The field of artificial intelligence is moving towards greater transparency and interpretability, with a focus on developing frameworks and methods that can provide explanations for model decisions. This is evident in the development of unified frameworks for attribution-based explainability, such as those that integrate multiple attribution methods and enable the development of novel techniques. Additionally, there is a growing trend towards making AI more accessible, particularly for individuals with visual impairments, through the development of wearable devices and extensible frameworks that enable personalized accessibility technologies. Noteworthy papers in this area include ABE, which proposes a unified framework for robust and faithful attribution-based explainability, and WhatsAI, which introduces a prototype extensible framework for creating personalized wearable visual accessibility technologies. PnPXAI is also notable for its universal XAI framework that supports diverse data modalities and neural network models.