Related papers: NovaLAD: A Fast, CPU-Optimized Document Extraction…

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…

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…

Capturing the compositional process which maps the meaning of words to that of documents is a central challenge for researchers in Natural Language Processing and Information Retrieval. We introduce a model that is able to represent the…

Incorporating external knowledge bases in traditional retrieval-augmented generation (RAG) relies on parsing the document, followed by querying a language model with the parsed information via in-context learning. While effective for…

While many NLP pipelines assume raw, clean texts, many texts we encounter in the wild, including a vast majority of legal documents, are not so clean, with many of them being visually structured documents (VSDs) such as PDFs. Conventional…

Prior study shows that pre-training techniques can boost the performance of visual document understanding (VDU), which typically requires models to gain abilities to perceive and reason both document texts and layouts (e.g., locations of…

Efficient and accurate extraction of key information from 2D engineering drawings is essential for advancing digital manufacturing workflows. Such information includes geometric dimensioning and tolerancing (GD&T), measures, material…

Recognizing the layout of unstructured digital documents is crucial when parsing the documents into the structured, machine-readable format for downstream applications. Recent studies in Document Layout Analysis usually rely on computer…

PDF documents contain critical visual elements such as figures, tables, and forms whose accurate extraction is essential for document understanding and multimodal retrieval-augmented generation (RAG). Existing PDF parsers often miss complex…

Recent years have witnessed a rapid growth of deep-network based services and applications. A practical and critical problem thus has emerged: how to effectively deploy the deep neural network models such that they can be executed…

We aim to develop a retrieval-augmented generation (RAG) framework that answers questions over a corpus of visually-rich documents presented in mixed modalities (e.g., charts, tables) and diverse formats (e.g., PDF, PPTX). In this paper, we…

Convolutional neural networks (CNNs) are increasingly being used in critical systems, where robustness and alignment are crucial. In this context, the field of explainable artificial intelligence has proposed the generation of high-level…

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…

Extracting structured data from HTML documents is a long-studied problem with a broad range of applications like augmenting knowledge bases, supporting faceted search, and providing domain-specific experiences for key verticals like…

Document Understanding is an evolving field in Natural Language Processing (NLP). In particular, visual and spatial features are essential in addition to the raw text itself and hence, several multimodal models were developed in the field…

This paper presents Youtu-Parsing, an efficient and versatile document parsing model designed for high-performance content extraction. The architecture employs a native Vision Transformer (ViT) featuring a dynamic-resolution visual encoder…

With the rapid advancement of tool-use capabilities in Large Language Models (LLMs), Retrieval-Augmented Generation (RAG) is shifting from static, one-shot retrieval toward autonomous, multi-turn evidence acquisition. However, existing…

Visual document retrieval aims to retrieve a set of document pages relevant to a query from visually rich collections. Existing methods often employ Vision-Language Models (VLMs) to encode queries and visual pages into a shared embedding…

Precise, object-aware control over visual content is essential for advanced image editing and compositional generation. Yet, most existing approaches operate on entire images holistically, limiting the ability to isolate and manipulate…

In this paper, we consider a different data format for images: vector graphics. In contrast to raster graphics which are widely used in image recognition, vector graphics can be scaled up or down into any resolution without aliasing or…