AI Research Wiki

Home

❯

architectures

Folder: architectures

5 items under this folder.

  • Apr 11, 2026

    BERT (Bidirectional Encoder Representations from Transformers)

    • architecture
    • encoder-only
    • pretraining
    • natural-language-understanding
  • Apr 11, 2026

    Encoder-Decoder Architecture

    • architecture
    • sequence-to-sequence
    • machine-translation
  • Apr 11, 2026

    Generative Pre-trained Transformer (GPT)

    • architecture
    • language-model
    • decoder-only
    • autoregressive
  • Apr 11, 2026

    Mixture of Experts (MoE)

    • architecture
    • sparse-models
    • scaling
    • efficiency
  • Apr 11, 2026

    Transformer

    • architecture
    • attention
    • sequence-modeling

Created with Quartz v4.5.2 © 2026

  • GitHub
  • Discord Community