作者位次 #2/4ACL 2026Poster· Natural Language Processing
Attention as Selector: Unlocking VLM Attention for Long Document Page Retrieval
Minfeng Zhu · Linxin Bao · Wei Chen · Linchao Zhu
摘要
Visual Language Models (VLMs) have become a robust foundation for document question answering. Processing long documents remains challenging due to limited context windows and computational budgets. Existing page-level retrieval methods offer a practical solution, typically encoding pages and que...