activity
20182026
most citedImproved training of end-to-end attention models for speech recognition

282 citations · 917 across the 32 of their papers we have counts for

collaborators
Showing 2025Show all

1 paper · 1 filter

cs.LG2025

Why Are Positional Encodings Nonessential for Deep Autoregressive Transformers? Revisiting a Petroglyph

Kazuki Irie

Do autoregressive Transformer language models require explicit positional encodings (PEs)? The answer is 'no' provided they have more than one layer -- they can distinguish sequenc…