Related papers: D2D: Digital Archive to MPEG-21 DIDL

Domain-specific languages (DSLs) play a crucial role in facilitating a wide range of software development activities in the context of model-driven engineering (MDE). However, a systematic understanding of their evolution is lacking, which…

A digital micromirror device (DMD) is an amplitude-type spatial light modulator. However, a complex-amplitude light modulation with a DMD can be achieved using the superpixel scheme. In the superpixel scheme, we notice that multiple…

Knowledge distillation (KD) is an efficient framework for compressing large-scale pre-trained language models. Recent years have seen a surge of research aiming to improve KD by leveraging Contrastive Learning, Intermediate Layer…

Transformer residual streams evolve by additive accumulation: each layer appends a feature update to a shared hidden state, but has no direct mechanism for replacing content that has become obsolete or conflicting. We introduce Deep Delta…

Digital repositories, either digital preservation systems or archival systems, periodically check the integrity of stored objects to assure users of their correctness. To do so, prior solutions calculate integrity metadata and require the…

Big data, i.e. collecting, storing and processing of data at scale, has recently been possible due to the arrival of clusters of commodity computers powered by application-level distributed parallel operating systems like HDFS/Hadoop/Spark,…

The Open Language Archives Community (OLAC) is a new project to build a worldwide system of federated language archives based on the Open Archives Initiative and the Dublin Core Metadata Initiative. This paper aims to disseminate the OLAC…

Despite the advanced intelligence abilities of large language models (LLMs) in various applications, they still face significant computational and storage demands. Knowledge Distillation (KD) has emerged as an effective strategy to improve…

In this work, we explore a Multilingual Information Retrieval (MLIR) task, where the collection includes documents in multiple languages. We demonstrate that applying state-of-the-art approaches developed for cross-lingual information…

For classification tasks, dictionary learning based methods have attracted lots of attention in recent years. One popular way to achieve this purpose is to introduce label information to generate a discriminative dictionary to represent…

Numerous digital humanities projects maintain their data collections in the form of text, images, and metadata. While data may be stored in many formats, from plain text to XML to relational databases, the use of the resource description…

The feasibility of deep neural networks (DNNs) to address data stream problems still requires intensive study because of the static and offline nature of conventional deep learning approaches. A deep continual learning algorithm, namely…

Transferring composite data structures with variable-length fields often requires designing non-trivial protocols that are not compatible between hardware designs. When each project designs its own data format and protocols the ability to…

Cultural heritage documentation induces the use of computerized techniques to manage and preserve the information produced. Geographical information systems have proved their potentialities in this scope, but they are not always adapted for…

The key challenge in semantic search is to create models that are both accurate and efficient in pinpointing relevant sentences for queries. While BERT-style bi-encoders excel in efficiency with pre-computed embeddings, they often miss…

This letter proposes two novel proactive cooperative caching approaches using deep learning (DL) to predict users' content demand in a mobile edge caching network. In the first approach, a (central) content server takes responsibilities to…

Diffusion distillation methods aim to compress the diffusion models into efficient one-step generators while trying to preserve quality. Among them, Distribution Matching Distillation (DMD) offers a suitable framework for training…

DIAL will enable users to analyze very large, event-based datasets using an application that is natural to the data format. Both the dataset and the processing may be distributed over a farm, a site (collection of farms) or a grid…

The Digital Public Library of America (DPLA) aggregates metadata for cultural heritage materials from 20 direct partners, or Hubs, across the United States. While the initial build-out of the DPLA's infrastructure used a lightweight…

Diffusion Language Models (dLLMs) have emerged as promising alternatives to Auto-Regressive (AR) models. While recent efforts have validated their pre-training potential and accelerated inference speeds, the post-training landscape for…