📽️ Check out Visual Odometry Transformer! VoT is an end-to-end model for getting accurate metric camera poses from monocular videos.

vladimiryugay.github.io/vot/

🖼️ Most text-to-image models only really work in English.
This limits who can use them and whose imagination they reflect.

We asked: can we build a small, efficient model that understands prompts in multiple languages natively?

Wie heeft toegang tot computerkracht tbv AI? Vooral big Tech. Een paar jaar geleden was dat nog de overheid. Illustratief: Musks xAI heeft 200.000 Nvidia-chips, de gehele Nederlandse wetenschap 650. www.volkskrant.nl/tech/de-over...

Congratulations dr. Tom van Sonsbeek 🥳

Congratulations Dr. @phillip-lippe.bsky.social 🥳

🧠 Union-over-Intersections: Object Detection beyond Winner-Takes-All by Aritra Bhowmik, Pascal Mettes, Martin R. Oswald, Cees Snoek.

🤖 TULIP: Token-length Upgraded CLIP by Ivona Najdenkoska, Mohammad Mahdi Derakhshani, Yuki Asano, Nanne van Noord, Marcel Worring, Cees Snoek. 13/n

🧠 One Hundred Neural Networks and Brains Watching Videos: Lessons from Alignment by Christina Sartzetaki, Gemma Roig, Cees Snoek, Iris Groen. 12/n

🤖 Near, far: Patch-ordering Enhances Vision Foundation Models' Scene Understanding by Valentinos Pariza, Mohammadreza Salehi, Gertjan Burghouts, Francesco Locatello, Yuki Asano. 11/n

🧠 Language Agents Meet Causality – Bridging LLMs and Causal World Models by John Gkountouras, Matthias Lindemann, Phillip Lippe, Efstratios Gavves, Ivan Titov. 10/n

🤖 Grounding Continuous Representations in Geometry: Equivariant Neural Fields by David Wessels, David Knigge, Samuele Papa, Riccardo Valperga, Sharvaree Vadgama, Efstratios Gavves, Erik Bekkers. 9/n

🧠 DynaPrompt: Dynamic Test-Time Prompt Tuning by Zehao Xiao, Shilin Yan, Jack Hong, Jiayin Cai, Xiaolong Jiang, Yao Hu, Jiayi Shen, Cheems Wang, Cees Snoek. 8/n

🤖 Dream to Manipulate: Compositional World Models Empowering Robot Imitation Learning with Imagination by Leonardo Barcellona, Andrii Zadaianchuk, Davide Allegro, Samuele Papa, Stefano Ghidoni, Efstratios Gavves. 7/n

🧠 Compositional Entailment Learning for Hyperbolic Vision-Language Models by Avik Pal, Max van Spengler, Guido Maria D'Amely di Melendugno, Alessandro Flaborea, Fabio Galasso, Pascal Mettes. 6/n

🤖 CaPo: Cooperative Plan Optimization for Efficient Embodied Multi-Agent Cooperation, by Jie Liu, Pan Zhou, Yingjun Du, Ah-Hwee Tan, Cees Snoek, Jan-Jakob Sonke, Efstratios Gavves. 5/n

🧠 BrainACTIV: Identifying visuo-semantic properties driving cortical selectivity using diffusion-based image manipulation by Diego García Cerdas, Christina Sartzetaki, Magnus Petersen, Gemma Roig, Pascal Mettes, Iris Groen. 4/n

🤖 An Image is Worth More Than 16x16 Patches: Exploring Transformers on Individual Pixels by Duy Kien Nguyen, Mahmoud Assran, Unnat Jain, Martin R. Oswald, Cees Snoek, Xinlei Chen. 3/n

Congratulations and a shout-out to all our students and (inter)national collaborators. w/ our amazing staff:
Iris Groen, Pascal Mettes, Yuki Asano (now in 🇩🇪), @egavves.bsky.social .

The 12 papers and their authors below; full paper details, data sets, and source code to follow separately: 2/n

✨ 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 ( #ICLR2025 ) in Singapore 🇸🇬. 1/n
👇👇👇 @ellisamsterdam.bsky.social

📢 There is still time to submit your application for the 2nd ELLIS Winter School on Foundation Models in 2025 which will be held from 18-21 March 2025 in Amsterdam!

We are excited to announce the 2nd ELLIS Winter School on Foundation Models in 2025, 18-21 March in Amsterdam. Secure your spot! ✨

🔗 Visit ivi.fnwi.uva.nl/ellis/events...

🚀 Apply forms.gle/bYbZi9J7NzCb...

#AI #ML #foundationmodels #ELLISforEurope #ELLISunitAmsterdam

📢 New preprint!

We benchmark 99 image and video models 🤖 on brain representational alignment to fMRI data of 10 humans 🧠 watching videos!
Here’s a quick breakdown:🧵⬇️

www.biorxiv.org/content/10.1...