Sanath Narayan

3
Papers
0
Total Citations

Papers (3)

Harnessing Frozen Unimodal Encoders for Flexible Multimodal Alignment

CVPR 2025arXiv
0
citations

Vision-Language Models Can't See the Obvious

ICCV 2025arXiv
0
citations

Do Vision and Language Encoders Represent the World Similarly?

CVPR 2024
0
citations