Research paper

Attention Is All You Need

Vaswani et al. · 2017 · NeurIPS

The transformer paper: the architecture behind current language models, cited here because most arguments about AI and knowledge rest on it.

Marginalia

Read in the margins

Highlight a passage, write beside it, and let an argument grow out of a single paragraph.

No passages highlighted yet. Be the first to mark one.

Passages saved by readers

We propose a new simple network architecture, the Transformer, based solely on attention mechanisms, dispensing with recurrence and convolutions entirely.

Abstract · saved by Lian Chen

Ideas generated by this source

Propositions raised or defended with this text.

Added to the library 12 Jan 2026.