Introduces a data-free preconditioning method for privacy-preserving deep learning, enabling effective model training under differential privacy constraints without requiring access to raw training data.
Read paper →CERN · UPF · Kosmico
Co-founder of Kosmico. PhD student by day. Open source on the side.
Co-founder of Kosmico, the native AI workspace for multiplayer and traceable research. Research scientist and PhD student at UPF, based at CERN in Geneva. I work on multimodal generative models and agentic systems for neurological diagnostics: federated learning, brain signals, and privacy-preserving medical AI. MSc in Data Science and BSc in Statistics from Sapienza University of Rome.
Co-founder
Kosmico
Multiplayer and traceable research
We are building Kosmico around a simple idea: the project, not the paper, should be the shared object of research. One native AI workspace where labs write, cite, experiment, and plan together, with Kosmo, an agent that lives inside your project and actually does the work.
Keep the work together
LaTeX, notebooks, PDFs, and code in one workspace with visible, scoped access. No more re-explaining context across scattered tools.
Make research multiplayer
Share the chain behind the paper, not just the PDF. Coauthors and their agents see hypotheses, experiments, and decisions as they develop.
Make progress legible
Failed attempts, direction changes, and evidence stay connected. Everyone can pick up where the project left off.
About
Multimodal generative models & agentic systems
My research sits between multimodal generative models and agentic systems: learning latent structure from brain signals on one side, and building agents that reason through clinical investigations with tools and protocols on the other. I also care about privacy, federated learning, and making models explainable in real clinical settings.
8
Publications
25
Citations
3
Institutions
3
Open-source projects
Multimodal Generative Models
Generative modelling of brain signals and neuroimaging. Flow-based latent learning from EEG, capturing uncertainty in cortical inference.
Agentic Systems
Tool-augmented agents for clinical neurology. Step-by-step investigation with diagnostic tools, hospital protocols, and evidence-based reasoning.
Private & Explainable AI
Federated learning and privacy-preserving training across hospitals. Explainable methods that stay interpretable when data cannot be shared.
Publications
Peer-reviewed work in federated learning, medical AI, and agentic systems
Proposes a federated architecture combining Transformers and Graph Neural Networks for brain tumor localization across multimodal MRI, with modality-level explainability while preserving patient privacy.
Read paper →Presents a semantics-aware communication fabric enabling large-scale coordination among AI agents, designed for scalable multi-agent systems with structured knowledge exchange.
Read paper →Experience
Work & education
Work
Building the native AI workspace for multiplayer and traceable research: one place where labs keep the work together, collaborate in context, and preserve the trajectory behind every result.
PhD Student, CERN
Developing generative models and agentic systems for neurological diagnostics, with a focus on multimodal brain signals, federated learning, and privacy-preserving clinical AI.
Research Scientist Intern, CERN
Graph Neural Networks for medical diagnostics, predicting stroke severity through brain connectivity analysis from EEG signals.
Education
PhD in AI for Neuroscience, Universitat Pompeu Fabra (UPF)
Doctoral research on multimodal generative models and agentic AI for neurological diagnostics, based at CERN in Geneva.
PhD in AI for Neuroscience, EPFL · EDNE Doctoral Program
Initial doctoral enrollment in Lausanne. Research on multimodal Graph Neural Networks, federated learning, and privacy-preserving medical AI for neurological conditions.
MSc in Data Science, Sapienza · 110/110 cum laude
Honors program graduate specializing in Deep Learning and Temporal Graph Neural Networks.
Open Source
Tools I build in the open
Free, AGPL-licensed projects. No telemetry, no accounts, just software that works.
MyDemoStudio
Native macOS screen recorder for polished product demos
Press record, get the polished cut. Re-renders your capture with auto-zoom, gradient backdrop, and a smooth cursor, with no subscription. Drivable by an AI agent over MCP with 24 tools.
SwiftSwiftUIMetalMCPAGPL-3.0
MyTripPlanner
AI road trip planner with the Ulisse agent
Self-hosted planner where Ulisse interviews you and builds itineraries live: stops, map, timings, budget. Runs on your Claude or ChatGPT subscription. No API keys.
TypeScriptNode.jsAI AgentAGPL
MyMacCleaner
macOS system utility with Liquid Glass UI
Open-source macOS app for smart scan, disk cleaning, space lens, duplicate finder, and performance monitoring. Code-signed and notarized.
SwiftSwiftUImacOSAGPL-3.0