We’re thrilled to welcome Yuki Asano, Professor at the University of Technology Nuremberg and head of the Fundamental AI (FunAI) Lab, to our heidelberg.ai / NCT Data Science Seminar series on May 13th at 5 pm in Heidelberg (INF280 Seminar Rooms K1+K2).

Surprise guest at the world modelling workshop Panel discussion.

📢 We have a PR[AI]RIE PhD position opening Centre Inria de Paris co advised with R. de Charette & Tuan-Hung VU [please distribute] 💡Topic: Physics-Grounded Vision Foundation Models ⏳Application deadline: 20 May 2025 🗓️ Start date: Fall 2025 📝Detailed description: linked below

It's interesting to see many handcrafted image cropping/sampling methods in recent VLMs [1,2,3,4], without an elegant end-to-end way to learn how to feed the images into the ViT [1/4]

UTN / Bavaria goes H200🔥

2025 is 40% complete.

It was fun with you all in Heidelberg! :)

See you all at our workshop in Hawaii!

unnecessary maths in diffusion papers

🚀 Thrilled to announce our paper, “Self-supervised Normality Learning and Divergence Vector-guided Model Merging for Zero-shot Congenital Heart Disease Detection in Fetal Ultrasound Videos,” is accepted at #MICCAI2025! 🥳 (1/n)

The CVPR 2025 Report has been updated! hirokatsukataoka.net/temp/presen/25… Compiled during CVPR in collaboration with LIMIT.Lab, cvpaper.challenge, and Visual Geometry Group (VGG), this report offers meta insights into the trends and tendencies observed at this year’s conference. #CVPR2025

New paper accepted at #ICCV2025: MoSiC, our new post-pretraining technique for upgrading vision foundation models like DINOv2R using videos, thanks to strong point trackers and Sinkhorn clustering. Check the thread below :)

Announcement of #ICCV2025 LIMIT Workshop! The submission deadline (10 July, HST) is approaching! Please consider to submit your paper(s). This is the 4-page submission.

New preprint! We present a simple alternative to activation steering: KV-cache steering (intervene on the history once instead of continuous intervention on the current activations). This allows, e.g., inducing reasoning in small LLMs by distilling traces from big models. No

Welcoming Ryousuke as our visiting postdoc at FunAI Lab :) Let's do some great research!

NeurIPS is pleased to officially endorse EurIPS, an independently-organized meeting taking place in Copenhagen this year, which will offer researchers an opportunity to additionally present their accepted NeurIPS work in Europe, concurrently with NeurIPS. Read more in our blog

🎉Meet the #3DV2026 Keynote Speakers! Jitendra Malik · University of California, Berkeley Angela Dai · Technical University of Munich Christian Rupprecht · University of Oxford Alec Jacobson · University of Toronto Bring your latest work and join us for the exciting keynotes!

Nice short summary!

Franca Nested Matryoshka Clustering for Scalable Visual Representation Learning

Today we release Franca, a new vision Foundation Model that matches and sometimes outperforms DINOv2. The data, the training code and the model weights (with intermediate checkpoints) are open-source, allowing everyone to build on this. Methodologically, we introduce two new