2026
From Weights to Concepts: Data-Free Interpretability of CLIP via Singular Vector Decomposition
Francesco Gentile, Nicola Dall'Asen, Francesco Tonini, Massimiliano Mancini, Lorenzo Vaquero, Elisa Ricci
CVPR 2026
As vision-language models are deployed at scale, understanding their internal mechanisms becomes increasingly critical. Existing interpretability methods predominantly rely on activations, making them dataset-dependent, vulnerable to data bias, and often restricted to coarse head-level explanations.