YASSER ABDELAZIZ DAHOU DJILALI

3
Papers
9
Total Citations

Papers (3)

Vision-Language Models Can't See the Obvious

ICCV 2025arXiv
7
citations

Harnessing Frozen Unimodal Encoders for Flexible Multimodal Alignment

CVPR 2025arXiv
2
citations

Do Vision and Language Encoders Represent the World Similarly?

CVPR 2024
0
citations