← Back to all news
arXiv Computer Vision By Yun Dai, Yuyun Chen, Jiarui Wen, Huiping Zhuang, Cen Chen, Ziqian Zeng

Sparse Attention for Video Generation Acceleration via Growing Sparsity and Reduced Search

Read the original on arXiv Computer Vision →

The paper introduces Growing Sparsity and Reduced Search (GSRS), a training‑free framework that accelerates Diffusion Transformers for video generation by progressively increasing sparsity and reusing early attention blocks to limit search space. GSRS uses Top‑p selection for adaptive sparsity and a precise evaluation scheme that computes exact attention weights with negligible overhead. Experiments on HunyuanVideo and Wan 2.1 show 1.55×–2.21× speedups while preserving generation quality comparable to full attention.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.

Related stories

arXiv Machine Learning
Jul 2

Mixture of Distributions Matters: Dynamic Sparse Attention for Efficient Video Diffusion Transformers

arXiv:2601. 11641v3 Announce Type: replace-cross Abstract: While Diffusion Transformers (DiTs) have achieved notable progress in video generation, this long-sequence generation task remains constrained by the quadratic complexity inherent to self-attention mechanisms, creating significant barriers to practical deployment.

By Yuxi Liu, Yipeng Hu, Zekun Zhang, Kunze Jiang, Kun Yuan
llmsdiffusionefficiencybenchmarks
More like this →
arXiv Computer Vision
Oct 9

iCATS: Fast Video Generation via Interaction-Aware Sparse Attention and Timestep-Adaptive Sparsity

iCATS introduces a training‑free sparse attention mechanism for Diffusion Transformers that accelerates video generation by reducing computations. It improves importance estimation by clustering query‑key dot‑product interactions and reformulates the objective as a quadratic form for low‑cost computation. The method also adapts sparsity dynamically across denoising timesteps using an SNR‑guided schedule and employs a tail‑merging strategy to enhance GPU kernel utilization, achieving significant speedups while maintaining high PSNR scores.

By Chengfeng Han, Baole Ai, Xianlu Bian, Jie Yao, Zilong Huang, Ang Wang, Dandan Ding
llmsdiffusionfine-tuningefficiencybenchmarks
More like this →
arXiv Computer Vision
Sep 28

Where Compute Matters: Heterogeneous Attention for Efficient Video Diffusion

The paper introduces HetA-DiT, a heterogeneous attention mechanism for video diffusion models that allocates computation based on token difficulty. A lightweight uncertainty branch predicts denoising difficulty, routing uncertain tokens through dense global attention while applying efficient local attention to reliable tokens. This adaptive routing retains global context where needed, offers a single parameter to balance quality and efficiency, and achieves competitive generation quality while only about 20% of tokens use dense attention.

By Olga Zatsarynna, Denis Korzhenkov, Juergen Gall, Amir Habibian, Mohsen Ghafoorian
llmsdiffusionefficiency
More like this →