English
Related papers

Related papers: PaddleOCR 3.0 Technical Report

200 papers

We present an ongoing initiative to provide open, very large, high-quality, and richly annotated textual datasets for almost 200 languages. At 30 trillion tokens, this is likely the largest generally available multilingual collection of LLM…

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…

Computer Vision and Pattern Recognition · Computer Science 2026-02-06 Hao Feng , Wei Shi , Ke Zhang , Xiang Fei , Lei Liao , Dingkang Yang , Yongkun Du , Xuecheng Wu , Jingqun Tang , Yang Liu , Hong Chen , Can Huang

Large vision language models (LVLMs) have improved the document understanding capabilities remarkably, enabling the handling of complex document elements, longer contexts, and a wider range of tasks. However, existing document understanding…

Artificial Intelligence · Computer Science 2025-07-16 Chao Deng , Jiale Yuan , Pi Bu , Peijie Wang , Zhong-Zhi Li , Jian Xu , Xiao-Hui Li , Yuan Gao , Jun Song , Bo Zheng , Cheng-Lin Liu

Multimodal document retrieval systems have shown strong progress in aligning visual and textual content for semantic search. However, most existing approaches remain heavily English-centric, limiting their effectiveness in multilingual…

Information Retrieval · Computer Science 2025-12-04 Adithya S Kolavi , Vyoman Jain

Retrieval-Augmented Generation (RAG) pipelines must address challenges beyond simple single-document retrieval, such as interpreting visual elements (tables, charts, images), synthesizing information across documents, and providing accurate…

Artificial Intelligence · Computer Science 2026-04-22 António Loison , Quentin Macé , Antoine Edy , Victor Xing , Tom Balough , Gabriel Moreira , Bo Liu , Manuel Faysse , Céline Hudelot , Gautier Viaud

Multimodal Large Language Models (MLLMs) have shown impressive performance on vision-language tasks, but their long Chain-of-Thought (CoT) capabilities in multimodal scenarios remain underexplored. Inspired by OpenAI's o3 model, which…

Computer Vision and Pattern Recognition · Computer Science 2025-08-19 Ye Wang , Qianglong Chen , Zejun Li , Siyuan Wang , Shijie Guo , Zhirui Zhang , Zhongyu Wei

For decades, corporations and governments have relied on scanned documents to record vast amounts of information. However, extracting this information is a slow and tedious process due to the sheer volume and complexity of these records.…

Computer Vision and Pattern Recognition · Computer Science 2024-12-17 Roman Colman , Minh Vu , Manish Bhattarai , Martin Ma , Hari Viswanathan , Daniel O'Malley , Javier E. Santos

Multimodal Vision Language Models (VLMs) have emerged as a transformative topic at the intersection of computer vision and natural language processing, enabling machines to perceive and reason about the world through both visual and textual…

Computer Vision and Pattern Recognition · Computer Science 2025-04-08 Zongxia Li , Xiyang Wu , Hongyang Du , Fuxiao Liu , Huy Nghiem , Guangyao Shi

In recent years, Multi-modal Large Language Models (MLLMs) have achieved strong performance in OCR-centric Visual Question Answering (VQA) tasks, illustrating their capability to process heterogeneous data and exhibit adaptability across…

Computer Vision and Pattern Recognition · Computer Science 2026-02-24 Chen Duan , Zhentao Guo , Pei Fu , Zining Wang , Kai Zhou , Pengfei Yan

Document retrieval is an important task for search and Retrieval-Augmented Generation (RAG) applications. Large Language Models (LLMs) have contributed to improving the accuracy of text-based document retrieval. However, documents with…

Information Retrieval · Computer Science 2025-05-22 Radek Osmulski , Gabriel de Souza P. Moreira , Ronay Ak , Mengyao Xu , Benedikt Schifferer , Even Oldridge

Efficient creation of accurate and editable 3D CAD models is critical in engineering design, significantly impacting cost and time-to-market in product innovation. Current manual workflows remain highly time-consuming and demand extensive…

Computer Vision and Pattern Recognition · Computer Science 2025-05-21 Anna C. Doris , Md Ferdous Alam , Amin Heyrani Nobari , Faez Ahmed

Language models for scientific tasks are trained on text from scientific publications, most distributed as PDFs that require parsing. PDF parsing approaches range from inexpensive heuristics (for simple documents) to computationally…

Document intelligence requires accurate text extraction and reliable reasoning over document content. We introduce \textbf{DISCO}, a \emph{Document Intelligence Suite for COmparative Evaluation}, that evaluates optical character recognition…

Computation and Language · Computer Science 2026-03-26 Kenza Benkirane , Dan Goldwater , Martin Asenov , Aneiss Ghodsi

3D Vision-Language Pre-training (3D-VLP) aims to provide a pre-train model which can bridge 3D scenes with natural language, which is an important technique for embodied intelligence. However, current 3D-VLP datasets are hindered by limited…

Computer Vision and Pattern Recognition · Computer Science 2024-07-09 Dejie Yang , Zhu Xu , Wentao Mo , Qingchao Chen , Siyuan Huang , Yang Liu

Recent advancements in large language models (LLMs) have driven interest in billion-scale retrieval models with strong generalization across retrieval tasks and languages. Additionally, progress in large vision-language models has created…

Information Retrieval · Computer Science 2025-05-06 Xueguang Ma , Luyu Gao , Shengyao Zhuang , Jiaqi Samantha Zhan , Jamie Callan , Jimmy Lin

Optical Character Recognition (OCR) technology is widely used to extract text from images of documents, facilitating efficient digitization and data retrieval. However, merely extracting text is insufficient when dealing with complex…

Outdoor advertisements remain a critical medium for modern marketing, yet accurately verifying billboard text visibility under real-world conditions is still challenging. Traditional Optical Character Recognition (OCR) pipelines excel at…

Computer Vision and Pattern Recognition · Computer Science 2025-07-17 Maciej Szankin , Vidhyananth Venkatasamy , Lihang Ying

Vision-language models (VLMs) have shown promise in 2D medical image analysis, but extending them to 3D remains challenging due to the high computational demands of volumetric data and the difficulty of aligning 3D spatial features with…

Computer Vision and Pattern Recognition · Computer Science 2025-12-17 Yu Xin , Gorkem Can Ates , Kuang Gong , Wei Shao

Large Vision Language Models (LVLMs) have shown strong capabilities in understanding and analyzing visual scenes across various domains. However, in the context of autonomous driving, their limited comprehension of 3D environments restricts…

Computer Vision and Pattern Recognition · Computer Science 2025-05-02 Jannik Lübberstedt , Esteban Rivera , Nico Uhlemann , Markus Lienkamp

We introduce VLM-Lens, a toolkit designed to enable systematic benchmarking, analysis, and interpretation of vision-language models (VLMs) by supporting the extraction of intermediate outputs from any layer during the forward pass of…

Computation and Language · Computer Science 2025-10-03 Hala Sheta , Eric Huang , Shuyu Wu , Ilia Alenabi , Jiajun Hong , Ryker Lin , Ruoxi Ning , Daniel Wei , Jialin Yang , Jiawei Zhou , Ziqiao Ma , Freda Shi