Jingyun Wang

feature alignment (1) unsupervised learning (1) contrastive learning (1) semantic segmentation (1) vision transformer (1) few-shot learning (1) knowledge distillation (1) in-context learning (1) question answering (1) video understanding (1) prompt learning (1) vision language model (1) multimodal large language model (1) prompt optimization (1) retrieval-augmented generation (1) memory mechanism (1) visual feature (1) exemplar retrieval (1) large language model (1) bias modeling (1)