Image de couverture de livre

SpecDiff: Accelerating Diffusion Model Inference with Self-Speculation

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Pan, Jiayi, Xu, Jiaming, Zhou, Yongkang, Dai, Guohao
Format:	Preprint
Publié:	2025
Sujets:	Computer Vision and Pattern Recognition Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

SpecPrune-VLA: Accelerating Vision-Language-Action Models via Action-Aware Self-Speculative Pruning
par: Wang, Hanzhen, et autres
Publié: (2025)

BalanceGS: Algorithm-System Co-design for Efficient 3D Gaussian Splatting Training on GPU
par: Wu, Junyi, et autres
Publié: (2025)

AdvDiff: Generating Unrestricted Adversarial Examples using Diffusion Models
par: Dai, Xuelong, et autres
Publié: (2023)

SpecEE: Accelerating Large Language Model Inference with Speculative Early Exiting
par: Xu, Jiaming, et autres
Publié: (2025)

MosaicDiff: Training-free Structural Pruning for Diffusion Model Acceleration Reflecting Pretraining Dynamics
par: Guo, Bowei, et autres
Publié: (2025)

BayesDiff: Estimating Pixel-wise Uncertainty in Diffusion via Bayesian Inference
par: Kou, Siqi, et autres
Publié: (2023)

SpeCa: Accelerating Diffusion Transformers with Speculative Feature Caching
par: Liu, Jiacheng, et autres
Publié: (2025)

MPQ-Diff: Mixed Precision Quantization for Diffusion Models
par: Maruzzelli, Rocco Manz, et autres
Publié: (2024)

SenCache: Accelerating Diffusion Model Inference via Sensitivity-Aware Caching
par: Haghighi, Yasaman, et autres
Publié: (2026)

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

SemDiff: Generating Natural Unrestricted Adversarial Examples via Semantic Attributes Optimization in Diffusion Models
par: Dai, Zeyu, et autres
Publié: (2025)

Zigzag Diffusion Sampling: Diffusion Models Can Self-Improve via Self-Reflection
par: Bai, Lichen, et autres
Publié: (2024)

Personalized Preference Fine-tuning of Diffusion Models
par: Dang, Meihua, et autres
Publié: (2025)

CubeDiff: Repurposing Diffusion-Based Image Models for Panorama Generation
par: Kalischek, Nikolai, et autres
Publié: (2025)

EmerDiff: Emerging Pixel-level Semantic Knowledge in Diffusion Models
par: Namekata, Koichi, et autres
Publié: (2024)

Diff-3DCap: Shape Captioning with Diffusion Models
par: Shu, Zhenyu, et autres
Publié: (2025)

Diff2Flow: Training Flow Matching Models via Diffusion Model Alignment
par: Schusterbauer, Johannes, et autres
Publié: (2025)

AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning
par: Guo, Yuwei, et autres
Publié: (2023)

DiffRatio: Training One-Step Diffusion Models Without Teacher Supervision
par: Chen, Wenlin, et autres
Publié: (2025)

DiffECG: A Versatile Probabilistic Diffusion Model for ECG Signals Synthesis
par: Neifar, Nour, et autres
Publié: (2023)

DiffEnc: Variational Diffusion with a Learned Encoder
par: Nielsen, Beatrix M. G., et autres
Publié: (2023)

T-Stitch: Accelerating Sampling in Pre-Trained Diffusion Models with Trajectory Stitching
par: Pan, Zizheng, et autres
Publié: (2024)

InvDiff: Invariant Guidance for Bias Mitigation in Diffusion Models
par: Hou, Min, et autres
Publié: (2024)

SlimDiff: Training-Free, Activation-Guided Hands-free Slimming of Diffusion Models
par: Roy, Arani, et autres
Publié: (2025)

DisCo-Diff: Enhancing Continuous Diffusion Models with Discrete Latents
par: Xu, Yilun, et autres
Publié: (2024)

FedDiff: Diffusion Model Driven Federated Learning for Multi-Modal and Multi-Clients
par: Li, DaiXun, et autres
Publié: (2023)

$\infty$-Diff: Infinite Resolution Diffusion with Subsampled Mollified States
par: Bond-Taylor, Sam, et autres
Publié: (2023)

DiffPAD: Denoising Diffusion-based Adversarial Patch Decontamination
par: Fu, Jia, et autres
Publié: (2024)

DiffDenoise: Self-Supervised Medical Image Denoising with Conditional Diffusion Models
par: Demir, Basar, et autres
Publié: (2025)

Token Pruning for Caching Better: 9 Times Acceleration on Stable Diffusion for Free
par: Zhang, Evelyn, et autres
Publié: (2024)

FOD-Diff: 3D Multi-Channel Patch Diffusion Model for Fiber Orientation Distribution
par: Tang, Hao, et autres
Publié: (2025)

Diff-Instruct: A Universal Approach for Transferring Knowledge From Pre-trained Diffusion Models
par: Luo, Weijian, et autres
Publié: (2023)

Diff-2-in-1: Bridging Generation and Dense Perception with Diffusion Models
par: Zheng, Shuhong, et autres
Publié: (2024)

DiffEditor: Boosting Accuracy and Flexibility on Diffusion-based Image Editing
par: Mou, Chong, et autres
Publié: (2024)

DiffAug: A Diffuse-and-Denoise Augmentation for Training Robust Classifiers
par: Sastry, Chandramouli, et autres
Publié: (2023)

PrecipDiff: Leveraging image diffusion models to enhance satellite-based precipitation observations
par: Dai, Ting-Yu, et autres
Publié: (2025)

Accelerating Diffusion Models for Inverse Problems through Shortcut Sampling
par: Liu, Gongye, et autres
Publié: (2023)

DiffCP: Ultra-Low Bit Collaborative Perception via Diffusion Model
par: Mao, Ruiqing, et autres
Publié: (2024)

Self-Bootstrapping for Versatile Test-Time Adaptation
par: Niu, Shuaicheng, et autres
Publié: (2025)

STLLaVA-Med: Self-Training Large Language and Vision Assistant for Medical Question-Answering
par: Sun, Guohao, et autres
Publié: (2024)