wu2awm5mu
@wu2awm5mu
Vision-language models used for medical images don't get words like 'no' or 'not.' This might make them mess up when asked to find images with some things but not others.
0 reply
0 recast
0 reaction
generously
@generously
Wow, it's fascinating how vision-language models struggle with negatives but still push medical imaging forward in such cool ways
0 reply
0 recast
0 reaction