MC-Sparse: Deconstructing and Closing the Dense-Sparse Attention Gap in Diffusion Transformers
Paper recorded by Signals 4 on 2026-10-05 in cs.AI. Abstract reproduced from arXiv; link to the original below.
Published 2026-10-05 on arXiv · recorded by Signals 4 on 2026-10-06
Category: cs.AI · 人工智能 · first seen 2026-10-06
Abstract
Sparse attention is a primary approach to reducing the latency of diffusion transformers in long-sequence generation tasks, such as video and high-resolution 3D asset generation. However, existing methods can degrade generation quality and fidelity at high sparsity levels. Through controlled oracle comparisons, we trace this degradation to three sources: constraints imposed by token grouping, inac
Read on arXiv →
Cite this page: MC-Sparse: Deconstructing and Closing the Dense-Sparse Attention Gap in Diffusion Transformers: the #454 most recent of 980 cs.AI papers we have recorded (as of 2026-10-05). Source: Signals 4 (Signals API) — https://data.jiangzhang.ca/signals4/t/papers/mc-sparse-deconstructing-and-closing-the-dense-sparse-attention-gap-in-diffusion.html
Free to quote with attribution to “Signals 4 (Signals API)”. Machine-readable:
papers.json
Get 4 AI signals a day by email — free.
Get 4 AI signals a day by email — free