Whether walking through the streets of Abu Dhabi, Luxembourg, or Paris, where I have spent years studying and collaborating, or hiking in the mountains of northern Italy, where I was born, I often find myself wondering how machines might perceive these environments: not merely reconstructing their geometry, but understanding their meaning and enabling interaction. My fascination lies in teaching machines to see the world beyond point clouds and pixels, to interpret space semantically, dynamically, and at scale. Working with structure from motion, photogrammetry, and Gaussian Splatting has deepened this curiosity; each method reveals part of the picture, yet none achieve real-time, semantically grounded understanding.

News 🎉

• 1 Paper accepted at ICCV 2025 Honolulu, Hawaii - **CAD-Assistant: Tool-Augmented VLLMs as Generic CAD Task Solvers ** - PAPER LINK
• 10th April 2025 Graduated from MBZUAI (Master)
• 1 Paper accepted at CVPR 2025 Nashville, TN - **All Languages Matter: Evaluating LMMs on Culturally Diverse 100 Languages **, Contributed as native speaker for a multimodal and multilingual LLM - PAPER LINK
• 1 Paper accepted at HEALTHINFO 2024 Nice, France - 🏆 Best Paper Award 🎉 - PAPER LINK
• 23rd March 2023 Graduated from the Free University of Bolzano (Bachelor)