正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

Here’s something you didn’t know LLMs can do – reconstruct articulated objects! Introducing Real2Code – our new real2sim approach that scalably reconstructs complex, multi-part articulated objects.

Mandi Zhao

4,878 subscribers

91,867 次观看 • 2 年前 •via X (Twitter)

教育新闻政治科学技术

Anya Rossi• Live Now

Private livecam show

0 条评论

暂无评论

原始帖子的评论将显示在这里

相关视频

Wouldn’t it be nice if ChatGPT could find your missing keys for you? Our latest research from Berkeley AI Research + Google AI suggests that robots can use large language models (LLMs) to find hidden objects faster. 🧵👇

Wouldn’t it be nice if ChatGPT could find your missing keys for you? Our latest research from Berkeley AI Research + Google AI suggests that robots can use large language models (LLMs) to find hidden objects faster. 🧵👇

Kaushik Shivakumar

58,523 次观看 • 3 年前

Introducing Attio Objects 🚀 We know how hard it is to find a CRM that fits your unique business model. That's why we built Attio Objects – our powerful data model with custom objects that gives you complete flexibility to structure your CRM exactly how you need it. Along with custom objects, we've also introduced new standard objects: - Workspaces and Users objects for PLG businesses. - A robust Deals object for sales-driven companies. This is the culmination of a 4-year effort, with 3 years of work put in even before launching Attio. Since day one, we've been determined to solve the fundamental problem in the CRM space: the trade-off between power and time-to-value. If you wanted power and flexibility, your CRM would take forever to build and not work well with your stack. If you wanted speed, you'd need to use highly opinionated, inflexible software that doesn't really work for your business. That ends today. With Attio, you no longer have to compromise. Build your CRM your way, fast. Iterate as you grow. High-growth startups like Replicate, , and Modal and more are already using Attio's object architecture to perfectly match their businesses and accelerate their growth. To get all the details, check out our blog post 👇

Introducing Attio Objects 🚀 We know how hard it is to find a CRM that fits your unique business model. That's why we built Attio Objects – our powerful data model with custom objects that gives you complete flexibility to structure your CRM exactly how you need it. Along with custom objects, we've also introduced new standard objects: - Workspaces and Users objects for PLG businesses. - A robust Deals object for sales-driven companies. This is the culmination of a 4-year effort, with 3 years of work put in even before launching Attio. Since day one, we've been determined to solve the fundamental problem in the CRM space: the trade-off between power and time-to-value. If you wanted power and flexibility, your CRM would take forever to build and not work well with your stack. If you wanted speed, you'd need to use highly opinionated, inflexible software that doesn't really work for your business. That ends today. With Attio, you no longer have to compromise. Build your CRM your way, fast. Iterate as you grow. High-growth startups like Replicate, , and Modal and more are already using Attio's object architecture to perfectly match their businesses and accelerate their growth. To get all the details, check out our blog post 👇

Attio

26,821 次观看 • 2 年前

Excited to share our new reference-to-video feature in Grok Imagine. You can drop in up to 7 image references and turn them into a video. The images can be characters, objects, or anything! Update the Grok app and give it a try! Honored to be part of this incredible team and contribute a small piece to it 🚀

Excited to share our new reference-to-video feature in Grok Imagine. You can drop in up to 7 image references and turn them into a video. The images can be characters, objects, or anything! Update the Grok app and give it a try! Honored to be part of this incredible team and contribute a small piece to it 🚀

Ethan He

198,931 次观看 • 5 个月前

Applying to university or know someone who is? ALX is introducing a new 3-Year Tech programme that will qualify you for a degree. Graduates will not only earn a certificate from ALX, but will also earn academic credits that can transferred to one our global partner universities.

Applying to university or know someone who is? ALX is introducing a new 3-Year Tech programme that will qualify you for a degree. Graduates will not only earn a certificate from ALX, but will also earn academic credits that can transferred to one our global partner universities.

ALX Africa

22,439 次观看 • 3 年前

New research from Databricks: LLMs Can Learn to Reason via Off-Policy RL Optimal Advantage-based Policy Optimization with Lagged Inference policy (OAPL) shows you don’t need strict on-policy training to improve reasoning. It matches or beats Group Relative Policy Optimization (GRPO), stays stable with large policy lag, and uses ~3× fewer training generations. For Databricks customers, it’s a simpler, practical, and equally powerful approach to RL that Databricks is pioneering internally — and bringing directly to Databricks customers, so enterprises can improve agents using the same methods we use for our in-house agents, without complex infrastructure changes.

New research from Databricks: LLMs Can Learn to Reason via Off-Policy RL Optimal Advantage-based Policy Optimization with Lagged Inference policy (OAPL) shows you don’t need strict on-policy training to improve reasoning. It matches or beats Group Relative Policy Optimization (GRPO), stays stable with large policy lag, and uses ~3× fewer training generations. For Databricks customers, it’s a simpler, practical, and equally powerful approach to RL that Databricks is pioneering internally — and bringing directly to Databricks customers, so enterprises can improve agents using the same methods we use for our in-house agents, without complex infrastructure changes.

Databricks AI Research

12,699 次观看 • 6 个月前

You can't 3D reconstruct glass from images... ...WRONG! Thanks for video diffusion, now just about anything is possible! Introducing...Diffusion Knows Transparency (DKT) Transparent and reflective objects usually break robot vision and photogrammetry pipelines because they don't follow the "solid object" rules standard cameras expect. DKT is a new AI model that repurposes the "internal physics engine" found in video generation models to solve this problem. Researchers took a massive video diffusion model (WAN) and fine-tuned it using a custom-built synthetic dataset to turn it into a high-precision depth sensor. To train the AI, they built the first massive synthetic video library of transparent objects, 1.32 million frames of perfectly labeled glass and metal objects in motion. Without ever seeing a "real" labeled video of glass during training, the model (DKT) outperformed all previous specialized systems on real-world benchmarks (ClearPose, DREDS). They created a "lightweight" 1.3B parameter version that runs fast enough (0.17s per frame) to be used on actual robot hardware. Two reasons I find this project important: 1. It further proves that synthetic data will be essential for training the next generation vision models. 2. In real-world robotic tests, using DKT's depth maps nearly doubled the success rate of robot arms trying to pick up objects on tricky reflective or translucent surfaces. At home robots will need to interact with these types of objects on a daily basis. Check out the project page here: Code is LIVE! #Computervision #Robotics #AI

You can't 3D reconstruct glass from images... ...WRONG! Thanks for video diffusion, now just about anything is possible! Introducing...Diffusion Knows Transparency (DKT) Transparent and reflective objects usually break robot vision and photogrammetry pipelines because they don't follow the "solid object" rules standard cameras expect. DKT is a new AI model that repurposes the "internal physics engine" found in video generation models to solve this problem. Researchers took a massive video diffusion model (WAN) and fine-tuned it using a custom-built synthetic dataset to turn it into a high-precision depth sensor. To train the AI, they built the first massive synthetic video library of transparent objects, 1.32 million frames of perfectly labeled glass and metal objects in motion. Without ever seeing a "real" labeled video of glass during training, the model (DKT) outperformed all previous specialized systems on real-world benchmarks (ClearPose, DREDS). They created a "lightweight" 1.3B parameter version that runs fast enough (0.17s per frame) to be used on actual robot hardware. Two reasons I find this project important: 1. It further proves that synthetic data will be essential for training the next generation vision models. 2. In real-world robotic tests, using DKT's depth maps nearly doubled the success rate of robot arms trying to pick up objects on tricky reflective or translucent surfaces. At home robots will need to interact with these types of objects on a daily basis. Check out the project page here: Code is LIVE! #Computervision #Robotics #AI

Jonathan Stephens

17,712 次观看 • 7 个月前

We’ve been working on something for 8 months. If you write emails, you know the struggle. You’re digging through your inbox, scrolling screenshots, trying to find inspiration that shouldn’t take this long. So Jimmy Kim and I built a solution. One place to search around 1,000,000 real ecommerce emails. But here’s the part I’m most excited about: You can click any email and get instant AI analysis on what worked, what didn’t, and why it converted. Real examples. Real breakdowns. Real insights you can use today. Free trial is live if you want to try it:

We’ve been working on something for 8 months. If you write emails, you know the struggle. You’re digging through your inbox, scrolling screenshots, trying to find inspiration that shouldn’t take this long. So Jimmy Kim and I built a solution. One place to search around 1,000,000 real ecommerce emails. But here’s the part I’m most excited about: You can click any email and get instant AI analysis on what worked, what didn’t, and why it converted. Real examples. Real breakdowns. Real insights you can use today. Free trial is live if you want to try it:

Chase Dimond | Email Marketing Nerd 📧

38,831 次观看 • 8 个月前

🚨 CHINESE SCIENTISTS JUST INVENTED 3D PRINTING THAT CREATES OBJECTS IN 0.6 SECONDS USING ONLY LIGHT. Researchers at Tsinghua University have developed a new method called DISH (Digital Incoherent Synthesis of Holographic light fields) that can print complex millimeter-scale objects almost instantly. Instead of slowly building layer by layer, the system fires thousands of precisely patterned light images from multiple angles into a still vat of liquid resin. Where the light overlaps, the resin instantly hardens into a solid 3D object. The entire process takes just 0.6 seconds. Why this matters: • It’s currently the fastest volumetric 3D printing method ever demonstrated • Achieves extremely fine detail features thinner than a human hair • The resin stays completely still, so there’s no vibration or distortion • It can work with watery (low-viscosity) resins, making it suitable for biological applications • The team has already printed complex structures like blood vessel-like tubes and even a tiny bust of a historical figure The deeper implication: Traditional 3D printing has always been limited by speed and the need to move either the print head or the resin. This approach removes both constraints by using light itself as the sculptor. Because it can print directly into still liquid (and potentially onto living tissue), it opens new possibilities in bioprinting, medical devices, and rapid manufacturing. If the technology can be scaled beyond millimeter sizes, it could fundamentally change how we think about making physical objects turning “print” from a slow process into something closer to instantaneous fabrication. We’re moving from “layer by layer” to “all at once.” How do you think instant volumetric 3D printing like this could change medicine, manufacturing, or everyday life if it becomes widely available? Follow for more frontier manufacturing and materials science breakthroughs.

🚨 CHINESE SCIENTISTS JUST INVENTED 3D PRINTING THAT CREATES OBJECTS IN 0.6 SECONDS USING ONLY LIGHT. Researchers at Tsinghua University have developed a new method called DISH (Digital Incoherent Synthesis of Holographic light fields) that can print complex millimeter-scale objects almost instantly. Instead of slowly building layer by layer, the system fires thousands of precisely patterned light images from multiple angles into a still vat of liquid resin. Where the light overlaps, the resin instantly hardens into a solid 3D object. The entire process takes just 0.6 seconds. Why this matters: • It’s currently the fastest volumetric 3D printing method ever demonstrated • Achieves extremely fine detail features thinner than a human hair • The resin stays completely still, so there’s no vibration or distortion • It can work with watery (low-viscosity) resins, making it suitable for biological applications • The team has already printed complex structures like blood vessel-like tubes and even a tiny bust of a historical figure The deeper implication: Traditional 3D printing has always been limited by speed and the need to move either the print head or the resin. This approach removes both constraints by using light itself as the sculptor. Because it can print directly into still liquid (and potentially onto living tissue), it opens new possibilities in bioprinting, medical devices, and rapid manufacturing. If the technology can be scaled beyond millimeter sizes, it could fundamentally change how we think about making physical objects turning “print” from a slow process into something closer to instantaneous fabrication. We’re moving from “layer by layer” to “all at once.” How do you think instant volumetric 3D printing like this could change medicine, manufacturing, or everyday life if it becomes widely available? Follow for more frontier manufacturing and materials science breakthroughs.

TheNewPhysics

347,458 次观看 • 2 个月前

Did you know that we recently added some exciting new routes to and from our Tirana base? 🤩 You can now #WIZZ to 🇷🇴 Bucharest, 🇧🇬 Sofia, 🇨🇿 Prague, 🇵🇱 Krakow, 🇮🇹 Palermo, 🇲🇹 Malta and 🇬🇷 Chania Which destination do you want to fly next on your travel bucket list? ✈️

Did you know that we recently added some exciting new routes to and from our Tirana base? 🤩 You can now #WIZZ to 🇷🇴 Bucharest, 🇧🇬 Sofia, 🇨🇿 Prague, 🇵🇱 Krakow, 🇮🇹 Palermo, 🇲🇹 Malta and 🇬🇷 Chania Which destination do you want to fly next on your travel bucket list? ✈️

Wizz Air

34,880 次观看 • 3 年前

You’re standing on the tarmac, the engine is powering up for takeoff, and suddenly you hear that unmistakable THWACK 💀✈️ Something just got sucked in while everything was still in pre-flight mode. The crew stops, the sound changes, and you can feel the whole vibe shift instantly. Now here’s the question for you — what actually happens next? Do they shut it down immediately? Run a check? Delay the flight? I’m genuinely curious what people who know aviation would do here. Drop your thoughts, theories, or facts below 👇 Let’s see who gets it right and teach the rest of us something new.

You’re standing on the tarmac, the engine is powering up for takeoff, and suddenly you hear that unmistakable THWACK 💀✈️ Something just got sucked in while everything was still in pre-flight mode. The crew stops, the sound changes, and you can feel the whole vibe shift instantly. Now here’s the question for you — what actually happens next? Do they shut it down immediately? Run a check? Delay the flight? I’m genuinely curious what people who know aviation would do here. Drop your thoughts, theories, or facts below 👇 Let’s see who gets it right and teach the rest of us something new.

MrTOHA

7,676,644 次观看 • 3 个月前

She represented me at a Bristol Business connect this morning. I couldn’t make it for the event, because of other prior engagements. Ultimately, I have a partner who is well rounded, supportive, knowledgeable and ambitious, I am willing to build more with her until eventually our family reach the perk of our goal. I remember when we were still courting I told her “ I didn’t promise you a luxurious life, but I can promise you a fulfilled life” If luxury comes as a result, glory to God. But to live a life of purpose is all we desire, which comes with its sacrifice and price. But I want us to leave this world and impact remains. Now that my phone has stop beeping every seconds, I need to remind some of you who said horrible things to me that life is beyond social media. You can disagree without insult, you can have a contrary view well articulated and projected. But you should not always be that person whose hands are design to demoralise others. All the best!!!

She represented me at a Bristol Business connect this morning. I couldn’t make it for the event, because of other prior engagements. Ultimately, I have a partner who is well rounded, supportive, knowledgeable and ambitious, I am willing to build more with her until eventually our family reach the perk of our goal. I remember when we were still courting I told her “ I didn’t promise you a luxurious life, but I can promise you a fulfilled life” If luxury comes as a result, glory to God. But to live a life of purpose is all we desire, which comes with its sacrifice and price. But I want us to leave this world and impact remains. Now that my phone has stop beeping every seconds, I need to remind some of you who said horrible things to me that life is beyond social media. You can disagree without insult, you can have a contrary view well articulated and projected. But you should not always be that person whose hands are design to demoralise others. All the best!!!

Noah SULAIMON

174,984 次观看 • 8 个月前

It pains me to know that the belief is that a therapist role is to "validate". I do not validate. If you are with me in a clinical setting and what you're saying doesn't make any damn sense, I'm going to have you walk me through it. What I've discovered is that a lot of the dysfunction people have is that they've never articulated their beliefs and so have no idea how absurd they are. Simply going through the exercise of having to explain yourself can be deeply rewarding. It's something we call "accountability". You literally account for yourself. Sure, I've had some female clients chimp out and flee never to be seen again at their first contact with a mirror. I've had many others weep openly that actually being held psychologically. One I will never get out of my mind was a wonderful 30-something year old woman who cried and said, "I have been in therapy for 7 years. Why has nobody ever challenged me and help me see that I'm the one causing all this shit?" That's an important question. And it's crucial that if you see a therapist, you don't see a charlatan. You can tell the good ones by their headgear.

It pains me to know that the belief is that a therapist role is to "validate". I do not validate. If you are with me in a clinical setting and what you're saying doesn't make any damn sense, I'm going to have you walk me through it. What I've discovered is that a lot of the dysfunction people have is that they've never articulated their beliefs and so have no idea how absurd they are. Simply going through the exercise of having to explain yourself can be deeply rewarding. It's something we call "accountability". You literally account for yourself. Sure, I've had some female clients chimp out and flee never to be seen again at their first contact with a mirror. I've had many others weep openly that actually being held psychologically. One I will never get out of my mind was a wonderful 30-something year old woman who cried and said, "I have been in therapy for 7 years. Why has nobody ever challenged me and help me see that I'm the one causing all this shit?" That's an important question. And it's crucial that if you see a therapist, you don't see a charlatan. You can tell the good ones by their headgear.

The People's Therapist 👏Expert👏

17,992 次观看 • 5 个月前

📢 Introducing the all-new Joltify Chain Point Hubs! 🎉 Join us today and invite your friends to start earning points! 🚀 Engage in quick and easy tasks to unlock thrilling rewards down the line! This hub is by INVITATION ONLY. This means you can only obtain invitation codes from our exclusive ambassadors, KOLs. Normal users can generate invitation codes only after they accumulate 160 points. 🌟 Don't miss out on this opportunity to be part of our vibrant community and reap the benefits that await you! #JoltifyPoints #CommunityRewards #JoinTheJourney

📢 Introducing the all-new Joltify Chain Point Hubs! 🎉 Join us today and invite your friends to start earning points! 🚀 Engage in quick and easy tasks to unlock thrilling rewards down the line! This hub is by INVITATION ONLY. This means you can only obtain invitation codes from our exclusive ambassadors, KOLs. Normal users can generate invitation codes only after they accumulate 160 points. 🌟 Don't miss out on this opportunity to be part of our vibrant community and reap the benefits that await you! #JoltifyPoints #CommunityRewards #JoinTheJourney

Joltify

3,006,085 次观看 • 2 年前

Gemini Omni is changing video creation and most people still don't know what it can actually do. Here are 7 things you can do with it right now: 1. Image to Video in multiple styles: Upload a photo. describe the style. Gemini Omni turns it into a video. cinematic, anime, realistic. 2. Reimagine camera angles: Take any image and visualize it from a completely different angle. no reshooting. just describe it. 3. Change backgrounds: Swap the background of any video through plain conversation. no green screen. no editing software. 4. Change hairstyle: Describe a new hairstyle. Gemini Omni applies it. characters stay consistent across every frame. 5. visualize with moodboards: feed it a moodboard, audio, and a brief. it builds the video around the full creative reference — not just a text prompt. 6. swap characters and objects mid-scene: replace people, props, and objects in an existing video. the scene stays consistent. the physics hold up. 7. edit physics: describe how you want things to move. Gemini Omni adjusts the physics of the scene through conversation.

Gemini Omni is changing video creation and most people still don't know what it can actually do. Here are 7 things you can do with it right now: 1. Image to Video in multiple styles: Upload a photo. describe the style. Gemini Omni turns it into a video. cinematic, anime, realistic. 2. Reimagine camera angles: Take any image and visualize it from a completely different angle. no reshooting. just describe it. 3. Change backgrounds: Swap the background of any video through plain conversation. no green screen. no editing software. 4. Change hairstyle: Describe a new hairstyle. Gemini Omni applies it. characters stay consistent across every frame. 5. visualize with moodboards: feed it a moodboard, audio, and a brief. it builds the video around the full creative reference — not just a text prompt. 6. swap characters and objects mid-scene: replace people, props, and objects in an existing video. the scene stays consistent. the physics hold up. 7. edit physics: describe how you want things to move. Gemini Omni adjusts the physics of the scene through conversation.

Poonam Soni

11,682 次观看 • 28 天前

Introducing Singularity AI Machines. One-click deployable GPUs with built-in LLMs. Deploy in one click, and within minutes you get an OpenAI-compatible API running high-speed inference on compute that stays under your control. You can literally deploy a machine and: 1. Apply to OpenRouter as a provider 2. Start your own AI business 3. Join Singularity Grid in one click without owning any hardware 4. Let AI agents launch and manage your machines for you Until now, becoming an AI provider felt like something only infra companies could do. We are making it accessible to literally everyone. Singularity AI Machines are live.

Introducing Singularity AI Machines. One-click deployable GPUs with built-in LLMs. Deploy in one click, and within minutes you get an OpenAI-compatible API running high-speed inference on compute that stays under your control. You can literally deploy a machine and: 1. Apply to OpenRouter as a provider 2. Start your own AI business 3. Join Singularity Grid in one click without owning any hardware 4. Let AI agents launch and manage your machines for you Until now, becoming an AI provider felt like something only infra companies could do. We are making it accessible to literally everyone. Singularity AI Machines are live.

The Singularity Layer

13,492 次观看 • 1 个月前

Is your toddler suddenly throwing (or dropping) everything they get their hands on? Food, toys… you name it. You’re not alone. This week I’ve been introducing play schemas, 9 common patterns that can help to demystify your toddler’s seemingly random behaviors. And you guessed it: this is one. We call it the trajectory schema. If you take nothing else away from this post, let it be this: your little one doesn’t throw things because they are misbehaving or “bad.” Babies throw things because they are babies. And they are learning as they do so. Learning about cause and effect. Learning about gravity. Learning what (and practicing something new) they can do with their bodies. Learning hand-eye coordination. It’s a completely normal part of development. And the fascination won’t last forever. The real question is, how do you manage it? First, be proactive. Expect that anything your little one handles might reasonably be thrown or dropped. So choose wisely, avoiding items that are valuable or might pose a danger to them or others if they suddenly took flight. Second, depending on the age of your child, begin introducing some natural consequences. Put the toy/object away temporarily after it is thrown (if throwing it is dangerous or inappropriate). And involve your child in the subsequent clean-up. You can also redirect. Explain which things are and are not for throwing. Model the correct use of these objects. Finally, lean into it. Recognizing that young children are drawn to throwing, provide items that are safe and acceptable to throw. Soft toys. Socks. Balls. And look for opportunities and settings for your little one to explore this urge safely and appropriately. How did you manage your toddler’s throwing phase? Welcome your tips and tricks! This sweet little throwing machine was posted to TT by kristinnicole122.

Is your toddler suddenly throwing (or dropping) everything they get their hands on? Food, toys… you name it. You’re not alone. This week I’ve been introducing play schemas, 9 common patterns that can help to demystify your toddler’s seemingly random behaviors. And you guessed it: this is one. We call it the trajectory schema. If you take nothing else away from this post, let it be this: your little one doesn’t throw things because they are misbehaving or “bad.” Babies throw things because they are babies. And they are learning as they do so. Learning about cause and effect. Learning about gravity. Learning what (and practicing something new) they can do with their bodies. Learning hand-eye coordination. It’s a completely normal part of development. And the fascination won’t last forever. The real question is, how do you manage it? First, be proactive. Expect that anything your little one handles might reasonably be thrown or dropped. So choose wisely, avoiding items that are valuable or might pose a danger to them or others if they suddenly took flight. Second, depending on the age of your child, begin introducing some natural consequences. Put the toy/object away temporarily after it is thrown (if throwing it is dangerous or inappropriate). And involve your child in the subsequent clean-up. You can also redirect. Explain which things are and are not for throwing. Model the correct use of these objects. Finally, lean into it. Recognizing that young children are drawn to throwing, provide items that are safe and acceptable to throw. Soft toys. Socks. Balls. And look for opportunities and settings for your little one to explore this urge safely and appropriately. How did you manage your toddler’s throwing phase? Welcome your tips and tricks! This sweet little throwing machine was posted to TT by kristinnicole122.

Dan Wuori

168,975 次观看 • 2 年前

Pi0 vs. ACT with BBox conditioning 🟦 Not many know you can push ACT to *almost-Pi0* generalisation by conditioning on bounding boxes (BBoxes). How is the training data collected? • Generate BBoxes for all pick-and-place objects in the scene.(I used Gemini) • Pick-and-place targets are selected randomly. • Add the BBox coordinates to the robot’s state. • Overlay the BBoxes in the visualisation so you know what to grab and where to drop. During inference: • Generate BBoxes for every object again. • Click the object you want to pick and its target spot; those BBoxes get added to the robot state. • Let the robot do the work for you 😃 Setup: - Trained ACT for 100k steps and fine-tuned Pi0 for only 20k. - Training data is 60 episodes and had *only* LEGO bricks. - Using single front camera (Laptop in this case) Got the idea from xun in LeRobot discord. Here’s ACT vs Pi0 on a toy car that isn’t in the dataset. 1/3

Pi0 vs. ACT with BBox conditioning 🟦 Not many know you can push ACT to almost-Pi0 generalisation by conditioning on bounding boxes (BBoxes). How is the training data collected? • Generate BBoxes for all pick-and-place objects in the scene.(I used Gemini) • Pick-and-place targets are selected randomly. • Add the BBox coordinates to the robot’s state. • Overlay the BBoxes in the visualisation so you know what to grab and where to drop. During inference: • Generate BBoxes for every object again. • Click the object you want to pick and its target spot; those BBoxes get added to the robot state. • Let the robot do the work for you 😃 Setup: - Trained ACT for 100k steps and fine-tuned Pi0 for only 20k. - Training data is 60 episodes and had only LEGO bricks. - Using single front camera (Laptop in this case) Got the idea from xun in LeRobot discord. Here’s ACT vs Pi0 on a toy car that isn’t in the dataset. 1/3

Shreyas Gite

34,863 次观看 • 1 年前