Moin

@moinnas

Joined February 2016

20 Following

12 Followers

1 Posts

moinnas retweeted

Pouya Pezeshkpour @PPezeshkpour

over 1 year ago

📢New Preprint 📢 Do VLMs reason fairly over text and image inputs? Absolutely not! When given conflicting image-text pairs, they strongly favor either text or image based on the task, and this bias is highly linked to sample difficulty. See our paper: https://t.co/Sz8IgNeeqz 1/n

PPezeshkpour's tweet photo. 📢New Preprint 📢
Do VLMs reason fairly over text and image inputs? Absolutely not! When given conflicting image-text pairs, they strongly favor either text or image based on the task, and this bias is highly linked to sample difficulty. See our paper:
https://t.co/Sz8IgNeeqz 1/n https://t.co/G95Lk974kP

595

Moin

@moinnas

Last Seen Users on Sotwe

Trends for you

Most Popular Users