Cover Image

MosaicDiff: Training-free Structural Pruning for Diffusion Model Acceleration Reflecting Pretraining Dynamics

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Guo, Bowei, Tang, Shengkun, Zeng, Cong, Shen, Zhiqiang
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Diff-ES: Stage-wise Structural Diffusion Pruning via Evolutionary Search
by: Liu, Zongfang, et al.
Published: (2026)

AdaDiff: Accelerating Diffusion Models through Step-Wise Adaptive Computation
by: Tang, Shengkun, et al.
Published: (2023)

BiGain: Unified Token Compression for Joint Generation and Classification
by: Liu, Jiacheng, et al.
Published: (2026)

SlimDiff: Training-Free, Activation-Guided Hands-free Slimming of Diffusion Models
by: Roy, Arani, et al.
Published: (2025)

Reflecting on the State of Rehearsal-free Continual Learning with Pretrained Models
by: Thede, Lukas, et al.
Published: (2024)

Sink-Aware Pruning for Diffusion Language Models
by: Myrzakhan, Aidar, et al.
Published: (2026)

SpecDiff: Accelerating Diffusion Model Inference with Self-Speculation
by: Pan, Jiayi, et al.
Published: (2025)

Variance-Based Pruning for Accelerating and Compressing Trained Networks
by: Berisha, Uranik, et al.
Published: (2025)

Exploring 3D Dataset Pruning
by: Zhao, Xiaohan, et al.
Published: (2026)

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

DiffRatio: Training One-Step Diffusion Models Without Teacher Supervision
by: Chen, Wenlin, et al.
Published: (2025)

Diff2Flow: Training Flow Matching Models via Diffusion Model Alignment
by: Schusterbauer, Johannes, et al.
Published: (2025)

OBS-Diff: Accurate Pruning For Diffusion Models in One-Shot
by: Zhu, Junhan, et al.
Published: (2025)

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

Language-Pretraining-Induced Bias: A Strong Foundation for General Vision Tasks
by: Luo, Yaxin, et al.
Published: (2026)

DiffAug: A Diffuse-and-Denoise Augmentation for Training Robust Classifiers
by: Sastry, Chandramouli, et al.
Published: (2023)

Understanding and Improving Training-free Loss-based Diffusion Guidance
by: Shen, Yifei, et al.
Published: (2024)

Streaming-dLLM: Accelerating Diffusion LLMs via Suffix Pruning and Dynamic Decoding
by: Xiao, Zhongyu, et al.
Published: (2026)

LAPTOP-Diff: Layer Pruning and Normalized Distillation for Compressing Diffusion Models
by: Zhang, Dingkun, et al.
Published: (2024)

Data Pruning in Generative Diffusion Models
by: Briq, Rania, et al.
Published: (2024)

Diffusion Models without Classifier-free Guidance
by: Tang, Zhicong, et al.
Published: (2025)

Accelerating Augmentation Invariance Pretraining
by: Lin, Jinhong, et al.
Published: (2024)

CamFreeDiff: Camera-free Image to Panorama Generation with Diffusion Model
by: Yuan, Xiaoding, et al.
Published: (2024)

FOD-Diff: 3D Multi-Channel Patch Diffusion Model for Fiber Orientation Distribution
by: Tang, Hao, et al.
Published: (2025)

SAM-DiffSR: Structure-Modulated Diffusion Model for Image Super-Resolution
by: Wang, Chengcheng, et al.
Published: (2024)

MPQ-Diff: Mixed Precision Quantization for Diffusion Models
by: Maruzzelli, Rocco Manz, et al.
Published: (2024)

Diff-Mosaic: Augmenting Realistic Representations in Infrared Small Target Detection via Diffusion Prior
by: Shi, Yukai, et al.
Published: (2024)

InvarDiff: Cross-Scale Invariance Caching for Accelerated Diffusion Models
by: Wu, Zihao
Published: (2025)

Adaptive Non-uniform Timestep Sampling for Accelerating Diffusion Model Training
by: Kim, Myunsoo, et al.
Published: (2024)

T-Stitch: Accelerating Sampling in Pre-Trained Diffusion Models with Trajectory Stitching
by: Pan, Zizheng, et al.
Published: (2024)

Just Leaf It: Accelerating Diffusion Classifiers with Hierarchical Class Pruning
by: Shanbhag, Arundhati S., et al.
Published: (2024)

Training-free Diffusion Acceleration with Bottleneck Sampling
by: Tian, Ye, et al.
Published: (2025)

Efficient Training of Diffusion Mixture-of-Experts Models: A Practical Recipe
by: Liu, Yahui, et al.
Published: (2025)

VipDiff: Towards Coherent and Diverse Video Inpainting via Training-free Denoising Diffusion Models
by: Xie, Chaohao, et al.
Published: (2025)

SemDiff: Generating Natural Unrestricted Adversarial Examples via Semantic Attributes Optimization in Diffusion Models
by: Dai, Zeyu, et al.
Published: (2025)

Pretrained Diffusion Models Are Inherently Skipped-Step Samplers
by: Xu, Wenju
Published: (2025)

DiffPattern-Flex: Efficient Layout Pattern Generation via Discrete Diffusion
by: Wang, Zixiao, et al.
Published: (2025)

Diff-3DCap: Shape Captioning with Diffusion Models
by: Shu, Zhenyu, et al.
Published: (2025)

CubeDiff: Repurposing Diffusion-Based Image Models for Panorama Generation
by: Kalischek, Nikolai, et al.
Published: (2025)

EmerDiff: Emerging Pixel-level Semantic Knowledge in Diffusion Models
by: Namekata, Koichi, et al.
Published: (2024)