Michele Merler

domain adaptation (2) transfer learning (2) metric learning (1) knowledge distillation (1) neural architecture search (1) language model (1) multi-head attention (1) pretrained language model (1) siamese network (1) architecture optimization (1) entity standardization (1) contrastive siamese network (1) hidden state transfer (1) model compression (1) architecture transfer (1) contrastive learning (1)