applsci-logo

Journal Browser

Journal Browser

The Age of Transformers: Emerging Trends and Applications

A special issue of Applied Sciences (ISSN 2076-3417). This special issue belongs to the section "Computing and Artificial Intelligence".

Deadline for manuscript submissions: 30 December 2025 | Viewed by 232

Special Issue Editors


E-Mail Website
Guest Editor
Department of Informatics, Computer and Telecommunications Engineering, International Hellenic University, Terma Magnesias Str., 62124 Serres, Greece
Interests: multimedia systems; digital image processing; digital signal processing; computer vision; computer graphics
Special Issues, Collections and Topics in MDPI journals

E-Mail Website
Guest Editor
Department of Informatics, Computer and Telecommunications Engineering, International Hellenic University, 62124 Serres, Greece
Interests: digital image processing; document processing; analysis and recognition; machine learning; digital signal processing

Special Issue Information

Dear Colleagues,

Transformer architectures, which were first introduced in 2017, have rapidly become the backbone of modern artificial intelligence, powering breakthroughs in natural language processing, vision, and multimodal learning. Their ability to model dependencies and adapt across tasks has led to a wave of innovative applications, from large language models to generative systems and intelligent agents.

As these technologies mature, their impact extends far beyond their computational origins, reaching into the worlds of culture, education, and heritage. This Special Issue explores how transformer models are transforming our approaches to preserving the past and shaping the future of learning.

We invite scholars, researchers, and practitioners to contribute original work that showcases how transformer-based technologies are being applied in cultural heritage and educational contexts. We are particularly interested in submissions that present novel applications, theoretical frameworks, or critical reflections on their use and implications.

Topics of interest include, but are not limited to, the following:

  • Digitization, preservation, and interpretation of cultural artifacts;
  • Personalized and adaptive learning environments;
  • Tools for enhancing accessibility and inclusion in education and heritage spaces;
  • Automated content generation and intelligent educational resource curation;
  • Language models and computational linguistics for cultural insight and dialogue;
  • Ethical, social, and philosophical dimensions of transformer-driven technologies.

We welcome a wide range of submissions, including theoretical explorations, empirical research, case studies, and technical innovations. Our aim is to promote interdisciplinary exchange and deepen the conversation around how transformer models are shaping the future of cultural and educational practices.

Prof. Dr. Athanasios Nikolaidis
Prof. Dr. Charalampos Strouthopoulos
Dr. George Pavlidis
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Applied Sciences is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2400 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  • transformer models
  • cultural heritage
  • educational technologies
  • artificial intelligence
  • natural language processing
  • digital humanities
  • personalized learning
  • adaptive learning
  • computational linguistics
  • machine learning
  • deep learning
  • content generation

Benefits of Publishing in a Special Issue

  • Ease of navigation: Grouping papers by topic helps scholars navigate broad scope journals more efficiently.
  • Greater discoverability: Special Issues support the reach and impact of scientific research. Articles in Special Issues are more discoverable and cited more frequently.
  • Expansion of research network: Special Issues facilitate connections among authors, fostering scientific collaborations.
  • External promotion: Articles in Special Issues are often promoted through the journal's social media, increasing their visibility.
  • Reprint: MDPI Books provides the opportunity to republish successful Special Issues in book format, both online and in print.

Further information on MDPI's Special Issue policies can be found here.

Published Papers (1 paper)

Order results
Result details
Select all
Export citation of selected articles as:

Research

17 pages, 588 KB  
Article
Diffusion-Inspired Masked Language Modeling for Symbolic Harmony Generation on a Fixed Time Grid
by Maximos Kaliakatsos-Papakostas, Dimos Makris, Konstantinos Soiledis, Konstantinos-Theodoros Tsamis, Vassilis Katsouros and Emilios Cambouropoulos
Appl. Sci. 2025, 15(17), 9513; https://doi.org/10.3390/app15179513 (registering DOI) - 29 Aug 2025
Viewed by 80
Abstract
We present a novel encoder-only Transformer model for symbolic music harmony generation, based on a fixed time-grid representation of melody and harmony. Inspired by denoising diffusion processes, our model progressively unmasks harmony tokens over a sequence of discrete stages, learning to reconstruct the [...] Read more.
We present a novel encoder-only Transformer model for symbolic music harmony generation, based on a fixed time-grid representation of melody and harmony. Inspired by denoising diffusion processes, our model progressively unmasks harmony tokens over a sequence of discrete stages, learning to reconstruct the full harmonic structure from partial context. Unlike autoregressive models, this formulation enables flexible, non-sequential generation and supports explicit control over harmony placement. The model is stage-aware, receiving timestep embeddings analogous to diffusion timesteps, and is conditioned on both a binary piano roll and a pitch class roll to capture melodic context. We explore two unmasking schedules—random token revealing and midpoint doubling—both requiring a fixed and significantly reduced number of model calls at inference time. While our approach achieves competitive performance with strong autoregressive baselines (GPT-2 and BART) across several harmonic metrics, its key advantages lie in controllability, structured decoding with fixed inference steps, and alignment with musical structure. Ablation studies further highlight the role of stage awareness and pitch class conditioning. Our results position this method as a viable and interpretable alternative for symbolic harmony generation and a foundation for future work on structured, controllable musical modeling. Full article
(This article belongs to the Special Issue The Age of Transformers: Emerging Trends and Applications)
Show Figures

Figure 1

Back to TopTop