Copertina

RainFusion2.0: Temporal-Spatial Awareness and Hardware-Efficient Block-wise Sparse Attention

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Chen, Aiyue, Liu, Yaofu, Huang, Junjian, Lian, Guang, Yao, Yiwu, Lan, Wangli, Lin, Jing, Ma, Zhixin, Zhou, Tingting
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Computer Vision and Pattern Recognition
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

RainFusion: Adaptive Video Generation Acceleration via Multi-Dimensional Visual Redundancy
di: Chen, Aiyue, et al.
Pubblicazione: (2025)

Astraea: A Token-wise Acceleration Framework for Video Diffusion Transformers
di: Liu, Haosong, et al.
Pubblicazione: (2025)

TIMERIPPLE: Accelerating vDiTs by Understanding the Spatio-Temporal Correlations in Latent Space
di: Miao, Wenxuan, et al.
Pubblicazione: (2025)

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

RainDiff: End-to-end Precipitation Nowcasting Via Token-wise Attention Diffusion
di: Nguyen, Thao, et al.
Pubblicazione: (2025)

Sparser Block-Sparse Attention via Token Permutation
di: Wang, Xinghao, et al.
Pubblicazione: (2025)

Compact Attention: Exploiting Structured Spatio-Temporal Sparsity for Fast Video Generation
di: Li, Qirui, et al.
Pubblicazione: (2025)

Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention
di: Yuan, Jingyang, et al.
Pubblicazione: (2025)

Block Sparse Flash Attention
di: Ohayon, Daniel, et al.
Pubblicazione: (2025)

The Spatial and Temporal Distribution of Rain‐On‐Snow Events and Their Driving Factors in China
di: Shiyu Li, et al.
Pubblicazione: (2025)

Fixed effects Bayesian testing in high‐dimensional linear mixed models
di: Jiamin Liu, et al.
Pubblicazione: (2026)

Dynamic Low-Rank Sparse Adaptation for Large Language Models
di: Huang, Weizhong, et al.
Pubblicazione: (2025)

StreamFlow: Streaming Flow Matching with Block-wise Guided Attention Mask for Speech Token Decoding
di: Guo, Dake, et al.
Pubblicazione: (2025)

VecAttention: Vector-wise Sparse Attention for Accelerating Long Context Inference
di: Liu, Anmin, et al.
Pubblicazione: (2026)

BLOSSOM: Block-wise Federated Learning Over Shared and Sparse Observed Modalities
di: R, Pranav M, et al.
Pubblicazione: (2026)

LoSA: Locality Aware Sparse Attention for Block-Wise Diffusion Language Models
di: Xi, Haocheng, et al.
Pubblicazione: (2026)

Feature Fusion Attention Network with CycleGAN for Image Dehazing, De-Snowing and De-Raining
di: Jain, Akshat
Pubblicazione: (2025)

Spatial-Temporal Attention Model for Traffic State Estimation with Sparse Internet of Vehicles
di: Xue, Jianzhe, et al.
Pubblicazione: (2024)

Block-Attention for Efficient Prefilling
di: Ma, Dongyang, et al.
Pubblicazione: (2024)

XAttention: Block Sparse Attention with Antidiagonal Scoring
di: Xu, Ruyi, et al.
Pubblicazione: (2025)

RazorAttention: Efficient KV Cache Compression Through Retrieval Heads
di: Tang, Hanlin, et al.
Pubblicazione: (2024)

SSTAF: Spatial-Spectral-Temporal Attention Fusion Transformer for Motor Imagery Classification
di: Muna, Ummay Maria, et al.
Pubblicazione: (2025)

CSA-Net: Channel-wise Spatially Autocorrelated Attention Networks
di: Nikzad, Nick, et al.
Pubblicazione: (2024)

Over-the-Air Fusion of Sparse Spatial Features for Integrated Sensing and Edge AI over Broadband Channels
di: Liu, Zhiyan, et al.
Pubblicazione: (2024)

From Drone Imagery to Livability Mapping: AI-powered Environment Perception in Rural China
di: Deng, Weihuan, et al.
Pubblicazione: (2025)

DCAU-Net: Differential Cross Attention and Channel-Spatial Feature Fusion for Medical Image Segmentation
di: Li, Yanxin, et al.
Pubblicazione: (2026)

Spatio-Temporal Attention Graph Neural Network for Remaining Useful Life Prediction
di: Huang, Zhixin, et al.
Pubblicazione: (2024)

SNN-Driven Multimodal Human Action Recognition via Sparse Spatial-Temporal Data Fusion
di: Zheng, Naichuan, et al.
Pubblicazione: (2025)

MedFormer: Hierarchical Medical Vision Transformer with Content-Aware Dual Sparse Selection Attention
di: Xia, Zunhui, et al.
Pubblicazione: (2025)

DTA: Dual Temporal-channel-wise Attention for Spiking Neural Networks
di: Kim, Minje, et al.
Pubblicazione: (2025)

MambaRain: Multi-Scale Mamba-Attention Framework for 0-3 Hour Precipitation Nowcasting
di: Shi, Chunlei, et al.
Pubblicazione: (2026)

Spatially-Aware Diffusion Models with Cross-Attention for Global Field Reconstruction with Sparse Observations
di: Zhuang, Yilin, et al.
Pubblicazione: (2024)

S2-Attention: Hardware-Aware Context Sharding Among Attention Heads
di: Lin, Xihui, et al.
Pubblicazione: (2024)

Fusion Matrix Prompt Enhanced Self-Attention Spatial-Temporal Interactive Traffic Forecasting Framework
di: Liu, Mu, et al.
Pubblicazione: (2024)

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

Dynamic Sparse No Training: Training-Free Fine-tuning for Sparse LLMs
di: Zhang, Yuxin, et al.
Pubblicazione: (2023)

Long-Tail Temporal Action Segmentation with Group-wise Temporal Logit Adjustment
di: Pang, Zhanzhong, et al.
Pubblicazione: (2024)

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

Toward a Finer‐Grained Understanding of Greater‐Occipital‐Nerve Block Duration in Migraine
di: Jing Lan
Pubblicazione: (2025)

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