M. Jehanzeb Mirza

vision-language model (2) distribution shift (2) few-shot learning (1) domain adaptation (1) computer vision (1) visual question answering (1) in-context learning (1) batch normalization (1) question answering (1) multimodal learning (1) semantic analysis (1) point cloud (1) multi-modal learning (1) object localization (1) feature representation (1) vision language model (1) masked autoencoder (1) bounding box (1) in-context example (1) compositional reasoning (1)