Quantization Error Compensation

Follow this topic Ask about this topic

Latest papers

16 papers3 papers in the last four weeks, against 2 the four weeks before. 0.0% of all new papers.

PerQ: Inverse Generative Modeling for Neural Image Compression via Quantization Error Compensation
Oct 19, 2026Tianhao Peng, Ho Man Kwan, Fan Zhang +2Quantization Error Compensation Learned Image Compression
Visual Information Lab, University of Bristol, UK · Tencent Media Lab, Palo Alto, USA
When Does Compensating Inherited Quantization Error Help? Mean-Square Guarantees for Layer-Wise Quantization and Their Limits
Oct 12, 2026Tianhao GuoQuantization Error Compensation Neural Network Quantization
College of Physics and Electronic Engineering, Shanxi University, Taiyuan 030006, China
Align, Then Correct: Training-Free Two-Stage Low-Rank Compensation for Extremely Quantized Large Language Models
Oct 6, 2026Seobin Song, Geonho Lee, Janghwan Lee +1LLM Quantization Post-Training Quantization
Hanyang University, Seoul, Republic of Korea · Qualcomm AI Research, Qualcomm Korea YH, Seoul, Republic of Korea
PulseQuant: Propagation-Guided Subspace Correction for 4-Bit Video Diffusion Transformers
Sep 27, 2026Yutong Wang, Xingtong Ge, Enhuai Liu +4Video Diffusion Models Diffusion Transformer
The University of Sydney · The Hong Kong University of Science and Technology · The Chinese University of Hong Kong +1
Understanding LLM Quantization through Activation-Guided Compensation and Orthogonal Residuals
Sep 18, 2026Yamato Narita, Issei SatoPost-Training Quantization Neural Network Quantization
Department of Computer Science, The University of Tokyo
SandwichQuant: Which Parameters Matter Before and After Quantization?
Aug 25, 2026Peng Xia, Junbiao PangNeural Network Quantization Quantization Error Compensation
School of Information Science and Technology, Beijing University of Technology Beijing, China
QuaSAR: Quantization Compensation via Stable Activation-Aware Rank Truncation
Aug 14, 2026Lin-Fa Lee, Yi-Yu Chang, Kuo-Hei YehQuantization Error Compensation Neural Network Quantization
Department of Institute of Artificial Intelligence Innovation National Yang Ming Chiao Tung University Hsinchu, Taiwan
Language-Conditional Dequantization: Recovering What Quantization Steals from Non-English Languages
Aug 12, 2026Nirmal ThomasLLM Quantization Post-Training Quantization
Prathama International
Cross-Layer Error Compensation and Finite-Sample Feature-Statistics Matching for Extreme Low-Bit Quantization of Large Language Models
Jul 16, 2026Ryona NodaLLM Quantization Binary Quantization
Ryo Noda
RDQ: Residual Distribution Quantization for Large Language Models
Jul 11, 2026Prateek SinghLLM Quantization Post-Training Quantization
SPEAR: A System for Post-Quantization Error-Adaptive Recovery Enabling Efficient Low-Bit LLM Serving
Jun 4, 2026Hongyuan Liu, Yawei Li, Zhiqiang Que +3LLM Quantization LLM Serving
University of Electronic Science and Technology of China · University of Bristol · 3ETH Zurich
Decomposing MXFP4 quantization error for LLM reinforcement learning: reducible bias, recoverable deadzone, and an irreducible floor
May 19, 2026Xiaocan Li, Shiliang Wu, Zheng ShenLLM Quantization 4-Bit Quantization
Huawei Canada
MARR: Module-Adaptive Residual Reconstruction for Low-Bit Post-Training Quantization
May 18, 2026Le Su, Xing Luo, Zhi JinLLM Quantization Post-Training Quantization
School of Intelligent Systems Engineering Shenzhen Campus of Sun Yat-sen University Shenzhen, Guangdong 518107, China · Department of Frontier Research Peng Cheng Laboratory Shenzhen, Guangdong 518055, China
Nonlinear Bipolar Compensation: Handling Outliers in Post-Training Quantization
May 14, 2026Peilin Sun, Jianxin WuActivation Outliers Quantization Error Compensation
State Key Laboratory of Novel Software Technology, Nanjing University, China · School of Artificial Intelligence, Nanjing University, China
Rethinking Residual Errors in Compensation-based LLM Quantization
Apr 9, 2026Shuaiting Li, Juncan Deng, Kedong Xu +5Quantization Error Compensation LLM Quantization
Zhejiang University · vivo Mobile Communication Co., Ltd
ARCQuant: Boosting NVFP4 Quantization with Augmented Residual Channels for LLMs
Jan 12, 2026Haoqian Meng, Yilun Luo, Yafei Zhao +3LLM Quantization 4-Bit Quantization
School of Computer Science and Technology, Tianjin University

Oct 19, 2026J/K move · Enter open · S save

PerQ: Inverse Generative Modeling for Neural Image Compression via Quantization Error Compensation

Tianhao Peng, Ho Man Kwan, Fan Zhang, Shan Liu+1

Visual Information Lab, University of Bristol, UK · Tencent Media Lab, Palo Alto, USA

Quantization Error Compensation Learned Image Compression Generative Image Compression

Open paper AskPDF arXiv

Neural image codecs face a fundamental trade-off between pixel fidelity and perceptual quality. Distortion-optimized codecs preserve pixel-wise fidelity but produce blurred reconstructions at low bitrates, whereas generative codecs leverage learned priors to improve perceptual quality but tend to exhibit saturating PSNR at higher bitrates and require separate models for different bitrate targets. We propose PerQ, which reframes perceptual reconstruction as inverse generative modeling with bounded support. Specifically, we define the quantization cell as the set of latents that yield the same transmitted symbols and derive a transport bound showing that reconstructions from this cell remain within a rate-determined radius of the codec output. This motivates performing generative reconstruction within the codec-induced quantization cell, rather than sampling from an unconstrained image prior. PerQ implements this principle by attaching a rate-conditioned flow-matching compensator to a frozen, multi-rate distortion-optimized backbone, enabling perceptual enhancement while preserving the backbone's coding performance. Experiments on Kodak and CLIC2020 show that PerQ achieves perceptual performance comparable to generative codecs such as MS-ILLM in LPIPS and FID, while maintaining competitive PSNR relative to distortion-optimized codecs such as ELIC. A single model checkpoint supports a wide bitrate range with fast decoding, and the compensator provides consistent gains across three different backbones. The implementation is available at https://jasminepp.github.io/PerQ/.