作者位次 #6/12ACL 2026Poster· Natural Language Processing
Doc- V^* : Coarse-to-Fine Interactive Visual Reasoning for Multi-Page Document VQA
Yuanlei Zheng · Pei Fu · Hang Li · Ziyang Wang · Yuyi Zhang · Wenyu Ruan · Xiaojin Zhang · zhongyu wei · Zhenbo Luo · Jian Luan · Wei Chen · Xiang Bai
摘要
Multi-page Document Visual Question Answering requires reasoning over semantics, layouts, and visual elements in long, visually dense documents. Existing OCR-free methods face a trade-off between capacity and precision: end-to-end models scale poorly with document length, while visual retrieval-b...