About Me

Hi, I’m Marco Mistretta, an AI enthusiast and dedicated PhD student at MICC. My research focuses on Multimodal Learning, Natural Language Processing, Contrastive Self-Supervised Learning, and Incremental Learning. I am particularly passionate about developing cutting-edge techniques for few-shot adaptation of Vision-Language Models, which I find incredibly useful in this era of exponentially growing large models.

Background

With a solid foundation in Computer Engineering and Artificial Intelligence, I am committed to advancing the field through pioneering research. As a researcher, I aim to explore innovative solutions to complex problems, striving to make a positive impact on society.

Research Interests

• Incremental/Continual/Lifelong Learning
• Natural Language Processing
• Contrastive Self-Supervised Learning
• Prompt Tuning/Learning
• Few-Shot Adaptation

Publications

• “RE-tune: Incremental Fine-Tuning of Biomedical Vision Language Models”, presented at Medical Imaging meets NeurIPS 23 🏥
• “Improving Zero-Shot Generalization of Learned Prompts via Unsupervised Knowledge Distillation”, accepted at ECCV 24 📄

Contact Information

Feel free to reach out to me through the following channels:

• LinkedIn 🔗
• Google Scholar 📚
• Email: marco.mistretta@unifi.it ✉️

Connect with me to stay updated on my latest research and projects! Grab a copy of my most recent resume 📄

---

Looking forward to connecting with fellow researchers and enthusiasts!