Imagen de Portada

DiTFastAttnV2: Head-wise Attention Compression for Multi-Modality Diffusion Transformers

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Zhang, Hanling, Su, Rundong, Yuan, Zhihang, Chen, Pengtao, Fan, Mingzhu Shen Yibo, Yan, Shengen, Dai, Guohao, Wang, Yu
Formato:	Preprint
Publicado:	2025
Materias:	Computer Vision and Pattern Recognition Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

DiTFastAttn: Attention Compression for Diffusion Transformer Models
por: Yuan, Zhihang, et al.
Publicado: (2024)

VGDFR: Diffusion-based Video Generation with Dynamic Latent Frame Rate
por: Yuan, Zhihang, et al.
Publicado: (2025)

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

DLFR-VAE: Dynamic Latent Frame Rate VAE for Video Generation
por: Yuan, Zhihang, et al.
Publicado: (2025)

E-CAR: Efficient Continuous Autoregressive Image Generation via Multistage Modeling
por: Yuan, Zhihang, et al.
Publicado: (2024)

$Δ$-DiT: A Training-Free Acceleration Method Tailored for Diffusion Transformers
por: Chen, Pengtao, et al.
Publicado: (2024)

VocabTailor: Dynamic Vocabulary Selection for Downstream Tasks in Small Language Models
por: Zhang, Hanling, et al.
Publicado: (2025)

CSKV: Training-Efficient Channel Shrinking for KV Cache in Long-Context Scenarios
por: Wang, Luning, et al.
Publicado: (2024)

ViDiT-Q: Efficient and Accurate Quantization of Diffusion Transformers for Image and Video Generation
por: Zhao, Tianchen, et al.
Publicado: (2024)

ProxyAttn: Guided Sparse Attention via Representative Heads
por: Wang, Yixuan, et al.
Publicado: (2025)

TS-Attn: Temporal-wise Separable Attention for Multi-Event Video Generation
por: Zhang, Hongyu, et al.
Publicado: (2026)

Attn-GS: Attention-Guided Context Compression for Efficient Personalized LLMs
por: Zeng, Shenglai, et al.
Publicado: (2026)

6Bit-Diffusion: Inference-Time Mixed-Precision Quantization for Video Diffusion Models
por: Su, Rundong, et al.
Publicado: (2026)

AttnMod: Attention-Based New Art Styles
por: Su, Shih-Chieh
Publicado: (2024)

D-Attn: Decomposed Attention for Large Vision-and-Language Models
por: Kuo, Chia-Wen, et al.
Publicado: (2025)

R2R: Efficiently Navigating Divergent Reasoning Paths with Small-Large Model Token Routing
por: Fu, Tianyu, et al.
Publicado: (2025)

AttnComp: Attention-Guided Adaptive Context Compression for Retrieval-Augmented Generation
por: Luo, Lvzhou, et al.
Publicado: (2025)

AttnCache: Accelerating Self-Attention Inference for LLM Prefill via Attention Cache
por: Song, Dinghong, et al.
Publicado: (2025)

AttnLRP: Attention-Aware Layer-Wise Relevance Propagation for Transformers
por: Achtibat, Reduan, et al.
Publicado: (2024)

FG-Attn: Leveraging Fine-Grained Sparsity In Diffusion Transformers
por: Durvasula, Sankeerth, et al.
Publicado: (2025)

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

SpecAttn: Speculating Sparse Attention
por: Shah, Harsh
Publicado: (2025)

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

Comp-Attn: Present-and-Align Attention for Compositional Video Generation
por: Zhang, Hongyu, et al.
Publicado: (2025)

DiT-IC: Aligned Diffusion Transformer for Efficient Image Compression
por: Shi, Junqi, et al.
Publicado: (2026)

LATTE: Low-Precision Approximate Attention with Head-wise Trainable Threshold for Efficient Transformer
por: Wang, Jiing-Ping, et al.
Publicado: (2024)

Multimodal Transformers are Hierarchical Modal-wise Heterogeneous Graphs
por: Jin, Yijie, et al.
Publicado: (2025)

Head-wise Shareable Attention for Large Language Models
por: Cao, Zouying, et al.
Publicado: (2024)

Causal Evidence for Attention Head Imbalance in Modality Conflict Hallucination
por: Jiang, Jinrui, et al.
Publicado: (2026)

DiffAttn: Diffusion-Based Drivers' Visual Attention Prediction with LLM-Enhanced Semantic Reasoning
por: Liu, Weimin, et al.
Publicado: (2026)

DiM: Diffusion Mamba for Efficient High-Resolution Image Synthesis
por: Teng, Yao, et al.
Publicado: (2024)

Cache-to-Cache: Direct Semantic Communication Between Large Language Models
por: Fu, Tianyu, et al.
Publicado: (2025)

SALAD: Achieve High-Sparsity Attention via Efficient Linear Attention Tuning for Video Diffusion Transformer
por: Fang, Tongcheng, et al.
Publicado: (2026)

FrameDiT: Diffusion Transformer with Matrix Attention for Efficient Video Generation
por: Le, Minh Khoa, et al.
Publicado: (2026)

AttnGCG: Enhancing Jailbreaking Attacks on LLMs with Attention Manipulation
por: Wang, Zijun, et al.
Publicado: (2024)

Attn-JGNN: Attention Enhanced Join-Graph Neural Networks
por: Zhang, Jixin
Publicado: (2025)

Attn-QAT: 4-Bit Attention With Quantization-Aware Training
por: Zhang, Peiyuan, et al.
Publicado: (2026)

DiTCtrl: Exploring Attention Control in Multi-Modal Diffusion Transformer for Tuning-Free Multi-Prompt Longer Video Generation
por: Cai, Minghong, et al.
Publicado: (2024)

Towards Better Multi-head Attention via Channel-wise Sample Permutation
por: Yuan, Shen, et al.
Publicado: (2024)

MixDQ: Memory-Efficient Few-Step Text-to-Image Diffusion Models with Metric-Decoupled Mixed Precision Quantization
por: Zhao, Tianchen, et al.
Publicado: (2024)