7 papers · 1 filter
WildDoc: How Far Are We from Achieving Comprehensive and Robust Document Understanding in the Wild?
An-Lan Wang, Jingqun Tang, Liao Lei +10
The rapid advancements in Multimodal Large Language Models (MLLMs) have significantly enhanced capabilities in Document Understanding. However, prevailing benchmarks like DocVQA an…
Dolphin: Document Image Parsing via Heterogeneous Anchor Prompting
Hao Feng, Shu Wei, Xiang Fei +10
Document image parsing is challenging due to its complexly intertwined elements such as text paragraphs, figures, formulas, and tables. Current approaches either assemble specializ…
OCRBench v2: An Improved Benchmark for Evaluating Large Multimodal Models on Visual Text Localization and Reasoning
Ling Fu, Zhebin Kuang, Jiajun Song +21
Scoring the Optical Character Recognition (OCR) capabilities of Large Multimodal Models (LMMs) has witnessed growing interest. Existing benchmarks have highlighted the impressive p…
TabPedia: Towards Comprehensive Visual Table Understanding with Concept Synergy
Weichao Zhao, Hao Feng, Qi Liu +9
Tables contain factual and quantitative data accompanied by various structures and contents that pose challenges for machine comprehension. Previous methods generally design task-s…
MTVQA: Benchmarking Multilingual Text-Centric Visual Question Answering
Jingqun Tang, Qi Liu, Yongjie Ye +14
Text-Centric Visual Question Answering (TEC-VQA) in its proper format not only facilitates human-machine interaction in text-centric visual environments but also serves as a de fac…
TextSquare: Scaling up Text-Centric Visual Instruction Tuning
Jingqun Tang, Chunhui Lin, Zhen Zhao +15
Text-centric visual question answering (VQA) has made great strides with the development of Multimodal Large Language Models (MLLMs), yet open-source models still fall short of lea…