Ming Dai

visual grounding (3) multimodal large language model (2) attention mechanism (2) referring image segmentation (2) multimodal learning (1) multi-modal learning (1) object localization (1) vision-language model (1) inference optimization (1) multimodal representation (1) multimodal fusion (1) inference acceleration (1) referring expression comprehension (1) multi-modal fusion (1) key-value cache (1) visual token pruning (1) object proposal (1) consistency constraint (1) referring expression segmentation (1) image-text comprehension (1)