Found but Not Read: When Extracted Text Closes the Retrieval-Reading Gap in Document Vision-Language Models

cs.CV

Submitted: 2026-10-02

Updated: 2026-10-02

Comments: 5 pages, 5 figures, 3 tables. Submitted to ICASSP 2027

Code: https://github.com/atoz03/fovedoc-sup

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Sources

• ColPali: Efficient Document Retrieval with Vision Language Models
• MMLongBench-Doc: Benchmarking Long-context Document Understanding with Visualizations
• Qwen3-VL Technical Report
• PP-OCR: A Practical Ultra Lightweight OCR System
• Qwen2.5-VL Technical Report
• LLaVA-OneVision: Easy Visual Task Transfer
• Building and better understanding vision-language models: insights and future directions

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models