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

arXiv: https://arxiv.org/abs/2601.11641 · HTML: https://mlsanity.com/paper/2601.11641/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Placed in Video generation, one of 14 directions in Diffusion models.
- Builds on 31 of its 43 references that are in the map.
- First posted on arXiv 14 Jan 2026.

## Placed in

- Diffusion models / [Video generation](https://mlsanity.com/diffusion/video-generation/)

## Builds on (most cited first, 30 of 31)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022)
- [Longformer: The Long-Document Transformer](https://mlsanity.com/paper/2004.05150/) (2020)
- [Wan: Open and Advanced Large-Scale Video Generative Models](https://mlsanity.com/paper/2503.20314/) (2025)
- [FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning](https://mlsanity.com/paper/2307.08691/) (2023)
- [Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets](https://mlsanity.com/paper/2311.15127/) (2023)
- [Prompt-to-Prompt Image Editing with Cross Attention Control](https://mlsanity.com/paper/2208.01626/) (2022)
- [CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer](https://mlsanity.com/paper/2408.06072/) (2024)
- [HunyuanVideo: A Systematic Framework For Large Video Generative Models](https://mlsanity.com/paper/2412.03603/) (2024)
- [AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning](https://mlsanity.com/paper/2307.04725/) (2023)
- [Plug-and-Play Diffusion Features for Text-Driven Image-to-Image Translation](https://mlsanity.com/paper/2211.12572/) (2022)
- [Open-Sora: Democratizing Efficient Video Production for All](https://mlsanity.com/paper/2412.20404/) (2024)
- [FateZero: Fusing Attentions for Zero-shot Text-based Video Editing](https://mlsanity.com/paper/2303.09535/) (2023)
- [Timestep Embedding Tells: It's Time to Cache for Video Diffusion Model](https://mlsanity.com/paper/2411.19108/) (2024)
- [Sparse VideoGen: Accelerating Video Diffusion Transformers with Spatial-Temporal Sparsity](https://mlsanity.com/paper/2502.01776/) (2025)
- [SageAttention: Accurate 8-Bit Attention for Plug-and-play Inference Acceleration](https://mlsanity.com/paper/2410.02367/) (2024)
- [FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference](https://mlsanity.com/paper/2502.20766/) (2025)
- [FasterCache: Training-Free Video Diffusion Model Acceleration with High Quality](https://mlsanity.com/paper/2410.19355/) (2024)
- [SpargeAttention: Accurate and Training-free Sparse Attention Accelerating Any Model Inference](https://mlsanity.com/paper/2502.18137/) (2025)
- [Adaptive Caching for Faster Video Generation with Diffusion Transformers](https://mlsanity.com/paper/2411.02397/) (2024)
- [Sparse VideoGen2: Accelerate Video Generation with Sparse Attention via Semantic-Aware Permutation](https://mlsanity.com/paper/2505.18875/) (2025)
- [Radial Attention: O(nlog n) Sparse Attention with Energy Decay for Long Video Generation](https://mlsanity.com/paper/2506.19852/) (2025)
- [Sparse-vDiT: Unleashing the Power of Sparse Attention to Accelerate Video Diffusion Transformers](https://mlsanity.com/paper/2506.03065/) (2025)
- [NAT: Neural Architecture Transformer for Accurate and Compact Architectures](https://mlsanity.com/paper/1910.14488/) (2019)
- [Accelerating Diffusion Transformer via Gradient-Optimized Cache](https://mlsanity.com/paper/2503.05156/) (2025)
- [QVD: Post-training Quantization for Video Diffusion Models](https://mlsanity.com/paper/2407.11585/) (2024)
- [LiteAttention: A Temporal Sparse Attention for Diffusion Transformers](https://mlsanity.com/paper/2511.11062/) (2025)

## Built on by (most cited first, 8 of 8)

- [SVG-EAR: Parameter-Free Linear Compensation for Sparse Video Generation via Error-aware Routing](https://mlsanity.com/paper/2603.08982/) (2026)
- [DFSAttn: Dynamic Fine-grained Sparse Attention for Efficient Video Generation](https://mlsanity.com/paper/2605.23445/) (2026)
- [RoPeSLR: 3D RoPE-driven Sparse-LowRank Attention for Efficient Diffusion Transformers](https://mlsanity.com/paper/2605.20659/) (2026)
- [Sparse Mixture-of-Experts Routing in Visual Diffusion Transformers:Diagnosis, Boundary Calibration and Evolutionary Roadmap from Routing Collapse to Selective Deadlock](https://mlsanity.com/paper/2605.19378/) (2026)
- [RoLA: Rotary-Positioned Low-Rank Linear Attention for Efficient Diffusion Transformers](https://mlsanity.com/paper/2609.06712/) (2026)
- [SCOPE: Subspace Clustering with Online Per-Head Top-K Estimation for Sparse Video Attention](https://mlsanity.com/paper/2608.12780/) (2026)
- [SparkDiffusion: Mitigating the High-Sparsity Trap --- A Unified Framework for up to 265× Single-GPU Acceleration of Visual Generation](https://mlsanity.com/paper/2609.23153/) (2026)
- [Parameterized Stripe Attention for Efficient Video Generation](https://mlsanity.com/paper/2609.37001/) (2026)

## Abstract (arXiv)

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. Although sparse attention methods attempt to address this challenge, existing approaches either rely on oversimplified static patterns or require computationally expensive sampling operations to achieve dynamic sparsity, resulting in inaccurate pattern predictions and degraded generation quality. To overcome these limitations, we propose a underlineMixture-underlineOf-underlineDistribution DiT (MOD-DiT), a novel sampling-free dynamic attention framework that accurately models evolving attention patterns through a two-stage process. First, MOD-DiT leverages prior information from early denoising steps and adopts a distributed mixing approach to model an efficient linear approximation model, which is then used to predict mask patterns for a specific denoising interval. Second, an online block masking strategy dynamically applies these predicted masks while maintaining historical sparsity information, eliminating the need for repetitive sampling operations. Extensive evaluations demonstrate consistent acceleration and quality improvements across multiple benchmarks and model architectures, validating MOD-DiT's effectiveness for efficient, high-quality video generation while overcoming the computational limitations of traditional sparse attention approaches.