Bidirectional Sparse Attention for Faster Video Diffusion Training

• URL: http://arxiv.org/abs/2509.01085v3
• Date: Thu, 11 Sep 2025 06:16:31 GMT
• Title: Bidirectional Sparse Attention for Faster Video Diffusion Training
• Authors: Chenlu Zhan, Wen Li, Chuyu Shen, Jun Zhang, Suhui Wu, Hao Zhang,
• Abstract summary: Video diffusion Transformer (DiT) models excel in generative quality but hit major computational bottlenecks when producing high-resolution, long-duration videos.<n>We propose a Bidirectional Sparse Attention (BSA) framework for faster video DiT training, the first to dynamically sparsify both Queries and Key-Value pairs within 3D full attention.<n>BSA significantly accelerates DiT training across long sequences, reducing FLOPs by up to 20x and achieving 17.79x faster attention training, while preserving or even surpassing the generative quality of full attention.
• Score: 14.523882232476092
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Video diffusion Transformer (DiT) models excel in generative quality but hit major computational bottlenecks when producing high-resolution, long-duration videos. The quadratic complexity of full attention leads to prohibitively high training and inference costs. Full attention inefficiency stems from two key challenges: excessive computation due to the inherent sparsity of Queries and Key-Value pairs, and redundant computation as fixed sparse patterns fail to leverage DiT's dynamic attention. To overcome this limitation, we propose a Bidirectional Sparse Attention (BSA) framework for faster video DiT training, the first to dynamically sparsify both Queries and Key-Value pairs within 3D full attention, thereby substantially improving training and inference efficiency. BSA addresses these issues through two key components. Query sparsity is optimized by selecting the most informative query tokens via semantic similarity and with a dynamic spatial-time training strategy, while KV sparsity is achieved by computing a statistical dynamic threshold to retain only the most salient KV blocks for computation. Extensive experiments demonstrate that BSA significantly accelerates DiT training across long sequences, reducing FLOPs by up to 20x and achieving 17.79x faster attention training, while preserving or even surpassing the generative quality of full attention.

Related papers

• Training-free Context-adaptive Attention for Efficient Long Context Modeling [57.703159205740185]
  Training-free Context-adaptive Attention (TCA-Attention) is a training-free sparse attention mechanism that selectively attends to only the informative tokens for efficient long-context inference.<n>TCA-Attention achieves a 2.8$times$ speedup and reduces KV cache by 61% at 128K context length while maintaining performance comparable to full attention.
  arXiv  Detail & Related papers  (2025-12-10T01:54:57Z)
• InfiniteVL: Synergizing Linear and Sparse Attention for Highly-Efficient, Unlimited-Input Vision-Language Models [49.08289742711585]
  We propose InfiniteVL, a linear-complexity VLM architecture that synergizes sliding window attention (SWA) with Gated DeltaNet.<n>We show that InfiniteVL achieves over 3.6times inference speedup while maintaining constant latency and memory footprint.<n>In streaming video understanding scenarios, it sustains a stable 24 FPS real-time prefill speed while preserving long-term memory cache.
  arXiv  Detail & Related papers  (2025-12-09T17:18:32Z)
• BitStopper: An Efficient Transformer Attention Accelerator via Stage-fusion and Early Termination [14.53308613746613]
  BitStopper is a fine-grained algorithm-architecture co-design that operates without a sparsity predictor.<n>It achieves 2.03x and 1.89x speedups over Sanger and SOFA, respectively, while delivering 2.4x and 2.1x improvements in energy efficiency.
  arXiv  Detail & Related papers  (2025-12-06T14:44:38Z)
• USV: Unified Sparsification for Accelerating Video Diffusion Models [11.011602744993942]
  Unified Sparsification for Video diffusion models is an end-to-end trainable framework.<n>It orchestrates sparsification across both the model's internal computation and its sampling process.<n>It achieves up to 83.3% speedup in the denoising process and 22.7% end-to-end acceleration, while maintaining high visual fidelity.
  arXiv  Detail & Related papers  (2025-12-05T14:40:06Z)
• VMoBA: Mixture-of-Block Attention for Video Diffusion Models [29.183614108287276]
  This paper introduces Video Mixture of Block Attention (VMoBA), a novel attention mechanism specifically adapted for Video Diffusion Models (VDMs)<n>Motivated by an in-depth analysis of attention patterns within pre-trained video transformers, VMoBA enhances the original MoBA framework with three key modifications.<n>Experiments demonstrate that VMoBA significantly accelerates the training of VDMs on longer sequences, achieving 2.92x FLOPs and 1.48x latency speedup.
  arXiv  Detail & Related papers  (2025-06-30T13:52:31Z)
• FullDiT2: Efficient In-Context Conditioning for Video Diffusion Transformers [63.788600404496115]
  FullDiT2 is an efficient in-context conditioning framework for general controllability in both video generation and editing tasks.<n>FullDiT2 achieves significant computation reduction and 2-3 times speedup in averaged time cost per diffusion step.
  arXiv  Detail & Related papers  (2025-06-04T17:57:09Z)
• Sparse-vDiT: Unleashing the Power of Sparse Attention to Accelerate Video Diffusion Transformers [24.105473321347894]
  We propose Sparse-vDiT, a sparsity acceleration framework for Video Diffusion Transformer (vDiT)<n>We show that Sparse-vDiT achieves 2.09$times$, 2.38$times$, and 1.67$times$ theoretical FLOP reduction, and actual inference speedups of 1.76$times$, 1.85$times$, and 1.58$times$, respectively.<n>Our work demonstrates that latent structural sparsity in vDiTs can be systematically exploited for long video synthesis.
  arXiv  Detail & Related papers  (2025-06-03T16:42:37Z)
• VORTA: Efficient Video Diffusion via Routing Sparse Attention [45.269274789183974]
  Video Diffusion Transformers (VDiTs) have achieved remarkable progress in high-quality video generation, but remain computationally expensive.<n>We propose VORTA, an acceleration framework with two novel components.<n>It achieves a $1.76times$ end-to-end speedup without quality loss on VBench.
  arXiv  Detail & Related papers  (2025-05-24T17:46:47Z)
• VSA: Faster Video Diffusion with Trainable Sparse Attention [21.593548582058403]
  Scaling video diffusion transformers (DiTs) is limited by their quadratic 3D attention, even though most of the attention mass concentrates on a small subset of positions.<n>We turn this observation into VSA, a trainable, hardware-efficient sparse attention that replaces full attention at emphboth training and inference.
  arXiv  Detail & Related papers  (2025-05-19T17:30:13Z)
• DSV: Exploiting Dynamic Sparsity to Accelerate Large-Scale Video DiT Training [85.04885553561164]
  Diffusion Transformers (DiTs) have shown remarkable performance in generating high-quality videos.<n>DiTs can consume up to 95% of processing time and demand specialized context parallelism.<n>This paper introduces DSV to accelerate video DiT training by leveraging the dynamic attention sparsity we empirically observe.
  arXiv  Detail & Related papers  (2025-02-11T14:39:59Z)
• Sparser is Faster and Less is More: Efficient Sparse Attention for Long-Range Transformers [58.5711048151424]
  We introduce SPARSEK Attention, a novel sparse attention mechanism designed to overcome computational and memory obstacles. Our approach integrates a scoring network and a differentiable top-k mask operator, SPARSEK, to select a constant number of KV pairs for each query. Experimental results reveal that SPARSEK Attention outperforms previous sparse attention methods.
  arXiv  Detail & Related papers  (2024-06-24T15:55:59Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.