Copertina

Error Propagation Mechanisms and Compensation Strategies for Quantized Diffusion

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Liu, Songwei, Zeng, Chao, Yan, Chenqian, Peng, Xurui, Wang, Xing, Chen, Fangmin, Mei, Xing
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Computer Vision and Pattern Recognition
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

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

ERTACache: Error Rectification and Timesteps Adjustment for Efficient Diffusion
di: Peng, Xurui, et al.
Pubblicazione: (2025)

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

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

Minimize Quantization Output Error with Bias Compensation
di: Gong, Cheng, et al.
Pubblicazione: (2024)

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

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

FoldGPT: Simple and Effective Large Language Model Compression Scheme
di: Liu, Songwei, et al.
Pubblicazione: (2024)

On Error Propagation of Diffusion Models
di: Li, Yangming, et al.
Pubblicazione: (2023)

ConvRot: Rotation-Based Plug-and-Play 4-bit Quantization for Diffusion Transformers
di: Huang, Feice, et al.
Pubblicazione: (2025)

TR-DQ: Time-Rotation Diffusion Quantization
di: Shao, Yihua, et al.
Pubblicazione: (2025)

First-Order Error Matters: Accurate Compensation for Quantized Large Language Models
di: Zheng, Xingyu, et al.
Pubblicazione: (2025)

Interleaved Block-based Learned Image Compression with Feature Enhancement and Quantization Error Compensation
di: Jiang, Shiqi, et al.
Pubblicazione: (2025)

Sampling-Aware Quantization for Diffusion Models
di: Zeng, Qian, et al.
Pubblicazione: (2025)

Uni-DocDiff: A Unified Document Restoration Model Based on Diffusion
di: Zhao, Fangmin, et al.
Pubblicazione: (2025)

Diffusion Model Quantization: A Review
di: Zeng, Qian, et al.
Pubblicazione: (2025)

Spectral-Structured Diffusion for Single-Image Rain Removal
di: Xing, Yucheng, et al.
Pubblicazione: (2026)

StyleTextGen: Style-Conditioned Multilingual Scene Text Generation
di: Chen, Zeyu, et al.
Pubblicazione: (2026)

Nonlinear Bipolar Compensation: Handling Outliers in Post-Training Quantization
di: Sun, Peilin, et al.
Pubblicazione: (2026)

Data-Free Quantization via Mixed-Precision Compensation without Fine-Tuning
di: Chen, Jun, et al.
Pubblicazione: (2023)

PTQ4DiT: Post-training Quantization for Diffusion Transformers
di: Wu, Junyi, et al.
Pubblicazione: (2024)

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

VQ-Seg: Vector-Quantized Token Perturbation for Semi-Supervised Medical Image Segmentation
di: Yang, Sicheng, et al.
Pubblicazione: (2026)

TADoc: Robust Time-Aware Document Image Dewarping
di: Zhao, Fangmin, et al.
Pubblicazione: (2025)

Visual Text Meets Low-level Vision: A Comprehensive Survey on Visual Text Processing
di: Shu, Yan, et al.
Pubblicazione: (2024)

3One2: One-step Regression Plus One-step Diffusion for One-hot Modulation in Dual-path Video Snapshot Compressive Imaging
di: Wang, Ge, et al.
Pubblicazione: (2025)

FQ-PETR: Fully Quantized Position Embedding Transformation for Multi-View 3D Object Detection
di: Yu, Jiangyong, et al.
Pubblicazione: (2025)

Corvid: Improving Multimodal Large Language Models Towards Chain-of-Thought Reasoning
di: Jiang, Jingjing, et al.
Pubblicazione: (2025)

DPEC: Dual-Path Error Compensation Method for Enhanced Low-Light Image Clarity
di: Wang, Shuang, et al.
Pubblicazione: (2024)

SeaS: Few-shot Industrial Anomaly Image Generation with Separation and Sharing Fine-tuning
di: Dai, Zhewei, et al.
Pubblicazione: (2024)

Mimir: Hierarchical Goal-Driven Diffusion with Uncertainty Propagation for End-to-End Autonomous Driving
di: Xing, Zebin, et al.
Pubblicazione: (2025)

QuEST: Low-bit Diffusion Model Quantization via Efficient Selective Finetuning
di: Wang, Haoxuan, et al.
Pubblicazione: (2024)

High-Fidelity Relightable Monocular Portrait Animation with Lighting-Controllable Video Diffusion Model
di: Guo, Mingtao, et al.
Pubblicazione: (2025)

3D-SSM: A Novel 3D Selective Scan Module for Remote Sensing Change Detection
di: Huang, Rui, et al.
Pubblicazione: (2025)

An Analysis on Quantizing Diffusion Transformers
di: Yang, Yuewei, et al.
Pubblicazione: (2024)

Towards All-Day Perception for Off-Road Driving: A Large-Scale Multispectral Dataset and Comprehensive Benchmark
di: Wang, Shuo, et al.
Pubblicazione: (2026)

MuSc-V2: Zero-Shot Multimodal Industrial Anomaly Classification and Segmentation with Mutual Scoring of Unlabeled Samples
di: Li, Xurui, et al.
Pubblicazione: (2025)

GarmentPainter: Efficient 3D Garment Texture Synthesis with Character-Guided Diffusion Model
di: Wu, Jinbo, et al.
Pubblicazione: (2026)

VoxelFormer: Parameter-Efficient Multi-Subject Visual Decoding from fMRI
di: Le, Chenqian, et al.
Pubblicazione: (2025)

LatentSync: Taming Audio-Conditioned Latent Diffusion Models for Lip Sync with SyncNet Supervision
di: Li, Chunyu, et al.
Pubblicazione: (2024)