On This Day in AI History

"Attention Is All You Need" introduces the Transformer

Google researchers posted 'Attention Is All You Need' to arXiv on June 12, 2017, introducing the Transformer architecture built entirely on attention mechanisms rather than recurrence or convolution. The design enabled far more parallelizable training and better long-range modeling. It became the foundation for virtually all modern large language models, including the GPT and BERT families.