Explainable artificial intelligence
Continual learning
Representation learning
Computational neuroscience
Drug discovery
Research Intern (Sep 2024 - Mar 2025)
Max Planck Institute for Software Systems
Developed an end-to-end gradient-based attribution framework to study alignment between large language models (LLMs) and human brain activity..
Conducted large-scale analyses across transformer, state-space, and hybrid architectures to investigate the relationship between brain alignment and next word-prediction, showing distinct feature reliance for the two prediction tasks.
Co-authored Fine-Grained Analysis of Brain–LLM Alignment through Input Attribution (under review, ICLR 2026).
AI Research Assistant (Nov 2023 - May 2024)
Sony AI
Ideated and implemented ProtoCRL, a prototype-based continual reinforcement learning architecture that automatically identifies event states, improving efficiency of experience replay and mitigating catastrophic forgetting across sequential tasks.
Co-authored ProtoCRL: Prototype-based Network for Continual Reinforcement Learning (Reinforcement Learning Journal, 2025), and did oral and poster presentations at the Reinforcement Learning Conference (2025).
XAI-based continual learning, Philosophy and Computer Science Summer School, University of Bayreuth, Germany, 2023
Explainable AI in Drug Discovery: Self-interpretable Graph Neural Network for Molecular Property Prediction using Concept Whitening, 3rd Molecules Medicinal Chemistry Symposium: Shaping Medicinal Chemistry for the New Decade, Sapienza University, Rome, Italy (2022)
XAI-based continual learning, Seminars in Artificial Intelligence and Robotics 2023/2024, Sapienza University, Rome, Italy
Explainable artificial intelligence, Machine Learning Course 2023/2024, Sapienza University, Rome, Italy
Object detection, Machine Learning Course 2023/2024, Sapienza University, Rome, Italy
XAI-based continual learning, Seminars in Artificial Intelligence and Robotics 2022/2023, Sapienza University, Rome, Italy
Explainable artificial intelligence for deep reinforcement learning (XAI4DRL) workshop @ AAAI2024 (link)
TA, Reinforcement Learning Course 2025/2026, Sapienza University, Rome, Italy
TA, Machine Learning Course 2023/2024, Sapienza University, Rome, Italy
TA, Reinforcement Learning Course 2023/2024, Sapienza University, Rome, Italy
TA, Seminars in Artificial Intelligence and Robotics 2022/2023, Sapienza University, Rome, Italy