Which contributor to the Transformer model is most recognized for their work on the attention mechanism that underpins its architecture?

The Transformer’s key idea is the attention mechanism, and the person most credited with its development for this model is Ashish Vaswani. In the 2017 paper that introduced the Transformer, Vaswani and his co‑authors formalized “scaled dot‑product attention” as the core building block, replacing recurrent layers with a self‑attention layer that can look at all positions in a sentence at once. This approach lets the model learn relationships between words regardless of distance, and it has become the foundation for all subsequent transformer‑based models. For example, when translating “the quick brown fox,” the attention mechanism lets the model instantly compare “quick” with “brown” and “fox” to decide the best translation, without needing to read the sentence word by word.