How Well Do Vision Models Encode Diagram Attributes?

Open Webpage

Haruto Yoshida, Keito Kudo, Yoichi Aoki, Ryota Tanaka, Itsumi Saito, Keisuke Sakaguchi, Kentaro Inui

Published: 2024, Last Modified: 17 Mar 2026ACL (Student Research Workshop) 2024EveryoneRevisionsBibTeXCC BY-SA 4.0