LightOnOCR: A 1B End-to-End Multilingual Vision-Language Model for State-of-the-Art OCR

• URL: http://arxiv.org/abs/2601.14251v1
• Date: Tue, 20 Jan 2026 18:58:32 GMT
• Title: LightOnOCR: A 1B End-to-End Multilingual Vision-Language Model for State-of-the-Art OCR
• Authors: Said Taghadouini, Adrien Cavaillès, Baptiste Aubertin,
• Abstract summary: We present textbfLightOnOCR-2-1B, a multilingual vision--language model that converts document images into clean, naturally ordered text without brittle OCR pipelines.<n>Trained on a large-scale, high-quality distillation mix with strong coverage of scans, French documents, and scientific PDFs, LightOnOCR-2 achieves state-of-the-art results on OlmOCR-Bench.<n>We release model checkpoints under Apache 2.0, and publicly release the dataset and textbfLightOnOCR-bbox-bench evaluation under their respective licenses.
• Score: 0.29410438275861583
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We present \textbf{LightOnOCR-2-1B}, a 1B-parameter end-to-end multilingual vision--language model that converts document images (e.g., PDFs) into clean, naturally ordered text without brittle OCR pipelines. Trained on a large-scale, high-quality distillation mix with strong coverage of scans, French documents, and scientific PDFs, LightOnOCR-2 achieves state-of-the-art results on OlmOCR-Bench while being 9$\times$ smaller and substantially faster than prior best-performing models. We further extend the output format to predict normalized bounding boxes for embedded images, introducing localization during pretraining via a resume strategy and refining it with RLVR using IoU-based rewards. Finally, we improve robustness with checkpoint averaging and task-arithmetic merging. We release model checkpoints under Apache 2.0, and publicly release the dataset and \textbf{LightOnOCR-bbox-bench} evaluation under their respective licenses.

Related papers

• SimpleOCR: Rendering Visualized Questions to Teach MLLMs to Read [43.28273039987167]
  We introduce the Visualized-Question (VQ) setting, where text queries are rendered directly onto images.<n>Despite possessing strong OCR capabilities, models suffer a performance degradation of up to 12.7% in the VQ setting.<n>We propose SimpleOCR, a plug-and-play training strategy that imposes a structural constraint on the learning process.
  arXiv  Detail & Related papers  (2026-02-25T21:36:30Z)
• olmOCR 2: Unit Test Rewards for Document OCR [29.547676834557105]
  olmOCR 2 is the latest in our family of powerful OCR systems for converting digitized print documents, like PDFs, into clean, naturally ordered plain text.<n> olmOCR 2 is powered by olmOCR-2-7B-1025, a specialized, 7B vision language model (VLM) trained using reinforcement learning.<n>We show that RL training on these test cases results in state-of-the-art performance on olmOCR-Bench, our English-language OCR benchmark.
  arXiv  Detail & Related papers  (2025-10-22T17:53:02Z)
• PaddleOCR-VL: Boosting Multilingual Document Parsing via a 0.9B Ultra-Compact Vision-Language Model [24.435689905776744]
  PaddleOCR-VL-0.9B is a compact yet powerful vision-language model (VLM)<n>It integrates a NaViT-style dynamic resolution visual encoder with the ERNIE-4.5-0.3B language model to enable accurate element recognition.<n>This innovative model efficiently supports 109 languages and excels in recognizing complex elements.
  arXiv  Detail & Related papers  (2025-10-16T10:18:48Z)
• VScan: Rethinking Visual Token Reduction for Efficient Large Vision-Language Models [57.2662376527586]
  VScan is a two-stage visual token reduction framework.<n>It addresses token redundancy by: (1) integrating complementary global and local scans with token merging during visual encoding, and (2) introducing pruning at intermediate layers of the language model.<n>VScan achieves a 2.91$times$ speedup in prefilling and a 10$times$ reduction in FLOPs, while retaining 95.4% of the original performance.
  arXiv  Detail & Related papers  (2025-05-28T17:59:08Z)
• Token-Shuffle: Towards High-Resolution Image Generation with Autoregressive Models [92.18057318458528]
  Token-Shuffle is a novel method that reduces the number of image tokens in Transformer.<n>Our strategy requires no additional pretrained text-encoder and enables MLLMs to support extremely high-resolution image synthesis.<n>In GenAI-benchmark, our 2.7B model achieves 0.77 overall score on hard prompts, outperforming AR models LlamaGen by 0.18 and diffusion models LDM by 0.15.
  arXiv  Detail & Related papers  (2025-04-24T17:59:56Z)
• VISTA-OCR: Towards generative and interactive end to end OCR models [3.7548609506798494]
  VISTA-OCR is a lightweight architecture that unifies text detection and recognition within a single generative model.<n>Built on an encoder-decoder architecture, VISTA-OCR is progressively trained, starting with the visual feature extraction phase.<n>To enhance the model's capabilities, we built a new dataset composed of real-world examples enriched with bounding box annotations and synthetic samples.
  arXiv  Detail & Related papers  (2025-04-04T17:39:53Z)
• Vision-centric Token Compression in Large Language Model [51.92055188780033]
  Vision Centric Token Compression (Vist) is a slow-fast compression framework that mirrors human reading.<n>On eleven in-context learning benchmarks, Vist achieves the same accuracy with 2.3 times fewer tokens, cutting FLOPs by 16% and memory by 50%.
  arXiv  Detail & Related papers  (2025-02-02T13:10:06Z)
• PDF-WuKong: A Large Multimodal Model for Efficient Long PDF Reading with End-to-End Sparse Sampling [63.93112754821312]
  Multimodal document understanding is a challenging task to process and comprehend large amounts of textual and visual information.<n>Recent advances in Large Language Models (LLMs) have significantly improved the performance of this task.<n>We introduce PDF-WuKong, a multimodal large language model (MLLM) which is designed to enhance multimodal question-answering (QA) for long PDF documents.
  arXiv  Detail & Related papers  (2024-10-08T12:17:42Z)
• EfficientOCR: An Extensible, Open-Source Package for Efficiently Digitizing World Knowledge [1.8434042562191815]
  EffOCR is a novel open-source optical character recognition (OCR) package. It meets both the computational and sample efficiency requirements for liberating texts at scale. EffOCR is cheap and sample efficient to train, as the model only needs to learn characters' visual appearance and not how they are used in sequence to form language.
  arXiv  Detail & Related papers  (2023-10-16T04:20:16Z)
• UReader: Universal OCR-free Visually-situated Language Understanding with Multimodal Large Language Model [108.85584502396182]
  We propose UReader, a first exploration of universal OCR-free visually-situated language understanding based on the Multimodal Large Language Model (MLLM) By leveraging the shallow text recognition ability of the MLLM, we only finetuned 1.2% parameters. Our single model achieves state-of-the-art ocr-free performance in 8 out of 10 visually-situated language understanding tasks.
  arXiv  Detail & Related papers  (2023-10-08T11:33:09Z)
• HiVLP: Hierarchical Vision-Language Pre-Training for Fast Image-Text Retrieval [85.28292877465353]
  This paper proposes a textbfHierarchical textbfVision-textbfLanguage textbfPre-Training for fast Image-Text Retrieval (ITR) Specifically, we design a novel hierarchical retrieval objective, which uses the representation of different dimensions for coarse-to-fine ITR.
  arXiv  Detail & Related papers  (2022-05-24T14:32:57Z)
• Unsupervised Vision-and-Language Pre-training via Retrieval-based Multi-Granular Alignment [66.77841319057299]
  We propose a novel unsupervised Vision-and-Language pre-training curriculum for non-parallel texts and images. We first construct a weakly aligned image-text corpus via a retrieval-based approach, then apply a set of multi-granular alignment pre-training tasks. A comprehensive ablation study shows each granularity is helpful to learn a stronger pre-trained model.
  arXiv  Detail & Related papers  (2022-03-01T05:34:01Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.