Prehistory — From Neural Networks to the TransformerKyunghyun Cho et al. (Université de Montréal)Kyunghyun Cho
Cho et al. publish Learning Phrase Representations using RNN Encoder-Decoder
Learning Phrase Representations using RNN Encoder-Decoder released on arXiv — proposed the GRU
Why it matters
Brought the encoder-decoder architecture and the GRU to machine translation, laying the groundwork for attention research
Source — Primary sources first; secondary reports are labelled “Press”
Paperarxiv.orghttps://arxiv.org/abs/1406.1078Added in Week 35, 2026 · See that week