Image de couverture de livre

LVSA: Training-Free Sparse Attention for Long Video Diffusion

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Glorian, Gael, Lamprou, Ioannis, Zhang, Zhen, Yuan, Yujie, Liu, Hongsheng
Format:	Preprint
Publié:	2026
Sujets:	Computer Vision and Pattern Recognition Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Mixture of Distributions Matters: Dynamic Sparse Attention for Efficient Video Diffusion Transformers
par: Liu, Yuxi, et autres
Publié: (2026)

Sparse Forcing: Native Trainable Sparse Attention for Real-time Autoregressive Diffusion Video Generation
par: Xu, Boxun, et autres
Publié: (2026)

Attention Frequency Modulation: Training-Free Spectral Modulation of Diffusion Cross-Attention
par: Oh, Seunghun, et autres
Publié: (2026)

Sparse-to-Sparse Training of Diffusion Models
par: Oliveira, Inês Cardoso, et autres
Publié: (2025)

RoPeSLR: 3D RoPE-driven Sparse-LowRank Attention for Efficient Diffusion Transformers
par: Liu, Yuxi, et autres
Publié: (2026)

Sparse-vDiT: Unleashing the Power of Sparse Attention to Accelerate Video Diffusion Transformers
par: Chen, Pengtao, et autres
Publié: (2025)

Radial Attention: $O(n\log n)$ Sparse Attention with Energy Decay for Long Video Generation
par: Li, Xingyang, et autres
Publié: (2025)

$\infty$-Video: A Training-Free Approach to Long Video Understanding via Continuous-Time Memory Consolidation
par: Santos, Saul, et autres
Publié: (2025)

Sparse VideoGen: Accelerating Video Diffusion Transformers with Spatial-Temporal Sparsity
par: Xi, Haocheng, et autres
Publié: (2025)

Training-free and Adaptive Sparse Attention for Efficient Long Video Generation
par: Xia, Yifei, et autres
Publié: (2025)

Towards Sparse Video Understanding and Reasoning
par: Xu, Chenwei, et autres
Publié: (2026)

Video Reconstruction using Diffusion-based Image-to-Video Generation with Trajectory Guidance
par: Bompai, Stelio, et autres
Publié: (2026)

Bidirectional Sparse Attention for Faster Video Diffusion Training
par: Zhan, Chenlu, et autres
Publié: (2025)

VideoNSA: Native Sparse Attention Scales Video Understanding
par: Song, Enxin, et autres
Publié: (2025)

Towards Better Alignment: Training Diffusion Models with Reinforcement Learning Against Sparse Rewards
par: Hu, Zijing, et autres
Publié: (2025)

MMInference: Accelerating Pre-filling for Long-Context VLMs via Modality-Aware Permutation Sparse Attention
par: Li, Yucheng, et autres
Publié: (2025)

NODI: Out-Of-Distribution Detection with Noise from Diffusion
par: Zhou, Jingqiu, et autres
Publié: (2024)

DiffusionOPD: A Unified Perspective of On-Policy Distillation in Diffusion Models
par: Li, Quanhao, et autres
Publié: (2026)

No Training, No Problem: Rethinking Classifier-Free Guidance for Diffusion Models
par: Sadat, Seyedmorteza, et autres
Publié: (2024)

Zero-Shot Video Restoration and Enhancement Using Pre-Trained Image Diffusion Model
par: Cao, Cong, et autres
Publié: (2024)

Tarsier: Recipes for Training and Evaluating Large Video Description Models
par: Wang, Jiawei, et autres
Publié: (2024)

OmniSparse: Training-Aware Fine-Grained Sparse Attention for Long-Video MLLMs
par: Chen, Feng, et autres
Publié: (2025)

Corruption-Aware Training of Latent Video Diffusion Models for Robust Text-to-Video Generation
par: Maduabuchi, Chika, et autres
Publié: (2025)

LightCache: Memory-Efficient, Training-Free Acceleration for Video Generation
par: Xiao, Yang, et autres
Publié: (2025)

Leveraging Latent Diffusion Models for Training-Free In-Distribution Data Augmentation for Surface Defect Detection
par: Girella, Federico, et autres
Publié: (2024)

PSA: Pyramid Sparse Attention for Efficient Video Understanding and Generation
par: Li, Xiaolong, et autres
Publié: (2025)

Cyclic Sparse Training: Is it Enough?
par: Gadhikar, Advait, et autres
Publié: (2024)

SmartFRZ: An Efficient Training Framework using Attention-Based Layer Freezing
par: Li, Sheng, et autres
Publié: (2024)

Light Interaction: Training-Free Inference Acceleration for Interactive Video World Models
par: Lu, Jiacheng, et autres
Publié: (2026)

Asymmetric Co-Training for Source-Free Few-Shot Domain Adaptation
par: Li, Gengxu, et autres
Publié: (2025)

FIS-DiT: Breaking the Few-Step Video Inference Barrier via Training-Free Frame Interleaved Sparsity
par: Tang, Jian, et autres
Publié: (2026)

SpargeAttention: Accurate and Training-free Sparse Attention Accelerating Any Model Inference
par: Zhang, Jintao, et autres
Publié: (2025)

TAP: A Token-Adaptive Predictor Framework for Training-Free Diffusion Acceleration
par: Zhu, Haowei, et autres
Publié: (2026)

Exploiting the Exact Denoising Posterior Score in Training-Free Guidance of Diffusion Models
par: Bellchambers, Gregory
Publié: (2025)

AnimateLCM: Computation-Efficient Personalized Style Video Generation without Personalized Video Data
par: Wang, Fu-Yun, et autres
Publié: (2024)

Dynamic Sparse Training with Structured Sparsity
par: Lasby, Mike, et autres
Publié: (2023)

Attend Locally, Remember Linearly: Linear Attention as Cross-Frame Memory for Autoregressive Video Diffusion
par: Li, Kunyang, et autres
Publié: (2026)

Investigating the Effectiveness of Cross-Attention to Unlock Zero-Shot Editing of Text-to-Video Diffusion Models
par: Motamed, Saman, et autres
Publié: (2024)

ManifoldGD: Training-Free Hierarchical Manifold Guidance for Diffusion-Based Dataset Distillation
par: Roy, Ayush, et autres
Publié: (2026)

RB-Modulation: Training-Free Personalization of Diffusion Models using Stochastic Optimal Control
par: Rout, Litu, et autres
Publié: (2024)