Yanqi Zhou

model compression (3) mixture of expert (3) sparse activation (3) transformer architecture (2) neural network (2) neural architecture search (2) transfer learning (2) language model (2) graph neural network (2) few-shot learning (2) multi-task learning (1) speech synthesis (1) conditional computation (1) efficient computing (1) vision transformer (1) knowledge distillation (1) distribution shift (1) knowledge transfer (1) catastrophic forgetting (1) parameter-efficient transfer learning (1)