Selected work

Projects

A tidy overview of some of the things I’ve built, studied, and tested.

Based in Italy • Last updated: April 2026

Browse by area

Showing all projects

Featured thesis

Bachelor’s thesis

Unveiling Protein Connections through Graph Neural Networks and ProtT5 Embeddings
My bachelor’s thesis asks a practical bioinformatics question: can a model suggest likely missing links between proteins, so researchers have better candidates to inspect? It combines protein sequence information with a known interaction network, with a NOTCH2-focused case study.

Bioinformatics Protein networks Link prediction Candidate ranking
Read thesis Interactive summary Slides PDF

Computer vision

UAV Anomaly Detection & Localization

A computer-vision pipeline for large drone images where the goal is simple: spot unusual objects or target areas quickly, then turn them into regions that can be checked or classified.

Aerial imagery Anomaly detection Localization Post-processing
  • Task: find candidate target areas inside high-resolution aerial frames.
  • Why: targets are rare and images are large, so narrowing the search saves time.
  • Output: heatmaps, bounding boxes, and crops that can feed the next classifier or demo.
More details

Dynamical systems

Lorenz Attractor Forecasting

A small forecasting study on a chaotic system: can a model predict the next movement, and how quickly do tiny mistakes grow when predictions are fed back into the model?

Dynamical systems Forecasting Time series Stability
  • Task: predict short pieces of motion in a system that is very sensitive to small changes.
  • Why: it is a clean toy problem for understanding the limits of time-series prediction.
  • Lesson: good short-term predictions do not automatically stay reliable over long rollouts.
Interactive demo Notebook export

Data analysis

EU Elections 2019 Data Analysis

Exploratory analysis of the 2019 European elections: data cleaning, hypothesis checks, and visual summaries.

Public data Data cleaning Visualization Exploratory analysis
  • Work: wrangling messy tables, checking consistency, and building reproducible notebooks.
  • Output: plots and narrative conclusions based on quantitative patterns.
Presentation PDF

Reinforcement learning

RL-Nav v1 — Oracle-Guided RL for Partial-Observation Navigation

Exam project combining reinforcement learning and LLM-based guidance for navigation in a stochastic PyBullet environment with a hidden goal, sparse local sensing, dense guidance embeddings, and recurrent control.

Reinforcement learning Navigation LLM guidance Partial observation
  • Work: designed the LLM oracle interface and constrained structured outputs.
  • Outcome: reached 62% held-out success while exposing robust execution as the main bottleneck.
Presentation PDF

Synthetic data

Synthetic Dataset Generation in Blender

Small synthetic-data pipeline for generating labeled images with domain randomization for YOLO-style training.

Synthetic data 3D rendering Domain randomization Object detection
  • Work: scene randomization, lighting changes, and label export.
  • Why: fast iteration when real data is expensive, limited, or hard to collect.
Synthetic render example 1 Synthetic render example 2

Engineering

Small Web / API Projects

Lightweight backend/API work and small apps focused on turning functionality into something usable and testable.

Web apps API design Frontend basics Small tools
  • Work: API schemas, endpoints, and clean integration with client logic.
  • Stack: OpenAPI, SQL fundamentals, HTML, CSS, and JavaScript.
This site! WasaText Mood tracker

Interactive experiments

Playground

A growing space for browser-native simulations, visual explainers, and small tools that are useful to explore but not necessarily large enough for standalone project pages.

Browser demos Interactive simulations Canvas Visual tools
  • Task: keep small interactive ideas discoverable as they evolve.
  • Why: simulations and sliders can explain some concepts better than static text.
Open playground