Tag
This paper presents the first foundation model-orchestrated workflow for crash safety design, enabling surrogate-assisted exploration for pedestrian protection that reduces evaluation time from hours to seconds, demonstrated in an automotive front-bumper case study.
This paper systematically studies how different evaluation objectives (accuracy, silhouette score, PCA reconstruction loss) and subset-size regularization directions affect search dynamics and solution quality in multiobjective unsupervised feature selection, showing that silhouette-based formulations bias toward trivial low-cardinality solutions while PCA loss yields compact subsets with competitive accuracy.