Automatically learning hybrid digital twins of dynamical systems

S Holt, T Liu, M van der Schaar - arxiv preprint arxiv:2410.23691, 2024 - arxiv.org
Digital Twins (DTs) are computational models that simulate the states and temporal
dynamics of real-world systems, playing a crucial role in prediction, understanding, and …

Controllable Sequence Editing for Counterfactual Generation

MM Li, K Li, Y Ektefaie, S Messica, M Zitnik - arxiv preprint arxiv …, 2025 - arxiv.org
Sequence models generate counterfactuals by modifying parts of a sequence based on a
given condition, enabling reasoning about" what if" scenarios. While these models excel at …

No Equations Needed: Learning System Dynamics Without Relying on Closed-Form ODEs

K Kacprzyk, M van der Schaar - arxiv preprint arxiv:2501.18563, 2025 - arxiv.org
Data-driven modeling of dynamical systems is a crucial area of machine learning. In many
scenarios, a thorough understanding of the model's behavior becomes essential for practical …

C-PPT: A Channel-Wise Prototypical Part Transformer for Interpretable Perioperative Complication Prediction with Blood Pressure

J Zhang, X Yang, Y Chen, R Sun - International Conference on Pattern …, 2024 - Springer
Continuous monitoring of multi-channel blood pressure during the perioperative period is
crucial for predicting complications. ProtoPNet has garnered attention as powerful tools for …