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 det
SpecSlot improves pixel-space generative Transformers by using localized spectral slots and restricted global attention to increase image detail without raising computational cost.
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 introduce SpecSlot, a pixel-space rectified-flow Transformer that decouples output detail from the length of the global attention sequence. SpecSlot expands each spatial anchor into multiple slots, each assigned a disjoint band of DCT coefficients; this separates anchor density from spectral subdivision.…
Summary and abstract excerpt via Hugging Face Papers ↗ · arXiv.
Read, Allocate, Route: Role-Coupled Tokenization for Pixel-Space Generative Transformers was first seen on Hugging Face · Daily papers on Oct 30, 2026. Since then it has appeared in 13 checks on 2 different days. Its best position was #7 of 30, reached on Oct 31, 03:28 UTC. It is #8 right now, climbing from #10 to #8 over the last 6 checks.
Position on Hugging Face · Daily papers at every check (lower is better).
Best rank per day (UTC).
▲ as reported by Hugging Face.
Yes. As of Oct 31, 09:28 UTC it is #8, climbing from #10 to #8 over the last 6 checks.
#7 on Hugging Face · Daily papers, on Oct 31, 03:28 UTC. Trendoday checks this list every 120 minutes.
It was first seen on Oct 30, 2026 and has been on the list on 2 days (13 checks) since.