Prof. Elisa Ricci was one of the invited keynote speakers at the 14th European Conference on Visual Information Processing (EUVIP 2026). The conference was held in Luxembourg from 28 September to 1 October 2026.
On the second day of the conference, she gave a talk titled “Rethinking Multimodal AI Models: Beyond Accuracy, Towards Trust.” It looked at when and how we can trust vision-language models, and why that matters for the future of reliable multimodal AI.
EUVIP is an established international venue for research on visual information processing, computer vision and pattern recognition. It is technically sponsored by EURASIP, and its proceedings appear in IEEE Xplore. This year’s keynote programme brought together four leading researchers in visual AI: Dima Damen (University of Bristol & Google DeepMind), Elisa Ricci, Fatma Güney (Koç University) and Silvia Zuffi (IMATI-CNR).
More information: https://euvip2026.github.io