Ronghang Hu

multimodal at @xAI | previously at Meta FAIR

[Elon Musk @elonmusk]

Iliad (Troy) trailer made by Grok Imagine 1.5, which was just released

[Hexiang (Frank) Hu @hexiang]

We are making a small step towards unified agent for media creation;

Please share feedback with us and we will keep iterating on it!

[Xinlei Chen @endernewton]

Spend more compute and get higher quality.

Any request for smoother experience to create, let us know!

[Pengchuan Zhang @PengchuanZ]

SAM 3.1 is here. SAM 3.1 is a significant improvement on video grounding: shifting from SAM2-like per-object propagation to MOT-style multi-object propagation. This change significantly reduces the computational cost, while maintaining the tracking accuracy!!!

[Xudong Lin @Xudong_Lin_AI]

Proud of our team that makes the huge leap happen compared to last version but this is just the start. Better models are lined up and we keep improving every week. Join us towards Superhuman Multimodal Intelligence https://t.co/66VPFDgMRy !!

[Ethan He @EthanHe_42]

Happy birthday to @xAI! Only 3 years old and already an incredible list of accomplishments

[Xudong Lin @Xudong_Lin_AI]

Join us to build the best mutlimodal model that understands the universe!
https://t.co/6houBQjsTZ

[xAI @xai]

Understanding requires imagining. Grok Imagine lets you bring what’s in your brain to life, and now it’s available via the world’s fastest, and most powerful video API: https://t.co/tqQwQVgCEI

Try it out and let your Imagination run wild.

[Nikhila Ravi @nikhilaravi]

One of the most highly requested features since we launched SAM 1 was the ability to prompt with text! @kate_saenko_ from SAM 3 team explains how we built an efficient data engine to collect high quality mask + text label annotations at scale and our new open vocabulary benchmark Segment Anything with Concepts (SA-Co).

[Niels Rogge @NielsRogge]

SAM-3 is out on @huggingface!

A big upgrade from SAM-2, and Meta finally added support for text prompts.

Here I tried it out on @hazardeden10's magical goal against @Arsenal using the text prompt "Chelsea player"

Works pretty well!

[Roboflow @roboflow]

we are going live tomorrow to get hands on with SAM 3

lots of demos and ongoing Q&A, join in

[Alexandr Wang @alexandr_wang]

Today we are releasing & open-sourcing Segment Anything 3 (SAM 3).

It is a state-of-the-art model for image & video segmentation, and builds upon the work of SAM & SAM 2.

SAM3 will also power features in Edits, Meta AI, & Facebook Marketplace soon.

https://t.co/ufppJ6gR3c

[AI at Meta @AIatMeta]

Meet SAM 3, a unified model that enables detection, segmentation, and tracking of objects across images and videos. SAM 3 introduces some of our most highly requested features like text and exemplar prompts to segment all objects of a target category.

Learnings from SAM 3 will help power new features in Instagram Edits and Vibes, bringing advanced segmentation capabilities directly to creators.

🔗 Learn more: https://t.co/CjMnf7fspz

[Nikhila Ravi @nikhilaravi]

🚀 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!

[Ronghang Hu @RonghangHu]

Below are what's contained in the SAM 2.1 Developer Suite:
- A new suite of improved model checkpoints (denoted as SAM 2.1) are released.
- The training (and fine-tuning) code has been released.
- The frontend + backend code for the SAM 2 web demo has been released.

[Ronghang Hu @RonghangHu]

SAM 2.1 Developer Suite (new checkpoints, training code, web demo) is released -- check it out at https://t.co/ie8XYJDAvA

[AI at Meta @AIatMeta]

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 feed.

1️⃣ We’re releasing SAM 2.1 an upgraded version of the Segment Anything Model 2 — and the SAM 2 Developer Suite featuring open source tools for training, inference and demos. New artifacts are live in the repo on GitHub ➡️ https://t.co/VxmxvQQaJS

2️⃣ We’re supporting 10+ presentations and workshops in areas like computer vision for smart glasses and the metaverse, 3D vision for eCommerce, egocentric research with Project Aria and more.

3️⃣ We’re presenting seven orals at ECCV — in addition to the 50+ publications from researchers at Meta that were accepted for this year’s conference. Look out for more details on some of these papers later this week.

4️⃣ Demos and discussions with Meta researchers at our booth all week — come by our booth to discuss projects like SAM 2, Ego-Exo4D, DINOv2 and more.

[Florent Daudens @fdaudens]

Quite a cool demo of Segment Anything 2 (even if Mbappe shoots the ball too fast for it! ;) ) https://t.co/Vk7AwOGsQQ

[Ronghang Hu @RonghangHu]

We are excited to release SAM 2, to segment anything in images and videos

Check out the code at https://t.co/x0NNs7Gs3y and demo at https://t.co/AavEuRP2xQ

[AI at Meta @AIatMeta]

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 ➡️ https://t.co/eTTDpxI60h

[AI at Meta @AIatMeta]

Today, we’re sharing a roundup of Meta AI’s recent cutting-edge multimodal research, which we believe will collectively lead to more interactive, immersive, and smarter AI systems of the future: https://t.co/gQX5AbGOgx

[Deepak Pathak @pathak2206]

We are presenting Worldsheet at #ICCV2021 this week as Oral. Join QnA Wed & Fri.

We updated the arXiv since v1: *Multi-layered* Worldsheets to autonomously handle sharp depth discontinuities/occlusions which a single sheet may fail to capture (Sec 3.5): https://t.co/PdD9UhXH5N