🔥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

Hey #CVPR2024! Our BRAVO robustness and reliability challenge is now up. We aim to stress-test and benchmark semantic segmentation models on urban scenes under diverse forms of natural degradation and realistic looking synthetic corruptions github.com/valeoai/bravo_…

Gilles Puy Spyros Gidaris Andrei Bursuc FAMix - a simple recipe for language-guided domain generalized segmentation will be presented at poster #379 Fri AM by Mohammad Fahes Tuan-Hung VU Andrei Bursuc and Raoul de Charette #CVPR2024 x.com/valeoai/status…

SPOT an object-centric self-supervised approach and highlight paper will be at poster #315 Fri AM with Ioannis Kakogeorgiou Spyros Gidaris #CVPR2024 x.com/IoannisKakogeo…

Happy to announce the Bravo Challenge, which aims to stress-test (i) the robustness of segmenters under natural and synthetic perturbations, and (ii) the ability to detect anomaly out-of-distribution (OOD) objects in urban scenes European Conference on Computer Vision #ECCV2026 #ECCV2024

WTF(rance)?!

Join us live tomorrow at 2:30pm CET for some exciting updates on our research! youtube.com/live/hm2IJSKcY…

Our simple and cheap CLIP-DINOiser made it to #ECCV2024 ! Work spearheaded by Monika Wysoczańska w/ help from Oriane Siméoni Michaël Ramamonjisoa Tomasz Trzcinski Patrick Pérez and myself

I’ll be attending #ICML2024 next week to present this excellent work led by Victor Letzelter ! Looking forward to chat about ill-posed machine learning tasks, data augmentation, pose estimation, eeg decoding or anything else ML at the poster session or around some coffee !

.Victor Letzelter will be at #ICML2024 to present his work on leveraging the geometric properties of the Winner-takes-all learners for conditional density estimation & uncertainty prediction, w/o modifying its original training scheme. Find a tl;dr below & come say hi at the posters

#ECCV2024 Tue Oct 1 (PM) Train Till You Drop: Towards Stable and Robust Source-free Unsupervised 3D Domain Adaptation Björn Michele, Alexandre Boulch, Tuan-Hung VU, Gilles Puy, Renaud Marlet, Nicolas Courty pdf: arxiv.org/pdf/2409.04409 code: github.com/valeoai/TTYD

Preparing to be🚅European Conference on Computer Vision #ECCV2026 ? Take a look at our recent works that we’ll present there. This year we're happy to share our results covering topics such as forecasting, tracking, domain adaptation, VLMs & LLMs and much more! Find out more 👇 and come meet us at #ECCV2024

You have an already trained sem. segmentation model ? You want to apply it to data with a domain shift ? You are afraid of degradation during the adaptation ? Then you might want to check out our work TTYD at European Conference on Computer Vision #ECCV2026 2024 in Milan. 👉 Poster # 73: Tuesday, 16:30 #ECCV2024

They did the pointer meme!!

🚨 Interested in domain adaptation and generalization for 3D data? 🚨 It’s tough to keep up with all the new amazing work. That’s why I’ve curated a comprehensive, easy-to-navigate list of publications. 📚 👉 Repo: bit.ly/DA_DG_3D

🚗🌆Introducing #DynamicCity: a 4D LiDAR framework for generating dynamic driving scenes!🔥 🚀Generate large-scale, long-duration scenes capturing real-world dynamics, powering versatile 4D generation applications. Project: dynamic-city.github.io Paper: arxiv.org/pdf/2410.18084

📚🔍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/2024-12-… 🧵👇

Meet Hibiki, our simultaneous speech-to-speech translation model, currently supporting 🇫🇷➡️🇬🇧. Hibiki produces spoken and text translations of the input speech in real-time, while preserving the speaker’s voice and optimally adapting its pace based on the semantic content of the

1/ Introducing 𝐃𝐲𝐧𝐚𝐦𝐢𝐜𝐂𝐢𝐭𝐲, a new generation framework capable of generating large-scale, dynamic, high-quality 4D scenes, featured as a ✨Spotlight✨ at #ICLR2025. 📕 Paper: arxiv.org/abs/2410.18084 🌏 Project: dynamic-city.github.io 🤗 Code (open-sourced):

🧵 Excited to share our latest work: FUTURIST - A unified transformer architecture for multimodal semantic future prediction, is accepted to #CVPR2025 ! Here's how it works (1/n) 👇 Links to the arxiv and github below

Meet MoshiVis🎙️🖼️, the first open-source real-time speech model that can talk about images! It sees, understands, and talks about images — naturally, and out loud. Voice interaction with a compact model endowed with visual understanding opens up new applications, from audio