📝 All Publications

Eleonora Gualdoni, Sonia Laguna, Louis Béthune, Joao Monteiro, Pierre Ablin, Marco Cuturi (2026). DynaMiCS: Fine-tuning LLMs with Performance Constraints using Dynamic Mixtures. Preprint - Arxiv.

Sonia Laguna, Jorge Da Silva Gonçalves, Moritz Vandenhirtz, Alain Ryser, Irene Cannistraci, Julia E. Vogt (2026). Rethinking Machine Unlearning: Models Designed to Forget via Key Deletion. In ICLR 2026 Workshop TTU (Oral) and extended Preprint - ArXiv.

Jonas Mirlach*, Sonia Laguna*, Julia E Vogt (2026). Reference-Guided Machine Unlearning. In ICLR 2026 Workshop AIWILD and extended Preprint - ArXiv.

Sonia Laguna*, Andrea Agostini*, Alain Ryser, Samuel Ruiperez-Campillo, Irene Cannistraci, Moritz Vandenhirtz, Stephan Mandt, Nicolas Deperrois, Farhad Nooralahzadeh, Michael Krauthammer, Thomas M Sutter, Julia E. Vogt (2026). Structure is Supervision: Multiview Masked Autoencoders for Radiology. In Transactions in Machine Learning Research (TMLR) 2026.

Wiktor Jan Hoffmann, Sonia Laguna, Moritz Vandenhirtz, Emanuele Palumbo, Julia E. Vogt (2026). Post-hoc Stochastic Concept Bottleneck Models. In ICLR 2026 Workshop Trustworthy AI.

Moritz Vandenhirtz, Samuel Ruiperez-Campillo, Sonia Laguna, Simon Böhi, Irene Cannistraci, Andrea Agostini, Ece Ozkan, Thomas M Sutter, Julia E. Vogt (2026). Foundation Model for Cardiac Time Series via Masked Latent Attention. In ICLR 2026 Workshop FM4Science.

Simon Böhi, Irene Cannistraci, Sergio Muñoz Gonzalez, Moritz Vandenhirtz, Sonia Laguna, Samuel Ruiperez-Campillo, Max Krähenmann, Andrea Agostini, Ece Ozkan, Thomas M Sutter, Julia E. Vogt (2026). Beyond Independent Frames: Latent Attention Masked Autoencoders for Multi-View Echocardiography. In ICLR 2026 Workshop FM4Science.

Sonia Laguna, Moritz Vandenhirtz, Julia E. Vogt (2026). Concepts Based Methods. Book Chapter in Explainable Artificial Intelligence and Interpretable Machine Learning in Education Book, Springer.

Nicolas Dickenmann, Yanis Merzouki, Sonia Laguna, Thy Nowak-Tran, Emanuele Palumbo, Gerda Binder, Julia E. Vogt (2026). Steering Generative Models for Accessibility: EasyRead Image Generation. In the CHI 2026 Conference on Human Factors in Computing Systems.

Sonia Laguna, Katarzyna Kobalczyk, Julia E. Vogt, Mihaela Van Der Schaar (2025). Interpretable Reward Modeling with Active Concept Bottlenecks. In ICML 2025 Workshop PRAL.