Home | Claudio Fanconi

Claudio Fanconi

Ph.D. Student in Machine Learning, University of Cambridge

Hello! I am second-year PhD student in Machine Learning and AI for Medicine at the University of Cambridge advised by Mihaela van der Schaar.

Previously, I graduated with a Bachelor's and Master's from ETH Zürich in Information Technology and Electrical Engineering with a focus on Machine Learning (ML). I conducted my Master's thesis under the supervision of Tina Hernandez-Boussard at Stanford University, researching predictive uncertainty and natural language processing to identify patients at risk of acute care use.

My current research topics are:
(i) the application of ML in high-stakes environments such as medicine
(ii) using machine learning to enhance human decision-making
(iii) the alignment and reasoning of large language models (LLMs).

Reach out to me with anything you want to talk about!

Additionally, please check out the Fanconi Cancer Foundation and their initiatives against Fanconi Anemia.

Updates

(2025/10) 📝 New preprint! (Paper): Operationalises adversarial inverse reinforcement learning to elicit reasoning in LLMs.
(2025/09) 📝 First-author paper accepted (poster) at NeurIPS 2025 (Paper): Researches cost-efficient cascaded-LLM Systems for decision-making.
(2025/06) 📝 Co-first-author paper accepted (oral, top 10%) at the ICML 2025 Workshop on AI Alignment together with Kasia (Paper): Develops a method for few-shot steerable alignment of rewards and policy models with neural processes.
(2024/09) 📝 Co-first-author paper accepted (poster) at NeurIPS 2024 (Paper): Demonstrates LLMs generating optimisation algorithms for their preference learning.
(2024/07) 📝 Published in JAMIA (Paper): Demonstrates BERT models can effectively identify depression concerns in cancer patients' portal messages.
(2024/04) 🎉 I have officially started a PhD in Machine Learning at the University of Cambridge under the supervision of Mihaela van der Schaar.
(2024/01) 📝 Published in JMIR Medical Informatics (Paper): Develops machine learning models to predict depression risk in cancer patients starting treatment.
(2023/09) 📝 Co-first-author paper accepted (poster) at EMNLP 2023 (Paper): Introduces prototype-based methods for enhanced interpretability in NLP.
(2023/06) 📝 First-author paper published in The Lancet eBioMedicine (Paper): Demonstrates the added value of uncertainty estimation to predict the risk of ACU for cancer patients.
(2023/03) 🎉 I have joined Sony AI as a junior research scientist (internship), working on computer vision algorithms for robotic perception systems.
(2023/03) 📝 First-author paper accepted at AMIA Informatics Summit 2023 (Paper): Clinical notes can predict acute care use in oncology patients nearly as well as structured data.
(2023/02) 📝 Published in Journal of Nephrology (Paper): Systematically reviews how artificial intelligence has been deployed to predict, diagnose, and treat chronic kidney disease.
(2022/10) 🎉 Graduated with an MSc in Information Technology and Electrical Engineering from ETH Zürich, after conducting my Master's thesis at Stanford University (Thesis).
(2021/06) 📝 Co-first-author paper accepted at an ICML 2021 Workshop (Paper): Critiques prototype-based networks, highlighting mismatches in latent-input space similarity.