Xin Xiao

contrastive learning (1) visual question answering (1) self-supervised learning (1) multimodal learning (1) code generation (1) modality alignment (1) synthetic data generation (1) synthetic datum (1) vision language model (1) cross-modal alignment (1) vision-language model (1) multi-modal alignment (1) electronic health record (1) visual correlation (1) token weighting (1) image-text alignment (1) clinical reasoning (1) data filtering (1) multi-modal data generation (1) code parsing (1)