2 papers
cs.AI2026
From Token Lists to Graph Motifs: Weisfeiler-Lehman Analysis of Sparse Autoencoder Features
Ruben Fernandez-Boullon, Pablo Magariños-Docampo, Javier Perez-Robles
Sparse autoencoders (SAEs) have become central to mechanistic interpretability, decomposing transformer activations into monosemantic features. Yet existing analyses characterise f…
cs.RO2026
A Modular Architecture Design for Autonomous Driving Racing in Controlled Environments
Brais Fontan-Costas, M. Diaz-Cacho, Ruben Fernandez-Boullon +2
This paper presents a modular autonomous driving architecture for Formula Student Driverless competition vehicles operating in closed-circuit environments. The perception module em…