Imagen de Portada

HadaNorm: Diffusion Transformer Quantization through Mean-Centered Transformations

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Federici, Marco, Del Chiaro, Riccardo, van Breugel, Boris, Whatmough, Paul, Nagel, Markus
Formato:	Preprint
Publicado:	2025
Materias:	Computer Vision and Pattern Recognition Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

STaMP: Sequence Transformation and Mixed Precision for Low-Precision Activation Quantization
por: Federici, Marco, et al.
Publicado: (2025)

Dissecting Quantization Error: A Concentration-Alignment Perspective
por: Federici, Marco, et al.
Publicado: (2026)

FPTQuant: Function-Preserving Transforms for LLM Quantization
por: van Breugel, Boris, et al.
Publicado: (2025)

Low-Rank Quantization-Aware Training for LLMs
por: Bondarenko, Yelysei, et al.
Publicado: (2024)

Q-DiT: Accurate Post-Training Quantization for Diffusion Transformers
por: Chen, Lei, et al.
Publicado: (2024)

Hardware-Friendly Static Quantization Method for Video Diffusion Transformers
por: Yi, Sanghyun, et al.
Publicado: (2025)

HQ-DiT: Efficient Diffusion Transformer with FP4 Hybrid Quantization
por: Liu, Wenxuan, et al.
Publicado: (2024)

CLQ: Cross-Layer Guided Orthogonal-based Quantization for Diffusion Transformers
por: Liu, Kai, et al.
Publicado: (2025)

Soft Mixture Denoising: Beyond the Expressive Bottleneck of Diffusion Models
por: Li, Yangming, et al.
Publicado: (2023)

Reflection Removal through Efficient Adaptation of Diffusion Transformers
por: Zakarin, Daniyar, et al.
Publicado: (2025)

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

Mixed Non-linear Quantization for Vision Transformers
por: Kim, Gihwan, et al.
Publicado: (2024)

PipeFlow: Pipelined Processing and Motion-Aware Frame Selection for Long-Form Video Editing
por: Munir, Mustafa, et al.
Publicado: (2025)

Amortized-Precision Quantization for Early-Exit Vision Transformers
por: Fang, Rui, et al.
Publicado: (2026)

BWCache: Accelerating Video Diffusion Transformers through Block-Wise Caching
por: Cui, Hanshuai, et al.
Publicado: (2025)

Boosting Camera Motion Control for Video Diffusion Transformers
por: Cheong, Soon Yau, et al.
Publicado: (2024)

DDT: Decoupled Diffusion Transformer
por: Wang, Shuai, et al.
Publicado: (2025)

MeanFlow Transformers with Representation Autoencoders
por: Hu, Zheyuan, et al.
Publicado: (2025)

Impact of Layer Norm on Memorization and Generalization in Transformers
por: Singhal, Rishi, et al.
Publicado: (2025)

SDiT: Spiking Diffusion Model with Transformer
por: Yang, Shu, et al.
Publicado: (2024)

Region-Adaptive Sampling for Diffusion Transformers
por: Liu, Ziming, et al.
Publicado: (2025)

DFQ-ViT: Data-Free Quantization for Vision Transformers without Fine-tuning
por: Tong, Yujia, et al.
Publicado: (2025)

Decoding Vision Transformers: the Diffusion Steering Lens
por: Takatsuki, Ryota, et al.
Publicado: (2025)

Dual Prompting Image Restoration with Diffusion Transformers
por: Kong, Dehong, et al.
Publicado: (2025)

Generative Pre-trained Autoregressive Diffusion Transformer
por: Zhang, Yuan, et al.
Publicado: (2025)

VQ4DiT: Efficient Post-Training Vector Quantization for Diffusion Transformers
por: Deng, Juncan, et al.
Publicado: (2024)

Trio-ViT: Post-Training Quantization and Acceleration for Softmax-Free Efficient Vision Transformer
por: Shi, Huihong, et al.
Publicado: (2024)

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

DVD-Quant: Data-free Video Diffusion Transformers Quantization
por: Li, Zhiteng, et al.
Publicado: (2025)

QuEPT: Quantized Elastic Precision Transformers with One-Shot Calibration for Multi-Bit Switching
por: Xu, Ke, et al.
Publicado: (2026)

PQV-Mobile: A Combined Pruning and Quantization Toolkit to Optimize Vision Transformers for Mobile Applications
por: Bhardwaj, Kshitij
Publicado: (2024)

Progressive Fine-to-Coarse Reconstruction for Accurate Low-Bit Post-Training Quantization in Vision Transformers
por: Ding, Rui, et al.
Publicado: (2024)

IPTQ-ViT: Post-Training Quantization of Non-linear Functions for Integer-only Vision Transformers
por: Kim, Gihwan, et al.
Publicado: (2025)

SpotEdit: Selective Region Editing in Diffusion Transformers
por: Qin, Zhibin, et al.
Publicado: (2025)

DDiT: Dynamic Patch Scheduling for Efficient Diffusion Transformers
por: Kim, Dahye, et al.
Publicado: (2026)

VMonarch: Efficient Video Diffusion Transformers with Structured Attention
por: Liang, Cheng, et al.
Publicado: (2026)

Rethinking Cross-Layer Information Routing in Diffusion Transformers
por: Xu, Chao, et al.
Publicado: (2026)

Image-Conditional Diffusion Transformer for Underwater Image Enhancement
por: Nie, Xingyang, et al.
Publicado: (2024)

OminiControl2: Efficient Conditioning for Diffusion Transformers
por: Tan, Zhenxiong, et al.
Publicado: (2025)

DT-NVS: Diffusion Transformers for Novel View Synthesis
por: Jang, Wonbong, et al.
Publicado: (2025)