Redirecting to original paper in 30 seconds...

Click below to go immediately or wait for automatic redirect

arxiv_cv 98% Match Research Paper Researchers in generative AI,Developers of image/video generation tools,Machine learning engineers 2 weeks ago

Re-ttention: Ultra Sparse Visual Generation via Attention Statistical Reshape

computer-vision › diffusion-models
📄 Abstract

Abstract: Diffusion Transformers (DiT) have become the de-facto model for generating high-quality visual content like videos and images. A huge bottleneck is the attention mechanism where complexity scales quadratically with resolution and video length. One logical way to lessen this burden is sparse attention, where only a subset of tokens or patches are included in the calculation. However, existing techniques fail to preserve visual quality at extremely high sparsity levels and might even incur non-negligible compute overheads. To address this concern, we propose Re-ttention, which implements very high sparse attention for visual generation models by leveraging the temporal redundancy of Diffusion Models to overcome the probabilistic normalization shift within the attention mechanism. Specifically, Re-ttention reshapes attention scores based on the prior softmax distribution history in order to preserve the visual quality of the full quadratic attention at very high sparsity levels. Experimental results on T2V/T2I models such as CogVideoX and the PixArt DiTs demonstrate that Re-ttention requires as few as 3.1% of the tokens during inference, outperforming contemporary methods like FastDiTAttn, Sparse VideoGen and MInference.
Authors (5)
Ruichen Chen
Keith G. Mills
Liyao Jiang
Chao Gao
Di Niu
Submitted
May 28, 2025
arXiv Category
cs.CV
arXiv PDF

Key Contributions

Proposes Re-ttention, a method for achieving very high sparse attention in Diffusion Transformers for visual generation. It leverages temporal redundancy and reshapes attention scores based on prior softmax distribution history to preserve visual quality at extreme sparsity levels, overcoming limitations of existing sparse attention techniques.

Business Value

Enables faster and more efficient generation of high-quality images and videos, reducing computational costs and enabling applications with limited resources.