Vector Quantization

Also known as VQ

Ask about this topic

Overview

Vector quantization replaces continuous vectors with indices into a set of representative codewords, reducing storage and creating discrete tokens for models. Common approaches learn codebooks with autoencoders, use residual or product quantization, or impose geometric structure such as lattices and spheres; they are evaluated on image and audio reconstruction, vector retrieval, language-model quality, and inference speed. Applications range from visual and speech tokenizers to compressed LLM weights and attention caches, where specialized kernels can determine whether smaller representations also run faster. A central tension is preserving task-relevant information at very low bit rates while avoiding codebook collapse, calibration costs, and hardware overhead; utilization alone does not guarantee low distortion or strong downstream results.

Latest papers

CardsList

122 papers20 papers in the last four weeks, up 67% on the four weeks before. 0.1% of all new papers.

  1. Can Discrete Tokens Serve as Semantically Lossless Representations of Visual Signals?

    Oct 27, 2026Jialv Zou, Xiaotong Li, Zhengrong Yue +6Visual Representation LearningVector Quantization

    Huazhong University of Science and Technology · Meituan LongCat · Shanghai Jiao Tong University +4

  2. CoS-VQ: Coordinated Shared-Scale Vector Quantization for Large Language Models

    Oct 27, 2026Zukang Xu, Zhixiong Zhao, Xing Hu +3LLM QuantizationVector Quantization

    Houmo AI · Peking University · Southeast University

  3. Transporting Quantiles to Codebook: Scalable Vector Quantization without Codebook Collapse

    Oct 26, 2026Yuwei Zeng, Zekun ShiVector QuantizationVector-Quantized Variational Autoencoder

    National University of Singapore · SEA AI Lab

  4. From Perception to Pixels: Human-Derived Visually Distinct Colors for Improved Dominant Color Extraction

    Oct 23, 2026Uldana Shyndali, Nurdaulet Toleugaliyev, Kuat Zharykbayev +2Human Visual PerceptionVector Quantization

    Kazakh-British Technical University, School of Information Technology and Engineering, Tole bi 59, Almaty, 050000, Kazakhstan

  5. SQuAT: Spherical Lattice Vector Quantization-Aware Training

    Oct 22, 2026Sebastian Loeschcke, Ivan Koryakovskiy, Tycho F. A. van der Ouderaa +4LLM QuantizationVector Quantization

    University of Copenhagen · Qualcomm AI Research

  6. Extreme Compression of Per-Layer Embeddings via Cross-Layer Latent Vector Quantization

    Oct 22, 2026Jiacheng Liu, Yaxin Luo, Xiaohan Zhao +5Embedding CompressionLLM Compression

    Mohamed bin Zayed University of Artificial Intelligence · Westlake University · Zhejiang University +2

  7. ClunoGS: Compact Language 3D Gaussian Splatting via Unified Optimization

    Oct 21, 2026Jian Xu, Yi Li, Ying Huang +43DGS CompressionLanguage-Embedded 3DGS

  8. Beyond 4 bits: Data-Centric Post-training Quantization and Recovery

    Oct 20, 2026Rhea Sanjay Sukthanker, Riccardo Grazzi, James Hensman +1LLM QuantizationPost-Training Quantization

    Applied Sciences Group (ASG), Microsoft · Microsoft Research

  9. E8-QAT: Efficient 2-Bit Quantization-Aware Training with Implicit Lattice Codebooks

    Oct 20, 2026Xinyu Lei, Hong Huang, Jiebin Zhang +6LLM QuantizationQuantization-Aware Training

    Peking University · City University of Hong Kong · Tencent

  10. Discrete Neural Interlingua for Ontology-Agnostic EHR Modeling

    Oct 19, 2026Tong Ding, Caiwei Tian, Dongmin Bang +6Tokenization in Language ModelsEHR Foundation Models

    Mass General Brigham AI Institute · Harvard University · Massachusetts Institute of Technology

  11. TRACE: Transformer Residual Activation Codebook Encoding for Communication-efficient Distributed Edge Inference

    Oct 15, 2026Muhammad Azlan Qazi, Alexandros Iosifidis, Qi ZhangEfficient Transformer InferenceTransformer Inference

    DIGIT and the Department of Electrical and Computer Engineering, Aarhus University, Denmark · the Data Science Research center, Tampere University, Finland

  12. Sliced Wasserstein Sketches with Error Certificates

    Oct 14, 2026Elaheh Akbari, James Liu, Keaton Hamm +1Sliced Wasserstein DistanceVector Quantization

    College of Connected Computing, Vanderbilt University · Department of Mathematics, Division of Data Science, University of Texas at Arlington

  13. E8 Lattice Key Quantization for Low-Bit KV-Cache Compression

    Oct 11, 2026Sasho Nedelkoski, Alexander Acker, Soeren Becker +2KV-Cache CompressionKV-Cache Quantization

    Technical University of Berlin Berlin, Germany · logsight.ai Berlin, Germany

  14. SAGE: Pushing 2-Bit Vector-Quantized LLMs toward Real-World Usability

    Oct 10, 2026Xianglong Yan, Zenan Wu, Kewei Zhang +2LLM QuantizationWeight-Only Quantization

    Shanghai Jiao Tong University

  15. The Polytopal Neural Network

    Oct 8, 2026A. Emilie J. Wedenborg, Anders V. Nørskov, Teresa Dorszewski +2Neural Network InterpretabilityGeometric Representation Learning

    Technical University of Denmark · UiT The Arctic University of Norway

  16. Optimal random quantisers for spherically symmetric distributions

    Oct 8, 2026Luc Pronzato, Anatoly ZhigljavskyVector QuantizationRate-Distortion Optimization

    Laboratoire I3S, CNRS-Université Côte d’Azur, Sophia Antipolis, France · School of Mathematics, Cardiff University, UK

  17. OrBIT: Structure-Guided Embedding Compression

    Oct 7, 2026Yunied Puig, Amit Kumar JaiswalEmbedding CompressionLLM Compression

    Jay Chaudhry Software Innovation Centre Indian Institute of Technology (BHU) Varanasi, India

  18. A Systematic Study of Semantic ID Spaces for Generative Information Retrieval

    Oct 6, 2026Alexia Allal, Hicham Randrianarivo, Sylvain LamprierResidual VQVector Quantization

    Artefact Research Center Paris, France · LERIA, Angers University Angers, France

  19. BARQ: Balanced Codebook Refinement for Low-Bit LLM Quantization

    Oct 3, 2026Chenhang Cui, Xu Xie, Linrui Xu +4LLM QuantizationLow-Bit Quantization

    National University of Singapore · Independent Researcher · Central South University

  20. Tailoring the Quantization Space for 1-Bit KV Cache Compression

    Oct 2, 2026Minsoo Cheong, Donghyun Son, Sungjoo YooBinary QuantizationKV-Cache Compression

    Stanford University · Seoul National University

  21. Derandomizing Dense Binary Hypervector Codebooks for Quantized Scalars

    Sep 29, 2026Dmitri Rachkovskij, Evgeny Osipov, Olexander Volkov +2Vector QuantizationHyperdimensional Computing

    Department of Computer Science, Electrical and Space Engineering, Luleå University of Technology, 971 87 Luleå, Sweden · Institute of Information Technologies and Systems, 03187 Kyiv, Ukraine · AI, Robotics and Cybersecurity Center (ARC) and Department of Computer Science, Örebro University, 70182 Örebro, Sweden +2

  22. FineSID: Scalable and Efficient Semantic Identifier Learning for Generative Recommendation

    Sep 29, 2026Song-Li Wu, Weinan Gan, Zhaocheng Du +2Semantic ID RecommendationVector Quantization

    Tsinghua University · Huawei Noah’s Ark Lab · University of Science and Technology of China

  23. TORQUE: Optimizing What (not) to Quantize Before and After Rotation

    Sep 28, 2026Ran Ben Basat, Michael Mitzenmacher, Shay VargaftikRotation-Based QuantizationVector Quantization

    University College London · Harvard University · VMware Research by Broadcom

  24. StableVQ: Practical Guidelines for Stable Vector-Quantized Tokenizer Training

    Sep 22, 2026Bao Tang, Jiahao Guo, Haoxiang Cao +4Straight-Through EstimatorVector Quantization

    Huazhong University of Science and Technology · KlingAI Research · South China Normal University

  25. SPHQuant: Efficient extreme low bit weight quantization for Vision-Language Models

    Sep 21, 2026Kewei Zhang, Zheng Chen, Haotong Qin +1VLM QuantizationEfficient VLM Inference

    Shanghai Jiao Tong University · The Hong Kong Polytechnic University

  26. ActionPiece: Rethinking Action Tokenization for Autoregressive Vision-Language-Action Models

    Sep 16, 2026Shijie Lian, Bin Yu, Zhaolong Shen +5Vector QuantizationRobotic Manipulation

    Huazhong University of Science and Technology · Zhongguancun Academy · DeepCybo +5

  27. M2Tok: Multi-head Multi-codebook Discrete Action Tokenization for Vision-Language-Action Models

    Sep 16, 2026Chunpu Xu, Zhixuan Liang, Yuhao Zhang +6Vector QuantizationVision-Language-Action Models

    The Hong Kong Polytechnic University, HongKong SAR, China · Shanghai AI Laboratory, Shanghai, China · The University of Hong Kong, HongKong SAR, China +2

  28. Storage-Scalable Progressive Semantic Communication via Knowledge-Base Reuse

    Sep 9, 2026Heng Zhu, Ye Liu, Kun Zhu +1Residual VQSemantic Communication

    College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics, Nanjing 210016, China

  29. When Does Low-Bit Quantization Preserve the Decisions of Vector Search?

    Sep 9, 2026Wenxuan Xiao, Xu CaoVector QuantizationLow-Bit Quantization

    Astrmira Tech.

  30. Tree-VQ: Progressive Image Compression from Pretrained Vector Quantizers

    Sep 3, 2026Mingming Ma, Xinkun Wang, Tianyi Xu +3Learned Image CompressionVector Quantization

    School of Artificial Intelligence Xidian University