Demi Guo

neural network (2) neural network pruning (1) transfer learning (1) sparse learning (1) machine translation (1) data augmentation (1) neural machine translation (1) semantic parsing (1) parameter-efficient transfer learning (1) compositional generalization (1) model pruning (1) generative model (1) autoregressive model (1) parameter efficient fine-tuning (1) pretrained language model (1) amortized variational inference (1) sequence-to-sequence model (1) compositional behavior (1) neural attention (1) variational attention (1)