Hello there! I’m Ivan Rinaldi, a PhD student at the University of Bari Aldo Moro, based in Bari (BA), Apulia, Italy 🇮🇹, and currently a visiting researcher in Amiens, France 🇫🇷. I am working in the CILab laboratory, pursuing a PhD on “Advanced Generative Models for Conversion between Images, Text, and Audio”, co-funded by AIVB.
In July 2024, I earned my Master’s degree in Computer Science (AI curriculum) at the University of Bari Aldo Moro. My thesis focused on Generative AI, specifically diffusion models and conditioned music generation from artworks.
Research Interests 🔍
The topics I spend most of my research time on.
Hobbies 🕹️
When I’m not researching, I’m probably doing one of these.
Selected Publications 📖
The Latest from Me
October 2026: Our work on audio analysis has been accepted for publication in the Multimedia Tools and Applications (MTAP) Journal! 🗣️
September 2026: I started a six-month research internship abroad at the MIS Laboratory at UPJV (Amiens, France 🇫🇷), under the supervision of Prof. Florence Levé!
February 2026: The preprint of our work Art2Mus: Artwork-to-Music Generation via Visual Conditioning and Large-Scale Cross-Modal Alignment is now available on arXiv! 🎨🎹
February 2026: Our work Handscribe: A Gloss-Free Framework for Sign Language Translation and Gloss Sequence Generation was accepted for publication in the Computer Vision and Image Understanding (CVIU) Journal! 🖐🏻🤌🏻
July 2025: I had the opportunity to attend the International Computer Vision Summer School (ICVSS2025) in Scicli (Ragusa), where I also presented a poster on my work Art2Mus: Bridging Visual Arts and Music through Cross-Modal Generation! ☀️
May 2025: The proceedings of Art2Mus: Bridging Visual Arts and Music through Cross-Modal Generation have been published by Springer! Feel free to check it out! ✨
October 2024: We released a preprint of our work Art2Mus: Bridging Visual Arts and Music through Cross-Modal Generation, which was recently presented at the AI4VA Workshop during ECCV 2024 in Milan this September! 🇮🇹 😎
August 2024: Our work Art2Mus: Bridging Visual Arts and Music through Cross-Modal Generation was accepted at the AI4VA Workshop at ECCV 2024 in Milan! 🇮🇹
July 2024: Our work Instructing and Prompting Large Language Models for Explainable Cross-domain Recommendations was accepted at RecSys 2024 in Bari! 🇮🇹
July 2024: I successfully defended my Master’s thesis in Deep Learning at the University of Bari Aldo Moro! 💻
June 2024: I attended AILC in Bari, where I deepened my knowledge of computational linguistics, digital humanities, and large language models! 🇮🇹
🐚 That’s all from my side! 🪸
Take a breather, watch the koi swim by, and let your thoughts flow like the ripples in the pond. You’ve earned it!
