AI Researcher in Vision–Language & Multimodal AI
PhD in Artificial Intelligence (Defense April 2026) @ AImageLab, UNIMORE
🤖 I am an AI researcher working on Vision–Language Models and Multimodal Large Language Models at AImageLab, University of Modena and Reggio Emilia.
👀 My research focuses on knowledge-intensive multimodal reasoning and retrieval-augmented generation (RAG).
I work on the design, training, and evaluation of large-scale multimodal systems, combining generative models with retrieval, grounding, and structured reasoning mechanisms.
Alongside academic research, I worked as an Applied Scientist Intern at Amazon Science (Cambridge, UK), conducting research on large-scale multimodal models within the Amazon AGI organization.
- Vision–Language Models (VLMs)
- Multimodal Large Language Models (MLLMs)
- Retrieval-Augmented Generation (RAG)
- Knowledge-based Visual Question Answering
- Multimodal reasoning and evaluation
My work has been published at top-tier venues including CVPR, ICLR, ACL, and BMVC.
👉 Full publication list available on Google Scholar.
- 🌍 Website: https://nicholasmoratelli.com
- 📖 Google Scholar: https://scholar.google.com/citations?user=8YkdgNkAAAAJ
- 💼 LinkedIn: https://www.linkedin.com/in/nicholas-moratelli
- 📧 Email: nicholas.moratelli@gmail.com