Check out Pau's thread on our new #ECCV2026 paper! 🧵 We propose a proxy for making model merging scalable for real-world computer vision tasks (merging encoders across diverse domains like 2D, 3D, and human understanding)

Pau de Jorge@pdejorge.bsky.social · last wk.

1/6 Excited to share that our paper on model merging was accepted at ECCV 2026! 🎉 We introduce an efficient, decoder-free proxy that makes model selection faster, simpler and practical across vision tasks. 📄 arxiv.org/abs/2604.12935 🌐 europe.naverlabs.com/task-alignment 🧵👇

1/6 Excited to share that our paper on model merging was accepted at ECCV 2026! 🎉 We introduce an efficient, decoder-free proxy that makes model selection faster, simpler and practical across vision tasks. 📄 arxiv.org/abs/2604.12935 🌐 europe.naverlabs.com/task-alignment 🧵👇

CVPR in Paris starting with Opening remarks from @davidpicard.eurosky.social

Multiple CVPR 2026 outstanding reviewer awards at @valeoai.bsky.social! Congrats to @anhquancao.bsky.social, D. Hurych, N. Samet, @t-martyniuk.bsky.social, Y. Xu, and alumni @gillespuy.bsky.social, S. Venkataramanan, F. Bartoccioni, @bjoernmichele.bsky.social. media.eventhosts.cc/Conferences/...

Research described in these 2 papers: UNIC - europe.naverlabs.com/unic #ECCV2024 DUNE - europe.naverlabs.com/dune #CVPR2025

🎬 Nice video illustrating our recent line of work on multi-teacher distillation for learning visual representations

NAVER LABS Europe@naverlabseurope.bsky.social · 4mo ago

How to scale visual perception in robotics w/o scaling compute? We present a distilled 'universal encoder' that's compact and compatible with multiple 2D&3D vision tasks! → up to 90% less encoding memory 🗜️ → 4× faster at inference 🚀 More info -->> tinyurl.com/universal-en...

Congratulations to our researchers Renaud Marlet and @abursuc.bsky.social on their repeated recognition as outstanding reviewers at #CVPR, #ICCV, and #ECCV👏👏👏 Thank you for your sharp insights, kindness, and dedication. It's key for the field to count on reviewers like you!

1/n New paper - V-GIFT 🎁 Self-supervised tasks like rotation prediction or colorization were big in 2018. Do they still matter? Yes. We turn them into visual instruction tuning data for MLLMs. Result: models rely more on the image and perform better on vision tasks 👀

ECCV 2026 deadline push at @naverlabseurope.bsky.social with @dlarlus.bsky.social @weinzaepfelp.bsky.social @mbsariyildiz.bsky.social @bjoernmichele.bsky.social @vincentleroy.bsky.social @rbregier.bsky.social + + + ....

🏹 Job alert: 3 PhD positions in AI, Earth Observation, and Science-Policy interface 📍 Vannes 🇫🇷 & Ispra 🇮🇹 📅 Apply by Jan 15th 🔗 https://www-obelix.irisa.fr/job-offers/

#BMVC2025

Björn Michele@bjoernmichele.bsky.social · 8mo ago

🚗🌐 Working on domain adaptation for 3D point clouds / LiDAR? We'll present MuDDoS at BMVC: a method that boosts multimodal distillation for 3D semantic segmentation under domain shift. 📍 BMVC 🕚 Monday, Poster Session 1: Multimodal Learning (11:00–12:30) 📌 Hadfield Hall #859

🚗🌐 Working on domain adaptation for 3D point clouds / LiDAR? We'll present MuDDoS at BMVC: a method that boosts multimodal distillation for 3D semantic segmentation under domain shift. 📍 BMVC 🕚 Monday, Poster Session 1: Multimodal Learning (11:00–12:30) 📌 Hadfield Hall #859

and Aniruddha Kembhavi, Adrien Gaidon, Nicolas Mansard, and Justin Carpentier as afternoon ones

One of those internships is on Gromov $\delta$-hyperbolicity for GNNs, and will be cosupervised together with Nicolas, myself and Laetitia Chapel. Take a look and spread the words !

Nicolas Keriven@nicolaskeriven.bsky.social · 9mo ago

I have several offers for Master internships / PhDs on graph ML funded by ERC MALAGA for 2026. Don't hesitate to contact me to apply! All infos here: nkeriven.github.io/malaga/

Happy to represent Ukraine at #ICCV2025 . Come see my poster today at 11:45 (#399)!

Our recent research will be presented at @iccv.bsky.social! #ICCV2025 We’ll present 5 papers about: 💡 self-supervised & representation learning 🌍 3D occupancy & multi-sensor perception 🧩 open-vocabulary segmentation 🧠 multimodal LLMs & explainability valeoai.github.io/posts/iccv-2...

Come say hi to our poster October 21st at 11:45 poster session 1 (#399)! We introduce unsupervised post-training of ViTs that enhances dense features for in-context tasks. First conference as a PhD student, really excited to meet new people.

Sophia Sirko-Galouchenko 🇺🇦@ssirko.bsky.social · last yr.

1/n 🚀New paper out - accepted at #ICCV2025! Introducing DIP: unsupervised post-training that enhances dense features in pretrained ViTs for dense in-context scene understanding Below: Low-shot in-context semantic segmentation examples. DIP features outperform DINOv2!

Aloha #iccv25 – here we come! Excited to be presenting new *St3R models PANSt3R, HAMSt3R & HOSt3R. We're also introducing ‘Geo4D' and ‘LUDVIG’ 🫢 giving invited talks and mentoring! Full @iccv.bsky.social programme below (or tinyurl.com/asbn5b5d) 🧵1/9

ICCV 2025

5 papers, invited speaker, WiCV sponsor and Challenge sponsor

tinyurl.com

Another great event for @valeoai.bsky.social team: a PhD defense of Corentin Sautier. His thesis «Learning Actionable LiDAR Representations w/o Annotations» covers the papers BEVContrast (learning self-sup LiDAR features), SLidR, ScaLR (distillation), UNIT and Alpine (solving tasks w/o labels).

So excited to attend the PhD defense of @bjoernmichele.bsky.social at @valeoai.bsky.social! He’s presenting his research results of the last 3 years in 3D domain adaptation: SALUDA (unsupervised DA), MuDDoS (multimodal UDA), TTYD (source-free UDA).

It’s PhD graduation season in the team! Today, @bjoernmichele.bsky.social is defending his PhD on "Domain Adaptation for 3D Data" Best of luck! 🚀

Congratulations to our lab colleagues who have been named Outstanding Reviewers at #ICCV2025 👏 Andrei Bursuc @abursuc.bsky.social Anh-Quan Cao @anhquancao.bsky.social Renaud Marlet Eloi Zablocki @eloizablocki.bsky.social @iccv.bsky.social iccv.thecvf.com/Conferences/...

Discovered that our RangeViT paper keeps being cited in what might be LLM-generated papers. Number of citations increased rapidly in the last weeks. Too good to be true. Papers popped up on different platforms, but mainly on ResearchGate with ~80 papers in just 3 weeks. [1/]

SKADA-Bench : Benchmarking Unsupervised Domain Adaptation Methods with Realistic Validation On Diverse Modalities, has been published published in TMLR today 🚀. It was a huge team effort to design (and publish) an open source fully reproducible DA benchmark 🧵1/n. openreview.net/forum?id=k9F...

1/ Can open-data models beat DINOv2? Today we release Franca, a fully open-sourced vision foundation model. Franca with ViT-G backbone matches (and often beats) proprietary models like SigLIPv2, CLIP, DINOv2 on various benchmarks setting a new standard for open-source research.

The most important aspect when facing data shift is the type of shift present in the data. I will give below a few examples of shifts and some existing methods to compensate for it.🧵1/6

I wrote a notebook for a lecture/exercice on image generation with flow matching. The idea is to use FM to render images composed of simple shapes using their attributes (type, size, color, etc). Not super useful but fun and easy to train! colab.research.google.com/drive/16GJyb... Comments welcome!

1/n 🚀New paper out - accepted at #ICCV2025! Introducing DIP: unsupervised post-training that enhances dense features in pretrained ViTs for dense in-context scene understanding Below: Low-shot in-context semantic segmentation examples. DIP features outperform DINOv2!

Going to the hospital because I broke my wrist smashing the endorse button: www.understandingai.org/p/i-got-fool...

I got fooled by AI-for-science hype—here's what it taught me

I used AI in my plasma physics research and it didn’t go the way I expected.

understandingai.org

Behind every great conference is a team of dedicated reviewers. Congratulations to this year’s #CVPR2025 Outstanding Reviewers! cvpr.thecvf.com/Conferences/...