olmOCR 2: Unit Test Rewards for Document OCR
We present olmOCR 2, the latest in our family of powerful OCR systems for converting digitized print documents, like PDFs, into clean, naturally ordered plain text. olmOCR 2 is powered by olmOCR-2-7B-1025, a specialized, 7B vision language model (VLM) trained using reinforcement learning with verifiable rewards (RLVR), where our rewards are a diverse set of binary unit tests. To scale unit test creation, we develop a pipeline for generating synthetic documents with diverse and challenging layouts, known ground-truth HTML source code, and extracted test cases. We show that RL training on these test cases results in state-of-the-art performance on olmOCR-Bench, our English-language OCR benchmark, with the largest improvements in math formula conversion, table parsing, and multi-column layouts compared to previous versions. We release our model, data and code under permissive open licenses.
Code (0)
등록된 구현이 없습니다.
Tasks
Reinforcement LearningSimilar Papers 제목 키워드 기반
olmOCR: Unlocking Trillions of Tokens in PDFs with Vision Language Models
PDF documents have the potential to provide trillions of novel, high-quality tokens for training language models. However, these documents come in a diversity of types with differing formats and visual layouts that pose …
DiversityLanguage ModelingLanguage ModellingLightOnOCR: A 1B End-to-End Multilingual Vision-Language Model for State-of-the-Art OCR
We present 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-sc…
Infinity Parser: Layout Aware Reinforcement Learning for Scanned Document Parsing
Document parsing from scanned images into structured formats remains a significant challenge due to its complexly intertwined elements such as text paragraphs, figures, formulas, and tables. Existing supervised fine-tuni…
Reinforcement LearningCan OCR-VLMs Read Devanagari? A Stress-Test Benchmark and Post-Correction Study
OCR systems, ranging from classical engines to specialised OCR vision-language models (OCR-VLMs) and frontier multimodal LLMs, report strong results on English and Chinese document benchmarks, yet their behaviour on Indi…
Efficient Document Parsing via Parallel Token Prediction
Document parsing, as a fundamental yet crucial vision task, is being revolutionized by vision-language models (VLMs). However, the autoregressive (AR) decoding inherent to VLMs creates a significant bottleneck, severely …