DMAP: Human-Aligned Structural Document Map for Multimodal Document Understanding.

@inproceedings{fu-2026-dmap, author = {Shunliang Fu and Yanxin Zhang and Yixin Xiang and Xiaoyu Du and Jinhui Tang}, editor = {Hakim Hacid and Yoelle Maarek and Francesco Bonchi and Ido Guy and Emine Yilmaz}, title = {{DMAP: Human-Aligned Structural Document Map for Multimodal Document Understanding}}, booktitle = {{Proceedings of the ACM Web Conference 2026, WWW 2026, Dubai, United Arab Emirates, originally scheduled for April 13-17, 2026, rescheduled for June 29 - July 3, 2026}}, pages = {2037--2048}, publisher = {ACM}, year = {2026}, url = {https://doi.org/10.1145/3774904.3792229}, doi = {https://doi.org/10.1145/3774904.3792229} }