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。

Computer vision models can now learn without labels! Visualizations from DinoV3.

Welch Labs

5,554 subscribers

18,058 次观看 • 2 个月前 •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

4 条评论

noodms024 的头像

noodms0242 个月前

Wow cool @welchlabs , did you make a tutorial on how to use DinoV3??

AI Mastery Guide 的头像

AI Mastery Guide2 个月前

Learning without labels is such a big step for vision models

مازن وذكاء الآلات 的头像

مازن وذكاء الآلات2 个月前

My opinion: It's all about scale now! The Game is Over! DINOv3 is out. Gram anchoring and dataset scaling give us dense features that beat specialized state of the art with no fine-tuning. Vision foundations are here.

nicolasmelo 的头像

nicolasmelo2 个月前

@PyBitz

相关视频

Introducing DINOv3: a state-of-the-art computer vision model trained with self-supervised learning (SSL) that produces powerful, high-resolution image features. For the first time, a single frozen vision backbone outperforms specialized solutions on multiple long-standing dense prediction tasks. Learn more about DINOv3 here:

Introducing DINOv3: a state-of-the-art computer vision model trained with self-supervised learning (SSL) that produces powerful, high-resolution image features. For the first time, a single frozen vision backbone outperforms specialized solutions on multiple long-standing dense prediction tasks. Learn more about DINOv3 here:

AI at Meta

901,210 次观看 • 1 年前

How can we learn 3D visual grounding with natural supervision—only looking at QA pairs, without ground truth bounding boxes or object classification labels? We inject explicit language priors, e.g., the symmetric property that A near B ⇒ B near A, in structured vision models.

How can we learn 3D visual grounding with natural supervision—only looking at QA pairs, without ground truth bounding boxes or object classification labels? We inject explicit language priors, e.g., the symmetric property that A near B ⇒ B near A, in structured vision models.

Joy Hsu

14,843 次观看 • 2 年前

Gemini can now transform your questions and complex concepts into customizable interactive visualizations directly in your chat. Adjust variables, rotate 3D models, and explore data for a more immersive way to learn and explore in Gemini.

Gemini can now transform your questions and complex concepts into customizable interactive visualizations directly in your chat. Adjust variables, rotate 3D models, and explore data for a more immersive way to learn and explore in Gemini.

Google Gemini

5,888,593 次观看 • 5 个月前

The Internet Computer brings the World Computer vision to life, letting you build anything onchain. Develop everything from custom web apps to AI without traditional IT.

The Internet Computer brings the World Computer vision to life, letting you build anything onchain. Develop everything from custom web apps to AI without traditional IT.

DFINITY Foundation

22,436 次观看 • 1 年前

in Singapore malls they literally use computer vision models and OCR every license plate so that you can look up your car and get personalized directions to your car from anywhere in the mall

in Singapore malls they literally use computer vision models and OCR every license plate so that you can look up your car and get personalized directions to your car from anywhere in the mall

swyx

107,891 次观看 • 8 个月前

Woke girls can learn from her, you can dance without removing your clothes too 🙏🏻

Sensitive content

Woke girls can learn from her, you can dance without removing your clothes too 🙏🏻

Voice of Hindus

248,187 次观看 • 1 年前

Introducing an approach to directly ground video generation models to policy execution without needing any action labels! Our approach uses a generic goal-conditioned exploration procedure to learn a policy that works across robots / embodiments!

Introducing an approach to directly ground video generation models to policy execution without needing any action labels! Our approach uses a generic goal-conditioned exploration procedure to learn a policy that works across robots / embodiments!

Yilun Du

21,409 次观看 • 1 年前

Can we synthesize 3D human-scene interactions without learning from any 3D data? Yes! Check out Lei Li's GenZI, a novel zero-shot approach to generating 3D interactions by distilling priors from large vision-language models.

Can we synthesize 3D human-scene interactions without learning from any 3D data? Yes! Check out Lei Li's GenZI, a novel zero-shot approach to generating 3D interactions by distilling priors from large vision-language models.

Angela Dai

107,013 次观看 • 2 年前

A developer figured out how to access Quest 3's passthrough cameras to run custom computer vision models. Details here:

A developer figured out how to access Quest 3's passthrough cameras to run custom computer vision models. Details here:

UploadVR

44,939 次观看 • 2 年前

SNAPCHAT PAID $150,000,000 FOR LOOKSERY - STARTUP IN DEEP LEARNING COMPUTER VISION This 1-hour Stanford lecture on "DL for Computer Vision" will teach you how to build same project from scratch. Bookmark it & watch today. Stanford's full course (19 lectures) on Deep Learning for Computer Vision below ↓

SNAPCHAT PAID $150,000,000 FOR LOOKSERY - STARTUP IN DEEP LEARNING COMPUTER VISION This 1-hour Stanford lecture on "DL for Computer Vision" will teach you how to build same project from scratch. Bookmark it & watch today. Stanford's full course (19 lectures) on Deep Learning for Computer Vision below ↓

Movez

57,869 次观看 • 3 个月前

Computer vision can see what happened — agentic AI explains why it matters and what to do next. Here’s how teams are upgrading video analytics with vision language models: 🔍 Turn video into searchable intelligence 🧠 Add context and reasoning to system alerts ⚡ Summarize complex scenes and answer questions automatically Read the blog to see 3 real-world ways to bring agentic AI to computer vision →

Computer vision can see what happened — agentic AI explains why it matters and what to do next. Here’s how teams are upgrading video analytics with vision language models: 🔍 Turn video into searchable intelligence 🧠 Add context and reasoning to system alerts ⚡ Summarize complex scenes and answer questions automatically Read the blog to see 3 real-world ways to bring agentic AI to computer vision →

NVIDIA AI

14,273 次观看 • 8 个月前

hi! Open Interpreter 0.2.0—The New Computer Update—is out today. everything's new. - OS Mode lets vision models operate your computer - We included a new model for precise GUI control - We're launching a Computer API for LLMs ↓

hi! Open Interpreter 0.2.0—The New Computer Update—is out today. everything's new. - OS Mode lets vision models operate your computer - We included a new model for precise GUI control - We're launching a Computer API for LLMs ↓

killian

422,858 次观看 • 2 年前

Polycam now supports SharePlay on Vision Pro! 🥽 You can now simultaneously view your captures on Vision Pro with others. Collaborate with your team seamlessly without screen sharing 🤝

Polycam now supports SharePlay on Vision Pro! 🥽 You can now simultaneously view your captures on Vision Pro with others. Collaborate with your team seamlessly without screen sharing 🤝

polycam

34,264 次观看 • 2 年前

Introducing Meta Perception Language Model (PLM): an open & reproducible vision-language model tackling challenging visual tasks. Learn more about how PLM can help the open source community build more capable computer vision systems. Read the research paper, and download the code and dataset:

Introducing Meta Perception Language Model (PLM): an open & reproducible vision-language model tackling challenging visual tasks. Learn more about how PLM can help the open source community build more capable computer vision systems. Read the research paper, and download the code and dataset:

AI at Meta

94,510 次观看 • 1 年前

Computer can now start and manage other Computer sessions from a prompt. In Slack, web, or other Computer surfaces, ask Computer to split work into separate sessions, and it creates each one and replies with links. You can also list, rename, or fork sessions by asking. Live now on the web for all Computer users.

Computer can now start and manage other Computer sessions from a prompt. In Slack, web, or other Computer surfaces, ask Computer to split work into separate sessions, and it creates each one and replies with links. You can also list, rename, or fork sessions by asking. Live now on the web for all Computer users.

Computer

18,624 次观看 • 1 个月前

🔥We're thrilled to announce: ShowUI Local Run!🔥 🧑‍💻Now, you can use our 2B vision-language-action model for Local Computer control! 💰30x Cheaper than Claude! 🔗Model: 🔗Computer Use OOTB: #ComputerUse #Agent #Claude

🔥We're thrilled to announce: ShowUI Local Run!🔥 🧑‍💻Now, you can use our 2B vision-language-action model for Local Computer control! 💰30x Cheaper than Claude! 🔗Model: 🔗Computer Use OOTB: #ComputerUse #Agent #Claude

Kevin Lin

14,578 次观看 • 1 年前

Computer can now take full control of Comet to complete tasks. When you’re in Comet, Computer spins up a browser agent that can access any site or logged‑in app with your permission, without the need for connectors or MCPs. Available to all Computer users on Comet.

Computer can now take full control of Comet to complete tasks. When you’re in Comet, Computer spins up a browser agent that can access any site or logged‑in app with your permission, without the need for connectors or MCPs. Available to all Computer users on Comet.

Perplexity

364,561 次观看 • 6 个月前

PERPLEXITY 🔥: Perplexity Pro and Max subscribers can now use a new Portable Computer on DGX Spark from NVIDIA, powered purely by local models! Available models: > PPLX 27B is a new post-trained model from Perplexity. > Qwen 3.8 27B > Nemotron 3.5 Lightning (coming soon) They really did it! 🤖

PERPLEXITY 🔥: Perplexity Pro and Max subscribers can now use a new Portable Computer on DGX Spark from NVIDIA, powered purely by local models! Available models: > PPLX 27B is a new post-trained model from Perplexity. > Qwen 3.8 27B > Nemotron 3.5 Lightning (coming soon) They really did it! 🤖

🚨 AI News | TestingCatalog

42,207 次观看 • 19 天前

Humans learn and improve from failures. Similarly, foundation models adapt based on human feedback. Can we leverage this failure understanding to enhance robotics systems that use foundation models? Introducing AHA—a vision-language model for detecting and reasoning over failures in robotic manipulation. Project page: 🧵Thread👇 Aha!

Humans learn and improve from failures. Similarly, foundation models adapt based on human feedback. Can we leverage this failure understanding to enhance robotics systems that use foundation models? Introducing AHA—a vision-language model for detecting and reasoning over failures in robotic manipulation. Project page: 🧵Thread👇 Aha!

Jiafei Duan

48,830 次观看 • 1 年前