相关论文: Dolphin-v2: Universal Document Parsing via Scalabl…

Recent document question answering models consist of two key components: the vision encoder, which captures layout and visual elements in images, and a Large Language Model (LLM) that helps contextualize questions to the image and…

Key Information Extraction (KIE) underpins the understanding of visual documents (e.g., receipts and contracts) by extracting precise semantic content and accurately capturing spatial structure. Yet existing multimodal large language models…

Document Understanding is a foundational AI capability with broad applications, and Document Question Answering (DocQA) is a key evaluation task. Traditional methods convert the document into text for processing by Large Language Models…

We introduce Multilingual Document Parsing Benchmark, the first benchmark for multilingual digital and photographed document parsing. Document parsing has made remarkable strides, yet almost exclusively on clean, digital, well-formatted…

Vision-Language Model (VLM) have gained widespread adoption in Open-Vocabulary (OV) object detection and segmentation tasks. Despite they have shown promise on OV-related tasks, their effectiveness in conventional vision tasks has thus far…

Image Captioning for state-of-the-art VLMs has significantly improved over time; however, this comes at the cost of increased computational complexity, making them less accessible for resource-constrained applications such as mobile devices…

In real life, various degradation scenarios exist that might damage document images, making it harder to recognize and analyze them, thus binarization is a fundamental and crucial step for achieving the most optimal performance in any…

Information Extraction from visually rich documents is a challenging task that has gained a lot of attention in recent years due to its importance in several document-control based applications and its widespread commercial value. The…

Advances in Visually Rich Document Understanding (VrDU) have enabled information extraction and question answering over documents with complex layouts. Two tropes of architectures have emerged -- transformer-based models inspired by LLMs,…

Existing Multimodal Large Language Models (MLLMs) suffer from significant performance degradation on the long document understanding task as document length increases. This stems from two fundamental challenges: 1) a low Signal-to-Noise…

Document layout analysis is a critical preprocessing step in document intelligence, enabling the detection and localization of structural elements such as titles, text blocks, tables, and formulas. Despite its importance, existing layout…

Harnessing the full potential of visually-rich documents requires retrieval systems that understand not just text, but intricate layouts, a core challenge in Visual Document Retrieval (VDR). The prevailing multi-vector architectures, while…

While Vision-Language Models (VLMs) have achieved notable progress in computational pathology (CPath), the gigapixel scale and spatial heterogeneity of Whole Slide Images (WSIs) continue to pose challenges for multimodal understanding.…

Medical vision language pre-training (VLP) has emerged as a frontier of research, enabling zero-shot pathological recognition by comparing the query image with the textual descriptions for each disease. Due to the complex semantics of…

Recent advances in Visually-rich Document Understanding rely on large Vision-Language Models like Donut, which perform document-level Visual Question Answering without Optical Character Recognition. Despite their effectiveness, these models…

Document-level natural language inference (DOCNLI) is a new challenging task in natural language processing, aiming at judging the entailment relationship between a pair of hypothesis and premise documents. Current datasets and baselines…

While recent large vision-language models (VLMs) have improved generalization in vision-language navigation (VLN), existing methods typically rely on end-to-end pipelines that map vision-language inputs directly to short-horizon discrete…

Flowcharts are indispensable tools in software design and business-process analysis, yet current vision-language models (VLMs) frequently misinterpret the directional arrows and graph topology that set these diagrams apart from natural…

Vision-language models (VLMs) extend the conventional large language models by integrating visual data, enabling richer multimodal reasoning and significantly broadens the practical applications of AI. However, including visual inputs also…

Retrieving accurate details from documents is a crucial task, especially when handling a combination of scanned images and native digital formats. This document presents a combined framework for text extraction that merges Optical Character…