Moreno D'Incà

unsupervised learning (1) contrastive learning (1) bias detection (1) text-to-image generation (1) model safety (1) visual classifier (1) diffusion model (1) language model (1) vision-language model (1) knowledge preservation (1) pretrained model (1) retrieval model (1) bias quantification (1) image augmentation (1) facial analysis (1) large language model (1) weight manipulation (1) unsafe content (1) open-set bias detection (1) vision question answering (1)