Publications | Claudio Fanconi

Publications

Learning Reasoning Reward Models from Expert Demonstration via Inverse Reinforcement Learning

Claudio Fanconi, Nicolas Astorga, Mihaela van der Schaar

ICLR 2026 Workshop on LLM Reasoning
Oral, top 5% (Outstanding Paper Award)

Learning Reasoning Reward Models from Expert Demonstration via Inverse Reinforcement Learning

Tiny Autoregressive Recursive Models

Paulius Rauba, Claudio Fanconi, Mihaela van der Schaar

ICLR 2026 Workshop on Recursive Self-Improvement & ICLR 2026 Latent and Implicit Thinking

Tiny Autoregressive Recursive Models

Cascaded Language Models for Cost-effective Human-AI Decision-Making

Claudio Fanconi, Mihaela van der Schaar

NeurIPS 2025 (Poster) & ICML 2025 Workshop on Multi Agent Systems

Cascaded Language Models for Cost-effective Human-AI Decision-Making

Few-shot Steerable Alignment: Adapting Rewards and LLM Policies with Neural Processes

Katarzyna Kobalczyk, Claudio Fanconi, Hao Sun, Mihaela van der Schaar

* denotes equal authorship.

ICML 2025 Workshop on Models of Human Feedback for AI Alignment
Oral, top 10%

Few-shot Steerable Alignment: Adapting Rewards and LLM Policies with Neural Processes

Discovering Preference Optimization Algorithms with and for Large Language Models

Chris Lu, Samuel Holt, Claudio Fanconi*, Alex J. Chan, Jakob Foerster‡, Mihaela van der Schaar‡, Robert Tjarko Lange‡

* denotes equal authorship.

NeurIPS 2024 (Poster) & ICML 2024 Workshop on AutoRL

Discovering Preference Optimization Algorithms with and for Large Language Models

Applying Natural Language Processing to Patient Messages to Identify Depression Concerns in Cancer Patients

Marieke van Buchem, Anne de Hond, Claudio Fanconi, Vaibhavi Shah, Max Schuessler, Ilse Kant, Ewout W Steyerberg, Tina Hernandez-Boussard

Journal of the American Medical Informatics Association

Applying Natural Language Processing to Patient Messages to Identify Depression Concerns in Cancer Patients

Predicting Depression Risk in Patients With Cancer Using Multimodal Data - Algorithm Development Study

Anne de Hond, Marieke van Buchem, Claudio Fanconi, Mohana Roy, Douglas Blayney, Ilse Kant, Ewout Steyerberg, Tina Hernandez-Boussard

JMIR Medical Informatics, 2024 Jan 18

Predicting Depression Risk in Patients With Cancer Using Multimodal Data - Algorithm Development Study

This Reads Like That - Deep Learning for Interpretable Natural Language Processing

Claudio Fanconi, Moritz Vandenhirtz, Severin Husmann, Julia E. Vogt

* denotes equal authorship.

EMNLP 2023 (Poster)

This Reads Like That - Deep Learning for Interpretable Natural Language Processing

A Bayesian Approach to Predictive Uncertainty in Chemotherapy Patients at Risk of Acute Care Use

Claudio Fanconi, Anne de Hond, Dylan Peterson, Angelo Capodici, Tina Hernandez-Boussard

The Lancet eBioMedicine, Volume 92, 2023

A Bayesian Approach to Predictive Uncertainty in Chemotherapy Patients at Risk of Acute Care Use

Natural Language Processing Methods to Identify Oncology Patients at High Risk for Acute Care with Clinical Notes

Claudio Fanconi, Marieke van Buchem, Tina Hernandez-Boussard

AMIA 2023 Informatics Summit (Presentation)

Natural Language Processing Methods to Identify Oncology Patients at High Risk for Acute Care with Clinical Notes

Predict, Diagnose, and Treat Chronic Kidney Disease with Machine Learning: a Systematic Literature Review

Francesco Sanmarchi, Claudio Fanconi, Davide Golinelli, Davide Gori, Tina Hernandez-Boussard, Angelo Capodici

Journal of Nephrology

Predict, Diagnose, and Treat Chronic Kidney Disease with Machine Learning: a Systematic Literature Review

This Looks Like That... Does it? Shortcomings of Latent Space Prototype Interpretability in Deep Networks

Adrian Hoffmann, Claudio Fanconi, Rahul Rade*, Jonas Kohler

* denotes equal authorship.

ICML 2021 Workshop on Theoretic Foundation, Criticism, and Application Trend of Explainable AI

This Looks Like That... Does it? Shortcomings of Latent Space Prototype Interpretability in Deep Networks