Copertina

PISA: Piecewise Sparse Attention Is Wiser for Efficient Diffusion Transformers

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Li, Haopeng, Shao, Shitong, Zhong, Wenliang, Zhou, Zikai, Bai, Lichen, Xiong, Hui, Xie, Zeke
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Computer Vision and Pattern Recognition
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

LIVEditor-14B: Lightning Unified Video Editing via In-Context Sparse Attention
di: Shao, Shitong, et al.
Pubblicazione: (2026)

IV-Mixed Sampler: Leveraging Image Diffusion Models for Enhanced Video Synthesis
di: Shao, Shitong, et al.
Pubblicazione: (2024)

Exploring Data-Free LoRA Transferability for Video Diffusion Models
di: Wang, Yuchen, et al.
Pubblicazione: (2026)

Zigzag Diffusion Sampling: Diffusion Models Can Self-Improve via Self-Reflection
di: Bai, Lichen, et al.
Pubblicazione: (2024)

Bag of Design Choices for Inference of High-Resolution Masked Generative Transformer
di: Shao, Shitong, et al.
Pubblicazione: (2024)

Efficient Video Diffusion Models: Advancements and Challenges
di: Shao, Shitong, et al.
Pubblicazione: (2026)

Optimizing Few-Step Generation with Adaptive Matching Distillation
di: Bai, Lichen, et al.
Pubblicazione: (2026)

Golden Noise for Diffusion Models: A Learning Framework
di: Zhou, Zikai, et al.
Pubblicazione: (2024)

CoRe^2: Collect, Reflect and Refine to Generate Better and Faster
di: Shao, Shitong, et al.
Pubblicazione: (2025)

Reflective Flow Sampling Enhancement
di: Zhou, Zikai, et al.
Pubblicazione: (2026)

CRAFT: Aligning Diffusion Models with Fine-Tuning Is Easier Than You Think
di: Sun, Zening, et al.
Pubblicazione: (2026)

Guidance Matters: Rethinking the Evaluation Pitfall for Text-to-Image Generation
di: Xie, Dian, et al.
Pubblicazione: (2026)

Not All Noises Are Created Equally:Diffusion Noise Selection and Optimization
di: Qi, Zipeng, et al.
Pubblicazione: (2024)

Weak-to-Strong Diffusion with Reflection
di: Bai, Lichen, et al.
Pubblicazione: (2025)

Alignment of Diffusion Models: Fundamentals, Challenges, and Future
di: Liu, Buhua, et al.
Pubblicazione: (2024)

FastLightGen: Fast and Light Video Generation with Fewer Steps and Parameters
di: Shao, Shitong, et al.
Pubblicazione: (2026)

Trainable Log-linear Sparse Attention for Efficient Diffusion Transformers
di: Zhou, Yifan, et al.
Pubblicazione: (2025)

Rethinking Centered Kernel Alignment in Knowledge Distillation
di: Zhou, Zikai, et al.
Pubblicazione: (2024)

Elucidating the Design Space of Dataset Condensation
di: Shao, Shitong, et al.
Pubblicazione: (2024)

MagicDistillation: Weak-to-Strong Video Distillation for Large-Scale Few-Step Synthesis
di: Shao, Shitong, et al.
Pubblicazione: (2025)

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

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

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

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

A Simple and Efficient Baseline for Zero-Shot Generative Classification
di: Qi, Zipeng, et al.
Pubblicazione: (2024)

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

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

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

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

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

TCSAFormer: Efficient Vision Transformer with Token Compression and Sparse Attention for Medical Image Segmentation
di: Xia, Zunhui, et al.
Pubblicazione: (2025)

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

SPT: Sequence Prompt Transformer for Interactive Image Segmentation
di: Cheng, Senlin, et al.
Pubblicazione: (2024)

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

Bridging Geometry-Coherent Text-to-3D Generation with Multi-View Diffusion Priors and Gaussian Splatting
di: Yang, Feng, et al.
Pubblicazione: (2025)

Bidirectional Sparse Attention for Faster Video Diffusion Training
di: Zhan, Chenlu, et al.
Pubblicazione: (2025)

SEDiT: Mask-Free Video Subtitle Erasure via One-step Diffusion Transformer
di: Hui, Zheng, et al.
Pubblicazione: (2026)

MagicInfinite: Generating Infinite Talking Videos with Your Words and Voice
di: Yi, Hongwei, et al.
Pubblicazione: (2025)

Sculpt4D: Generating 4D Shapes via Sparse-Attention Diffusion Transformers
di: Yin, Minghao, et al.
Pubblicazione: (2026)

DynamicRad: Content-Adaptive Sparse Attention for Long Video Diffusion
di: Long, Yongji, et al.
Pubblicazione: (2026)