Generative AI Model
Generative AI models are computational systems designed to create new content, such as text, images, and audio, by learning patterns from existing data. Current research emphasizes improving efficiency and scalability of these models, particularly focusing on architectures like transformers and diffusion models, and addressing challenges like bias mitigation, data security, and responsible AI practices. The widespread adoption of generative AI across diverse fields, from medicine and law to art and entertainment, necessitates rigorous research into its capabilities, limitations, and societal impact.
Papers
Prompt-to-OS (P2OS): Revolutionizing Operating Systems and Human-Computer Interaction with Integrated AI Generative Models
Gabriele Tolomei, Cesare Campagnano, Fabrizio Silvestri, Giovanni Trappolini
Metadata-Conditioned Generative Models to Synthesize Anatomically-Plausible 3D Brain MRIs
Wei Peng, Tomas Bosschieter, Jiahong Ouyang, Robert Paul, Ehsan Adeli, Qingyu Zhao, Kilian M. Pohl