# POINTS-Reader: Distillation-Free Adaptation of Vision-Language Models for Document Conversion

arXiv: https://arxiv.org/abs/2509.01215 · HTML: https://mlsanity.com/paper/2509.01215/

## Key facts

- Cited by 34 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 19 of its 28 references that are in the map.
- First posted on arXiv 1 Sep 2025.

## Placed in

- Multimodal LLMs / vision-language models / [Document understanding and multimodal RAG](https://mlsanity.com/mllm/document-understanding-and-multimodal-rag/)

## Builds on (most cited first, 19 of 19)

- [Improved Baselines with Visual Instruction Tuning](https://mlsanity.com/paper/2310.03744/) (2023)
- [Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution](https://mlsanity.com/paper/2409.12191/) (2024)
- [LLaVA-OneVision: Easy Visual Task Transfer](https://mlsanity.com/paper/2408.03326/) (2024)
- [Pix2Struct: Screenshot Parsing as Pretraining for Visual Language Understanding](https://mlsanity.com/paper/2210.03347/) (2022)
- [InternLM-XComposer: A Vision-Language Large Model for Advanced Text-image Comprehension and Composition](https://mlsanity.com/paper/2309.15112/) (2023)
- [MinerU: An Open-Source Solution for Precise Document Content Extraction](https://mlsanity.com/paper/2409.18839/) (2024)
- [Nougat: Neural Optical Understanding for Academic Documents](https://mlsanity.com/paper/2308.13418/) (2023)
- [Image-based table recognition: data, model, and evaluation](https://mlsanity.com/paper/1911.10683/) (2019)
- [Patch n' Pack: NaViT, a Vision Transformer for any Aspect Ratio and Resolution](https://mlsanity.com/paper/2307.06304/) (2023)
- [mPLUG-DocOwl 1.5: Unified Structure Learning for OCR-free Document Understanding](https://mlsanity.com/paper/2403.12895/) (2024)
- [PP-OCR: A Practical Ultra Lightweight OCR System](https://mlsanity.com/paper/2009.09941/) (2020)
- [OmniDocBench: Benchmarking Diverse PDF Document Parsing with Comprehensive Annotations](https://mlsanity.com/paper/2412.07626/) (2024)
- [olmOCR: Unlocking Trillions of Tokens in PDFs with Vision Language Models](https://mlsanity.com/paper/2502.18443/) (2025)
- [mPLUG-DocOwl2: High-resolution Compressing for OCR-free Multi-page Document Understanding](https://mlsanity.com/paper/2409.03420/) (2024)
- [CC-OCR: A Comprehensive and Challenging OCR Benchmark for Evaluating Large Multimodal Models in Literacy](https://mlsanity.com/paper/2412.02210/) (2024)
- [Focus Anywhere for Fine-grained Multi-page Document Understanding](https://mlsanity.com/paper/2405.14295/) (2024)
- [SmolDocling: An ultra-compact vision-language model for end-to-end multi-modal document conversion](https://mlsanity.com/paper/2503.11576/) (2025)
- [PP-StructureV2: A Stronger Document Analysis System](https://mlsanity.com/paper/2210.05391/) (2022)
- [POINTS: Improving Your Vision-language Model with Affordable Strategies](https://mlsanity.com/paper/2409.04828/) (2024)

## Built on by (most cited first, 30 of 34)

- [MinerU2.5: A Decoupled Vision-Language Model for Efficient High-Resolution Document Parsing](https://mlsanity.com/paper/2509.22186/) (2025)
- [PaddleOCR-VL: Boosting Multilingual Document Parsing via a 0.9B Ultra-Compact Vision-Language Model](https://mlsanity.com/paper/2510.14528/) (2025)
- [DeepSeek-OCR 2: Visual Causal Flow](https://mlsanity.com/paper/2601.20552/) (2026)
- [PaddleOCR-VL-1.5: Towards a Multi-Task 0.9B VLM for Robust In-the-Wild Document Parsing](https://mlsanity.com/paper/2601.21957/) (2026)
- [GLM-OCR Technical Report](https://mlsanity.com/paper/2603.10910/) (2026)
- [Dolphin-v2: Universal Document Parsing via Scalable Anchor Prompting](https://mlsanity.com/paper/2602.05384/) (2026)
- [PaddleOCR-VL-1.6: Expanding the Frontier of Document Parsing with Under-Optimized Region Refinement and Progressive Post-Training](https://mlsanity.com/paper/2606.03264/) (2026)
- [HunyuanOCR-1.5: Making Lightweight OCR VLMs Faster and Better](https://mlsanity.com/paper/2607.04884/) (2026)
- [MonkeyOCR v1.5 Technical Report: Unlocking Robust Document Parsing for Complex Patterns](https://mlsanity.com/paper/2511.10390/) (2025)
- [FireRed-OCR Technical Report](https://mlsanity.com/paper/2603.01840/) (2026)
- [Youtu-Parsing: Perception, Structuring and Recognition via High-Parallelism Decoding](https://mlsanity.com/paper/2601.20430/) (2026)
- [DocPTBench: Benchmarking End-to-End Photographed Document Parsing and Translation](https://mlsanity.com/paper/2511.18434/) (2025)
- [Reading or Reasoning? Format Decoupled Reinforcement Learning for Document OCR](https://mlsanity.com/paper/2601.08834/) (2025)
- [Unlimited OCR Works](https://mlsanity.com/paper/2606.23050/) (2026)
- [Towards Real-World Document Parsing via Realistic Scene Synthesis and Document-Aware Training](https://mlsanity.com/paper/2603.23885/) (2026)
- [DOCR-Inspector: Fine-Grained and Automated Evaluation of Document Parsing with VLM](https://mlsanity.com/paper/2512.10619/) (2025)
- [HSD: Training-Free Acceleration for Document Parsing Vision-Language Models with Hierarchical Speculative Decoding](https://mlsanity.com/paper/2602.12957/) (2026)
- [Logics-Parsing-Omni Technical Report](https://mlsanity.com/paper/2603.09677/) (2026)
- [OvisOCR2 Technical Report](https://mlsanity.com/paper/2607.13639/) (2026)
- [TRivia: Self-supervised Fine-tuning of Vision-Language Models for Table Recognition](https://mlsanity.com/paper/2512.01248/) (2025)
- [POINTS-GUI-G: GUI-Grounding Journey](https://mlsanity.com/paper/2602.06391/) (2026)
- [Uni-Parser Technical Report](https://mlsanity.com/paper/2512.15098/) (2025)
- [Boosting Document Parsing Efficiency and Performance with Coarse-to-Fine Visual Processing](https://mlsanity.com/paper/2603.24326/) (2026)
- [LingDT-VL-OCR: Structure-Aware Document-Level Parsing with Fine-Grained Visual Reference](https://mlsanity.com/paper/2603.11044/) (2026)
- [Efficient Document Parsing via Parallel Token Prediction](https://mlsanity.com/paper/2603.15206/) (2026)
- [SEA-Vision: A Multilingual Benchmark for Comprehensive Document and Scene Text Understanding in Southeast Asia](https://mlsanity.com/paper/2603.15409/) (2026)
- [StrucTab: A Structured Optimization Framework for Table Parsing](https://mlsanity.com/paper/2606.29905/) (2026)
- [POINTS-Seeker: An Open Recipe for Multimodal Search Agents with Visual Memory Management](https://mlsanity.com/paper/2604.14029/) (2026)
- [TexOCR: Advancing Document OCR Models for Compilable Page-to-LaTeX Reconstruction](https://mlsanity.com/paper/2604.22880/) (2026)
- [Parser-Oriented Structural Refinement for a Stable Layout Interface in Document Parsing](https://mlsanity.com/paper/2604.02692/) (2026)

## Abstract (arXiv)

High-quality labeled data is essential for training accurate document conversion models, particularly in domains with complex formats such as tables, formulas, and multi-column text. However, manual annotation is both costly and time-consuming, while automatic labeling using existing models often lacks accuracy in handling such challenging scenarios. Consequently, training student models by distilling outputs from teacher models can significantly limit their performance in real-world applications. In this paper, we propose a fully automated, distillation-free framework comprising two stages for constructing high-quality document extraction datasets and models capable of handling diverse document formats and layouts. In the first stage, we introduce a method for generating large-scale, diverse synthetic data, which enables a model to extract key elements in a unified format with strong initial performance. In the second stage, we present a self-improvement approach that further adapts the model, initially trained on synthetic data, to real-world documents. Specifically, we first use the fine-tuned model to annotate real documents, then apply a suite of filtering strategies to verify annotation quality, and finally retrain the model on the verified dataset. By iteratively repeating this process, we progressively enhance both the model's conversion capabilities and the quality of the generated data. We train a public POINTS-1.5 model to obtain POINTS-Reader, which surpasses many existing public and proprietary models of comparable or larger size. Our model is available at https://github.com/Tencent/POINTS-Reader.