Related papers: olmOCR 2: Unit Test Rewards for Document OCR

Optical character recognition (OCR) technology has been widely used in various scenes, as shown in Figure 1. Designing a practical OCR system is still a meaningful but challenging task. In previous work, considering the efficiency and…

Despite significant advances in document understanding, determining the correct orientation of scanned or photographed documents remains a critical pre-processing step in the real world settings. Accurate rotation correction is essential…

This paper introduces an open-source benchmark for evaluating Vision-Language Models (VLMs) on Optical Character Recognition (OCR) tasks in dynamic video environments. We present a curated dataset containing 1,477 manually annotated frames…

Given the ubiquity of handwritten documents in human transactions, Optical Character Recognition (OCR) of documents have invaluable practical worth. Optical character recognition is a science that enables to translate various types of…

Conventional Optical Character Recognition (OCR) systems are challenged by variant invoice layouts, handwritten text, and low-quality scans, which are often caused by strong template dependencies that restrict their flexibility across…

Document parsing has garnered widespread attention as vision-language models (VLMs) advance OCR capabilities. However, the field remains fragmented across dozens of specialized models with varying strengths, forcing users to navigate…

Optical Chemical Structure Recognition (OCSR) is critical for converting 2D molecular diagrams from printed literature into machine-readable formats. While Vision-Language Models have shown promise in end-to-end OCR tasks, their direct…

While Reinforcement Learning with Verifiable Rewards (RLVR) is effective for deterministically checkable tasks, many vision-language tasks are partially verifiable, demanding multi-criteria supervision (e.g., perceptual details, reasoning…

The advent of large language models (LLMs) has revolutionized natural language processing, enabling unprecedented capabilities in understanding and generating human-like text. However, the computational cost and convergence times associated…

We investigate OCR-augmented generation with Vision Language Models (VLMs), exploring tasks in Korean and English toward multilingualism. To support research in this domain, we train and release KLOCR, a strong bilingual OCR baseline…

Visually Rich Document Understanding (VRDU) has become a pivotal area of research, driven by the need to automatically interpret documents that contain intricate visual, textual, and structural elements. Recently, Multimodal Large Language…

Large Multimodal Models (LMMs) have become increasingly versatile, accompanied by impressive Optical Character Recognition (OCR) related capabilities. Existing OCR-related benchmarks emphasize evaluating LMMs' abilities of relatively simple…

Text and formulas constitute the core informational components of many documents. Accurately and efficiently recognizing both is crucial for developing robust and generalizable document parsing systems. Recently, vision-language models…

Reinforcement learning (RL) has driven recent breakthroughs in large language models (LLMs), especially for tasks where rewards can be computed automatically, such as code generation. However, it is less effective in open-ended medical…

Multimodal large language models (MLLMs) have shown impressive capabilities across various domains, excelling in processing and understanding information from multiple modalities. Despite the rapid progress made previously, insufficient OCR…

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-tuning methods often…

Documents are a core part of many businesses in many fields such as law, finance, and technology among others. Automatic understanding of documents such as invoices, contracts, and resumes is lucrative, opening up many new avenues of…

Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as a prevailing paradigm for enhancing reasoning in Multimodal Large Language Models (MLLMs). However, relying solely on outcome supervision risks reward hacking, where…

DeepSeek-OCR utilizes an optical 2D mapping approach to achieve high-ratio vision-text compression, claiming to decode text tokens exceeding ten times the input visual tokens. While this suggests a promising solution for the LLM…

Optical character recognition (OCR) and multilingual text understanding remain major failure modes of multimodal large language models (MLLMs), particularly in real-world images containing cluttered layouts, small fonts, blur, occlusion,…