Paola Cascante-Bonilla

vision-language model (3) synthetic datum (2) continual learning (2) visual question answering (2) vision language model (2) compositional reasoning (2) domain adaptation (1) transfer learning (1) zero-shot learning (1) curriculum learning (1) image retrieval (1) self-supervised learning (1) attention mechanism (1) data augmentation (1) vision transformer (1) program synthesis (1) visual grounding (1) scene understanding (1) data-free learning (1) code generation (1)