Thread
John Langford on "Full-bandwidth Transformer"
The senior author quotes the lead author's thread and gives the paper in one sentence: modifying transformer training to support recursive state turns out to be both easy and desirable by all measures.
The posts are embedded from X. The figure notes under them are written by this wiki.
This is a fun project: Modifying transformer training to support recursive state turns out to be both easy and desirable by all measures. https://t.co/etucnAy3M3
— John Langford (@JohnCLangford) August 11, 2026