What Do VLMs NOTICE? A Mechanistic Interpretability Pipeline for Noise-free Text-Image Corruption and Evaluation
Paper
• 2406.16320 • Published
• 3
Michal Golovanevsky
mgolov
·
AI & ML interests
None yet
Recent Activity
updated
a dataset 3 days ago
mgolov/graded-color-attribution published
a dataset 3 days ago
mgolov/graded-color-attribution new activity
6 months ago
mgolov/shape-blind-dataset:Improve dataset card: Update task category, add tags, and add sample usage Organizations
authored 2 papers 12 months ago