Zhenda Xie

representation learning (4) self-supervised learning (4) masked image modeling (4) transfer learning (3) object detection (3) contrastive learning (3) image classification (3) vision transformer (3) multimodal learning (3) semantic segmentation (2) mixture of expert (2) image generation (2) multimodal understanding (2) vision-language model (2) transformer architecture (2) autoregressive model (2) model scaling (2) attention mechanism (1) zero-shot learning (1) efficient computing (1)