作者位次 #2/9ACL 2026Findings· Findings of ACL
A Survey on MLLM -based Visually Rich Document Understanding: Methods, Challenges, and Emerging Trends
Yihao Ding · Siwen Luo · Yue Dai · Yanbei Jiang · Zechuan Li · Qiang Sun · Geoffrey Martin · Wei Liu · Yifan Peng
摘要
Visually Rich Document Understanding (VRDU) has become a pivotal area of research, driven by the need to automatically interpret documents that contain intricate visual, textual, and structural elements. Recently, Multimodal Large Language Models (MLLMs) have demonstrated significant promise in t...