🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

At #ICML2023, Chay (Chaitanya (Chay) Ryali) will present Hiera, a hierarchical vision transformer that is fast, powerful, and simple. Code+models at: github.com/facebookresear… If interested, please come to the oral presentation on Tue 25 Jul 5:30pm HST or poster #219 on Wed 26 Jul 2pm HST.

Hiera: A Hierarchical Vision Transformer without the Bells-and-Whistles ⬇️ bit.ly/3OrVBW3 6/7

I'm incredibly excited to announce our new company, DatologyAI! Training models is hard and identifying the right data is the most important and difficult part -- our goal DatologyAI to make optimizing training data at scale easy and automatic across modalities.

New blog post! Some thoughts about diffusion distillation. Actually, quite a lot of thoughts 🤭 Please share your thoughts as well! sander.ai/2024/02/28/par…

✈️Excited to attend #CVPR in Seattle! My team at Meta (FAIR) is hiring Research Scientists & Engineers to work on multimodal models across image/video. *Full-time* roles only starting ASAP in NYC/Bay Area/Seattle. Stop by the Meta booth or DM me to chat! 😀

Introducing Meta Segment Anything Model 2 (SAM 2) — the first unified model for real-time, promptable object segmentation in images & videos. SAM 2 is available today under Apache 2.0 so that anyone can use it to build their own experiences Details ➡️ go.fb.me/p749s5

SAM 2 is the next generation of the Segment Anything Model for images we released last year! SAM 2 comes with all the great features from SAM (promptable, zero shot generalization, fast inference, Apache 2.0 license), but now also for video! Here's what's in SAM 2🧵👇

We dropped another awesome open model: SAM 2. This one comes with the data and an easy-to-use demo. It extends the original Segment Anything Model, to work on video. Enjoy!

Meta Segment Anything Model v2 (SAM 2) is out. Can segment images and videos. Open source under Apache-2 license. Web demo, paper, and datasets available. Amazing performance.

Just wow..... absolutely amazing Balloon scene from up. Video desaturated so you can see the balloon I am tracking with SAM v2

👋Catch SAM 2 team at European Conference on Computer Vision #ECCV2026: Sun 09/29: Christoph Feichtenhofer is giving talks at the VOTS2024 workshop (9am) & Omnilabel workshop (2:15pm) Mon 09/30: I'm speaking at the LSVOS workshop (2pm) & Yuan-Ting Hu WiCV (2:45pm) Tue-Fri: Q&A AI at Meta Booth (10:30/4:30)

We’re on the ground at #ECCV2024 in Milan this week to showcase some of our latest research, new research artifacts and more. Here are 4️⃣ things you won’t want to miss from Meta FAIR, GenAI and Reality Labs Research this week whether you’re here in person or following from your

🚀 Excited to announce new SAM 2.1 model checkpoints & the SAM 2 Developer Suite: 🤖 We’re releasing full training/fine tuning code for SAM 2 so you can customize it for your use case. 💻For the first time we’re publishing the frontend & backend code for our SAM 2 web demo!

A few days ago, I spoke with nature about my work at the interface between disciplines nature.com/articles/d4158…

Something I said the other day offhand and have been reflecting on a lot... Open-ended research questions are the devil. Never pitch or pursue them. The job of a senior research leader is to represent a program of open ended research as a sequence of clear and precise questions.

I agree with the whole thread, it’s very well put. But let’s not forget the whole current focused bet mode across all big labs is entirely based on inventions made in the grassroots mode. Both modes need each other, although their weighting/footprint may vary over time.

Excited to share updates about a new collaboration with the Bibliothèque Nationale de France, Fisheye Immersive, and the artist Ruben Fro, who used our SegmentAnything2 model, to produce a breathtaking new work called "Deep Diving".

Don't sleep on this! 🔥 Meta dropped swiss army knives for vision with A2.0 license ❤️ > image/video encoders for vision language and spatial understanding (object detection etc) > VLM outperforms InternVL3 and Qwen2.5VL 🔥 > Gigantic video and image datasets 👏

🌟Thrilled to share that SAM 2 was awarded a Best Paper Honourable Mention Award at #ICLR2025, one of 6 papers recognized out of 11000+ submissions! 👏This project was the result of amazing work by an exceptional team at AI at Meta FAIR: Valentin Gabeur , Yuan-Ting Hu,Ronghang Hu,