GlFoMR: A Glance-then-Focus Multimodal Reasoning Framework for Diagram Question Answering

Open Webpage

Yaxian Wang, Bifan Wei, Jun Liu, Lingling Zhang, Shuting He, Jun Li, Qika Lin

Published: 01 Jan 2025, Last Modified: 02 Aug 2025SIGIR 2025EveryoneRevisionsBibTeXCC BY-SA 4.0