Prehistory — From Neural Networks to the TransformerNal Kalchbrenner et al. (DeepMind)Google DeepMind
DeepMind publishes Neural Machine Translation in Linear Time (ByteNet) on arXiv
Neural Machine Translation in Linear Time (ByteNet) released on arXiv
Why it matters
An alternative that processed sequences with dilated convolutions instead of recurrence. One branch of the race to move beyond recurrence
Source — Primary sources first; secondary reports are labelled “Press”
Paperarxiv.orghttps://arxiv.org/abs/1610.10099Added in Week 35, 2026 · See that week