Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

DINOv2 by Meta AI is the first method for training computer vision models that uses self-supervised learning to achieve results matching or exceeding industry standards. More details and a demo ⬇️

AIatMeta's profile picture

AI at Meta

811,182 subscribers

96,119 Aufrufe • vor 3 Jahren •via X (Twitter)

Wissenschaft & TechnologieNachrichten & PolitikBildung
LIVE

Anya Rossi• Live Now

Private livecam show

0 Kommentare

Keine Kommentare verfügbar

Kommentare vom Original-Post werden hier angezeigt

Ähnliche Videos

This is literally magic 🤯 FMA-Net is a new AI method for video deblurring! It uses complex motion representation learning for spatio-temporally-variant restoration with kernels that are aware of motion trajectories. More info below ⬇️⬇️
0:19

This is literally magic 🤯 FMA-Net is a new AI method for video deblurring! It uses complex motion representation learning for spatio-temporally-variant restoration with kernels that are aware of motion trajectories. More info below ⬇️⬇️

Alex Carlier

144,268 Aufrufe • vor 2 Jahren

Can you make a jigsaw puzzle with two different solutions? Or an image that changes appearance when flipped? We can do that, and a lot more, by using diffusion models to generate optical illusions! Continue reading for more illusions and method details 🧵
0:12

Can you make a jigsaw puzzle with two different solutions? Or an image that changes appearance when flipped? We can do that, and a lot more, by using diffusion models to generate optical illusions! Continue reading for more illusions and method details 🧵

Daniel Geng

125,796 Aufrufe • vor 2 Jahren

many parts of Hugging Face Hub is actually powered by open machine learning models 🥹 translation feature is one of them, it uses a very tiny (600M) multilingual translation model by AI at Meta 💗
0:13

many parts of Hugging Face Hub is actually powered by open machine learning models 🥹 translation feature is one of them, it uses a very tiny (600M) multilingual translation model by AI at Meta 💗

merve

14,958 Aufrufe • vor 1 Jahr

Placing objects sounds simple… until robots have to do it. This method makes it simple, fast & reliable. [Github ⬇️] Robotic object placement is tough, especially with stacking, hanging, or insertion. AnyPlace is a new two-stage method that uses only synthetic data and a vision-language model to teach robots where and how to place objects; even in the real world. Why this works ✅ Finds the right spot with help from vision-language models ✅ Handles stacking, insertion, and hanging with no real-world training ✅ Trained on synthetic data using Blender and IsaacSim ✅ Works in the real world without fine-tuning It shows that smart use of simulation and language models can make robotic placement tasks easier, faster, and more reliable. Github: Paper: Thank you for sharing Animesh Garg !
0:13

Placing objects sounds simple… until robots have to do it. This method makes it simple, fast & reliable. [Github ⬇️] Robotic object placement is tough, especially with stacking, hanging, or insertion. AnyPlace is a new two-stage method that uses only synthetic data and a vision-language model to teach robots where and how to place objects; even in the real world. Why this works ✅ Finds the right spot with help from vision-language models ✅ Handles stacking, insertion, and hanging with no real-world training ✅ Trained on synthetic data using Blender and IsaacSim ✅ Works in the real world without fine-tuning It shows that smart use of simulation and language models can make robotic placement tasks easier, faster, and more reliable. Github: Paper: Thank you for sharing Animesh Garg !

Ilir Aliu - eu/acc

22,843 Aufrufe • vor 1 Jahr

😍 Love the famous AI VTuber Neuro-sama 💜 but cant always talk to her? Made one for your self! 😏 First look on the Neuro-sama same AI voice for More details ⬇️
0:19

😍 Love the famous AI VTuber Neuro-sama 💜 but cant always talk to her? Made one for your self! 😏 First look on the Neuro-sama same AI voice for More details ⬇️

Neko · 絢香猫 [email protected]

12,322 Aufrufe • vor 1 Jahr

We just shipped React Native ExecuTorch v0.8.0 – our biggest release yet! 👏🏼 ➡️ Vision Camera integration that runs computer vision models directly on your camera feed, in realtime. Also new: multiple CV models (including RF-DETR (Roboflow) and Liquid AI's Vision Language), Bare React Native support, and more. Takes minutes to try – check out the repo! ⬇️
0:12

We just shipped React Native ExecuTorch v0.8.0 – our biggest release yet! 👏🏼 ➡️ Vision Camera integration that runs computer vision models directly on your camera feed, in realtime. Also new: multiple CV models (including RF-DETR (Roboflow) and Liquid AI's Vision Language), Bare React Native support, and more. Takes minutes to try – check out the repo! ⬇️

Software Mansion

36,833 Aufrufe • vor 3 Monaten

Introducing screengrasp - The new SOTA agent click position model - beating Anthropic Computer Use, OmniParser and Molmo by a wide margin. - Simplified API access to the best click models on the market. 🔁Retweet and DM for free API credits. More details 👇
0:18

Introducing screengrasp - The new SOTA agent click position model - beating Anthropic Computer Use, OmniParser and Molmo by a wide margin. - Simplified API access to the best click models on the market. 🔁Retweet and DM for free API credits. More details 👇

Florian S

54,319 Aufrufe • vor 1 Jahr

Meta released LongVU: a new video LM that can handle long videos (great performance, battle-tested by me ⚔) TLDR; 1️⃣ downsample using DINOv2 to eliminate redundant scenes 🦖 2️⃣ fuse rest of the features using DINOv2 and SigLIP 3️⃣ select some tokens, pass to Qwen2/Llama-3.2-3B
0:11

Meta released LongVU: a new video LM that can handle long videos (great performance, battle-tested by me ⚔) TLDR; 1️⃣ downsample using DINOv2 to eliminate redundant scenes 🦖 2️⃣ fuse rest of the features using DINOv2 and SigLIP 3️⃣ select some tokens, pass to Qwen2/Llama-3.2-3B

merve

49,546 Aufrufe • vor 1 Jahr

The previously unidentified new Russian loitering munition is the V2U, according to GUR. It uses a Chinese Leetop A203 minicomputer and likely computer vision for recognizing targets. It might also use LTE. The video shows two V2U countered by Ukraine’s Azov Brigade.
0:19

The previously unidentified new Russian loitering munition is the V2U, according to GUR. It uses a Chinese Leetop A203 minicomputer and likely computer vision for recognizing targets. It might also use LTE. The video shows two V2U countered by Ukraine’s Azov Brigade.

Rob Lee

161,948 Aufrufe • vor 1 Jahr

Golden Age WarriorZ a time where WarriorZ travel Universe to Universe looking for ones that possess super intelligence and powers far beyond the Norm to achieve their highest potentials for good or bad. Follow To Stay Updated For More Details…
0:12

Golden Age WarriorZ a time where WarriorZ travel Universe to Universe looking for ones that possess super intelligence and powers far beyond the Norm to achieve their highest potentials for good or bad. Follow To Stay Updated For More Details…

Golden Age WarriorZ

98,552 Aufrufe • vor 2 Jahren

HashPower is evolving to RAX Finance. We are building the world’s first Financial Layer for AI Compute, a specialized on-chain market where GPU capacity becomes a tradable, yield-bearing RWA. We are backed by the giants of the industry including HashKey Capital, FBG Capital, and more. Institutional grade. DeFi native. A breakdown of the vision 🧵👇
0:15

HashPower is evolving to RAX Finance. We are building the world’s first Financial Layer for AI Compute, a specialized on-chain market where GPU capacity becomes a tradable, yield-bearing RWA. We are backed by the giants of the industry including HashKey Capital, FBG Capital, and more. Institutional grade. DeFi native. A breakdown of the vision 🧵👇

RAX Finance

29,467 Aufrufe • vor 7 Monaten

🚀Thrilled to share what we’ve been building at TRI over the past several months: our first Large Behavior Models (LBMs) are here! I’m proud to have been a core contributor to the multi-task policy learning and post-training efforts. At TRI, we’ve been researching how LBMs can help robots learn faster, better, and more efficiently. The key takeaways: ✅ We built an evaluation pipeline to benchmark LBM performance with real 𝐬𝐭𝐚𝐭𝐢𝐬𝐭𝐢𝐜𝐚𝐥 𝐜𝐨𝐧𝐟𝐢𝐝𝐞𝐧𝐜𝐞 ✅ Pre-training on hundreds of tasks makes models more robust—plus, we can teach new, complex tasks with 80% 𝐥𝐞𝐬𝐬 𝐝𝐚𝐭𝐚 ✅ The bigger and more diverse the pre-training, the better the results Check out our overview video, webpage and paper for more details: ✨ 🌎 📄 We hope this work helps move the field of robotics forward!
0:18

🚀Thrilled to share what we’ve been building at TRI over the past several months: our first Large Behavior Models (LBMs) are here! I’m proud to have been a core contributor to the multi-task policy learning and post-training efforts. At TRI, we’ve been researching how LBMs can help robots learn faster, better, and more efficiently. The key takeaways: ✅ We built an evaluation pipeline to benchmark LBM performance with real 𝐬𝐭𝐚𝐭𝐢𝐬𝐭𝐢𝐜𝐚𝐥 𝐜𝐨𝐧𝐟𝐢𝐝𝐞𝐧𝐜𝐞 ✅ Pre-training on hundreds of tasks makes models more robust—plus, we can teach new, complex tasks with 80% 𝐥𝐞𝐬𝐬 𝐝𝐚𝐭𝐚 ✅ The bigger and more diverse the pre-training, the better the results Check out our overview video, webpage and paper for more details: ✨ 🌎 📄 We hope this work helps move the field of robotics forward!

Zubair Irshad

20,314 Aufrufe • vor 11 Monaten

Memo is a robot that uses AI to perform household tasks effectively. Today Sunday announced its Series B, and we’re proud to be investors. Training robots for the home is hard — the environment is messy, dynamic, and full of edge cases. So Sunday is training robots directly on real households. Founders Tony Zhao and Cheng Chi built a glove-based system that lets hundreds of contributors record everyday tasks in their own homes, creating high-fidelity demonstrations that feed directly into robot learning. Home robotics will be defined by the companies that learn fastest from real homes. Sunday is building that loop. More here: Aaref Hilaly Amanda Huang
0:12

Memo is a robot that uses AI to perform household tasks effectively. Today Sunday announced its Series B, and we’re proud to be investors. Training robots for the home is hard — the environment is messy, dynamic, and full of edge cases. So Sunday is training robots directly on real households. Founders Tony Zhao and Cheng Chi built a glove-based system that lets hundreds of contributors record everyday tasks in their own homes, creating high-fidelity demonstrations that feed directly into robot learning. Home robotics will be defined by the companies that learn fastest from real homes. Sunday is building that loop. More here: Aaref Hilaly Amanda Huang

Bain Capital Ventures

21,327 Aufrufe • vor 3 Monaten

As humans’ role in the AI production process shrinks, they may lose control. The end result could be models trained by models, to achieve goals set by models, whose safety is verified only by models Illustration: Timo Lenzen
0:10

As humans’ role in the AI production process shrinks, they may lose control. The end result could be models trained by models, to achieve goals set by models, whose safety is verified only by models Illustration: Timo Lenzen

The Economist

28,262 Aufrufe • vor 21 Tagen

Today, Nesa is excited to announce cross-chain support with Sei. As part of this new development, Nesa will be featuring a dedicated ramp for Sei’s rich ecosystem of applications to seamlessly integrate with AI. Now any Sei dapp can run AI inference on hundreds of models supported by Nesa, including the largest LLMs and most popular models across Vision, Language, and Generative AI. For developers, we’ll have information soon on how to access AI inference on Nesa via smart contracts from the Sei blockchain. Stay tuned for more details on this ground breaking development for decentralized AI.
0:16

Today, Nesa is excited to announce cross-chain support with Sei. As part of this new development, Nesa will be featuring a dedicated ramp for Sei’s rich ecosystem of applications to seamlessly integrate with AI. Now any Sei dapp can run AI inference on hundreds of models supported by Nesa, including the largest LLMs and most popular models across Vision, Language, and Generative AI. For developers, we’ll have information soon on how to access AI inference on Nesa via smart contracts from the Sei blockchain. Stay tuned for more details on this ground breaking development for decentralized AI.

Nesa

79,638 Aufrufe • vor 2 Jahren

Ultralytics YOLO11 vs Ultralytics YOLO26: Which one runs faster? ⚡ Evaluate inference speed and performance across both models in the ONNX format to understand how YOLO26 improves efficiency for real-time computer vision applications. Read more ➡️ #Ultralytics #YOLO26 #AI #Research #ComputerVision
0:12

Ultralytics YOLO11 vs Ultralytics YOLO26: Which one runs faster? ⚡ Evaluate inference speed and performance across both models in the ONNX format to understand how YOLO26 improves efficiency for real-time computer vision applications. Read more ➡️ #Ultralytics #YOLO26 #AI #Research #ComputerVision

Ultralytics

22,668 Aufrufe • vor 2 Monaten

First look at SPARTA, a distributed AI training algorithm that avoids synchronization by randomly exchanging sparse sets of parameters ( 1,000x reduction in inter-GPU communication, enabling training of large models over slow bandwidths without specialized infrastructure. SPARTA works on its own but can also be combined with sync-based low communication training algorithms like DiLoCo for even better performance.
0:16

First look at SPARTA, a distributed AI training algorithm that avoids synchronization by randomly exchanging sparse sets of parameters ( 1,000x reduction in inter-GPU communication, enabling training of large models over slow bandwidths without specialized infrastructure. SPARTA works on its own but can also be combined with sync-based low communication training algorithms like DiLoCo for even better performance.

EXO Labs

99,301 Aufrufe • vor 1 Jahr

Are you safer with LIDAR, or are you safer with vision? This is a false dichotomy. The more pertinent question today is "do you have something, or do you have nothing?" As you can see from the clips below, vision based systems avoid countless potential collisions every day. The difference between a crash and no crash isn't what sensor suite you chose — it's whether you have any AI on your car at all. Even if we concede that LIDAR may help prevent some additional crashes, we are really debating whether it is 1% of crashes or 0.00001% of crashes. Not all crashes are super complex and require lasers to detect. Most are simple, routine, and can easily be prevented by today's vision based AI. In fact, evidence is mounting that computer vision based systems can actually outperform more traditional approaches to self-driving. Why? Because the low cost of cameras enables you to create a much larger, more varied, and more diverse dataset. If you want to have expensive custom cars that's fine, but you're going to get fewer vehicles for the same budget. Seeing what's in front of you now is actually less important than predicting what's going to happen next — and the large scale datasets used to train pure vision systems are the best for predicting what's next. Counter-intuitively, the simpler and lower cost sensor actually has properties that make it better suited for training advanced AI. Computer vision based self-driving is often framed by LIDAR proponents as "cheaping out" on the sensor suite to save money. But it's not about being cheap, it's about bringing the technology to everyone. 1.2 million people die on the road every year around the world. That's around 39 million people who've died on the roads around the world since I was born — equivalent to a city the size of Tokyo or New Delhi getting wiped off the map. The status quo is simply unacceptable, and something has to be done to fix it as soon as possible. Of the 1.2 million people that will die on the roads this year, about 40,000 will be Americans. That's about 3%. So if we moved entirely to self-driving cars in America and brought crashes down to 0, 97% of the world's crash fatalities would still be taking place as usual. Deploying a $200,000+ retrofitted self-driving car may work in a few American cities, but it is not going to make sense in most places around the world where fares are much cheaper. Most often, the choice is not between LIDAR and vision. It's between vision or nothing. The best system is the system that's there running on my car when I need it to save my life. To say that all self-driving cars must have LIDAR is to sentence most of the world to death. We can't write off computer vision if we want to make a serious dent in this problem. It's going to be a key piece of the solution. Let LIDAR based players build the best self-driving car they can, and let vision based players do the same. We need to be trying everything
0:16

Are you safer with LIDAR, or are you safer with vision? This is a false dichotomy. The more pertinent question today is "do you have something, or do you have nothing?" As you can see from the clips below, vision based systems avoid countless potential collisions every day. The difference between a crash and no crash isn't what sensor suite you chose — it's whether you have any AI on your car at all. Even if we concede that LIDAR may help prevent some additional crashes, we are really debating whether it is 1% of crashes or 0.00001% of crashes. Not all crashes are super complex and require lasers to detect. Most are simple, routine, and can easily be prevented by today's vision based AI. In fact, evidence is mounting that computer vision based systems can actually outperform more traditional approaches to self-driving. Why? Because the low cost of cameras enables you to create a much larger, more varied, and more diverse dataset. If you want to have expensive custom cars that's fine, but you're going to get fewer vehicles for the same budget. Seeing what's in front of you now is actually less important than predicting what's going to happen next — and the large scale datasets used to train pure vision systems are the best for predicting what's next. Counter-intuitively, the simpler and lower cost sensor actually has properties that make it better suited for training advanced AI. Computer vision based self-driving is often framed by LIDAR proponents as "cheaping out" on the sensor suite to save money. But it's not about being cheap, it's about bringing the technology to everyone. 1.2 million people die on the road every year around the world. That's around 39 million people who've died on the roads around the world since I was born — equivalent to a city the size of Tokyo or New Delhi getting wiped off the map. The status quo is simply unacceptable, and something has to be done to fix it as soon as possible. Of the 1.2 million people that will die on the roads this year, about 40,000 will be Americans. That's about 3%. So if we moved entirely to self-driving cars in America and brought crashes down to 0, 97% of the world's crash fatalities would still be taking place as usual. Deploying a $200,000+ retrofitted self-driving car may work in a few American cities, but it is not going to make sense in most places around the world where fares are much cheaper. Most often, the choice is not between LIDAR and vision. It's between vision or nothing. The best system is the system that's there running on my car when I need it to save my life. To say that all self-driving cars must have LIDAR is to sentence most of the world to death. We can't write off computer vision if we want to make a serious dent in this problem. It's going to be a key piece of the solution. Let LIDAR based players build the best self-driving car they can, and let vision based players do the same. We need to be trying everything

Whole Mars Catalog

45,801 Aufrufe • vor 1 Jahr

Quick demo of LFM 2.5 VL 1.6B model by Liquid AI that I recently added to Locally AI - Local AI Chat Running locally on iPhone 17 Pro at ~90tk/s with MLX Small vision-language models are improving fast
0:10

Quick demo of LFM 2.5 VL 1.6B model by Liquid AI that I recently added to Locally AI - Local AI Chat Running locally on iPhone 17 Pro at ~90tk/s with MLX Small vision-language models are improving fast

Adrien Grondin

32,556 Aufrufe • vor 5 Monaten