The field of AI-driven storytelling and content generation is rapidly evolving, with a focus on integrating multiple modalities and enhancing the user experience. Recent research has explored the application of generative AI in various domains, including cultural heritage visualization, AR storytelling, and software development. A key direction in this field is the development of frameworks and pipelines that can seamlessly integrate semantic metadata, 3D models, and storytelling elements to create immersive and interactive experiences. Another area of interest is the investigation of design spaces for multi-modal content generation and the evaluation of AI-generated content in different contexts. Furthermore, the importance of provenance and transparency in AI-generated media has been highlighted, with a need for accessible and effective indicators for both sighted and blind individuals. Noteworthy papers in this area include:

• From Metadata to Storytelling: A Framework For 3D Cultural Heritage Visualization on RDF Data, which introduces a pipeline for integrating semantic metadata and storytelling.
• An Exploratory Study on Multi-modal Generative AI in AR Storytelling, which develops a testbed for multi-modal content generation and evaluates the interactions with AI to generate content.