I build machine learning systems that are measured honestly and hold up outside the notebook - from vision models and multimodal retrieval to learning on edge devices.
01
ICMI ’26 - International Conference on Multimodal Interaction, Napoli
A desk-mounted edge device that tracks sitting posture with on-device pose estimation and corrects it through haptic and visual feedback. Published at ICMI ’26; in a 30-person user study every participant reported better postural awareness and none found it intrusive.
MSc in Computer Science - Sapienza University of Rome
Master’s thesis: a pipeline that turns smartphone photos of evacuation floor plans into clean, editable maps for an indoor navigation system for people with visual and motor disabilities. RT-DETR-L reaches 0.894 mAP@50 and a human-in-the-loop editor replaces manual tracing with quick corrections.
Advanced Machine Learning - Sapienza University of Rome, a.y. 2025/26
Violent actions are rare in motion datasets, so standard classifiers ignore them. We adapt TMR++ text-aligned motion embeddings with first-order MAML and a violence-aware loss: at 30 shots per class the model detects 73.1% of violent actions at a 1% false-positive rate.
02
I’m a computer scientist from Sapienza University of Rome, where I’m about to start a PhD. My work sits where machine learning meets real constraints: noisy data, tight compute budgets, evaluation that has to convince someone other than me.
Before and alongside research I’ve spent a lot of time on plain software engineering - backends, APIs, deployment - which is why I care about the whole pipeline, not only the model in the middle of it.
MSc in Computer Science
Sapienza University of Rome
2024 – 2026
BSc Computer Science
Sapienza University of Rome
2020 – 2024
03
I’m about to start a PhD at Sapienza University of Rome. If you want to talk about research, a possible collaboration or one of the projects here, email is the best way to reach me.
fraponi98@gmail.com