Andrew M Dai

sparse activation (2) multi-task learning (2) mixture of expert (2) transfer learning (1) text classification (1) self-supervised learning (1) neural machine translation (1) language modeling (1) multimodal learning (1) model fusion (1) clinical outcome prediction (1) sequence learning (1) recurrent neural network (1) language model (1) parameter efficiency (1) pretrained model (1) expert routing (1) text-to-image diffusion model (1) multilingual learning (1) recurrent network (1)