Read, Allocate, Route: Role-Coupled Tokenization for Pixel-Space Generative Transformers

Paper recorded by Signals 4 on 2026-10-29 in cs.AI. Abstract reproduced from arXiv; link to the original below.

Published 2026-10-29 on arXiv · recorded by Signals 4 on 2026-10-30

Category: cs.AI · 人工智能 · first seen 2026-10-30

Abstract

Pixel-space generative Transformers typically use one token per image patch, so capturing finer detail requires more tokens and makes global attention increasingly expensive. We observe that finer detail does not necessarily require more global communication: low-frequency structure benefits from global exchange, while high-frequency detail can be modeled locally. Based on this insight, we introdu

Read on arXiv →