Hernán Maina

visual question answering (3) masked language model (2) social bia (2) multimodal learning (1) visual grounding (1) visual dialog (1) multimodal interaction (1) selective prediction (1) low-resource language (1) benchmark dataset (1) language model (1) large multimodal model (1) multimodal model (1) large multi-modal model (1) cultural diversity (1) word embedding (1) fairness evaluation (1) dialogue system (1) calibration method (1) error analysis (1)