Cover Image

RobuQ: Pushing DiTs to W1.58A2 via Robust Activation Quantization

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Yang, Kaicheng, Zhang, Xun, Qin, Haotong, Lin, Yucheng, Yang, Kaisen, Yan, Xianglong, Zhang, Yulun
Format:	Preprint
Published:	2025
Subjects:	Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Q-DiT4SR: Exploration of Detail-Preserving Diffusion Transformer Quantization for Real-World Image Super-Resolution
by: Zhang, Xun, et al.
Published: (2026)

TreeQ: Pushing the Quantization Boundary of Diffusion Transformer via Tree-Structured Mixed-Precision Search
by: Yang, Kaicheng, et al.
Published: (2025)

QuantSR+: Pushing the Limit of Quantized Image Super-Resolution Networks
by: Qin, Haotong, et al.
Published: (2026)

BiDM: Pushing the Limit of Quantization for Diffusion Models
by: Zheng, Xingyu, et al.
Published: (2024)

AdaTSQ: Pushing the Pareto Frontier of Diffusion Transformers via Temporal-Sensitivity Quantization
by: Zhang, Shaoqiu, et al.
Published: (2026)

TaQ-DiT: Time-aware Quantization for Diffusion Transformers
by: Liu, Xinyan, et al.
Published: (2024)

MeshCraft: Exploring Efficient and Controllable Mesh Generation with Flow-based DiTs
by: He, Xianglong, et al.
Published: (2025)

Quant-dLLM: Post-Training Extreme Low-Bit Quantization for Diffusion Large Language Models
by: Zhang, Tianao, et al.
Published: (2025)

Progressive Binarization with Semi-Structured Pruning for LLMs
by: Yan, Xianglong, et al.
Published: (2025)

xDiT: an Inference Engine for Diffusion Transformers (DiTs) with Massive Parallelism
by: Fang, Jiarui, et al.
Published: (2024)

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

PT$^2$-LLM: Post-Training Ternarization for Large Language Models
by: Yan, Xianglong, et al.
Published: (2025)

BiLLM: Pushing the Limit of Post-Training Quantization for LLMs
by: Huang, Wei, et al.
Published: (2024)

QArtSR: Quantization via Reverse-Module and Timestep-Retraining in One-Step Diffusion based Image Super-Resolution
by: Zhu, Libo, et al.
Published: (2025)

Untwisting RoPE: Frequency Control for Shared Attention in DiTs
by: Mikaeili, Aryan, et al.
Published: (2026)

Unveiling Redundancy in Diffusion Transformers (DiTs): A Systematic Study
by: Sun, Xibo, et al.
Published: (2024)

U-DiTs: Downsample Tokens in U-Shaped Diffusion Transformers
by: Tian, Yuchuan, et al.
Published: (2024)

On-Chip Hardware-Aware Quantization for Mixed Precision Neural Networks
by: Huang, Wei, et al.
Published: (2023)

AnchorDiff: Training-Free Concept Grounding for MM-DiTs via Anchor-Based Graph Propagation
by: Zhang, Jian, et al.
Published: (2026)

On Statistical Rates and Provably Efficient Criteria of Latent Diffusion Transformers (DiTs)
by: Hu, Jerry Yao-Chieh, et al.
Published: (2024)

ReCalKV: Low-Rank KV Cache Compression via Head Reordering and Offline Calibration
by: Yan, Xianglong, et al.
Published: (2025)

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

DiVE: DiT-based Video Generation with Enhanced Control
by: Jiang, Junpeng, et al.
Published: (2024)

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

QVGen: Pushing the Limit of Quantized Video Generative Models
by: Huang, Yushi, et al.
Published: (2025)

SOAR: Scale Optimization for Accurate Reconstruction in NVFP4 Quantization
by: Bao, Chengzhu, et al.
Published: (2026)

DiT4DiT: Jointly Modeling Video Dynamics and Actions for Generalizable Robot Control
by: Ma, Teli, et al.
Published: (2026)

Rethinking Multi-Condition DiTs: Eliminating Redundant Attention via Position-Alignment and Keyword-Scoping
by: Zhou, Chao, et al.
Published: (2026)

HeadRouter: A Training-free Image Editing Framework for MM-DiTs by Adaptively Routing Attention Heads
by: Xu, Yu, et al.
Published: (2024)

Improving Sampling for Masked Diffusion Models via Information Gain
by: Yang, Kaisen, et al.
Published: (2026)

TQ-DiT: Efficient Time-Aware Quantization for Diffusion Transformers
by: Hwang, Younghye, et al.
Published: (2025)

LRQ-DiT: Log-Rotation Post-Training Quantization of Diffusion Transformers for Image and Video Generation
by: Yang, Lianwei, et al.
Published: (2025)

QuantFace: Efficient Quantization for Face Restoration
by: Li, Jiatong, et al.
Published: (2025)

PassionSR: Post-Training Quantization with Adaptive Scale in One-Step Diffusion based Image Super-Resolution
by: Zhu, Libo, et al.
Published: (2024)

Low-bit Model Quantization for Deep Neural Networks: A Survey
by: Liu, Kai, et al.
Published: (2025)

DiT-HC: Enabling Efficient Training of Visual Generation Model DiT on HPC-oriented CPU Cluster
by: Zhang, Jinxiao, et al.
Published: (2026)

Q-MambaIR: Accurate Quantized Mamba for Efficient Image Restoration
by: Chen, Yujie, et al.
Published: (2025)

BiVM: Accurate Binarized Neural Network for Efficient Video Matting
by: Qin, Haotong, et al.
Published: (2025)

FlashEdit: Decoupling Speed, Structure, and Semantics for Precise Image Editing
by: Wu, Junyi, et al.
Published: (2025)

GenMask: Adapting DiT for Segmentation via Direct Mask Generation
by: Yang, Yuhuan, et al.
Published: (2026)