Robo Santa is here! π
π€ We introduce REALM, a real-to-sim validated benchmark for robot manipulation. High-fidelity simulation + aligned control = real-world proxy. Stress-test your policy! π
Web martin-sedlacek.com/realm/#takea...
GH github.com/martin-sedla...
arXiv arxiv.org/abs/2512.19562
1/4
Posts by Cees Snoek
π½οΈ 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/
πΌοΈ 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 π₯³
Congratulations Dr. @phillip-lippe.bsky.social π₯³
π§ Union-over-Intersections: Object Detection beyond Winner-Takes-All by Aritra Bhowmik, Pascal Mettes, Martin R. Oswald, Cees Snoek.
π€ TULIP: Token-length Upgraded CLIP by Ivona Najdenkoska, Mohammad Mahdi Derakhshani, Yuki Asano, Nanne van Noord, Marcel Worring, Cees Snoek. 13/n
π§ One Hundred Neural Networks and Brains Watching Videos: Lessons from Alignment by Christina Sartzetaki, Gemma Roig, Cees Snoek, Iris Groen. 12/n
π€ Near, far: Patch-ordering Enhances Vision Foundation Models' Scene Understanding by Valentinos Pariza, Mohammadreza Salehi, Gertjan Burghouts, Francesco Locatello, Yuki Asano. 11/n
π§ Language Agents Meet Causality β Bridging LLMs and Causal World Models by John Gkountouras, Matthias Lindemann, Phillip Lippe, Efstratios Gavves, Ivan Titov. 10/n
π€ 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
π§ 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
π€ 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
π§ 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
π€ 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
π§ BrainACTIV: Identifying visuo-semantic properties driving cortical selectivity using diffusion-based image manipulation by Diego GarcΓa Cerdas, Christina Sartzetaki, Magnus Petersen, Gemma Roig, Pascal Mettes, Iris Groen. 4/n
π€ 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 π©πͺ), @egavves.bsky.social .
The 12 papers and their authors below; full paper details, data sets, and source code to follow separately: 2/n
β¨ The VIS Lab at the #University of #Amsterdam is proud and excited to announce it has #TWELVE papers π accepted for the leading #AI-#makers conference on representation learning ( #ICLR2025 ) in Singapore πΈπ¬. 1/n
πππ @ellisamsterdam.bsky.social
π’ 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! β¨
π Visit ivi.fnwi.uva.nl/ellis/events...
π Apply forms.gle/bYbZi9J7NzCb...
#AI #ML #foundationmodels #ELLISforEurope #ELLISunitAmsterdam