3 papers
cs.LG2026
Learning Contextual Runtime Monitors for Safe AI-Based Autonomy
Alejandro Luque-Cerpa, Mengyuan Wang, Emil Carlsson +3
We introduce a novel framework for learning context-aware runtime monitors for AI-based control ensembles. Machine-learning (ML) controllers are increasingly deployed in (autonomou…
cs.GT2025
An Application of Membrane Computing to Humanitarian Relief via Generalized Nash Equilibrium
Alejandro Luque-Cerpa, David Orellana-MartÃn, Miguel A. Gutiérrez-Naranjo
Natural and political disasters, including earthquakes, hurricanes, and tsunamis, but also migration and refugees crisis, need quick and coordinated responses in order to support v…
cs.CV2025
Metric-Guided Synthesis of Class Activation Mapping
Alejandro Luque-Cerpa, Elizabeth Polgreen, Ajitha Rajan +1
Class activation mapping (CAM) is a widely adopted class of saliency methods used to explain the behavior of convolutional neural networks (CNNs). These methods generate heatmaps t…