Trending

arXiv:2606.19379

How Linear Is a Transformer Feed-Forward Block? Per-Block Linear Recoverability Is Learned, Not Architectural

Jun 12, 2026submitted

153citations

View PDF arXiv page Code4.0k

Preview of How Linear Is a Transformer Feed-Forward Block? Per-Block Linear Recoverability Is Learned, Not Architectural

TL;DR

AI-GENERATED

State-of-the-art research on How Linear Is a Transformer Feed-Forward achieving benchmark breakthroughs.

TASKS

METHODS

Zero-Shot Learning

Related Papers