3 papers
cs.CV2026
COGITAO: A Visual Reasoning Framework To Study Compositionality & Generalization
Yassine Taoudi-Benchekroun, Klim Troyan, Pascal Sager +3
The ability to compose learned concepts and apply them in novel settings is key to human intelligence, but remains a persistent limitation in state-of-the-art machine learning mode…
cs.LG2026
Continual Learning through Control Minimization
Sander de Haan, Yassine Taoudi-Benchekroun, Pau Vilimelis Aceituno +1
Catastrophic forgetting remains a fundamental challenge for neural networks when tasks are trained sequentially. In this work, we reformulate continual learning as a control proble…
cs.RO2025
Robust-Sub-Gaussian Model Predictive Control for Safe Ultrasound-Image-Guided Robotic Spinal Surgery
Yunke Ao, Manish Prajapat, Yarden As +6
Safety-critical control using high-dimensional sensory feedback from optical data (e.g., images, point clouds) poses significant challenges in domains like autonomous driving and r…