https://link.springer.com/collections/abiddicdga

MOTIVATION AND SCOPE

Artificial Intelligence (AI) is rapidly transforming real-world systems, driven by advances such as Large Language Models (LLMs), Vision Transformers (ViTs), Convolutional Neural Networks (CNNs), and Generative AI (GenAI). As these models become increasingly powerful, a key challenge is ensuring that they are not only accurate, but also interpretable, efficient, and suitable for responsible deployment.

This Special Issue aims to collect contributions addressing interpretability and efficiency in modern AI systems, spanning methodological advances, theoretical insights, and real-world applications.

Topics of interest include (but are not limited to):

• Explainable approaches for deep learning architectures (LLMs, ViTs, CNNs, GNNs)
• Interpretability techniques for generative and multimodal AI
• Model compression and acceleration (e.g., pruning, distillation)
• Trade-offs between interpretability, efficiency, and accuracy
• Case studies in domains such as healthcare, finance, and education

Interdisciplinary contributions are strongly encouraged, with the goal of making AI systems more transparent, efficient, and scalable in practice.

MANUSCRIPT SUBMISSION INSTRUCTIONS

Submissions should be made through the journal’s submission system:

https://link.springer.com/collections/abiddicdga

All manuscripts will undergo peer review according to the journal’s standard policies. Papers should present original, unpublished work and must comply with the journal’s author guidelines.

MANUSCRIPT FORMATTING GUIDELINES

Authors are invited to follow the journal’s Guide for Authors:

https://link.springer.com/journal/44163/submission-guidelines

Feel free to share this call with interested colleagues.

Guest Editors