Do VLMs Have Bad Eyes? Diagnosing Compositional Failures via Mechanistic Interpretability
Paper
•
2508.16652
•
Published
Ashwath Vaithinathan Aravindan
ashwath-vaithina
·
AI & ML interests
None yet
Recent Activity
updated
a model
3 days ago
ashwath-vaithina/sealing-the-backdoor-unlearning-adversarial-triggers-in-diffusion-models
new activity
5 days ago
ashwath-vaithina/toy-shapes-dataset:Add VLM task category
new activity
6 days ago
ashwath-vaithina/toy-shapes-dataset:Improve metadata: Update task category and add relevant tags
Organizations
