impossible. Try CUA on our playground and Act SDK for free!

We’ve been working with OpenAI for the past few weeks to test their latest Computer-using Agent model. On our evals, CUA has set a new SOTA. Once integrated with an agent, it can complete long-horizon tasks previously impossible. Try CUA on our playground and Act SDK for free!

Scrapybara

89,674 views • 1 year ago

We are publishing our first deep dive on what we believe is one of the most challenging layers in egocentric data - SLAM and VIO in the context of long-horizon state tracking. We break down how SLAM and VIO fail in egocentric settings - visual features vanish at close range, depth sensors saturate, fast head motion blurs frames, and these failures don't always occur in isolation. They hit at the exact same moment, leading to compounding errors and making the downstream data unusable. We believe the foundation for high-quality egocentric data demands sub-centimeter precision over long episodes ranging from a few minutes to up to an hour.

We are publishing our first deep dive on what we believe is one of the most challenging layers in egocentric data - SLAM and VIO in the context of long-horizon state tracking. We break down how SLAM and VIO fail in egocentric settings - visual features vanish at close range, depth sensors saturate, fast head motion blurs frames, and these failures don't always occur in isolation. They hit at the exact same moment, leading to compounding errors and making the downstream data unusable. We believe the foundation for high-quality egocentric data demands sub-centimeter precision over long episodes ranging from a few minutes to up to an hour.

FPV Labs

41,955 views • 4 months ago

I’ve completed all the tasks on Axis Robotics I Made a Video Showing How to Complete Axis Robotics Tasks Easily! Many people are getting stuck while completing Axis Robotics tasks, and some of you asked me to make a detailed video So I made a step-by-step video showing the easiest way to complete the tasks If you haven’t started yet, you can still join early. The project has already raised around $12M, and the Points System is now LIVE 🔗 > Create / log in to your account > Go to Training Tasks > Complete the available tasks > Submit your work properly > Sign your completed tasks > Keep completing different tasks to build your Points Points depend on more than just activity: - Task difficulty - Number of valid tasks - Quality of your submissions - Diversity of tasks - Genuine referrals Don’t keep repeating the same task, Focus on completing different and higher-quality tasks If you’re new to Axis, I recommend starting early and learning the process now instead of waiting until more users join I explained the full process in my video so you can follow it easily Who’s already farming Axis Points?

I’ve completed all the tasks on Axis Robotics I Made a Video Showing How to Complete Axis Robotics Tasks Easily! Many people are getting stuck while completing Axis Robotics tasks, and some of you asked me to make a detailed video So I made a step-by-step video showing the easiest way to complete the tasks If you haven’t started yet, you can still join early. The project has already raised around $12M, and the Points System is now LIVE 🔗 > Create / log in to your account > Go to Training Tasks > Complete the available tasks > Submit your work properly > Sign your completed tasks > Keep completing different tasks to build your Points Points depend on more than just activity: - Task difficulty - Number of valid tasks - Quality of your submissions - Diversity of tasks - Genuine referrals Don’t keep repeating the same task, Focus on completing different and higher-quality tasks If you’re new to Axis, I recommend starting early and learning the process now instead of waiting until more users join I explained the full process in my video so you can follow it easily Who’s already farming Axis Points?

Shadat Official | Airdrop

23,952 views • 12 days ago

Scaling vision-language-action (VLA) models to high-DoF dexterous hands has long been a "holy grail" challenge due to the high-dimensional action space and data scarcity. As a wrap up of the year 2025, we are releasing GR-Dexter, a holistic hardware-model-data framework for generalist manipulation on a bimanual dexterous-hand robot. This is the first VLA system to achieve: ✅ High-DoF Control: Managing a 56-DoF bimanual system (21-DoF per hand). ✅ Long-Horizon Tasks with tool use: Vacuuming, bread serving with tongs, and table decluttering. ✅ Open-World Generalization: Robust performance with unseen objects and abstract instructions. Project page: ArXiv:

Scaling vision-language-action (VLA) models to high-DoF dexterous hands has long been a "holy grail" challenge due to the high-dimensional action space and data scarcity. As a wrap up of the year 2025, we are releasing GR-Dexter, a holistic hardware-model-data framework for generalist manipulation on a bimanual dexterous-hand robot. This is the first VLA system to achieve: ✅ High-DoF Control: Managing a 56-DoF bimanual system (21-DoF per hand). ✅ Long-Horizon Tasks with tool use: Vacuuming, bread serving with tongs, and table decluttering. ✅ Open-World Generalization: Robust performance with unseen objects and abstract instructions. Project page: ArXiv:

Xiao Ma

93,908 views • 7 months ago

We’ve raised $50 million in Series A funding from DST Global Partners, NVIDIA (NVIDIA’s venture capital arm), redalpine , prosusventures , and Moonfire Ventures , following our $7.35M seed round from Frst , Moonfire Ventures , and redalpine just a few months earlier, to build the autonomy stack that makes humanoid robots adaptive, intelligent, and ready for real-world deployment at scale. In less than a year, our team has shown that long-horizon whole-body humanoid control can scale across hardware and tasks by leveraging the power of simulation and reinforcement learning. This funding will help us grow our team, scale our compute and robot fleets, and accelerate the commercialization of our autonomy stack with OEM partners globally. You can find more details in the links shared in the comments.

We’ve raised $50 million in Series A funding from DST Global Partners, NVIDIA (NVIDIA’s venture capital arm), redalpine , prosusventures , and Moonfire Ventures , following our $7.35M seed round from Frst , Moonfire Ventures , and redalpine just a few months earlier, to build the autonomy stack that makes humanoid robots adaptive, intelligent, and ready for real-world deployment at scale. In less than a year, our team has shown that long-horizon whole-body humanoid control can scale across hardware and tasks by leveraging the power of simulation and reinforcement learning. This funding will help us grow our team, scale our compute and robot fleets, and accelerate the commercialization of our autonomy stack with OEM partners globally. You can find more details in the links shared in the comments.

Flexion

71,334 views • 8 months ago

General Intuition CEO Pim de Witte, who's building foundation models trained on video game controller input data ("action-labeled gameplay clips"), says general intelligence won't "taste like an LLM": "We have a scale of data that's going to allow us to jump to the frontier in one capability — which is any system that can be controlled with a game controller (which is most robots) — and then, you can use that to create a sufficiently general intelligence." "As humans, the decision to talk or type is a very, very small subset of the actions that we can actually take." "So in order to create a sufficiently general intelligence to play 10,000+ video games, the model has to be able to predict across the entire action space of human cognition when they're interacting with these environments. Which are 2D and 3D environments, interfaces, long-horizon tasks, short-horizon tasks, [etc.]." "It has to be a sufficiently general intelligence in order to predict actions. Therefore, the type of model you get out is not going to taste like an LLM. This model is going to be incredibly good at navigating unforeseen environments. It's going to be incredibly good at zero-shotting any task that can be done with a game controller."

General Intuition CEO Pim de Witte, who's building foundation models trained on video game controller input data ("action-labeled gameplay clips"), says general intelligence won't "taste like an LLM": "We have a scale of data that's going to allow us to jump to the frontier in one capability — which is any system that can be controlled with a game controller (which is most robots) — and then, you can use that to create a sufficiently general intelligence." "As humans, the decision to talk or type is a very, very small subset of the actions that we can actually take." "So in order to create a sufficiently general intelligence to play 10,000+ video games, the model has to be able to predict across the entire action space of human cognition when they're interacting with these environments. Which are 2D and 3D environments, interfaces, long-horizon tasks, short-horizon tasks, [etc.]." "It has to be a sufficiently general intelligence in order to predict actions. Therefore, the type of model you get out is not going to taste like an LLM. This model is going to be incredibly good at navigating unforeseen environments. It's going to be incredibly good at zero-shotting any task that can be done with a game controller."

TBPN

80,482 views • 1 month ago

Agent development is moving forward. While production scaling traditionally required manual infrastructure setup and provisioning sandboxes from scratch, there's now a faster path. Managed Agents in the Gemini API are officially live. Get maximum agentic power with zero infrastructure overhead. One simple API call delivers a managed, remote sandbox for your agent so you can focus entirely on behavior. 📁 Fully customizable with your instructions, tools, and data via and 🌐 Test, iterate, and scale long-horizon tasks natively in the cloud. The hardest part of building agents is now the part you don't have to build. 👇 Get started now:

Agent development is moving forward. While production scaling traditionally required manual infrastructure setup and provisioning sandboxes from scratch, there's now a faster path. Managed Agents in the Gemini API are officially live. Get maximum agentic power with zero infrastructure overhead. One simple API call delivers a managed, remote sandbox for your agent so you can focus entirely on behavior. 📁 Fully customizable with your instructions, tools, and data via and 🌐 Test, iterate, and scale long-horizon tasks natively in the cloud. The hardest part of building agents is now the part you don't have to build. 👇 Get started now:

Google for Developers

39,294 views • 2 months ago

Experiments in progress. The one on the right has been learning for ~3 hours, the one in the middle for ~1 hour, and the one on the left just started a few minutes ago. The initial motivation for making the physical Atari was just to commit ourselves to a subset of algorithms that can make progress in this setup. This commitment rules out algorithms that require billions of samples to learn (or worse, require multiple environments running in parallel). Atari games are simple enough that we should be able to show learning on them in a short amount of time with no prior knowledge. Since then, I've realized that this setup is also a good way to compare different paradigms in robotics in a principled way. These paradigms are sim2real, learning from tele-operated data, and learning directly on the robots. So far, I have observed that getting sim2real to work reliably is hard. It requires tweaks that don't scale. Policies that can play perfectly in simulation fall apart because of latencies and the messiness of the real world. These aspects could be modeled to improve the simulation, but not without sinking significant human engineering hours. I have higher hopes for learning from tele-operated data, but that requires a human to learn the task first. These experiments are on my to-do list. I have to learn to play some of the games well through the robot. I’m half-decent at playing Pong and Ms Pacman now. Learning directly on robots is looking like the most promising approach. This approach takes away pesky distribution shifts and makes it possible to have algorithms that continually improve with more data and time without any human intervention. It feels great to let experiments run overnight and wake up to find improved policies. With learning on robots, I should, in principle, be able to go on a long vacation and come back to find better policies for complex tasks beyond Atari games. Whether that is possible with current learning algorithms is a different question.

Experiments in progress. The one on the right has been learning for ~3 hours, the one in the middle for ~1 hour, and the one on the left just started a few minutes ago. The initial motivation for making the physical Atari was just to commit ourselves to a subset of algorithms that can make progress in this setup. This commitment rules out algorithms that require billions of samples to learn (or worse, require multiple environments running in parallel). Atari games are simple enough that we should be able to show learning on them in a short amount of time with no prior knowledge. Since then, I've realized that this setup is also a good way to compare different paradigms in robotics in a principled way. These paradigms are sim2real, learning from tele-operated data, and learning directly on the robots. So far, I have observed that getting sim2real to work reliably is hard. It requires tweaks that don't scale. Policies that can play perfectly in simulation fall apart because of latencies and the messiness of the real world. These aspects could be modeled to improve the simulation, but not without sinking significant human engineering hours. I have higher hopes for learning from tele-operated data, but that requires a human to learn the task first. These experiments are on my to-do list. I have to learn to play some of the games well through the robot. I’m half-decent at playing Pong and Ms Pacman now. Learning directly on robots is looking like the most promising approach. This approach takes away pesky distribution shifts and makes it possible to have algorithms that continually improve with more data and time without any human intervention. It feels great to let experiments run overnight and wake up to find improved policies. With learning on robots, I should, in principle, be able to go on a long vacation and come back to find better policies for complex tasks beyond Atari games. Whether that is possible with current learning algorithms is a different question.

Khurram Javed

52,110 views • 8 months ago

While we understand how challenging the HOH position can be, Sheba will always stay committed to the task ! Sheba will pull her weight and support every HOH accordingly. The wager is a general team effort and as you know, Queen Sheba doesn’t joke with tasks !!! Let’s stay focused on VOTING SHEBA, we are almost at the end of the line !!! #BBNaija #ShebaGamde

While we understand how challenging the HOH position can be, Sheba will always stay committed to the task ! Sheba will pull her weight and support every HOH accordingly. The wager is a general team effort and as you know, Queen Sheba doesn’t joke with tasks !!! Let’s stay focused on VOTING SHEBA, we are almost at the end of the line !!! #BBNaija #ShebaGamde

Sheba BBNAIJA

69,498 views • 3 days ago

Tesla's Chief Designer Franz on Optimus: "It's going to be huge piece of Tesla, a huge piece in our world, as we look into the future, the ability to take menial tasks and things that you don't necessarily want to do and have them uploaded to somebody, a human, that can do that. We've been designing the robot that really looks at how humans work in the world. This world is designed around humans, and so I think having a robot that can do the things that humans can do can really start to take those menial tasks away and enrich in our lives, make our lives better we get to spend more time doing the things that we love. It's been incredibly fast paced, but the progress is, like, unbelievable in the short amount of time that the team has been working on it, and we've been growing the team and building the project the same time. I think we're breaking ground in this space everyday. The team is really energized and fired out. Elon Musk is incredibly involved in this. It's a great project to be a part of, and seeing where the future is gonna go and how it's going to enrich our lives is super exciting."

Tesla's Chief Designer Franz on Optimus: "It's going to be huge piece of Tesla, a huge piece in our world, as we look into the future, the ability to take menial tasks and things that you don't necessarily want to do and have them uploaded to somebody, a human, that can do that. We've been designing the robot that really looks at how humans work in the world. This world is designed around humans, and so I think having a robot that can do the things that humans can do can really start to take those menial tasks away and enrich in our lives, make our lives better we get to spend more time doing the things that we love. It's been incredibly fast paced, but the progress is, like, unbelievable in the short amount of time that the team has been working on it, and we've been growing the team and building the project the same time. I think we're breaking ground in this space everyday. The team is really energized and fired out. Elon Musk is incredibly involved in this. It's a great project to be a part of, and seeing where the future is gonna go and how it's going to enrich our lives is super exciting."

DogeDesigner

202,945 views • 10 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 • 3 months ago

Thrilled to share one of my favorite works this year: DexNDM! We bridge the Sim2Real gap for dexterous in-hand rotation, achieving a true "0-to-1" advancement. The key? DexNDM learns from biased, real-world data without needing any successful demonstrations. Now a general-purpose dexterous hand can stably rotate large books, long rods, & complex objects around any axis, from any wrist pose. This powerful primitive enables complex, long-horizon tasks like teleoperated screwing and furniture assembly. 📄 Paper: 🌐 Project Page:

Thrilled to share one of my favorite works this year: DexNDM! We bridge the Sim2Real gap for dexterous in-hand rotation, achieving a true "0-to-1" advancement. The key? DexNDM learns from biased, real-world data without needing any successful demonstrations. Now a general-purpose dexterous hand can stably rotate large books, long rods, & complex objects around any axis, from any wrist pose. This powerful primitive enables complex, long-horizon tasks like teleoperated screwing and furniture assembly. 📄 Paper: 🌐 Project Page:

Li Yi

38,751 views • 9 months ago

Synthetic data will provide the next trillion tokens to fuel our hungry models. I'm excited to announce MimicGen: massively scaling up data pipeline for robot learning! We multiply high-quality human data in simulation with digital twins. Using 50,000 training episodes across 18 tasks, multiple simulators, and even in the real-world! The idea is simple: 1. Humans tele-operate the robot to complete a task. It is extremely high-quality but also very slow and expensive. 2. We create a digital twin of the robot and the scene in high-fidelity, GPU-accelerated simulation. 3. We can now move objects around, replace with new assets, and even change the robot hand - basically augment the training data with procedural generation. 4. Export the successful episodes, and feed that to a neural network! You now have an near-infinite stream of data. One of the key reasons that robotics lags far behind other AI fields is the lack of data: you cannot scrape control signals from the internet. They simply don't exist in-the-wild. MimicGen shows the power of synthetic data and simulation to keep our scaling laws alive. I believe this principle apply beyond robotics. We are quickly exhausting the high-quality, real tokens from the web. Artificial intelligence from artificial data will be the way forward. We are big fans of the OSS community. As usual, we open-source everything, including the generated dataset! - Website: - Paper: - Dataset is hosted on HuggingFace (thanks AK!!): - Code: MimicGen is led by Ajay Mandlekar, deep dive in the thread:

Synthetic data will provide the next trillion tokens to fuel our hungry models. I'm excited to announce MimicGen: massively scaling up data pipeline for robot learning! We multiply high-quality human data in simulation with digital twins. Using 50,000 training episodes across 18 tasks, multiple simulators, and even in the real-world! The idea is simple: 1. Humans tele-operate the robot to complete a task. It is extremely high-quality but also very slow and expensive. 2. We create a digital twin of the robot and the scene in high-fidelity, GPU-accelerated simulation. 3. We can now move objects around, replace with new assets, and even change the robot hand - basically augment the training data with procedural generation. 4. Export the successful episodes, and feed that to a neural network! You now have an near-infinite stream of data. One of the key reasons that robotics lags far behind other AI fields is the lack of data: you cannot scrape control signals from the internet. They simply don't exist in-the-wild. MimicGen shows the power of synthetic data and simulation to keep our scaling laws alive. I believe this principle apply beyond robotics. We are quickly exhausting the high-quality, real tokens from the web. Artificial intelligence from artificial data will be the way forward. We are big fans of the OSS community. As usual, we open-source everything, including the generated dataset! - Website: - Paper: - Dataset is hosted on HuggingFace (thanks AK!!): - Code: MimicGen is led by Ajay Mandlekar, deep dive in the thread:

Jim Fan

332,238 views • 2 years ago

Robots need to be able to apply pressure and make contact with objects as needed in order to accomplish their tasks. From compliance to working safely around humans to whole-body manipulation of heavy objects, combining force and position control can dramatically expand the capabilities of robots. This is especially true for legged robots, which have so much ability to exert forces on the world around them. But how do we train robots which can do this? Baoxiong Jia tells us more in our discussion of his team’s recent, Best Paper Award winning work on learning a unified policy for position and force control, called UniFP. To learn more, watch Episode #49 of RoboPapers, hosted by Michael Cho - Rbt/Acc and Chris Paxton.

Robots need to be able to apply pressure and make contact with objects as needed in order to accomplish their tasks. From compliance to working safely around humans to whole-body manipulation of heavy objects, combining force and position control can dramatically expand the capabilities of robots. This is especially true for legged robots, which have so much ability to exert forces on the world around them. But how do we train robots which can do this? Baoxiong Jia tells us more in our discussion of his team’s recent, Best Paper Award winning work on learning a unified policy for position and force control, called UniFP. To learn more, watch Episode #49 of RoboPapers, hosted by Michael Cho - Rbt/Acc and Chris Paxton.

RoboPapers

44,803 views • 8 months ago

The DeepSeek-R1 paper is a gem! Highly encourage everyone to read it. It's clear that LLM reasoning capabilities can be learned in different ways. RL, if applied correctly and at scale, can lead to some really powerful and interesting scaling and emergent properties. There is more to RL than meets the eye! Here is my breakdown of the paper along with a few tests: The multi-state training might not make sense initially but they provide clues on optimizations that we can continue to tap into. Data quality is still very important for enhancing the usability of the LLM. Unlike other reasoning LLMs, DeepSeek-R1's training recipe and weights are open so we can build on top of it. This opens up exciting research opportunities. About the attached clip: the previous preview model wasn't able to solve this task. DeepSeek-R1 can solve this and many other tasks that o1 can solve. It's a very good model for coding and math.

The DeepSeek-R1 paper is a gem! Highly encourage everyone to read it. It's clear that LLM reasoning capabilities can be learned in different ways. RL, if applied correctly and at scale, can lead to some really powerful and interesting scaling and emergent properties. There is more to RL than meets the eye! Here is my breakdown of the paper along with a few tests: The multi-state training might not make sense initially but they provide clues on optimizations that we can continue to tap into. Data quality is still very important for enhancing the usability of the LLM. Unlike other reasoning LLMs, DeepSeek-R1's training recipe and weights are open so we can build on top of it. This opens up exciting research opportunities. About the attached clip: the previous preview model wasn't able to solve this task. DeepSeek-R1 can solve this and many other tasks that o1 can solve. It's a very good model for coding and math.

elvis

140,692 views • 1 year ago

Here’s the windmill assembly demo we showed at CES 2026 — the one no one saw coming. North executes a fully autonomous, long-horizon dexterous sequence with sustained hand–eye–tactile coordination and assembly-level precision enabled by tactile feedback. It’s also robust to disturbance: you can reposition the objects, and North will still identify them and recover the task. This is powered by CraftNet (VTLA) — using tactile feedback to continuously fine-tune the last-millimeter interaction, enabling reliable execution across 30+ steps. Read more about CraftNet: #Sharpa #SharpaWave #SharpaNorth #CraftNet #System0 #CES2026

Here’s the windmill assembly demo we showed at CES 2026 — the one no one saw coming. North executes a fully autonomous, long-horizon dexterous sequence with sustained hand–eye–tactile coordination and assembly-level precision enabled by tactile feedback. It’s also robust to disturbance: you can reposition the objects, and North will still identify them and recover the task. This is powered by CraftNet (VTLA) — using tactile feedback to continuously fine-tune the last-millimeter interaction, enabling reliable execution across 30+ steps. Read more about CraftNet: #Sharpa #SharpaWave #SharpaNorth #CraftNet #System0 #CES2026

Sharpa

87,951 views • 7 months ago

There is no such thing as a safe or trustworthy ALPR. Companies like Flock are driven by profit and in order to compete for contracts they have to create more and more powerful surveillance tools so they can sell more of our data. As long as we live in a system driven by profit where private companies own and control our data there is no way to remove the dangers of ALPRs. That is why we are here today to call for a total ban on ALPRs in Chandler.

There is no such thing as a safe or trustworthy ALPR. Companies like Flock are driven by profit and in order to compete for contracts they have to create more and more powerful surveillance tools so they can sell more of our data. As long as we live in a system driven by profit where private companies own and control our data there is no way to remove the dangers of ALPRs. That is why we are here today to call for a total ban on ALPRs in Chandler.

Orwell Day

10,864 views • 2 days ago