Young Kyun Jang

Architectures (1)

large language model (6) multimodal learning (3) vision-language model (3) cross-modal retrieval (2) semi-supervised learning (2) semantic similarity (2) contrastive learning (2) image retrieval (2) product quantization (2) large multimodal model (2) composed image retrieval (2) transfer learning (1) prompt engineering (1) vision-language alignment (1) self-supervised learning (1) image classification (1) model robustness (1) adversarial attack (1) visual question answering (1) metric learning (1)