Yanshu Li

multimodal in-context learning (3) vision-language model (2) large vision-language model (2) domain adaptation (2) visual token (2) road damage detection (2) self-supervised learning (1) semantic consistency (1) visual question answering (1) multimodal learning (1) question answering (1) task mapping (1) image-text pair (1) parameter-efficient fine-tuning (1) object detection (1) hallucination mitigation (1) multimodal large language model (1) multilingual nlp (1) zero-shot transfer (1) low-rank adaptation (1)