cs.CVDec 14, 2025

UniDoc: Towards Unified Thinking in Documents

Authors: Qixin Xu, Haozhe Wang, Che Liu, Fangzhen Lin, Wenhu Chen

Organizations: Tsinghua University · University of Waterloo · The Hong Kong University of Science and Technology · Imperial College London

Abstract

Answering questions over long, visually rich documents demands both cross-page structural reasoning and fine-grained visual understanding. Existing approaches sacrifice one for the other: retrieval-augmented methods fragment documents and lose inter-page structure; monolithic vision-language models preserve structure but scale poorly beyond a few pages. This impasse stems from a false premise: that the macroscopic task of evidence retrieval and the microscopic task of detailed reasoning must either be split into separate systems or be processed identically. By decoupling their perceptual resolutions rather than their architectures, a single model can achieve the structural holism of monolithic processing alongside the efficiency of targeted retrieval. UniDoc realizes this through two resolution-adaptive stages: a Fast Reading stage processes all pages at low resolution to structurally identify evidence pages, and a Focused Thinking stage re-processes only those pages at high resolution for multimodal inference. To train this pipeline, we construct 30K multi-hop reasoning instances with stage-level supervision. On MMLongBench-Doc, UniDoc yields relative accuracy gains of 55.7% on Qwen2.5-VL-7B and 16.9% on Qwen3-VL-8B, while significantly reducing token cost relative to uniform high-resolution processing. Error analysis identifies page retrieval and fine-grained visual reasoning as the remaining bottlenecks, delineating concrete targets for future work.

Figures & tables

Appendix figures & tables15 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. DocSeeker: Structured Visual Reasoning with Evidence Grounding for Long Document Understanding

    Apr 14, 2026Hao Yan, Yuliang Liu, Xingchen Liu +5Document UnderstandingLong-Document Visual Question Answering

  2. Doc-V*:Coarse-to-Fine Interactive Visual Reasoning for Multi-Page Document VQA

    Apr 15, 2026Yuanlei Zheng, Pei Fu, Hang Li +9Document QALong-Document Visual Question Answering