Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
Towards Fast and Disentangled Counterfactuals for Visual Foundation Models
Sidney Bender, Benedikt Kunz, Ahmed Zeid +3
Foundation models remain vulnerable to spurious correlations and ``Clever Hans'' strategies. Explainable machine learning can find and remove such strategies for classifiers withou…
cs.LG2026
SCE-LITE-HQ: Smooth visual counterfactual explanations with generative foundation models
Ahmed Zeid, Sidney Bender
Modern neural networks achieve strong performance but remain difficult to interpret in high-dimensional visual domains. Counterfactual explanations (CFEs) provide a principled appr…