Ruiming Chen

transfer learning (3) knowledge distillation (3) model compression (3) image classification (1) vision transformer (1) multimodal learning (1) model architecture (1) model decomposition (1) contrastive language-image pretraining (1) polynomial decomposition (1) diverse-scale model (1) neural network initialization (1) model initialization (1) neural network (1) transformer architecture (1) representation learning (1)