Do VLMs Have Bad Eyes? Diagnosing Compositional Failures via Mechanistic Interpretability

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Aravindan, Ashwath Vaithinathan, Jha, Abha, Kulkarni, Mihir
Format:	Preprint
Published:	2025
Subjects:	Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2508.16652