Scaling Multimodal Retrieval and Generation for Long Documents through Visual Tiling and Context Compression.

@inproceedings{jin-2026-scaling, author = {Yi Jin and Weichao Chen and Shengjie Zhao}, editor = {Stevan Rudinac and Zi Huang and Marcel Worring and Lucia Vadicamo and Xirong Li and Pascal Mettes and Lizi Liao}, title = {{Scaling Multimodal Retrieval and Generation for Long Documents through Visual Tiling and Context Compression}}, booktitle = {{Proceedings of the 2026 International Conference on Multimedia Retrieval, ICMR 2026, Amsterdam, The Netherlands, June 16-19, 2026}}, pages = {128--137}, publisher = {ACM}, year = {2026}, url = {https://doi.org/10.1145/3805622.3810822}, doi = {https://doi.org/10.1145/3805622.3810822} }