Image de couverture de livre

Post-Training Quantization for Diffusion Transformer via Hierarchical Timestep Grouping

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Ding, Ning, Han, Jing, Tian, Yuchuan, Xu, Chao, Han, Kai, Tang, Yehui
Format:	Preprint
Publié:	2025
Sujets:	Computer Vision and Pattern Recognition
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

GPT4Image: Large Pre-trained Models Help Vision Models Learn Better on Perception Task
par: Ding, Ning, et autres
Publié: (2023)

Timestep-Aware Correction for Quantized Diffusion Models
par: Yao, Yuzhe, et autres
Publié: (2024)

Instruct-IPT: All-in-One Image Processing Transformer via Weight Modulation
par: Tian, Yuchuan, et autres
Publié: (2024)

DyDiT++: Diffusion Transformers with Timestep and Spatial Dynamics for Efficient Visual Generation
par: Zhao, Wangbo, et autres
Publié: (2025)

GhostNetV3: Exploring the Training Strategies for Compact Models
par: Liu, Zhenhua, et autres
Publié: (2024)

TCAQ-DM: Timestep-Channel Adaptive Quantization for Diffusion Models
par: Huang, Haocheng, et autres
Publié: (2024)

DiC: Rethinking Conv3x3 Designs in Diffusion Models
par: Tian, Yuchuan, et autres
Publié: (2024)

Learning Quantized Adaptive Conditions for Diffusion Models
par: Liang, Yuchen, et autres
Publié: (2024)

Q-DiT: Accurate Post-Training Quantization for Diffusion Transformers
par: Chen, Lei, et autres
Publié: (2024)

U-DiTs: Downsample Tokens in U-Shaped Diffusion Transformers
par: Tian, Yuchuan, et autres
Publié: (2024)

ADFQ-ViT: Activation-Distribution-Friendly Post-Training Quantization for Vision Transformers
par: Jiang, Yanfeng, et autres
Publié: (2024)

TMPQ-DM: Joint Timestep Reduction and Quantization Precision Selection for Efficient Diffusion Models
par: Sun, Haojun, et autres
Publié: (2024)

Token Compensator: Altering Inference Cost of Vision Transformer without Re-Tuning
par: Jie, Shibo, et autres
Publié: (2024)

Post-Training Quantization via Residual Truncation and Zero Suppression for Diffusion Models
par: Kim, Donghoon, et autres
Publié: (2025)

Towards Accurate Post-Training Quantization of Vision Transformers via Error Reduction
par: Zhong, Yunshan, et autres
Publié: (2024)

AdaLog: Post-Training Quantization for Vision Transformers with Adaptive Logarithm Quantizer
par: Wu, Zhuguanyu, et autres
Publié: (2024)

QArtSR: Quantization via Reverse-Module and Timestep-Retraining in One-Step Diffusion based Image Super-Resolution
par: Zhu, Libo, et autres
Publié: (2025)

LRQ-DiT: Log-Rotation Post-Training Quantization of Diffusion Transformers for Image and Video Generation
par: Yang, Lianwei, et autres
Publié: (2025)

Memory-Space Visual Prompting for Efficient Vision-Language Fine-Tuning
par: Jie, Shibo, et autres
Publié: (2024)

Towards Accurate Post-training Quantization for Diffusion Models
par: Wang, Changyuan, et autres
Publié: (2023)

SAM-DiffSR: Structure-Modulated Diffusion Model for Image Super-Resolution
par: Wang, Chengcheng, et autres
Publié: (2024)

Generative Multimodal Pretraining with Discrete Diffusion Timestep Tokens
par: Pan, Kaihang, et autres
Publié: (2025)

Data-efficient Large Vision Models through Sequential Autoregression
par: Guo, Jianyuan, et autres
Publié: (2024)

Weight Group-wise Post-Training Quantization for Medical Foundation Model
par: Chen, Yineng, et autres
Publié: (2026)

AIQViT: Architecture-Informed Post-Training Quantization for Vision Transformers
par: Jiang, Runqing, et autres
Publié: (2025)

QVGGT: Post-Training Quantized Visual Geometry Grounded Transformer
par: Pan, Zhizhen, et autres
Publié: (2026)

Cat: Post-Training Quantization Error Reduction via Cluster-based Affine Transformation
par: Zoljodi, Ali, et autres
Publié: (2025)

Progressive Fine-to-Coarse Reconstruction for Accurate Low-Bit Post-Training Quantization in Vision Transformers
par: Ding, Rui, et autres
Publié: (2024)

PTQ4DiT: Post-training Quantization for Diffusion Transformers
par: Wu, Junyi, et autres
Publié: (2024)

EfficientQuant: An Efficient Post-Training Quantization for CNN-Transformer Hybrid Models on Edge Devices
par: Saha, Shaibal, et autres
Publié: (2025)

Free Video-LLM: Prompt-guided Visual Perception for Efficient Training-free Video LLMs
par: Han, Kai, et autres
Publié: (2024)

AlignHuman: Improving Motion and Fidelity via Timestep-Segment Preference Optimization for Audio-Driven Human Animation
par: Liang, Chao, et autres
Publié: (2025)

U-REPA: Aligning Diffusion U-Nets to ViTs
par: Tian, Yuchuan, et autres
Publié: (2025)

MGRQ: Post-Training Quantization For Vision Transformer With Mixed Granularity Reconstruction
par: Yang, Lianwei, et autres
Publié: (2024)

MPTQ-ViT: Mixed-Precision Post-Training Quantization for Vision Transformer
par: Tai, Yu-Shan, et autres
Publié: (2024)

GeminiFusion: Efficient Pixel-wise Multimodal Fusion for Vision Transformer
par: Jia, Ding, et autres
Publié: (2024)

Early-Bird Diffusion: Investigating and Leveraging Timestep-Aware Early-Bird Tickets in Diffusion Models for Efficient Training
par: Whalen, Lexington, et autres
Publié: (2025)

Post-Training Quantization for Video Matting
par: Zhu, Tianrui, et autres
Publié: (2025)

A Survey on Transformer Compression
par: Tang, Yehui, et autres
Publié: (2024)

Adaptive Non-uniform Timestep Sampling for Accelerating Diffusion Model Training
par: Kim, Myunsoo, et autres
Publié: (2024)