Muhammad Maaz

vision-language model (3) transfer learning (3) video understanding (2) large multimodal model (2) vision language model (2) visual grounding (2) multimodal learning (2) object detection (1) image segmentation (1) multi-modal learning (1) visual encoder (1) domain generalization (1) prompt learning (1) instruction tuning (1) machine translation (1) open-vocabulary detection (1) few-shot learning (1) model scaling (1) zero-shot learning (1) representation learning (1)