Related papers: E-books and Graphics with LaTeXML

Text clustering serves as a fundamental technique for organizing and interpreting unstructured textual data, particularly in contexts where manual annotation is prohibitively costly. With the rapid advancement of Large Language Models…

Recent advances in multimodal large language models (MLLMs) have enabled image-based question-answering capabilities. However, a key limitation is the use of CLIP as the visual encoder; while it can capture coarse global information, it…

XML database query languages have been studied extensively, but XML database updates have received relatively little attention, and pose many challenges to language design. We are developing an XML update language called Flux, which stands…

Large language models (LLMs) are increasingly used to assist scientists across diverse workflows. A key challenge is generating high-quality figures from textual descriptions, often represented as TikZ programs that can be rendered as…

PDF documents have the potential to provide trillions of novel, high-quality tokens for training language models. However, these documents come in a diversity of types with differing formats and visual layouts that pose a challenge when…

Document parsing from scanned images into structured formats remains a significant challenge due to its complexly intertwined elements such as text paragraphs, figures, formulas, and tables. Existing supervised fine-tuning methods often…

Authoring documents in MKM formats like OMDoc is a very tedious task. After years of working on a semantically annotated corpus of sTeX documents (GenCS), we identified a set of common, time-consuming subtasks, which can be supported in an…

The evolution of web applications relies on iterative code modifications, a process that is traditionally manual and time-consuming. While Large Language Models (LLMs) can generate UI code, their ability to edit existing code from new…

Text--image retrieval is necessary for applications such as product recommendation. Embedding-based approaches like CLIP enable efficient large-scale retrieval via vector similarity search, but they are primarily trained on literal…

Continuous embeddings of tokens in computer programs have been used to support a variety of software development tools, including readability, code search, and program repair. Contextual embeddings are common in natural language processing…

In this work we investigate whether browser-native technologies can be used to perform photo manipulation tasks e.g cropping, resizing or rotating an image within the current mainstream browser. By the use of a case study we will analyze…

The production of digital documents has been growing rapidly in academic, business, and health environments, presenting new challenges in the efficient extraction and analysis of unstructured information. This work investigates the use of…

This paper presents an approach to authoring a textbook titled Interactive OpenMP Programming with the assistance of Large Language Models (LLMs). The writing process utilized state-of-the-art LLMs, including Gemini Pro 1.5, Claude 3, and…

NeXML is a powerful and extensible exchange standard recently proposed to better meet the expanding needs for phylogenetic data and metadata sharing. Here we present the RNeXML package, which provides users of the R programming language…

While open source communities attract diverse contributors across the globe, only a few open source software repositories provide essential documentation, such as ReadMe or CONTRIBUTING files, in languages other than English. Recently,…

We introduce REPLUG, a retrieval-augmented language modeling framework that treats the language model (LM) as a black box and augments it with a tuneable retrieval model. Unlike prior retrieval-augmented LMs that train language models with…

Cross-modal text-molecule retrieval task bridges molecule structures and natural language descriptions. Existing methods predominantly focus on aligning text modality and molecule modality, yet they overlook adaptively adjusting the…

Evaluating text-to-image generative models remains a challenge, despite the remarkable progress being made in their overall performances. While existing metrics like CLIPScore work for coarse evaluations, they lack the sensitivity to…

Embedding models are crucial for various natural language processing tasks but can be limited by factors such as limited vocabulary, lack of context, and grammatical errors. This paper proposes a novel approach to improve embedding…

Visual text is a crucial component in both document and scene images, conveying rich semantic information and attracting significant attention in the computer vision community. Beyond traditional tasks such as text detection and…