Settings

Theme

Tinted Frames: Question Framing Blinds Vision-Language Models

davidhalladay.github.io

4 points by ritwikgupta 22 days ago · 1 comment

Reader

ritwikguptaOP 22 days ago

VLMs are selectively blind — they decide how much to look at an image based on question framing (open-ended vs Yes/No vs MCQ), even when the same visual reasoning is required.

Keyboard Shortcuts

j
Next item
k
Previous item
o / Enter
Open selected item
?
Show this help
Esc
Close modal / clear selection