DeepNet: Scaling Transformers to 1,000 Layers

Article Properties

• DOI (url)

  10.1109/tpami.2024.3386927
• Publication Date

  2024/01/01
• Journal

  IEEE Transactions on Pattern Analysis and Machine Intelligence
• Indian UGC (journal)
• Hongyu Wang School of Computer and Control Engineering, University of Chinese Academy of Sciences, Beijing, China ORCID (unauthenticated)
• Shuming Ma Microsoft Research
• Li Dong Microsoft Research ORCID (unauthenticated)
• Shaohan Huang Microsoft Research
• Dongdong Zhang Microsoft Research ORCID (unauthenticated)
• Furu Wei Microsoft Research