Hi there! I'm Matteo Caligiuri, a PhD student in Artificial Intelligence at the University of Padova 🇮🇹 as part of the MEDIALab. My research is centered around Computer Vision, with a particular focus on Federated Learning and the integration of Foundation Models into distributed AI systems. I’m deeply fascinated by how machines perceive and interpret the visual world, from semantic segmentation and object recognition to multimodal reasoning. My work often bridges the gap between cutting-edge theory and practical applications, and I love contributing to projects that make AI more scalable, robust, and accessible.
- 🧠 Deep Learning for Computer Vision
- 🌐 Federated Learning & Edge AI
- 🧩 Multimodal Learning (RGB-D, Vision-Language, etc.)
- 🏗️ Scalable and Modular AI Systems
- 🛠️ Open Source & Reproducible Research
Outside academia, I’m a huge fan of the Open Source ecosystem. I enjoy experimenting with new tools, frameworks, and platforms — and I’m always keen on contributing back when I can. Whether it’s fine-tuning a model, building efficient pipelines, or just tinkering with code, I love staying hands-on with technology.
Curiosity drives everything I do. I believe that the best work comes from a blend of rigor, creativity, and constant exploration. I’m always on the lookout for new challenges and collaborations — whether it's an exciting research question or a compelling software project.
