@article{transformerattention2017,
  title = {Attention Is All You Need (the Transformer architecture)},
  author = {Vaswani, A. and Shazeer, N. and Parmar, N. and Uszkoreit, J. and Jones, L. and Gomez, A. N. and Kaiser, L. and Polosukhin, I.},
  year = {2017},
  journal = {NeurIPS 2017},
  url = {https://arxiv.org/abs/1706.03762},
  abstract = {Vaswani et al. (2017) introduced the Transformer, a sequence-to-sequence architecture based entirely on self-attention and feed-forward layers, dispensing with recurrence and convolution. The attention mechanism allows every position in a sequence to attend to every other position in parallel, making both training and inference substantially more scalable than recurrent architectures. The Transformer became the architectural substrate of BERT, GPT, DALL-E, the denoising U-Nets in diffusion models and the motion-generation models used in animation research. Every major generative tool in the repository's collection either is a Transformer or is conditioned by one.},
  keywords = {generative-ai, ai-literacy},
  note = {AI \& Animation Education Knowledge Base}
}