About Me
Hi! 👋 I'm Lorenzo! I'm a passionate computer engineer currently pursuing a Ph.D. in Vision-Language Artificial Intelligence at the University of Pisa. I work as an Associate Researcher at the Institute of Information Science and Technologies (ISTI) of the National Research Council (CNR) in Pisa, Italy, under the supervision of the best possible team of mentors: Dr. Fabrizio Falchi, Dr. Fabio Carrara, Dr. Nicola Messina, and Dr. Giuseppe Amato.
During my Ph.D., I have published at top-tier computer vision conferences such as CVPR (Highlight Poster) and ICCV, and received Best Paper Awards at both CBMI and IEEE-CH. From May to August 2025, I had the opportunity to fulfill one of my childhood dreams by joining the Walt Disney family, working at Disney Research | Studios in Zürich as a Research Intern, where I worked on the design and end-to-end training of large-scale diffusion models, supervised by Dr. Vinicius C. Azevedo.
My research interests lie in the field of Vision-Language Models (VLMs), with a focus on understanding, analyzing, and enhancing the representations learned by foundational models such as CLIP and DINO for image–text understanding. Building upon these representations, I explored a wide range of applications — including image–text matching, retrieval, open-vocabulary object detection, semantic segmentation, image captioning, and text-conditioned image generation. I am also particularly fascinated by approaches that minimize or eliminate human supervision (unsupervised and weakly-supervised learning).
Outside of research, I’m a little bit of a nerd. I love video games, tv series, and films. I’m also very passionate about sports: I like to ski (in the winter), play beach volleyball (in the summer), and tennis (all year round).
If you ever come to Italy, make sure to visit Collodi, the wonderful hometown of both Pinocchio and me!
Some cool stuffs about my journey
My Research Journey
Here’s a map showing the main stops in my academic and research path.
CVPR 2024 Interview
Read my interview on Computer Vision News.
Latest News
- September 2025 Our paper "ReCoptic: Computer Vision for the Reconstruction of Dismembered Coptic Codices" received the Best Paper Award at the IEEE International Conference on Cyber Humanities (IEEE CH 2025) , in Florence, Italy!
- July 2025 Our paper "Talking to DINO: Bridging Self-Supervised Vision Backbones with Language for Open-Vocabulary Segmentation" at ICCV 2025 in Honolulu, Hawaii!
- May 2025 I'm joining Disney Research | Studios to work as a Research Intern in Zürich (Switzerland), to work on large-scale diffusion models for image generation. I'll be there until August 2025
- July 2024 I attended the International Computer Vision Summer School 2024 in Sicily, where I also presented a poster on our CVPR paper.
- September 2024 Our paper "Is CLIP the Main Roadblock for Fine-Grained Open-World Perception?" won the Best Paper Award at the International Conference on Content-Based Multimedia Indexing (CBMI 2024) , in Rekyavik, Iceland!
- June 2024 Our paper "The Devil is in the Fine-Grained Details: Evaluating Open-Vocabulary Object Detectors for Fine-Grained Understanding" was selected as a Highlight Paper at CVPR 2024 in Seattle, Washington!
- September 2023 I attended in the ELLIS Summer School on Large-Scale AI for Research and Industry in Modena.
- March 2023 I'm joining the Artificial Intelligence for Media and Humanities (AIMH) Lab at the Institute of Information Science and Technologies (ISTI–CNR) in Pisa as a Research Associate.