🔥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

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

Hi everyone, I am thrilled to share that our recent study “Optimization-Free Image Immunization Against Diffusion-Based Editing” is now available on ArXiv. ArXiv: arxiv.org/abs/2411.17957 Project Webpage: diffvax.github.io

Downloaded a model's weights and wondering whether it has been poisoned or not? Meet our method, TRODO (Trojan scanning by Detection of Adversarial shift in Out-of-Distribution samples), accepted in #NeurIPS 2024. 1/ Paper: neurips.cc/virtual/2024/p… Code: github.com/rohban-lab/TRO…

We are delighted that our proposal for the Workshop on “Spurious Correlation and Shortcut Learning: Foundations and Solutions” has been accepted at ICLR 2026 2025, hosting many brilliant keynote speakers and panelists. Stay tuned: scslworkshop.github.io Spurious Correlation & Shortcut Learning Workshop 1/

🎉 Excited to introduce "The One RING: a Robotic Indoor Navigation Generalist" – our latest work on achieving cross-embodiment generalization in robot visual navigation! 🤖🌍 RING is a universal navigation policy trained entirely in simulation on diverse, random embodiments at

Interested in building generative models to improve 2D / 3D perception? Research internship positions available in Qualcomm AI Research in Amsterdam: careers.qualcomm.com/careers/job/44… #data_generation #generative_augmentation #diffusuion #GaussianSplatting #3dgeneration #internship

We initially started with voluntary reviews, then required each author to review, and now, if they fail to meet the deadline, their papers will be desk-rejected. These changes feel quite forceful, and my first impression isn't positive—they seem like very binary decisions to me.

This layer in DINO-v2 dedicates about half its attention mass to a single operation. Each of the sixteen heads independently learns the same circuit to perform this task. What is this all-important operation? The “no-op”. That’s right, we’re spending half our computation to do…

✨ The VIS Lab at the @University of Amsterdam is proud and excited to announce it has #TWELVE papers  🚀  accepted for the leading #AI-#makers conference on representation learning (#ICLR) in Singapore 🇸🇬. 1/n 👇👇👇

It would be great if Overleaf could integrate axiv-latex-cleaner as an option in its menu when downloading source files 🤲🙏.

Very happy to share that our work "TokenFormer: Rethinking Transformer Scaling with Tokenized Model Parameters" has been accepted to ICLR2025 as a spotlight. Tokenformer proposes a new way to incrementally scale transformer training. arxiv.org/pdf/2410.23168

Excited to share that the recordings and slides of our SSLBIG tutorial are now online! If you notice any missing reference or have feedback, feel free to reach out. European Conference on Computer Vision #ECCV2026 Stay tuned for future editions! webpage: shashankvkt.github.io/eccv2024-SSLBI… Youtube: youtube.com/@SSLBiG_tutori…

🚀 Excited to share our #ICLR2025 paper! 🤖 AROS: Adversarially Robust Out-of-Distribution Detection through Stability 📄 Paper:openreview.net/forum?id=GrDne… 🔹 #AI_safety 🔹 #Trustworthy_ML 🗓️ Poster Session: Fri 25 Apr 10-12:30 📍 Hall3+Hall 2B (#327)

Happening in 5 minutes at Hall 3 poster stand #330. #ICLR2025

A couple of updates: Happy to share that we have released the code for CTRL-O: github.com/dido1998/CTRL-O Also, Rabiul Awal will be giving a talk about CTRL-O at 3:35 pm today in the multimodal algorithmic reasoning workshop #CVPR2025

Check out our self-supervised method, which leverages motion signals via point trackers to enhance feature extractors like DINOv2 for various dense tasks. It scales to large models and even works with VLMs. Let motion guide your model—better features, bigger gains.

1/ New & old work on self-supervised representation learning (SSL) with ViTs: MOCA ☕ - Predicting Masked Online Codebook Assignments w/ Spyros Gidaris Oriane Siméoni Antonín Vobecký Matthieu Cord N. Komodakis, P. Pérez #TMLR #ICLR2025 Grab a ☕ and brace for a story & a 🧵