Imagen de Portada

Compute Only 16 Tokens in One Timestep: Accelerating Diffusion Transformers with Cluster-Driven Feature Caching

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Zheng, Zhixin, Wang, Xinyu, Zou, Chang, Wang, Shaobo, Zhang, Linfeng
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

Accelerating Diffusion Transformers with Token-wise Feature Caching
por: Zou, Chang, et al.
Publicado: (2024)

SpeCa: Accelerating Diffusion Transformers with Speculative Feature Caching
por: Liu, Jiacheng, et al.
Publicado: (2025)

Rethinking Token-wise Feature Caching: Accelerating Diffusion Transformers with Dual Feature Caching
por: Zou, Chang, et al.
Publicado: (2024)

Forecast then Calibrate: Feature Caching as ODE for Efficient Diffusion Transformers
por: Zheng, Shikang, et al.
Publicado: (2025)

Accelerating Diffusion-based Video Editing via Heterogeneous Caching: Beyond Full Computing at Sampled Denoising Timestep
por: Liu, Tianyi, et al.
Publicado: (2026)

Let Features Decide Their Own Solvers: Hybrid Feature Caching for Diffusion Transformers
por: Zheng, Shikang, et al.
Publicado: (2025)

HiCache: A Plug-in Scaled-Hermite Upgrade for Taylor-Style Cache-then-Forecast Diffusion Acceleration
por: Feng, Liang, et al.
Publicado: (2025)

Token Pruning for Caching Better: 9 Times Acceleration on Stable Diffusion for Free
por: Zhang, Evelyn, et al.
Publicado: (2024)

DisCa: Accelerating Video Diffusion Transformers with Distillation-Compatible Learnable Feature Caching
por: Zou, Chang, et al.
Publicado: (2026)

Forecast the Principal, Stabilize the Residual: Subspace-Aware Feature Caching for Efficient Diffusion Transformers
por: Chen, Guantao, et al.
Publicado: (2026)

Token Caching for Diffusion Transformer Acceleration
por: Lou, Jinming, et al.
Publicado: (2024)

ProCache: Constraint-Aware Feature Caching with Selective Computation for Diffusion Transformer Acceleration
por: Cao, Fanpu, et al.
Publicado: (2025)

Timestep Embedding Tells: It's Time to Cache for Video Diffusion Model
por: Liu, Feng, et al.
Publicado: (2024)

Generative Multimodal Pretraining with Discrete Diffusion Timestep Tokens
por: Pan, Kaihang, et al.
Publicado: (2025)

Relational Feature Caching for Accelerating Diffusion Transformers
por: Son, Byunggwan, et al.
Publicado: (2026)

HarmoniCa: Harmonizing Training and Inference for Better Feature Caching in Diffusion Transformer Acceleration
por: Huang, Yushi, et al.
Publicado: (2024)

LazyMAR: Accelerating Masked Autoregressive Models via Feature Caching
por: Yan, Feihong, et al.
Publicado: (2025)

Reasoning Physical Video Generation with Diffusion Timestep Tokens via Reinforcement Learning
por: Lin, Wang, et al.
Publicado: (2025)

Accelerating Diffusion Models with One-to-Many Knowledge Distillation
por: Zhang, Linfeng, et al.
Publicado: (2024)

Accelerating Diffusion Transformer via Gradient-Optimized Cache
por: Qiu, Junxiang, et al.
Publicado: (2025)

Learning-to-Cache: Accelerating Diffusion Transformer via Layer Caching
por: Ma, Xinyin, et al.
Publicado: (2024)

Accelerating Diffusion Transformer via Error-Optimized Cache
por: Qiu, Junxiang, et al.
Publicado: (2025)

Towards More Accurate Diffusion Model Acceleration with A Timestep Tuner
por: Xia, Mengfei, et al.
Publicado: (2023)

FreqCa: Accelerating Diffusion Models via Frequency-Aware Caching
por: Liu, Jiacheng, et al.
Publicado: (2025)

Layer- and Timestep-Adaptive Differentiable Token Compression Ratios for Efficient Diffusion Transformers
por: You, Haoran, et al.
Publicado: (2024)

DyDiT++: Diffusion Transformers with Timestep and Spatial Dynamics for Efficient Visual Generation
por: Zhao, Wangbo, et al.
Publicado: (2025)

Exploring Multi-Timestep Multi-Stage Diffusion Features for Hyperspectral Image Classification
por: Zhou, Jingyi, et al.
Publicado: (2023)

From Sketch to Fresco: Efficient Diffusion Transformer with Progressive Resolution
por: Zheng, Shikang, et al.
Publicado: (2026)

FORA: Fast-Forward Caching in Diffusion Transformer Acceleration
por: Selvaraju, Pratheba, et al.
Publicado: (2024)

From Reusing to Forecasting: Accelerating Diffusion Models with TaylorSeers
por: Liu, Jiacheng, et al.
Publicado: (2025)

Autoregressive Image Generation Needs Only a Few Lines of Cached Tokens
por: Qin, Ziran, et al.
Publicado: (2025)

WorldCache: Accelerating World Models for Free via Heterogeneous Token Caching
por: Feng, Weilun, et al.
Publicado: (2026)

TASR: Timestep-Aware Diffusion Model for Image Super-Resolution
por: Lin, Qinwei, et al.
Publicado: (2024)

HybridStitch: Pixel and Timestep Level Model Stitching for Diffusion Acceleration
por: Sun, Desen, et al.
Publicado: (2026)

Accelerating Rectified Flow Models via Trajectory-Aware Caching
por: Liu, Xiao, et al.
Publicado: (2026)

DiffSparse: Accelerating Diffusion Transformers with Learned Token Sparsity
por: Zhu, Haowei, et al.
Publicado: (2026)

Timestep-Aware Correction for Quantized Diffusion Models
por: Yao, Yuzhe, et al.
Publicado: (2024)

Frequency-Aware Error-Bounded Caching for Accelerating Diffusion Transformers
por: Li, Guandong
Publicado: (2026)

Cached Adaptive Token Merging: Dynamic Token Reduction and Redundant Computation Elimination in Diffusion Model
por: Saghatchian, Omid, et al.
Publicado: (2025)

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