We're thrilled to join the ambitious ELLIOT project towards European large open-multimodal foundation models. The project kick-off is today!

ELSA will be extended!🎉 The European Commission decided to extend the duration of our Lighthouse on Secure and Safe AI. We will now run for an additional 12 months until August 2026. Find more details in the official press release: elsa-ai.eu/official-ext... Congratulations to the network!

Check out our MOCA self-supervised learning approach unifying the learning principles of both discriminative & masked image modelling paradigms. With a non-linear path, MOCA has been accepted at #TMLR and presented in the TMLR poster session at #iclr2025

Check out DIP (Dense In-context Post-training) @iccv.bsky.social: an effective post-training strategy to unleash dense awareness of features from your favorite pre-trained encoder (DINOv2, CLIP, MAE) We leverage meta-learning-like pseudo-tasks w/ pseudo-labels. Kudos @ssirko.bsky.social 👇 #iccv2025

How to make your DINOv2 excel at dense in-context scene understanding tasks. Check out DIP an effective post-training strategy by @ssirko.bsky.social @spyrosgidaris.bsky.social ‬ @vobeckya.bsky.social ‬@abursuc.bsky.social and Nicolas Thome 👇 #iccv2025

Hey #IV2025, @t-martyniuk.bsky.social is presenting her LiDPM work today! tl;dr: LiDPM - a point diffusion strategy for scene completion from outdoor LiDAR point clouds. Check out the paper and code below if you can't make it for the poster.

🚀Thrilled to introduce JAFAR—a lightweight, flexible, plug-and-play module that upsamples features from any Foundation Vision Encoder to any desired output resolution (1/n) Paper : arxiv.org/abs/2506.11136 Project Page: jafar-upsampler.github.io Github: github.com/PaulCouairon...

Just back from CVPR@Paris 🥐, what a fantastic event! Great talks, great posters, and great to connect with the French & European vision community. Kudos to the organizers, hoping that it returns next year! 🤞 #CVPR2025 @cvprconference.bsky.social

Great to see our team presenting their work at #ICLR2025! Here are a few moments captured from the conference. 📸

👏 Huge congrats to our research scientist Elias Ramzi for winning the AFRIF 2024 PhD award for his thesis "Robust image retrieval with deep learning", conducted at CNAM. Well deserved recognition for amazing work! 🏆 🔗 afrif.irisa.fr?page_id=54

Our recent research will be presented at #ICLR2025 @iclr_conf: VLMs, LLMs, diffusion models, self-supervised learning, physics-informed learning… Find out more below 🧵 valeoai.github.io/posts/2025-0...

We have a very special guest visiting us today: the one and only Alyosha Efros

🚗 Ever wondered if an AI model could learn to drive just by watching YouTube? 🎥👀 We trained a 1.2B parameter model on 1,800+ hours of raw driving videos. No labels. No maps. Just pure observation. And it works! 🤯 🧵👇 [1/10]

We've just had our annual gathering to get together and brainstorm on new exciting ideas and projects ahead -- stay tuned! This is also an excellent occasion to fit all team members in a photo 📸

📚🔍Excited to share our work at #NeurIPS2024! Dive into representation learning, optimization, explainability, VLMs & LLMs, and more. Check out our blog post to know more about our 7 papers: valeoai.github.io/posts/2024-1... 🧵👇