Abstract: As the two most common display content of Augmented Reality (AR), the creation process of image and text often requires a human to execute. However, due to the rapid advances in Artificial Intelligence (AI), today the media content can be automatically generated by software. The ever-improving quality of AI-generated content (AIGC) has opened up new scenarios employing such content, which is expected to be applied in AR. In this paper, we attempt to explore the design space for projecting AI-generated image and text into an AR display. Specifically, we perform an exploratory study and suggest a user-function-environment'' design thinking by building a preliminary prototype and conducting focus groups based on it. Abstract: Explainable AI (XAI) has established itself as an important component of AI-driven interactive systems.

Explainable AI (XAI) has established itself as an important component of AI-driven interactive systems. With Augmented Reality (AR) becoming more integrated in daily lives, the role of XAI also becomes essential in AR because end-users will frequently interact with intelligent services. However, it is unclear how to design effective XAI experiences for AR. We propose XAIR, a design framework that addresses "when", "what", and "how" to provide explanations of AI output in AR. The framework was based on a multi-disciplinary literature review of XAI and HCI research, a large-scale survey probing 500+ end-users' preferences for AR-based explanations, and three workshops with 12 experts collecting their insights about XAI design in AR. XAIR's utility and effectiveness was verified via a study with 10 designers and another study with 12 end-users. XAIR can provide guidelines for designers, inspiring them to identify new design opportunities and achieve effective XAI designs in AR.

In addition to the impressive predictive power of machine learning (ML) models, more recently, explanation methods have emerged that enable an interpretation of complex non-linear learning models such as deep neural networks. Gaining a better understanding is especially important e.g. for safety-critical ML applications or medical diagnostics etc. While such Explainable AI (XAI) techniques have reached significant popularity for classifiers, so far little attention has been devoted to XAI for regression models (XAIR). In this review, we clarify the fundamental conceptual differences of XAI for regression and classification tasks, establish novel theoretical insights and analysis for XAIR, provide demonstrations of XAIR on genuine practical regression problems, and finally discuss the challenges remaining for the field.