PhD in Computer Vision
Multimodal AI for 3D-Language Understanding (defended on March 25, 2026)
University of Bologna
CINECA LEONARDO ISCRA-B and ISCRA-C Project Grant Recipient.
Andrea Amaduzzi
PhD in Computer Vision (Multimodal AI)
Thesis: Multimodal AI for 3D-Language Understanding (defended on March 25, 2026)
Ex-Intern at Niantic Spatial (September 2025 - March 2026)
Research interests: Multimodal LLMs, 3D-language tasks, spatial reasoning
Hi! I completed my PhD in Computer Vision at the University of Bologna, defending my thesis Multimodal AI for 3D-Language Understanding on March 25, 2026.
My research centers on multimodal LLMs, 3D-language tasks, and spatial reasoning.
I have extensive hands-on experience in multi-node training and fine-tuning of Multimodal LLMs on GPU clusters, utilizing tens of machines.
I recently completed my PhD and am exploring full-time roles.
Feel free to reach out to discuss potential opportunities or collaborations!
Here you can find my CV.