Imagen de Portada

Trainable Log-linear Sparse Attention for Efficient Diffusion Transformers

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Zhou, Yifan, Xiao, Zeqi, Wei, Tianyi, Yang, Shuai, Pan, Xingang
Formato:	Preprint
Publicado:	2025
Materias:	Computer Vision and Pattern Recognition
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Alias-Free Latent Diffusion Models: Improving Fractional Shift Equivariance of Diffusion Latent Space
por: Zhou, Yifan, et al.
Publicado: (2025)

Video Diffusion Models are Training-free Motion Interpreter and Controller
por: Xiao, Zeqi, et al.
Publicado: (2024)

Trajectory Attention for Fine-grained Video Motion Control
por: Xiao, Zeqi, et al.
Publicado: (2024)

WorldMem: Long-term Consistent World Simulation with Memory
por: Xiao, Zeqi, et al.
Publicado: (2025)

Dense Semantic Matching with VGGT Prior
por: Yang, Songlin, et al.
Publicado: (2025)

TokensGen: Harnessing Condensed Tokens for Long Video Generation
por: Ouyang, Wenqi, et al.
Publicado: (2025)

FreeFlux: Understanding and Exploiting Layer-Specific Roles in RoPE-Based MMDiT for Versatile Image Editing
por: Wei, Tianyi, et al.
Publicado: (2025)

Enhancing MMDiT-Based Text-to-Image Models for Similar Subject Generation
por: Wei, Tianyi, et al.
Publicado: (2024)

VSA: Faster Video Diffusion with Trainable Sparse Attention
por: Zhang, Peiyuan, et al.
Publicado: (2025)

Bokeh Diffusion: Defocus Blur Control in Text-to-Image Diffusion Models
por: Fortes, Armando, et al.
Publicado: (2025)

PISA: Piecewise Sparse Attention Is Wiser for Efficient Diffusion Transformers
por: Li, Haopeng, et al.
Publicado: (2026)

Sparse Forcing: Native Trainable Sparse Attention for Real-time Autoregressive Diffusion Video Generation
por: Xu, Boxun, et al.
Publicado: (2026)

PI-Light: Physics-Inspired Diffusion for Full-Image Relighting
por: Liang, Zhexin, et al.
Publicado: (2026)

Boosting Monocular Metric Depth Estimation via Bokeh Rendering
por: Zhang, Hangwei, et al.
Publicado: (2025)

PnP-U3D: Plug-and-Play 3D Framework Bridging Autoregression and Diffusion for Unified Understanding and Generation
por: Chen, Yongwei, et al.
Publicado: (2026)

SparseDiT: Token Sparsification for Efficient Diffusion Transformer
por: Chang, Shuning, et al.
Publicado: (2024)

Recurrent Autoregressive Diffusion: Global Memory Meets Local Attention
por: Chen, Taiye, et al.
Publicado: (2025)

Efficient Diffusion Transformer with Step-wise Dynamic Attention Mediators
por: Pu, Yifan, et al.
Publicado: (2024)

From Sparse to Dense: Multi-View GRPO for Flow Models via Augmented Condition Space
por: Bu, Jiazi, et al.
Publicado: (2026)

VORTA: Efficient Video Diffusion via Routing Sparse Attention
por: Sun, Wenhao, et al.
Publicado: (2025)

MvDrag3D: Drag-based Creative 3D Editing via Multi-view Generation-Reconstruction Priors
por: Chen, Honghua, et al.
Publicado: (2024)

Mixture of Distributions Matters: Dynamic Sparse Attention for Efficient Video Diffusion Transformers
por: Liu, Yuxi, et al.
Publicado: (2026)

LiteAttention: A Temporal Sparse Attention for Diffusion Transformers
por: Shmilovich, Dor, et al.
Publicado: (2025)

Filter-Guided Diffusion for Controllable Image Generation
por: Gu, Zeqi, et al.
Publicado: (2023)

QuantSparse: Comprehensively Compressing Video Diffusion Transformer with Model Quantization and Attention Sparsification
por: Feng, Weilun, et al.
Publicado: (2025)

Hand2World: Autoregressive Egocentric Interaction Generation via Free-Space Hand Gestures
por: Wang, Yuxi, et al.
Publicado: (2026)

ElasticDiT: Efficient Diffusion Transformers via Elastic Architecture and Sparse Attention for High-Resolution Image Generation on Mobile Devices
por: Du, Kunpeng, et al.
Publicado: (2026)

Live2Diff: Live Stream Translation via Uni-directional Attention in Video Diffusion Models
por: Xing, Zhening, et al.
Publicado: (2024)

Block-Sparse Global Attention for Efficient Multi-View Geometry Transformers
por: Wang, Chung-Shien Brian, et al.
Publicado: (2025)

BinaryAttention: One-Bit QK-Attention for Vision and Diffusion Transformers
por: Xiao, Chaodong, et al.
Publicado: (2026)

MVIP-NeRF: Multi-view 3D Inpainting on NeRF Scenes via Diffusion Prior
por: Chen, Honghua, et al.
Publicado: (2024)

Sprint: Sparse-Dense Residual Fusion for Efficient Diffusion Transformers
por: Park, Dogyun, et al.
Publicado: (2025)

3DEnhancer: Consistent Multi-View Diffusion for 3D Enhancement
por: Luo, Yihang, et al.
Publicado: (2024)

Efficient-vDiT: Efficient Video Diffusion Transformers With Attention Tile
por: Ding, Hangliang, et al.
Publicado: (2025)

I2VEdit: First-Frame-Guided Video Editing via Image-to-Video Diffusion Models
por: Ouyang, Wenqi, et al.
Publicado: (2024)

SP$^2$T: Sparse Proxy Attention for Dual-stream Point Transformer
por: Wan, Jiaxu, et al.
Publicado: (2024)

Efficient Long-Context Modeling in Diffusion Language Models via Block Approximate Sparse Attention
por: Zhang, Wenhu, et al.
Publicado: (2026)

STream3R: Scalable Sequential 3D Reconstruction with Causal Transformer
por: Lan, Yushi, et al.
Publicado: (2025)

Textured 3D Regenerative Morphing with 3D Diffusion Prior
por: Yang, Songlin, et al.
Publicado: (2025)

SpargeAttention2: Trainable Sparse Attention via Hybrid Top-k+Top-p Masking and Distillation Fine-Tuning
por: Zhang, Jintao, et al.
Publicado: (2026)