This paper explores the application of generative AI, specifically conditional flow matching, for the inverse design of ship propellers. It aims to generate multiple propeller geometries that achieve specified performance targets, overcoming limitations of traditional forward models and addressing data scarcity through simulated data and augmentation.

This paper introduces and evaluates a novel Rhetorical Structure Theory (RST)-based in-context learning method to improve the quality of AI-generated educational diagrams, finding that while it reduces hallucinations, LLMs still struggle with complex inputs and require careful application in educational contexts.

This paper introduces CM-GAI, a continuum mechanics-based theoretical framework that extends optimal transport theory to describe data dynamics. It enables generative tasks with limited data by integrating physical consistency, successfully demonstrated across material, structural, and system-level mechanical engineering problems.

This paper introduces EndoRare, a novel one-shot generative framework that synthesizes diverse, high-fidelity images of rare gastrointestinal lesions from a single reference. It significantly enhances the diagnostic accuracy of AI models and improves the training of novice clinicians by providing realistic and varied case examples.

This paper introduces a novel generative AI framework that combines a variational autoencoder (VAE) with a quantitative structure-activity relationship (QSAR) model to efficiently discover synthetically viable odorant molecules, addressing the challenge of limited olfactory data. The framework generates novel chemical structures with desirable olfactory properties, validated for synthetic accessibility and stability.

This paper provides a comprehensive empirical analysis of generative AI adoption, usage patterns, and literacy among Italian-speaking adults. It highlights widespread GenAI use, its replacement of traditional technologies, low user literacy, and a significant gender divide, particularly in older generations.