Firehose

29 OCT 2026 · Paper

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

This paper introduces a new architecture for generative transformers that allows them to capture finer details without increasing the length of the global attention sequence, making them more efficient and effective. Practitioners may care about this approach as it could lead to significant improvements in image and text generation models.

generative transformers pixel-space models rectified-flow transformers DCT coefficients local attention spectral subdivision

Browse by tag

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