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.

Today we’re announcing two new updates in our computer vision work — a new, expanded license for our DINOv2 model and the release of FACET, a comprehensive new benchmark dataset to help evaluate and improve fairness in vision models. More details ➡️ 🧵

AI at Meta

808,309 subscribers

453,947 views • 2 years ago •via X (Twitter)

News & Politics Science & Technology

Anya Rossi• Live Now

Private livecam show

10 Comments

AI at Meta2 years ago

To support innovation in computer vision, we’re making DINOv2 available under the Apache 2.0 license + releasing a collection of DINOv2-based dense prediction models for semantic image segmentation and monocular depth estimation. Try our updated demo ➡️

AI at Meta2 years ago

We’re also releasing FACET, a comprehensive benchmark dataset to evaluate fairness of models across different vision tasks involving people. It consists of 32K images, labeled by expert annotators for demographic & physical attributes. Explore FACET ➡️

GMN TV ETHIOPIA2 years ago

My Facebook page with over 600K followers has been taken away by somebody else /probably hacker/ without my knowledge. I have Been trying to report the case to you guys but my account was also disabled at the same exact time without any wrong doing by me. Please help me.

SamBam2 years ago

Meta Ai has been knocking it out of the park.

Nid All | AI art and more 🤖2 years ago

We had the King of coding codellama and then we have this what a great work 🔥

Jeremy Peterson2 years ago

META over here quietly moving the state of the art forward. Couple these innovations with the context of a highly accessible next generation AR headset/glasses and all of a sudden it starts making sense.

Luca2 years ago

You guys are shipping like crazy

⟁ndrew V2 years ago

I see what you’re doing.

radAI2 years ago

Nice effort!!

Rufus2 years ago

This is good.

Related Videos

Announcing our vision of Demo Driven Development, and our latest suite of new product updates:

Announcing our vision of Demo Driven Development, and our latest suite of new product updates:

Caroline Clark 🕹

11,631 views • 2 years ago

Today we're sharing the next milestone in our Seamless Communication research — a new family of AI translation models that preserve expression and deliver near-real time streaming translations. More on this new work ➡️ More on the individual models 🧵

Today we're sharing the next milestone in our Seamless Communication research — a new family of AI translation models that preserve expression and deliver near-real time streaming translations. More on this new work ➡️ More on the individual models 🧵

AI at Meta

728,765 views • 2 years ago

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

421,586 views • 2 years ago

In 2025 we met new challenges, reached new milestones, and launched new programs in our pursuit to save and improve more lives. Thanks to our partners and amazing team at Bloomberg Philanthropies for their vision and collaboration - here's to an even more ambitious 2026!

In 2025 we met new challenges, reached new milestones, and launched new programs in our pursuit to save and improve more lives. Thanks to our partners and amazing team at Bloomberg Philanthropies for their vision and collaboration - here's to an even more ambitious 2026!

Patti Harris

20,539 views • 6 months ago

ANNOUNCEMENT: A New Chapter Begins We’re excited to unveil a bold new chapter in our journey — Hendrik has officially rebranded. This evolution reflects more than just a new logo or look. It represents our growth, our vision for the future, and our commitment to pushing...

HENDRIK

38,560 views • 11 months ago

In the first installment of our “New Murabba: Vision in Focus” series, our CEO, Michael Dyke reveals the ambitious vision behind Riyadh’s new, modern downtown—a unique community where you can live, work, and play.

In the first installment of our “New Murabba: Vision in Focus” series, our CEO, Michael Dyke reveals the ambitious vision behind Riyadh’s new, modern downtown—a unique community where you can live, work, and play.

New Murabba

804,005 views • 1 year ago

The future of work is about to get better! We’re excited to announce our latest product release, which includes all-new updates to help businesses like yours stay ahead in the new world of work. Learn more:

The future of work is about to get better! We’re excited to announce our latest product release, which includes all-new updates to help businesses like yours stay ahead in the new world of work. Learn more:

Fiverr

16,764 views • 2 years ago

Our vision is for AI that uses world models to adapt in new and dynamic environments and efficiently learn new skills. We’re sharing V-JEPA 2, a new world model with state-of-the-art performance in visual understanding and prediction. V-JEPA 2 is a 1.2 billion-parameter model, trained on video, that can enable zero-shot planning in robots—allowing them to plan and execute tasks in unfamiliar environments. Learn more about V-JEPA 2 ➡️ As we continue working toward our goal of achieving advanced machine intelligence (AMI), we’re also releasing three new benchmarks for evaluating how well existing models can reason about the physical world from video. Learn more and download the new benchmarks ➡️

Our vision is for AI that uses world models to adapt in new and dynamic environments and efficiently learn new skills. We’re sharing V-JEPA 2, a new world model with state-of-the-art performance in visual understanding and prediction. V-JEPA 2 is a 1.2 billion-parameter model, trained on video, that can enable zero-shot planning in robots—allowing them to plan and execute tasks in unfamiliar environments. Learn more about V-JEPA 2 ➡️ As we continue working toward our goal of achieving advanced machine intelligence (AMI), we’re also releasing three new benchmarks for evaluating how well existing models can reason about the physical world from video. Learn more and download the new benchmarks ➡️

AI at Meta

309,704 views • 1 year ago

Today we’re celebrating 10 years of the Meta FAIR lab in Paris by sharing a collection of new models, datasets and some exciting milestones in the impacts of open source — all laddering up to our ongoing work to achieve Advanced Machine Intelligence (AMI). 1️⃣ Meta PARTNR is a framework for human-robot collaboration that builds on our existing work in this space with a new dataset and a large planning model enabling robots to accomplish complex tasks alongside humans. 2️⃣ Meta Audiobox Aesthetics enables the automatic evaluation of audio aesthetics, providing a comprehensive assessment of audio quality across speech, music and sound. 3️⃣ Open Source Machine Translation Benchmark is a carefully crafted collection with the aim of building an unprecedented multilingual machine translation benchmark for the community. 4️⃣ Two new breakthrough studies using AI to further our understanding of language in the brain.

Today we’re celebrating 10 years of the Meta FAIR lab in Paris by sharing a collection of new models, datasets and some exciting milestones in the impacts of open source — all laddering up to our ongoing work to achieve Advanced Machine Intelligence (AMI). 1️⃣ Meta PARTNR is a framework for human-robot collaboration that builds on our existing work in this space with a new dataset and a large planning model enabling robots to accomplish complex tasks alongside humans. 2️⃣ Meta Audiobox Aesthetics enables the automatic evaluation of audio aesthetics, providing a comprehensive assessment of audio quality across speech, music and sound. 3️⃣ Open Source Machine Translation Benchmark is a carefully crafted collection with the aim of building an unprecedented multilingual machine translation benchmark for the community. 4️⃣ Two new breakthrough studies using AI to further our understanding of language in the brain.

AI at Meta

85,774 views • 1 year ago

We’ve hired 58 people since January 2026, and today we’re announcing another wave of over 50 new jobs in Dublin and Lisbon across our sales, engineering, speakers, investors, growth and startup teams. We’ve two new incredible offices in Dublin City centre, and are hunting for a third. If you’d like to work in an office with other human beings, travel the world, and help build Web Summit, get in touch. We’re looking for Mandarin speakers in particular to work in our Dublin and Lisbon offices, and across a range of roles. Oh and any journalist looking for a new role, we’re hiring.

We’ve hired 58 people since January 2026, and today we’re announcing another wave of over 50 new jobs in Dublin and Lisbon across our sales, engineering, speakers, investors, growth and startup teams. We’ve two new incredible offices in Dublin City centre, and are hunting for a third. If you’d like to work in an office with other human beings, travel the world, and help build Web Summit, get in touch. We’re looking for Mandarin speakers in particular to work in our Dublin and Lisbon offices, and across a range of roles. Oh and any journalist looking for a new role, we’re hiring.

Paddy Cosgrave

22,183 views • 2 months ago

Together with the Ego4D consortium, we recently released Ego-Exo4D: A diverse, large-scale multi-modal, multi-view, video dataset and benchmark. Learn more about the work ➡️ Access the dataset ➡️ This work could help to advance AI models' understanding of complex human skills & enable new applications for AR systems, robotics & more.

Together with the Ego4D consortium, we recently released Ego-Exo4D: A diverse, large-scale multi-modal, multi-view, video dataset and benchmark. Learn more about the work ➡️ Access the dataset ➡️ This work could help to advance AI models' understanding of complex human skills & enable new applications for AR systems, robotics & more.

AI at Meta

78,039 views • 2 years ago

Additionally, looking towards the future, we’re releasing PARTNR: a benchmark for Planning And Reasoning Tasks in humaN-Robot collaboration. Built on Habitat 3.0, it’s the largest benchmark of its kind to study and evaluate human-robot collaboration in household activities By providing a standardized benchmark and dataset we hope to enable new research on robots that can not only operate in isolation, but in collaboration with people. Details and code ➡️

Additionally, looking towards the future, we’re releasing PARTNR: a benchmark for Planning And Reasoning Tasks in humaN-Robot collaboration. Built on Habitat 3.0, it’s the largest benchmark of its kind to study and evaluate human-robot collaboration in household activities By providing a standardized benchmark and dataset we hope to enable new research on robots that can not only operate in isolation, but in collaboration with people. Details and code ➡️

AI at Meta

20,244 views • 1 year ago

Check out our 2025 highlights in computer vision! 🚀Five new *St3R models (MASt3R-SfM, MUSt3R, PanSt3R, HAMSt3R, HOSt3R ) 🤩Anny parametric 3D human model (Apache 2.0) 🤟Universal encoder for all-in-one vision FM More info ▶️

Check out our 2025 highlights in computer vision! 🚀Five new *St3R models (MASt3R-SfM, MUSt3R, PanSt3R, HAMSt3R, HOSt3R ) 🤩Anny parametric 3D human model (Apache 2.0) 🤟Universal encoder for all-in-one vision FM More info ▶️

NAVER LABS Europe

12,504 views • 6 months ago

We’re introducing major updates to Gemini in @GoogleChrome for MacOS, Windows and Chromebook Plus. Built on Gemini 3, our most intelligent model, these powerful new AI features can help you multitask more easily and get the most out of the web 🧵

We’re introducing major updates to Gemini in @GoogleChrome for MacOS, Windows and Chromebook Plus. Built on Gemini 3, our most intelligent model, these powerful new AI features can help you multitask more easily and get the most out of the web 🧵

Google

2,158,026 views • 4 months ago

A New Era for Lightspark Today, we're excited to share our new brand identity. It's built for developers ready to leave legacy systems behind and build faster, more open payments for the world. See our new refreshed Lightspark site: Learn about our new brand and vision:

Lightspark

21,025 views • 1 year ago

Today we’re sharing two new advances in our generative AI research: Emu Video & Emu Edit. Details ➡️ These new models deliver exciting results in high quality, diffusion-based text-to-video generation & controlled image editing w/ text instructions. 🧵

Today we’re sharing two new advances in our generative AI research: Emu Video & Emu Edit. Details ➡️ These new models deliver exciting results in high quality, diffusion-based text-to-video generation & controlled image editing w/ text instructions. 🧵

AI at Meta

798,183 views • 2 years ago

#WATCH | Lucknow, UP: Samajwadi Party Chief Akhilesh Yadav says, "Today, we are going to start a program, and the first one will be in Bangalore. We will visit various places and work on 'Vision India' and 'New India' programs. The aim of 'Vision India' is to move 'New India' forward and create new ideas and new paths... Young India is progressive. We have a fight with those who are old-fashioned. Our India and our thinking are not about division, and to fight those who have divisive thinking, we want vision and a new India that fulfils the target... That's why we are going to work on the basis of 'New India,' 'New Vision'..."

#WATCH | Lucknow, UP: Samajwadi Party Chief Akhilesh Yadav says, "Today, we are going to start a program, and the first one will be in Bangalore. We will visit various places and work on 'Vision India' and 'New India' programs. The aim of 'Vision India' is to move 'New India' forward and create new ideas and new paths... Young India is progressive. We have a fight with those who are old-fashioned. Our India and our thinking are not about division, and to fight those who have divisive thinking, we want vision and a new India that fulfils the target... That's why we are going to work on the basis of 'New India,' 'New Vision'..."

ANI

75,431 views • 7 months ago

Announcing our new and stable release of Segment Anything for Microscopy! We introduce new features and improve the tool to segment microscopy data with a few clicks, like the mitochondria in the video, first segmented automatically and then corrected interactively.

Announcing our new and stable release of Segment Anything for Microscopy! We introduce new features and improve the tool to segment microscopy data with a few clicks, like the mitochondria in the video, first segmented automatically and then corrected interactively.

Constantin Pape

45,373 views • 2 years ago

Today, we celebrated the groundbreaking for our new School of Medicine in the historic BullStreet District in downtown Columbia, a vision more than a decade in the making. Learn more about the School of Medicine Columbia and our Health Sciences Campus. 🩺

Today, we celebrated the groundbreaking for our new School of Medicine in the historic BullStreet District in downtown Columbia, a vision more than a decade in the making. Learn more about the School of Medicine Columbia and our Health Sciences Campus. 🩺

University of South Carolina

15,701 views • 1 year ago

🌟 Today we’re sharing the vision for a New Web3 — a more interconnected, human internet that drives new value systems and can lay the foundation for a new digital society. Here is the first of two articles, detailing the journey of our evolution and why we built new standards. This one is for the visionaries and dreamers of the initial Ethereum vision of a decentralised internet and shows how we can evolve it into a universal decentralized operating system, entailing the whole of web3. This one is slightly more technical. 👉 Read on Medium:

🌟 Today we’re sharing the vision for a New Web3 — a more interconnected, human internet that drives new value systems and can lay the foundation for a new digital society. Here is the first of two articles, detailing the journey of our evolution and why we built new standards. This one is for the visionaries and dreamers of the initial Ethereum vision of a decentralised internet and shows how we can evolve it into a universal decentralized operating system, entailing the whole of web3. This one is slightly more technical. 👉 Read on Medium:

LUKSO

93,954 views • 1 year ago