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

@inproceedings{wang-2025-glfomr, author = {Yaxian Wang and Bifan Wei and Jun Liu and Lingling Zhang and Shuting He and Jun Li and Qika Lin}, editor = {Nicola Ferro and Maria Maistro and Gabriella Pasi and Omar Alonso and Andrew Trotman and Suzan Verberne}, title = {{GlFoMR: A Glance-then-Focus Multimodal Reasoning Framework for Diagram Question Answering}}, booktitle = {{Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2025, Padua, Italy, July 13-18, 2025}}, pages = {1130--1140}, publisher = {ACM}, year = {2025}, url = {https://doi.org/10.1145/3726302.3729990}, doi = {https://doi.org/10.1145/3726302.3729990} }