Cover Image

BLADE: Block-Sparse Attention Meets Step Distillation for Efficient Video Generation

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Gu, Youping, Li, Xiaolong, Hu, Yuhao, Chen, Minqi, Zhuang, Bohan
Format:	Preprint
Published:	2025
Subjects:	Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

PSA: Pyramid Sparse Attention for Efficient Video Understanding and Generation
by: Li, Xiaolong, et al.
Published: (2025)

FlashBlock: Attention Caching for Efficient Long-Context Block Diffusion
by: Chen, Zhuokun, et al.
Published: (2026)

Consistent Flow Distillation for Text-to-3D Generation
by: Yan, Runjie, et al.
Published: (2025)

Radial Attention: $O(n\log n)$ Sparse Attention with Energy Decay for Long Video Generation
by: Li, Xingyang, et al.
Published: (2025)

Sparse-vDiT: Unleashing the Power of Sparse Attention to Accelerate Video Diffusion Transformers
by: Chen, Pengtao, et al.
Published: (2025)

VideoNSA: Native Sparse Attention Scales Video Understanding
by: Song, Enxin, et al.
Published: (2025)

Generalized Neighborhood Attention: Multi-dimensional Sparse Attention at the Speed of Light
by: Hassani, Ali, et al.
Published: (2025)

Rectified SpaAttn: Revisiting Attention Sparsity for Efficient Video Generation
by: Liu, Xuewen, et al.
Published: (2025)

pi-Flow: Policy-Based Few-Step Generation via Imitation Distillation
by: Chen, Hansheng, et al.
Published: (2025)

SparseSwin: Swin Transformer with Sparse Transformer Block
by: Pinasthika, Krisna, et al.
Published: (2023)

Score identity Distillation: Exponentially Fast Distillation of Pretrained Diffusion Models for One-Step Generation
by: Zhou, Mingyuan, et al.
Published: (2024)

Adaptive Video Distillation: Mitigating Oversaturation and Temporal Collapse in Few-Step Generation
by: You, Yuyang, et al.
Published: (2026)

SANA-Video: Efficient Video Generation with Block Linear Diffusion Transformer
by: Chen, Junsong, et al.
Published: (2025)

Denoising Score Distillation: From Noisy Diffusion Pretraining to One-Step High-Quality Generation
by: Chen, Tianyu, et al.
Published: (2025)

Transition Matching Distillation for Fast Video Generation
by: Nie, Weili, et al.
Published: (2026)

Beyond Conventional Transformers: The Medical X-ray Attention (MXA) Block for Improved Multi-Label Diagnosis Using Knowledge Distillation
by: Rand, Amit, et al.
Published: (2025)

VideoGPA: Distilling Geometry Priors for 3D-Consistent Video Generation
by: Du, Hongyang, et al.
Published: (2026)

AnyFlow: Any-Step Video Diffusion Model with On-Policy Flow Map Distillation
by: Gu, Yuchao, et al.
Published: (2026)

Diffusion Adversarial Post-Training for One-Step Video Generation
by: Lin, Shanchuan, et al.
Published: (2025)

DiffCLIP: Differential Attention Meets CLIP
by: Hammoud, Hasan Abed Al Kader, et al.
Published: (2025)

Ride the Wave: Precision-Allocated Sparse Attention for Smooth Video Generation
by: Zhang, Wentai, et al.
Published: (2026)

Make It Efficient: Dynamic Sparse Attention for Autoregressive Image Generation
by: Xiang, Xunzhi, et al.
Published: (2025)

VARestorer: One-Step VAR Distillation for Real-World Image Super-Resolution
by: Zhu, Yixuan, et al.
Published: (2026)

One-Step Diffusion Distillation through Score Implicit Matching
by: Luo, Weijian, et al.
Published: (2024)

DistillKac: Few-Step Image Generation via Damped Wave Equations
by: Han, Weiqiao, et al.
Published: (2025)

Efficient Video Diffusion with Sparse Information Transmission for Video Compression
by: Zhou, Mingde, et al.
Published: (2026)

Prism: Spectral-Aware Block-Sparse Attention
by: Wang, Xinghao, et al.
Published: (2026)

Efficient Image Generation with Variadic Attention Heads
by: Walton, Steven, et al.
Published: (2022)

Flash-DMD: Towards High-Fidelity Few-Step Image Generation with Efficient Distillation and Joint Reinforcement Learning
by: Chen, Guanjie, et al.
Published: (2025)

AdaCluster: Adaptive Query-Key Clustering for Sparse Attention in Video Generation
by: Tan, Haoyue, et al.
Published: (2026)

COMODO: Cross-Modal Video-to-IMU Distillation for Efficient Egocentric Human Activity Recognition
by: Chen, Baiyu, et al.
Published: (2025)

SpikeVideoFormer: An Efficient Spike-Driven Video Transformer with Hamming Attention and $\mathcal{O}(T)$ Complexity
by: Zou, Shihao, et al.
Published: (2025)

SLA2: Sparse-Linear Attention with Learnable Routing and QAT
by: Zhang, Jintao, et al.
Published: (2026)

Vision-Language Meets the Skeleton: Progressively Distillation with Cross-Modal Knowledge for 3D Action Representation Learning
by: Chen, Yang, et al.
Published: (2024)

One-Step is Enough: Sparse Autoencoders for Text-to-Image Diffusion Models
by: Surkov, Viacheslav, et al.
Published: (2024)

Motion meets Attention: Video Motion Prompts
by: Chen, Qixiang, et al.
Published: (2024)

InteractiveVideo: User-Centric Controllable Video Generation with Synergistic Multimodal Instructions
by: Zhang, Yiyuan, et al.
Published: (2024)

Self-Attention through Kernel-Eigen Pair Sparse Variational Gaussian Processes
by: Chen, Yingyi, et al.
Published: (2024)

BSA: Ball Sparse Attention for Large-scale Geometries
by: Brita, Catalin E., et al.
Published: (2025)

On the Diversity and Realism of Distilled Dataset: An Efficient Dataset Distillation Paradigm
by: Sun, Peng, et al.
Published: (2023)