Meta presents Watermark Anything with Localized Messages

Amazing work led by Tom Sander @ICLR and Pierre Fernandez

Check out our latest capabilities (web search, canvas, pixtral large, PDF upload) on chat.mistral.ai

I am in NeurIPS week :) Friday, Presenting our spotlight work: Watermarking Makes LLMs Radioactive ☢️ (arxiv.org/abs/2402.14904) Sunday, speaking at the image watermarking workshop about our latest Watermark Anything work (arxiv.org/abs/2411.07231) DM me if you’d like to chat :)

🎉Exciting news from AI at Meta FAIR! We've released a Watermark Anything Model under the MIT license! It was announced yesterday: ai.meta.com/blog/meta-fair… Great project with Pierre Fernandez et al. ! We're close to hitting 1,000 stars on GitHub. Give it a try: github.com/facebookresear… 🚀

Presenting our spotlight poster Watermark Makes Language Models Radioactive at NeurIPS today from 4:30 - 7:30 pm poster session in East Hall #2411. Video, Poster and Slides: neurips.cc/virtual/2024/p… neurips.cc/media/neurips-… with Tom Sander @ICLR

Watermarking images treated as a segmentation task for much improved robustness 🧵📖 Read of the day, season 3, day 4: « Watermark Anything with Localized Messages », by Tom Sander @ICLR, Pierre Fernandez et al from AI at Meta As watermarking becomes more and more of a necessity to conform

Makes you wonder what kind of evidence they have, and got me thinking about this Neurips paper: arxiv.org/pdf/2402.14904. Any chance it's radioactive watermarking Tom Sander @ICLR Pierre Fernandez?

And Watermark Anything got accepted at ICLR 2025 🎉

This is my first paper done at FAIR. We show that adaptive visual token segmentation, especially in subobject-level (i.e., subwords in images), enables VLMs to have a better and faster learning of image understanding! arxiv.org/pdf/2402.14327

1/ Happy to share my first accepted paper as a PhD student at Meta and École normale supérieure | PSL which I will present at ICLR 2026: 📚 Our work proposes difFOCI, a novel rank-based objective for ✨better feature learning✨ In collab with David Lopez-Paz, Giulio Biroli and Levent Sagun!

I am at ICLR this week, presenting Watermark Anything on Saturday, and another work on radioactive benchmarks at the WM workshop on Sunday. Reach out if you want to discuss Watermarking, Distillation Protecion, Memorization, or else :)

Presenting at 3PM, poster #496. We just passed the 1k stars on GitHub🌟 long live neat open sourcing Pierre Fernandez

Our first LLM coding agent: Devstral. It's the SoTA OSS model on SWE-Bench Verified by a large margin, while being only 24B. It's still a research preview specific to SWE tasks. For regular code completion Codestral might still be the best bet. Let us know your feedback!

Exciting PhD position open at FAIR in Paris. We are looking for a candidate to join our team and contribute to advancing the field of AI, especially reinforcement learning. Find more details and apply below. Feel free to reach out to me by email. metacareers.com/jobs/192266079…

There's a lot of work now on LLM watermarking. But can we extend this to transformers trained for autoregressive image generation? Yes, but it's not straightforward 🧵(1/10)