Jinliang Zheng

transfer learning (2) masked autoencoder (2) representation learning (2) computer vision (1) self-supervised learning (1) cross-domain learning (1) image reconstruction (1) neural architecture search (1) visual grounding (1) instruction following (1) parameter efficient (1) robot control (1) vision model (1) multimodal model (1) self-supervised pre-training (1) encoder-decoder architecture (1) architecture optimization (1) masked image modeling (1) pretraining finetuning (1) swin transformer (1)