Yu Hen Hu

model compression (1) zero-shot learning (1) vision transformer (1) few-shot learning (1) curriculum learning (1) self-supervised learning (1) multimodal learning (1) visual representation (1) efficient inference (1) vision-language model (1) noisy label (1) token pruning (1) clip model (1) prompt tuning (1) masked image modeling (1) masked autoencoding (1)