Pooyan's picture

Pooyan

pooyanrg

·

pooyanrg

AI & ML interests

None yet

Recent Activity

upvoted a paper 26 days ago

SketchVLM: Vision language models can annotate images to explain thoughts and guide users

updated a Space 8 months ago

pooyanrg/resultsBlindTest

published a Space 9 months ago

pooyanrg/resultsBlindTest

View all activity

Organizations

authored 2 papers 11 months ago

Improving Zero-Shot Object-Level Change Detection by Incorporating Visual Correspondence

Paper • 2501.05555 • Published Jan 9, 2025 • 1

TAB: Transformer Attention Bottlenecks enable User Intervention and Debugging in Vision-Language Models

Paper • 2412.18675 • Published Dec 24, 2024 • 1

authored a paper almost 2 years ago

Vision language models are blind

Paper • 2407.06581 • Published Jul 9, 2024 • 84