Document Analysis

The olmOCR Project: Building Fully Open OCR using VLMs ACL 2026 Towards Real-World Document Parsing via Realistic Scene Synthesis and Document-Aware Training CVPR 2026 TRACE: Traversal Retrieval-Augmented Chain of Evidence for Document Understanding ACL 2026 UNIKIE-BENCH: Benchmarking Large Multimodal Models for Key Information Extraction in Visual Documents ACL 2026 UniMERNet: A Universal Network for Real-World Mathematical Expression Recognition CVPR 2026 Visual Document Understanding and Reasoning: A Multi-Agent Collaboration Framework with Agent-Wise Adaptive Test-Time Scaling CVPR 2026 What's Wrong with Synthetic Data for Scene Text Recognition? A Strong Synthetic Engine with Diverse Simulations and Self-Evolution CVPR 2026 Zero-shot Jianzi Recognition as Structured Visual Information Extraction in Open Compositional Symbolic Systems ACL 2026 A Bounding Box is Worth One Token - Interleaving Layout and Text in a Large Language Model for Document Understanding ACL 2025 Adaptive Markup Language Generation for Contextually-Grounded Visual Document Understanding CVPR 2025 ADCD-Net: Robust Document Image Forgery Localization via Adaptive DCT Feature and Hierarchical Content Disentanglement ICCV 2025 A Deep Learning Method for Document Shadow Removal with Sobel Prior under Mask Supervision AAAI 2025 AID-Agent: An LLM-Agent for Advanced Extraction and Integration of Documents ACL 2025 An Exemplar-based Framework for Chinese Text Recognition AAAI 2025 Any Information Is Just Worth One Single Screenshot: Unifying Search With Visualized Information Retrieval ACL 2025 A Query-Response Framework for Whole-Page Complex-Layout Document Image Translation with Relevant Regional Concentration ACL 2025 Arctic-TILT. Business Document Understanding at Sub-Billion Scale ACL 2025 Automating the Expansion of Instrument Typicals in Piping and Instrumentation Diagrams (P&IDs) AAAI 2025 Benchmarking Table Extraction: Multimodal LLMs vs Traditional OCR ACL 2025 Beyond End-to-End VLMs: Leveraging Intermediate Text Representations for Superior Flowchart Understanding NAACL 2025 Bootstrapping AI: Interdisciplinary Approaches to Assessing OCR Quality in English-Language Historical Documents NAACL 2025 Bringing Suzhou Numerals into the Digital Age: A Dataset and Recognition Study on Ancient Chinese Trade Records NAACL 2025 BuDDIE: A Business Document Dataset for Multi-task Information Extraction COLING 2025 CalligraphicOCR for Chinese Calligraphy Recognition EMNLP 2025 ChartGaze: Enhancing Chart Understanding in LVLMs with Eye-Tracking Guided Attention Refinement EMNLP 2025