Peizhi Zhao

visual grounding (3) cross-modal learning (2) multimodal large language model (2) scene understanding (1) question answering (1) text generation (1) multimodal learning (1) image captioning (1) document understanding (1) multi-modal learning (1) person re-identification (1) referring expression (1) instance segmentation (1) semantic space (1) cross-modal alignment (1) referring expression comprehension (1) linguistic structure (1) multimodal chain-of-thought (1) financial reasoning (1) cross-modal matching (1)