Qinglong Zhang

vision-language model (3) multi-modal learning (2) vision transformer (2) image classification (2) foundation model (2) multimodal learning (1) object detection (1) semantic segmentation (1) visual explanation (1) multimodal large language model (1) model interpretability (1) gradient-based method (1) robot control (1) saliency map (1) embodied ai (1) zero-shot image classification (1) deep neural network (1) vision-language alignment (1) self-attention mechanism (1) zero-shot learning (1)