Liqiang Niu

contrastive learning (1) text-to-image synthesis (1) information retrieval (1) multimodal learning (1) joint learning (1) adaptive inference (1) large multimodal model (1) vision-language model (1) multimodal large language model (1) distributed representation (1) image understanding (1) visual token (1) word embedding (1) multimodal embedding (1) hard negative mining (1) optical character recognition (1) multi-attribute learning (1) visual language understanding (1) multimodal machine translation (1) image-to-text translation (1)