4 papers
On the Robustness of Tabular Foundation Models: Test-Time Attacks and In-Context Defenses
Mohamed Djilani, Thibault Simonetto, Karim Tit +4
Recent tabular Foundational Models (FM) such as TabPFN and TabICL, leverage in-context learning to achieve strong performance without gradient updates or fine-tuning. However, thei…
Constraint-Guided Prediction Refinement via Deterministic Diffusion Trajectories
Pantelis Dogoulis, Fabien Bernier, Félix Fourreau +2
Many real-world machine learning tasks require outputs that satisfy hard constraints, such as physical conservation laws, structured dependencies in graphs, or column-level relatio…
ABS: Enforcing Constraint Satisfaction On Generated Sequences Via Automata-Guided Beam Search
Vincenzo Collura, Karim Tit, Laura Bussi +2
Sequence generation and prediction form a cornerstone of modern machine learning, with applications spanning natural language processing, program synthesis, and time-series forecas…
KCLNet: Physics-Informed Power Flow Prediction via Constraints Projections
Pantelis Dogoulis, Karim Tit, Maxime Cordy
In the modern context of power systems, rapid, scalable, and physically plausible power flow predictions are essential for ensuring the grid's safe and efficient operation. While t…