cv

Research Intern

Institute of Science and Technology Austria (ISTA)

Research in causal learning and multimodal foundation models within the Locatello Group.

• Co-first author for a paper on unsupervised causal effect discovery in RCTs (theory + library).
• Developing frameworks combining causality and deep learning for large-scale multimodal systems.

Research Student

GLADIA · Sapienza University of Rome

Research on scalable model merging, interpretability, and ability estimation for large language models.

• Scaled evolutionary model merging using consumer GPUs (50× speedup, 2% data usage, 85% performance retained).
• Two first-author papers accepted to ICML 2025 and ACL 2025.
• Co-first author for a paper proving injectivity of LLM representations and presenting the first exact inversion algorithm (viral tweet with 4.7M views).

Research Student

ETH Zürich (LRE Lab)

Applied causal inference to explain and assess LLM performance on math word problems.

• Worked on applying causal inference techniques to large language models to detect spurious heuristics in reasoning tasks.
• Ran large-scale experiments on high-performance computing clusters.

Research Assistant

Vrije Universiteit Amsterdam · KAI Lab

Research at the intersection of knowledge graphs and hallucination mitigation in LLMs.

• Designed Text-to-Graph and Graph-to-Text methods for content planning.
• Trained and evaluated multiple knowledge-graph-integrated LLMs.

Research Student

Sapienza University of Rome

NLP research in e-justice applications using specialized large language models.

• Developed GPT-2-based writing assistant for legal documents.
• Publication at ECAI 2023 (CICERO project).
• Conducted evaluation with legal professionals.

Technology Assistant

Network Institute VU Amsterdam

Technical support for interdisciplinary projects in XR, VR, and motion capture.

• Worked with Unity, C#, iClone, Motive, and Optitrack.
• Organized and presented at Surf XR-On Tour and Reshaping Work 2022 Conference.

Master of Science

École Polytechnique Fédérale de Lausanne (EPFL)

Data Science

• Coursework focused on the Mathematics of data science

Bachelor of Science

Vrije Universiteit Amsterdam

Artificial Intelligence (Major) & Mathematics (Minor)

• Honours Programme (30 credits of advanced coursework, e.g. PDEs)

Bachelor’s Degree

Sapienza University of Rome

Philosophy

• Focused on formal logic and philosophy of language

KHMW Young Talent Incentive Award

Royal Holland Society of Sciences and Humanities

National award presented to the student with the highest GPA in their degree program at a Dutch research university.

Intelligent Systems Competition — 1st Place

Vrije Universiteit Amsterdam

Ranked 1st out of 270 students by developing an intelligent agent for the card game Schnapsen.

Do Sparse Autoencoders Transfer Across Base and Finetuned LLMs?

NeurIPS 2024 Workshop

CICERO: A GPT-2-based Writing Assistant in e-justice

ECAI 2023

Mergenetic: A Simple Evolutionary Model Merging Library

ACL 2025 · System Demonstrations

Activation Patching for Interpretable Steering in Music Generation

Under Review

MERGE³: Efficient Evolutionary Merging on Consumer-grade GPUs

ICML 2025

Exploratory Causal Inference in SAEnce

Under Review

Language Models are Injective and Hence Invertible

Under Review