Incredibly excited to announce the 1st edition of our tutorial at European Conference on Computer Vision #ECCV2026 w/ the amazing Yuki and mrz.salehi! "Time is precious: Self-Supervised Learning Beyond Images" on 30th Sept. from 09:00 to 13:00 at Amber 7+ 8 Catch the details here⬇️ shashankvkt.github.io/eccv2024-SSLBI…

We're heading to Milan 🍕 for #ECCV2024 next week! Come chat with the team and see our latest work 👇

Over the last 10 years, in motion forecasting, we saw: 🗄️ many independently developed datasets 🔧many independently trained/tested models What’s next? 🤔 There are two key questions that are hard to address… 🧵🔽

TTYD: Towards Stable and Robust Source-free Unsupervised 3D Domain Adaptation by Björn Michele Alexandre Boulch Tuan-Hung VU Gilles Puy Renaud MARLET Nicolas Courty tl;dr: Know when to stop training in source-free domain adaptation! #ECCV2024 📖 bit.ly/TTYD_Paper

🍕 Heading to Milan for #ECCV2024! Our team has put together a mega-thread of our papers. I'll be presenting works on LLMs/VLMs, motion forecasting, and corner-case generation for autonomous driving. Looking forward to great discussions!

I will present this afternoon 16:30 - 18:30 our work on source-free unsupervised domain adaptation. Meet me at the poster location 73. x.com/Bjoern_Michele…

Poster #72 #ECCV2024 is already up and running with Monika Wysoczańska Michaël Ramamonjisoa Andrei Bursuc. Come by if you want to talk about open-vocabulary semantic segmentation at low cost!

Check out the CLIP-DINOiser idea and say hi to the team in the posters of Wednesday afternoon. Poster #72 #ECCV2024

Come to find out the answer to the question of Thibaut Loiseau and Tuan-Hung VU on the use of synthetic data for reliability of segmenters. They are at poster #167 in the Wednesday PM session #ECCV2024

Together with Andrei Bursuc , we have an opening for a Master's (M2) internship in long-range video understanding at valeo.ai in the beautiful city of Paris. Please fill out the form before 10th December. forms.gle/RrFhAzkcwG2yZT… Don't hesitate to reach out if you have any questions

We are looking for an MSc intern for 2025 for a project on self-supervised learning with Shashank and I at valeo.ai in Paris. Find out more details in the post below and check out the achievements of our interns from the past years here valeoai.github.io/interns/

🌟 Calling all MSc students passionate about computer vision and ML! We’re offering research internships about diffusion models, multi-modal transformers, continual learning, & more. 4 exciting openings await! 🔗 Learn more: valeoai.github.io/interns/ RT to spread the word! 🙌

📢 Exciting opportunity alert! We (valeo.ai) just posted our annual research internship openings in computer vision & ML. Check out the openings and the great achievements by our past interns here: valeoai.github.io/interns/

Working on ill-posed machine learning tasks, interested in multi-heads neural networks and data #uncertainty quantification ? Sharing here our latest research, which will be presented at NeurIPS Conference in December.

🚗 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]