mlsanityData to 14 Oct 2026

ABot-OCR Technical Report

arXiv 2605.27978 ↗First posted 27 May 2026cs.CVcited by 3

On the map: Multimodal LLMs / vision-language models → Document understanding and multimodal RAG

Abstract (arXiv)

We introduce ABot-OCR, an end-to-end vision-language model that transcribes a page image directly into clean Markdown in a single forward pass. By doing so, our approach completely eliminates the need for brittle modular orchestration. To maximize parsing fidelity, we develop a dedicated data engine to provide large-scale, structurally consistent supervision. Furthermore, we propose Decoupled Heterogeneous Document Optimization, a structure-constrained reinforcement learning method that sharpens textual accuracy and strictly enforces markup well-formedness beyond supervised fine-tuning alone. Extensive evaluations demonstrate the superior performance of our framework. On the OmniDocBench v1.5 and v1.6 benchmarks, ABot-OCR achieves state-of-the-art scores of 92.81 and 93.30 among all end-to-end systems, substantially narrowing the performance gap relative to strong pipeline baselines. Finally, comprehensive multilingual text recognition across ten diverse languages further confirms the robust generalizability of ABot-OCR.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Placed in Document understanding and multimodal RAG, one of 16 directions in Multimodal LLMs / vision-language models. Builds on 25 of its 40 references that are in the map. First posted on arXiv 27 May 2026.

Builds on

25 of 40 references.

Closest ancestors · 2

Same direction, newest first

  1. 2025PaddleOCR-VL: Boosting Multilingual Document Parsing via a 0.9B Ultra-Compact Vision-Language Model16 Oct
  2. 2025MinerU2.5: A Decoupled Vision-Language Model for Efficient High-Resolution Document Parsing26 Sep

Other references · 23

  1. 2017Proximal Policy Optimization Algorithmscited by 15,215
  2. 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 9,379
  3. 2022ChartQA: A Benchmark for Question Answering about Charts with Visual and Logical Reasoningcited by 1,479
  4. 2025GLM-4.5V and GLM-4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learningcited by 466
  5. 2025Seed1.5-VL Technical Reportcited by 373
  6. 2018DVQA: Understanding Data Visualizations via Question Answeringcited by 340
  7. 2019PlotQA: Reasoning over Scientific Plotscited by 321
  8. 2019Image-based table recognition: data, model, and evaluationcited by 237
  9. 2024General OCR Theory: Towards OCR-2.0 via a Unified End-to-end Modelcited by 180
  10. 2022Chart-to-Text: A Large-Scale Benchmark for Chart Summarizationcited by 169
  11. 2023UniChart: A Universal Vision-language Pretrained Model for Chart Comprehension and Reasoningcited by 160
  12. 2024OmniDocBench: Benchmarking Diverse PDF Document Parsing with Comprehensive Annotationscited by 150
11 more
  1. 2023VisText: A Benchmark for Semantically Rich Chart Captioningcited by 112
  2. 2025MonkeyOCR: Document Parsing with a Structure-Recognition-Relation Triplet Paradigmcited by 87
  3. 2024DocLayout-YOLO: Enhancing Document Layout Analysis through Diverse Synthetic Data and Global-to-Local Adaptive Perceptioncited by 82
  4. 2025Dolphin: Document Image Parsing via Heterogeneous Anchor Promptingcited by 79
  5. 2025Docling: An Efficient Open-Source Toolkit for AI-driven Document Conversioncited by 63
  6. 2026PaddleOCR-VL-1.5: Towards a Multi-Task 0.9B VLM for Robust In-the-Wild Document Parsingcited by 57
  7. 2026MinerU2.5-Pro: Pushing the Limits of Data-Centric Document Parsing at Scalecited by 27
  8. 2026Dolphin-v2: Universal Document Parsing via Scalable Anchor Promptingcited by 22
  9. 2017Beagle: Automated Extraction and Interpretation of Visualizations from the Webcited by 19
  10. 2025UniRec-0.1B: Unified Text and Formula Recognition with 0.1B Parameterscited by 13
  11. 2026FireRed-OCR Technical Reportcited by 13

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 3.

3 papers.

  1. 2026HunyuanOCR-1.5: Making Lightweight OCR VLMs Faster and Bettercited by 14
  2. 2026OvisOCR2 Technical Reportcited by 5
  3. 2026Xiaomi-OCR-0 Technical Reportcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026LightOnOCR: A 1B End-to-End Multilingual Vision-Language Model for State-of-the-Art OCR
  2. 2026DocOCR-Eval: A Correction-Based Framework for OCR Tool Selection Without Ground Truth
  3. 2026LayoutLite: Token-Level Implicit Layout Analysis for Efficient Document OCR
  4. 2025Reading or Reasoning? Format Decoupled Reinforcement Learning for Document OCR
  5. 2025Infinity Parser: Layout Aware Reinforcement Learning for Scanned Document Parsing
  6. 2025Infinity Parser: Layout Aware Reinforcement Learning for Scanned Document Parsing
  7. 2026DharmaOCR: Specialized Small Language Models for Structured OCR that outperform Open-Source and Commercial Baselines
  8. 2026GutenOCR: A Grounded Vision-Language Front-End for Documents