Vector Quantization

Also known as VQ

Follow this topic Ask about this topic

Momentum

8 papers in the last four weeks, level with the four weeks before. 0.1% of all new papers.

Jul 13Week of Sep 28

Latest papers 86

All topics

Distributional Matching for Vector Quantization: A Unified Theoretical and Empirical Framework
Jul 17, 2026Xianghong Fang, Litao Guo, Hengchao Chen +8Distribution Matching Vector Quantization
University of Toronto · The Hong Kong University of Science and Technology · Lehigh University +2
AVQ-Attention: Adaptive Vector-Quantized Attention
Jul 14, 2026Winfried van den dool, Patrick Forré, Amir Habibian +2Transformer Attention Vector Quantization
QUVA Lab, University of Amsterdam, The Netherlands · AMLab, Informatics Institute, University of Amsterdam, The Netherlands · AI4Science Lab, University of Amsterdam, The Netherlands +3
Clustered Codebook Quantization for 2D Gaussian-based Image Compression
Jul 6, 2026Runze Cheng, Yicheng Zhan, Josef Spjut +1Learned Image Compression Vector Quantization
University College London · London, UK · NVIDIA +1
Sparse-Aware Vector Quantization for Bandwidth-Efficient Collaborative 3D Semantic Occupancy Prediction
Jul 2, 2026Feng Li, Chaokun Zhang, Gong ChenCommunication-Efficient Collaborative Perception 3D Occupancy Prediction
School of Computer Science and Technology, Tianjin University, Tianjin, China · School of Cybersecurity, Tianjin University, Tianjin, China
GSRQ: Gain-Shape Residual Quantization for Sub-1-bit KV Cache
Jul 1, 2026Soosung Kim, Minjae Park, Eui-Young Chung +1LLM Compression Residual VQ
Department of Electrical and Electronic Engineering, Yonsei University, Seoul, Republic of Korea · Department of Systems Semiconductor Engineering, Yonsei University, Seoul, Republic of Korea
GEAR: Guided End-to-End AutoRegression for Image Synthesis
Jun 30, 2026Bin Lin, Zheyuan Liu, Chenguo Lin +8Vector Quantization Autoregressive Image Generation
Peking University · Tencent Hunyuan
CascadeOcc: Rethinking 3D Occupancy World Models with Cascaded VQ Representations
Jun 26, 2026Kyumin Hwang, Wonhyeok Choi, Jaeyeul Kim +3World Model Learning 3D Occupancy Prediction
Daegu Gyeongbuk Institute of Science and Technology (DGIST), Daegu 42988, South Korea
Safe Autoregressive Image Generation with Iterative Self-Improving Codebooks
Jun 25, 2026Yunqi Xue, Zhijiang Li, Philip Torr +1T2I Generation Image Generation
School of Information Management, Wuhan University, Wuhan, China · Torr Vision Group, University of Oxford, Oxford, United Kingdom
Enhancing BEST-RQ Pseudo-Label Quality through Online Refinement for Automatic Speech Recognition
Jun 24, 2026Jingjing Xu, Zijian Yang, Mohammad Zeineldeen +3Automatic Speech Recognition Vector Quantization
Machine Learning and Human Language Technology Group, RWTH Aachen University, Germany · Apptek GmbH, Aachen, Germany
VQActFlow: Vector-Quantized Action Mode Steering for Multi-Task Robot Manipulation
Jun 19, 2026Zhigen Zhao, Mark Leggiero, Yipu Chen +5Latent Action Learning Language-Conditioned Robot Manipulation
Institute for Robotics and Intelligent Machines (IRIM), Georgia Institute of Technology, Atlanta, GA 30332
Fast-TurboQuant: A Multiplier-Free Online Vector Quantization Approach
Jun 19, 2026Pedro M. R. Pereira, Felipe A. P. de Figueiredo, Rausley A. A. de SouzaLLM Quantization Rotation-Based Quantization
National Institute of Telecommunications (Inatel), Santa Rita do Sapucaí, MG 37536-001, Brazil
Towards Robust Generative Speech Enhancement Using Vector Quantisation-Based Neural Audio Codec
Jun 15, 2026Haixin Zhao, Nilesh MadhuNeural Audio Codecs Vector Quantization
IDLab, Ghent University - imec, Belgium
VQ4SNN: Vector Quantization for Memory-Efficient FPGA Spiking Neural Networks
Jun 12, 2026Dimitrios Sekertzis, Giorgos DimitrakopoulosMemory-Efficient Inference Vector Quantization
Integrated Circuits Lab, Electrical and Computer Engineering, Democritus University of Thrace (DUTH), Greece
NSVQ: Mitigating Codebook Collapse by Stabilizing Encoder Drift in Vector Quantization
Jun 9, 2026Hao Lu, Yongxin Guo, Onur Koyun +3Vector Quantization
Wake Forest University School of Medicine / Advocate Health · Wake Forest University School of Medicine · Advocate Health
UniSVQ: 2-bit Unified Scalar-Vector Quantization
Jun 9, 2026Haoyu Wang, Haiyan Zhao, Xingyu Yu +4LLM Quantization Vector Quantization
Department of Computer Science and Technology, Tsinghua University, Beijing, China · School of Software and Microelectronics, Peking University, Beijing, China · School of Physics, Beihang University, Beijing, China
ColBERTSaR: Sparsified ColBERT Index via Product Quantization
Jun 4, 2026Eugene Yang, Andrew Yates, Dawn Lawrie +3Vector Quantization Multi-Vector Retrieval
Johns Hopkins University, Baltimore, MD, USA
Adversarial Attacks on Robot Localization Systems via Deep Feature Perturbation
Jun 1, 2026Zhenyu Li, Tianyi ShangAdversarial Attacks Vector Quantization
Shandong Academy of Sciences · Fuzhou University
HiTokSR: A Coarse-to-Fine Tokenizer with Hierarchical Codebooks for High-Fidelity Real-World Image Super-Resolution
May 31, 2026Mingxi LiImage Tokenization Vector Quantization
Inner Product Aware Quantization: Provably Fast, Accurate, and Adaptive Algorithms
May 29, 2026Nathan White, Krish SingalVector Quantization Neural Network Quantization
University of Pennsylvania
MergeTok: Unified Continuous and Discrete Visual Tokenization via Token Merging
May 29, 2026Luyuan Zhang, Siyuan Li, Zedong Wang +7Variational Autoencoders Token Merging
1Tsinghua University · 2Westlake University · 3Zhejiang University +3
QAM-W: Joint 2D Codebook Quantization for LLM Weights via Hadamard Rotation and Activation-Aware Scaling
May 25, 2026Preetam Sharma, Kacper DobekLLM Quantization Rotation-Based Quantization
Independent Research · Institute of Computing Science Poznan University of Technology, Poznan, Poland
Channel-wise Vector Quantization
May 25, 2026Wei Song, Tianhang Wang, Yitong Chen +5Image Tokenization Visual Tokenization
Shanghai Innovation Institute · Westlake University · Zhejiang University +2
EVA: Accelerating LLM Decoding via an Efficient Vector Quantization Architecture
May 22, 2026Bowen Duan, Cong Guo, Chiyue Wei +8Vector Quantization LLM Inference Acceleration
Duke University, USA
Efficient Learned Image Compression without Entropy Coding
May 22, 2026Hao Cao, Wenqi Guo, Zhijin Qin +1Learned Image Compression Vector Quantization
Department of Electronic Engineering, Tsinghua University · Department of Automation, Tsinghua University · State Key Laboratory of Space Network and Communications +1
OCTOPUS: Optimized KV Cache for Transformers via Octahedral Parametrization Under optimal Squared error quantization
May 20, 2026Mark Boss, Vikram Voleti, Simon Donné +1KV Caching Memory-Efficient Optimization
Stability AI
MGVQ: Synergizing Multi-dimensional Sensitivity-Aware and Gradient-Hessian Fusion for Vector Quantization
May 20, 2026Zhong Wang, Zukang Xu, Xing Hu +1Mixed-Precision Quantization Vision-Language Models
Bauman Moscow State Technical University · Houmo AI
Block-Sphere Vector Quantization
May 19, 2026Heesang Ann, Joongkyu Lee, Min-hwan OhRotation-Based Quantization Vector Quantization
Seoul National University
IVF-TQ: Calibration-Free Streaming Vector Search via a Codebook-Free Residual Layer
May 17, 2026Tarun SharmaVector Quantization Approximate Nearest Neighbor Search
Independent Researcher USA
VQ-Atom: Semantic Discretization of Local Atomic Environments for Molecular Representation Learning
May 16, 2026Takayuki KimuraVector Quantization Molecular Representation Learning
Atoms as Language, LLC
PrismQuant: Rate-Distortion-Optimal Vector Quantization for Gaussian-Mixture Sources
May 15, 2026Bumsu Park, Chanho Park, Youngmok Park +1Rate-Distortion Theory Gaussian Mixture Models
Department of Electrical Engineering POSTECH Pohang, South Korea

Jul 17, 2026, cs.CVJ/K move · Enter open · S save

Distributional Matching for Vector Quantization: A Unified Theoretical and Empirical Framework

Xianghong Fang, Litao Guo, Hengchao Chen, Yuxuan Zhang+7

University of Toronto · The Hong Kong University of Science and Technology · Lehigh University+2

Distribution Matching Vector Quantization

Open paper AskPDF arXiv

The effectiveness of modern visual representation learning and autoregressive models critically depends on vector quantization (VQ), which discretizes continuous feature representations using a learnable codebook. Despite its widespread use, existing VQ methods often suffer from training instability and codebook collapse, arising from gradient mismatch induced by the straight-through estimator and the under-utilization of code vectors. In this work, we show that both issues can be traced to a fundamental mismatch between the distributions of feature vectors and code vectors, leading to inefficient representation and information loss. Building on this observation, we propose a distributional matching framework for vector quantization. We introduce principled criteria for desirable VQ behavior and demonstrate through theoretical analysis and empirical evaluation that aligning feature and code vector distributions provides a unifying mechanism for mitigating training instability and codebook collapse. We instantiate this framework using a Wasserstein-based objective with an efficient closed-form under a mild Gaussian approximation, and further show that a nonparametric alternative based on maximum mean discrepancy yields comparable performance. Extensive experiments on visual tokenization benchmarks support the effectiveness and robustness of the proposed approach.

Momentum

Related topics

Latest papers 86