paper-with-me

Papers

OCRBench v2: An Improved Benchmark for Evaluating Large Multimodal Models on Visual Text Localization and Reasoning

2024-12-31 · Ling Fu, Biao Yang, Zhebin Kuang, Jiajun Song, Yuzhe Li, Linghao Zhu, Qidi Luo, Xinyu Wang, Hao Lu, Mingxin Huang, Zhang Li, Guozhi Tang, Bin Shan, Chunhui Lin, Qi Liu, Binghong Wu, Hao Feng, Hao liu, Can Huang, Jingqun Tang, Wei Chen, Lianwen Jin, Yuliang Liu, Xiang Bai

Scoring the Optical Character Recognition (OCR) capabilities of Large Multimodal Models (LMMs) has witnessed growing interest recently. Existing benchmarks have highlighted the impressive performance of LMMs in text recognition; however, their abilities on certain challenging tasks, such as text localization, handwritten content extraction, and logical reasoning, remain underexplored. To bridge this gap, we introduce OCRBench v2, a large-scale bilingual text-centric benchmark with currently the most comprehensive set of tasks (4x more tasks than the previous multi-scene benchmark OCRBench), the widest coverage of scenarios (31 diverse scenarios including street scene, receipt, formula, diagram, and so on), and thorough evaluation metrics, with a total of 10,000 human-verified question-answering pairs and a high proportion of difficult samples. After carefully benchmarking state-of-the-art LMMs on OCRBench v2, we find that 20 out of 22 LMMs score below 50 (100 in total) and suffer from five-type limitations, including less frequently encountered text recognition, fine-grained perception, layout perception, complex element parsing, and logical reasoning. The benchmark and evaluation scripts are available at https://github.com/Yuliang-liu/MultimodalOCR.

📄 PDF Abstract BibTeX arXiv:2501.00321

Code (1)

yuliang-liu/multimodalocr 공식 구현 pytorch

Tasks

BenchmarkingLogical ReasoningOptical Character RecognitionOptical Character Recognition (OCR)Question Answering

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically

Similar Papers 제목 키워드 기반

ThaiOCRBench: A Task-Diverse Benchmark for Vision-Language Understanding in Thai

2025-11-06 · Surapon Nonesung, Teetouch Jaknamon, Sirinya Chaiophat, Natapong Nitarach 외 arxiv

We present ThaiOCRBench, the first comprehensive benchmark for evaluating vision-language models (VLMs) on Thai text-rich visual understanding tasks. Despite recent progress in multimodal modeling, existing benchmarks pr…

OCRBench: On the Hidden Mystery of OCR in Large Multimodal Models

2023-05-13 · Yuliang Liu, Zhang Li, Mingxin Huang, Biao Yang 외

Large models have recently played a dominant role in natural language processing and multimodal vision-language learning. However, their effectiveness in text-related visual tasks remains relatively unexplored. In this p…

Key Information ExtractionNutritionOptical Character RecognitionOptical Character Recognition (OCR)+3

Mono-InternVL-1.5: Towards Cheaper and Faster Monolithic Multimodal Large Language Models

2025-07-16 · Gen Luo, Wenhan Dou, Wenhao Li, Zhaokai Wang 외 arxiv

This paper focuses on monolithic Multimodal Large Language Models (MLLMs), which integrate visual encoding and language decoding into a single model. Existing structures and pre-training strategies for monolithic MLLMs o…

Qianfan-VL: Domain-Enhanced Universal Vision-Language Models

2025-09-19 · Daxiang Dong, Mingming Zheng, Dong Xu, Bairong Zhuang 외 arxiv

We present Qianfan-VL, a series of multimodal large language models ranging from 3B to 70B parameters, achieving state-of-the-art performance through innovative domain enhancement techniques. Our approach employs multi-s…

Mathematical Reasoning

Mono-InternVL: Pushing the Boundaries of Monolithic Multimodal Large Language Models with Endogenous Visual Pre-training

2024-10-10 · CVPR 2025 1 · Gen Luo, Xue Yang, Wenhan Dou, Zhaokai Wang 외

In this paper, we focus on monolithic Multimodal Large Language Models (MLLMs) that integrate visual encoding and language decoding into a single LLM. In particular, we identify that existing pre-training strategies for …

Mixture-of-ExpertsVisual Question Answering