Unlocking Multimodal Document Intelligence: From Current Triumphs to Future Frontiers of Visual Document Retrieval
This paper surveys the VDR landscape as a retrieval problem in its own right, rather than as the front end of a generation pipeline, and does so specifically through the lens of the Multimodal Large Language Model (MLLM) era, and dives into the methodological evolution along two orthogonal axes.
Yibo Yan, Jiahao Huo, Guanbo Feng et al.
· arXiv.org · 9 citations