Skip to main content

Research · Technical

Attention Is All You Need (the Transformer architecture)

NeurIPS 2017 · Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, L., Polosukhin, I. · Jun 2017

Key points

  1. The Transformer replaces recurrence and convolution with self-attention, allowing models to weigh relationships across an entire sequence in parallel.
  2. It is the architectural substrate of the large language and diffusion models underlying current generative image, video and motion tools.
  3. Its scalability enabled the foundation-model era on which the repository's generative-AI entries depend.

Summary

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.

Source

Source: NeurIPS 2017 ↗ (Research)

Cite this item

Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, L. & Polosukhin, I. (2017). ‘Attention Is All You Need (the Transformer architecture)’, NeurIPS 2017. Available at: https://arxiv.org/abs/1706.03762

Your reference manager can also read this page directly: with the Zotero (or Mendeley) browser connector installed, save it straight to your library. Whole-collection exports: RIS, BibTeX, CSL-JSON.