Yueze Wang

zero-shot learning (3) multimodal learning (3) visual prompting (2) instruction tuning (2) vision-language model (2) visual question answering (2) referring expression (1) multi-modal learning (1) attention mechanism (1) image captioning (1) few-shot learning (1) image editing (1) in-context learning (1) visual reasoning (1) text-to-image generation (1) visual grounding (1) instance segmentation (1) ai safety (1) knowledge distillation (1) benchmark evaluation (1)