相关论文: Scaling Accessible Mathematics on arXiv: HTML Conv…

The NeurIPS 2023 Machine Learning for Audio Workshop brings together machine learning (ML) experts from various audio domains. There are several valuable audio-driven ML tasks, from speech emotion recognition to audio event detection, but…

Over the past decade, the high performance computing community has become increasingly concerned that preserving the reliable, digital machine model will become too costly or infeasible. In this paper we discuss four approaches for…

Conversion of spoken mathematical expressions is a challenging task that involves transcribing speech into a strictly structured symbolic representation while addressing the ambiguity inherent in the pronunciation of equations. Although…

Content annotation at scale remains challenging, requiring substantial human expertise and effort. This paper presents a case study in code documentation analysis, where we explore the balance between automation efficiency and annotation…

Large language models (LLMs) are increasingly used for analytical tasks, yet their effectiveness in real-world applications remains underexamined, partly due to the opacity of proprietary models. We evaluate ChatGPT (GPT-3.5 and GPT-4) on…

LLM-agents are increasingly used to accelerate the progress of scientific research. Yet a persistent bottleneck is data access: agents not only lack readily available tools for retrieval, but also have to work with unstrcutured,…

This essay was invited for publication in Nieuw Archief voor Wiskunde; it will also appear in translation in the SMF Gazette and in the DMV Mitteilungen. I discuss the recent trends in scholarly communication in mathematics, the current…

Tables are a common means to display data in human-friendly formats. Many authors have worked on proposals to extract those data back since this has many interesting applications. In this article, we summarise and compare many of the…

Accessible machine learning algorithms, software, and diagnostic tools for energy-efficient devices and systems are extremely valuable across a broad range of application domains. In scientific domains, real-time near-sensor processing can…

Large language models (LLMs) have rapidly advanced natural language processing, driving significant breakthroughs in tasks such as text generation, machine translation, and domain-specific reasoning. The field now faces a critical dilemma…

The increasing size and complexity of machine learning (ML) models have driven the growing need for custom hardware accelerators capable of efficiently supporting ML workloads. However, the design of such accelerators remains a…

The Open Access movement in scientific publishing and search engines like Google Scholar have made scientific articles more broadly accessible. During the last decade, the availability of scientific papers in full text has become more and…

Large foundation models have achieved significant performance gains through scalable training on massive datasets. However, the field of \textbf{H}andwritten \textbf{M}athematical \textbf{E}xpression \textbf{R}ecognition (HMER) has been…

This document explains how to create or modify an existing LATEX document with commands enabling computations in the HTML5 output: when the reader opens the HTML5 output, he can run a computation in his browser, or modify the command to be…

With the recent focus in the accessibility field, researchers from academia and industry have been very active in developing innovative techniques and tools for assistive technology. Especially with handheld devices getting ever powerful…

Large Language Models (LLMs) have demonstrated exceptional capabilities in various natural language tasks, often achieving performances that surpass those of humans. Despite these advancements, the domain of mathematics presents a…

Over the past few decades, the amount of scientific articles and technical literature has increased exponentially in size. Consequently, there is a great need for systems that can ingest these documents at scale and make the contained…

Document understanding is a key business process in the data-driven economy since documents are central to knowledge discovery and business insights. Converting documents into a machine-processable format is a particular challenge here due…

As AI capabilities continue to grow exponentially on economically relevant human expert tasks, with task completion horizons doubling every 7 months according to the Model Evaluation and Threat Research (METR), we are interested in how this…

Implementation of an editing process for Content MathML formulas in common visual style is a real challenge for a software developer who does not really want the user to have to understand the structure of Content MathML in order to edit an…