Video & Image Sense Lab

We make sense of video and images with artificial and human intelligence. The lab studies computer vision, deep learning and cognitive science. We are based at the Informatics Institute of the University of Amsterdam.

The VIS Lab embeds four public-private AI labs. QUVA Lab with Qualcomm, Atlas Lab with TomTom, AIM Lab with the Inception Institute of Artificial Intelligence and POP-AART with the Netherlands Cancer Institute and Elekta Oncology Systems. Spin-off's from the lab include Kepler Vision Technologies and Ellogon.ai.

News

  • [2026-5] 3 outstanding AC awards at CVPR.
  • [2026-5] Congratulations to Dr. Sarah Rastegar for obtaining the doctorate degree.
  • [2026-5] 3 papers accepted at ICML.
  • [2026-4] NeoBabel demonstrated to Her Royal Highness Catharina-Amalia, Princess of Orange and the Mayor of Amsterdam, Femke Halsema.
  • [2026-3] Congratulations to VIS-lab alumnus Dr. Tao Hu for being promoted to Full Professor at Huazhong University of Science and Technology.
  • [2026-2] Congratulations to Dr. Duy-Kien Nguyen for obtaining the doctorate degree.
  • [2026-1] 9 papers accepted at ICLR.
  • [2025-12] Congratulations to Dr. Amber Brands for obtaining the doctorate degree.
  • [2025-11] Congratulations to Dr. Yingjun Du for obtaining the doctorate degree, cum laude.
  • [2025-10] Iris Groen and Pascal Mettes awarded NWO Vidi Grant.

Old News

Recent Publications

Quickly discover relevant content by filtering publications.

What Layers When: Learning to Skip Compute in LLMs with Residual Gates

ICLR 2026

Distributional Vision-Language Alignment by Cauchy-Schwarz Divergence

ICLR 2026

MoAlign: Motion-Centric Representation Alignment for Video Diffusion Models

ICLR 2026

OrthoRF: Exploring Orthogonality in Object-Centric Representations

ICLR 2026

Prompt-Robust Vision-Language Models via Meta-Finetuning

ICLR 2026

Contact