Imagen de Portada

ERTACache: Error Rectification and Timesteps Adjustment for Efficient Diffusion

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Peng, Xurui, Yan, Chenqian, Liu, Hong, Ma, Rui, Chen, Fangmin, Wang, Xing, Wu, Zhihua, Liu, Songwei, Lin, Mingbao
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

Error Propagation Mechanisms and Compensation Strategies for Quantized Diffusion
por: Liu, Songwei, et al.
Publicado: (2025)

Hybrid SD: Edge-Cloud Collaborative Inference for Stable Diffusion Models
por: Yan, Chenqian, et al.
Publicado: (2024)

Motion-Aware Caching for Efficient Autoregressive Video Generation
por: Xu, Jing, et al.
Publicado: (2026)

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

Test-Time Temporal Sampling for Efficient MLLM Video Understanding
por: Wang, Kaibin, et al.
Publicado: (2025)

DreamLite: A Lightweight On-Device Unified Model for Image Generation and Editing
por: Feng, Kailai, et al.
Publicado: (2026)

DiffusionTrend: A Minimalist Approach to Virtual Fashion Try-On
por: Zhan, Wengyi, et al.
Publicado: (2024)

Relation Rectification in Diffusion Model
por: Wu, Yinwei, et al.
Publicado: (2024)

Timestep-Aware Block Masking for Efficient Diffusion Model Inference
por: He, Haodong, et al.
Publicado: (2026)

Tuning Timestep-Distilled Diffusion Model Using Pairwise Sample Optimization
por: Miao, Zichen, et al.
Publicado: (2024)

TAP: A Token-Adaptive Predictor Framework for Training-Free Diffusion Acceleration
por: Zhu, Haowei, et al.
Publicado: (2026)

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

Early-Bird Diffusion: Investigating and Leveraging Timestep-Aware Early-Bird Tickets in Diffusion Models for Efficient Training
por: Whalen, Lexington, et al.
Publicado: (2025)

AccDiffusion: An Accurate Method for Higher-Resolution Image Generation
por: Lin, Zhihang, et al.
Publicado: (2024)

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

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

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

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

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

UniTransfer: Video Concept Transfer via Progressive Spatial and Timestep Decomposition
por: Lei, Guojun, et al.
Publicado: (2025)

AccDiffusion v2: Towards More Accurate Higher-Resolution Diffusion Extrapolation
por: Lin, Zhihang, et al.
Publicado: (2024)

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

Redefining Temporal Modeling in Video Diffusion: The Vectorized Timestep Approach
por: Liu, Yaofang, et al.
Publicado: (2024)

TMPQ-DM: Joint Timestep Reduction and Quantization Precision Selection for Efficient Diffusion Models
por: Sun, Haojun, et al.
Publicado: (2024)

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

CTCal: Rethinking Text-to-Image Diffusion Models via Cross-Timestep Self-Calibration
por: Guo, Xiefan, et al.
Publicado: (2026)

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

Pusa V1.0: Unlocking Temporal Control in Pretrained Video Diffusion Models via Vectorized Timestep Adaptation
por: Liu, Yaofang, et al.
Publicado: (2025)

Train Short, Inference Long: Training-free Horizon Extension for Autoregressive Video Generation
por: Li, Jia, et al.
Publicado: (2026)

EasyInv: Toward Fast and Better DDIM Inversion
por: Zhang, Ziyue, et al.
Publicado: (2024)

CutDiffusion: A Simple, Fast, Cheap, and Strong Diffusion Extrapolation Method
por: Lin, Mingbao, et al.
Publicado: (2024)

TCAQ-DM: Timestep-Channel Adaptive Quantization for Diffusion Models
por: Huang, Haocheng, et al.
Publicado: (2024)

L3DR: 3D-aware LiDAR Diffusion and Rectification
por: Liu, Quan, et al.
Publicado: (2026)

Conditional Prototype Rectification Prompt Learning
por: Chen, Haoxing, et al.
Publicado: (2024)

ObjectAdd: Adding Objects into Image via a Training-Free Diffusion Modification Fashion
por: Zhang, Ziyue, et al.
Publicado: (2024)

Move and Act: Enhanced Object Manipulation and Background Integrity for Image Editing
por: Jiang, Pengfei, et al.
Publicado: (2024)

Post-Training Quantization for Diffusion Transformer via Hierarchical Timestep Grouping
por: Ding, Ning, et al.
Publicado: (2025)

TimeStep Master: Asymmetrical Mixture of Timestep LoRA Experts for Versatile and Efficient Diffusion Models in Vision
por: Zhuang, Shaobin, et al.
Publicado: (2025)

ITA-MDT: Image-Timestep-Adaptive Masked Diffusion Transformer Framework for Image-Based Virtual Try-On
por: Hong, Ji Woo, et al.
Publicado: (2025)

AsyncDiff: Asynchronous Timestep Conditioning for Enhanced Text-to-Image Diffusion Inference
por: Xu, Longhuan, et al.
Publicado: (2025)