Explainable Artificial Intelligence (XAI) seeks to overcome the challenge of opacity in many advanced AI models, often referred to as 'black-box' systems. With artificial intelligence increasingly deployed in sensitive and impactful domains—including healthcare, brain-computer interfaces, autonomous vehicles, biomedical signal processing, and security-critical environments—transparent and interpretable models have become imperative. Ensuring model interpretability fosters user trust and compliance with ethical and regulatory standards and enhances the practical applicability and societal acceptance of AI technologies.

This Methods Collection aims to consolidate cutting-edge research that significantly advances XAI's theory and practical implementation. We invite rigorous and innovative contributions exploring novel ante-hoc (inherently interpretable) and post-hoc (model-agnostic or model-specific) explanation methodologies, as well as pioneering applications of established XAI techniques in emerging fields such as brain-computer interfaces, biomedical signal processing, object detection, and cybersecurity. 

Furthermore, the collection encourages submissions detailing user-friendly, interactive toolboxes and software platforms, facilitating broader accessibility and adoption of sophisticated explainability methods. By fostering interdisciplinary collaboration and presenting comprehensive advancements, this collection will provide valuable insights and practical tools for researchers, practitioners, and policymakers, thereby driving the development and widespread integration of explainable AI solutions.