CentriQ: Calibration-Free Quantization of Diffusion Transformers via Exact Mean Centering

arXiv:2610.06260 · cs.CV, cs.AI, cs.RO · Submitted 2026-10-05 · Read on arXiv

cs.CV, cs.AI, cs.RO

Submitted: 2026-10-05

Updated: 2026-10-05

Project page: https://dropbox.github.io/hqq_blog

Terminology

• Calibration — 1× in this paper · explained in 7 episodes
• Quantization — 1× in this paper · explained in 12 episodes
• Transformer — 1× in this paper · explained in 2 episodes

Sources

• ConvRot: Rotation-Based Plug-and-Play 4-bit Quantization for Diffusion Transformers
• OrbitQuant: Data-Agnostic Quantization for Image and Video Diffusion Transformers
• HQ-DiT: Efficient Diffusion Transformer with FP4 Hybrid Quantization
• Q-Drift: Quantization-Aware Drift Correction for Diffusion Model Sampling
• DiRotQ: Rotation-Aware Quantization for 4-bit Diffusion Transformers
• LRQ-DiT: Log-Rotation Post-Training Quantization of Diffusion Transformers for Image and Video Generation
• AdaTSQ: Pushing the Pareto Frontier of Diffusion Transformers via Temporal-Sensitivity Quantization

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models