• search
    search
  • reviewers
    reviewers
  • feeds
    feeds
  • assignments
    assignments
  • settings
  • logout

Towards Being Parameter-Efficient: A Stratified Sparsely Activated Transformer with Dynamic Capacity.

Haoran XuMaha ElbayadKenton MurrayJean MaillardVedanuj Goswami
Published in: CoRR (2023)
Keyphrases