相关论文: Docling Technical Report
Despite significant progress on current state-of-the-art image generation models, synthesis of document images containing multiple and complex object layouts is a challenging task. This paper presents a novel approach, called DocSynth, to…
Document Question Answering (DocQA) focuses on answering questions grounded in given documents, yet existing DocQA agents lack effective tool utilization and largely rely on closed-source models. In this work, we introduce DocDancer, an…
This paper introduces HADES, a novel tool for automatic comparative documents with similar structures. HADES is designed to streamline the work of professionals dealing with large volumes of documents, such as policy documents, legal acts,…
Many medical imaging techniques utilize fitting approaches for quantitative parameter estimation and analysis. Common examples are pharmacokinetic modeling in DCE MRI/CT, ADC calculations and IVIM modeling in diffusion-weighted MRI and…
This work introduces TopoBench, an open-source library designed to standardize benchmarking and accelerate research in topological deep learning (TDL). TopoBench decomposes TDL into a sequence of independent modules for data generation,…
This report evaluates PDF-to-Markdown conversion using recent Vision-Language Models (VLMs) on challenging French documents. Document parsing is a critical step for Retrieval-Augmented Generation (RAG) pipelines, where transcription and…
Multimodal document understanding is a challenging task to process and comprehend large amounts of textual and visual information. Recent advances in Large Language Models (LLMs) have significantly improved the performance of this task.…
For visual document understanding (VDU), self-supervised pretraining has been shown to successfully generate transferable representations, yet, effective adaptation of such representations to distribution shifts at test-time remains to be…
Scientific documents contain tables that list important information in a concise fashion. Structure and content extraction from tables embedded within PDF research documents is a very challenging task due to the existence of visual features…
We are presenting a set of multilingual text analysis tools that can help analysts in any field to explore large document collections quickly in order to determine whether the documents contain information of interest, and to find the…
Structured data offers a sophisticated mechanism for the organization of information. Existing methodologies for the text-serialization of structured data in the context of large language models fail to adequately address the heterogeneity…
The library scikit-fda is a Python package for Functional Data Analysis (FDA). It provides a comprehensive set of tools for representation, preprocessing, and exploratory analysis of functional data. The library is built upon and integrated…
Machine Learning software documentation is different from most of the documentations that were studied in software engineering research. Often, the users of these documentations are not software experts. The increasing interest in using…
Document understanding with multimodal large language models (MLLMs) requires not only accurate answers but also explicit, evidence-grounded reasoning, especially in high-stakes scenarios. However, current document MLLMs still fall short of…
In large technology companies, the requirements for managing and organizing technical documents created by engineers and managers have increased dramatically in recent years, which has led to a higher demand for more scalable, accurate, and…
PDF files are primarily intended for human reading rather than automated processing. In addition, the heterogeneous content of PDFs, such as text, tables, and images, poses significant challenges for parsing and information extraction. To…
Multimodal documents contain diverse elements, such as tables, figures, and layouts, which can complicate retrieval tasks. While current approaches typically combine dense visual embedding models with supervised rerankers to achieve…
Data exploration and quality analysis is an important yet tedious process in the AI pipeline. Current practices of data cleaning and data readiness assessment for machine learning tasks are mostly conducted in an arbitrary manner which…
Extracting information from academic PDF documents is crucial for numerous indexing, retrieval, and analysis use cases. Choosing the best tool to extract specific content elements is difficult because many, technically diverse tools are…
Creating high-quality figures and visualizations for scientific papers is a time-consuming task that requires both deep domain knowledge and professional design skills. Despite over 2.5 million scientific papers published annually, the…