mlsanityData to 14 Oct 2026

DocFusion: A Unified Framework for Document Parsing Tasks

arXiv 2412.12505 ↗First posted 17 Dec 2024cs.CLcited by 5

Not on the map. Why?

Abstract (arXiv)

Document parsing is essential for analyzing complex document structures and extracting fine-grained information, supporting numerous downstream applications. However, existing methods often require integrating multiple independent models to handle various parsing tasks, leading to high complexity and maintenance overhead. To address this, we propose DocFusion, a lightweight generative model with only 0.28B parameters. It unifies task representations and achieves collaborative training through an improved objective function. Experiments reveal and leverage the mutually beneficial interaction among recognition tasks, and integrating recognition data significantly enhances detection performance. The final results demonstrate that DocFusion achieves state-of-the-art (SOTA) performance across four key tasks.

Key facts. Cited by 5 papers in the map (data through 14 Oct 2026). Builds on 18 of its 37 references that are in the map. First posted on arXiv 17 Dec 2024.

Builds on

18 of 37 references.

References · 18

  1. 2020End-to-End Object Detection with Transformerscited by 7,414
  2. 2020Deformable DETR: Deformable Transformers for End-to-End Object Detectioncited by 3,422
  3. 2021BEiT: BERT Pre-Training of Image Transformerscited by 2,375
  4. 2023Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyondcited by 2,224
  5. 2023Retrieval-Augmented Generation for Large Language Models: A Surveycited by 2,212
  6. 2024YOLOv10: Real-Time End-to-End Object Detectioncited by 515
  7. 2020LayoutLMv2: Multi-modal Pre-training for Visually-Rich Document Understandingcited by 408
  8. 2023Nougat: Neural Optical Understanding for Academic Documentscited by 245
  9. 2024General OCR Theory: Towards OCR-2.0 via a Unified End-to-end Modelcited by 180
  10. 2021RocketQAv2: A Joint Training Method for Dense Passage Retrieval and Passage Re-rankingcited by 176
  11. 2024TextMonkey: An OCR-Free Large Multimodal Model for Understanding Documentcited by 174
  12. 2021Adversarial Retriever-Ranker for dense text retrievalcited by 83
6 more
  1. 2024DocLayout-YOLO: Enhancing Document Layout Analysis through Diverse Synthetic Data and Global-to-Local Adaptive Perceptioncited by 82
  2. 2023Improving Table Structure Recognition with Visual-Alignment Sequential Coordinate Modelingcited by 41
  3. 2023Towards Understanding the Capability of Large Language Models on Code Clone Detection: A Surveycited by 15
  4. 2019Pattern Generation Strategies for Improving Recognition of Handwritten Mathematical Expressionscited by 13
  5. 2024Visually Guided Generative Text-Layout Pre-training for Document Intelligencecited by 12
  6. 2017Fully Convolutional Neural Networks for Page Segmentation of Historical Document Imagescited by 9

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 2; 2026: 3.

5 papers.

  1. 2025Dolphin: Document Image Parsing via Heterogeneous Anchor Promptingcited by 79
  2. 2026Dolphin-v2: Universal Document Parsing via Scalable Anchor Promptingcited by 22
  3. 2025Improving RL Exploration for LLM Reasoning through Retrospective Replaycited by 19
  4. 2026DM0: An Embodied-Native Vision-Language-Action Model towards Physical AIcited by 12
  5. 2026Efficient Document Parsing via Parallel Token Predictioncited by 2