Paper Accepted @CVPR
Publication date: 17/03/2025
🎉 Happy to share that our paper "ReAG: Reasoning-Augmented Generation for Knowledge-based Visual Question Answering" has been accepted at CVPR 2026 in Denver! 🎉
I completed my Ph.D. at the University of Modena and Reggio Emilia, conducting my research at AImageLab, co-advised by Prof. Rita Cucchiara, Prof.Lorenzo Baraldi and Prof. Marcella Cornia.
My current research focuses on cutting-edge multimodal architectures and their integration with advanced retrieval techniques. I have extensive experience with NLP tasks and foundation models such as CLIP, and have worked extensively with vision-and-language architectures, primarily focusing on their evaluation and addressing the problem of hallucination. Recently, I have been working on the training and development of multimodal large language models, including LLaVA and its derivatives.
During my Ph.D., I also spent six months as a research intern at Amazon in London.
Recent News
Some Important Milestones
-
2026
PhD Dissertation
AImageLab, University of Modena and Reggio Emilia
-
2025
Doctoral Consortium at CVPR 2025
-
2025
Amazon Research Internship
6-month internship at Amazon London.
-
2022
Best Student Paper Award (CBMI)
"Retrieval-augmented Transformer for Image Captioning”
-
2022
Starting PhD Student
AImageLab, University of Modena and Reggio Emilia
-
2022
Master Thesis Award
Premio alla Memoria Davide Rabotti
-
2022
M.S in Artificial Intelligence
University of Modena and Reggio Emilia.
All News
Paper Accepted @CVPR
Publication date: 22/11/2025
🎉 Happy to share that our paper "Recurrence-Enhanced Vision-and-Language Transformers for Robust Multimodal Document Retrieval" has been accepted at CVPR 2025 in Nashville! 🎉
EuroHPC Extreme Scale grant
Publication date: 10/04/2025
Our project "VISTA – Versatile Intelligent Systems for Tailored and Adaptive Next-Generation Multimodal AI" was accepted for the EuroHPC Extreme Scale grant, with an allocation of almost 1M GPU hours. Read the news on the UNIMORE website
Introducing LLaVA-MORE
Publication date: 08/03/2024
🎉 We are introducing LLaVA-MORE, a family of models that enhances LLaVA by integrating LLaMA 3.1 as the language model. Check out our Github repo! 🎉
Participation to National and European Projects
ELLIOT Project
2025 – Ongoing
Contributing to the European initiative for developing multimodal AI systems.
PRIN 2022: Vision-Language Reasoning
2023 – Ongoing
Participating in the Italian National Research Project on multimodal reasoning and vision-language alignment.