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. Quantizing With Randomized Hadamard Transforms: Efficient Heuristic Now Proven

    May 7, 2026Ran Ben-Basat, William Kuszmaul, Michael Mitzenmacher +2QuantizationRotation-Based Quantization

    UCL and Broadcom · Carnegie Mellon University · Harvard University +2

  2. Efficient Multivector Retrieval with Token-Aware Clustering and Hierarchical Indexing

    Apr 30, 2026Silvio Martinico, Franco Maria Nardini, Cosimo Rulli +1ClusteringVector Quantization

    University of Pisa & ISTI–CNR · Pisa, Italy · ISTI–CNR +1

  3. Efficient VQ-QAT and Mixed Vector/Linear quantized Neural Networks

    Apr 25, 2026Terry Gou, Puneet GuptaQuantization-Aware TrainingVector Quantization

  4. FASQ: Flexible Accelerated Subspace Quantization for Calibration-Free LLM Compression

    Apr 22, 2026Ye Qiao, Yian Wang, Zhiheng Chen +2LLM CompressionGPU Acceleration

    University of California, Irvine Irvine, California, USA

  5. Revisiting RaBitQ and TurboQuant: A Symmetric Comparison of Methods, Theory, and Experiments

    Apr 21, 2026Jianyang Gao, Yutong Gou, Yuexuan Xu +5Vector QuantizationKV-Cache Quantization

    ETH Zurich · Nanyang Technological University · University of Michigan +2

  6. A Note on TurboQuant and the Earlier DRIVE/EDEN Line of Work

    Apr 20, 2026Ran Ben-Basat, Yaniv Ben-Itzhak, Gal Mendelson +3Residual VQVector Quantization

    UCL and Broadcom · VMware Research by Broadcom · North Carolina State University +2

  7. AQPIM: Breaking the PIM Capacity Wall for LLMs with In-Memory Activation Quantization

    Apr 20, 2026Kosuke Matsushima, Yasuyuki Okoshi, Masato Motomura +1Compute-in-MemoryLong-Context Language Model Inference

    Institute of Science Tokyo†

  8. A Hierarchical Spatiotemporal Action Tokenizer for In-Context Imitation Learning in Robotics

    Apr 16, 2026Fawad Javed Fateh, Ali Shah Ali, Murad Popattia +4ICL for RoboticsVector Quantization

    Retrocausal, Inc., Redmond, WA 98052, USA

  9. Unsupervised Skeleton-Based Action Segmentation via Hierarchical Spatiotemporal Vector Quantization

    Apr 16, 2026Umer Ahmed, Syed Ahmed Mahmood, Fawad Javed Fateh +3Temporal Action SegmentationVector Quantization

    Retrocausal, Inc. Redmond, WA

  10. Self-Organizing Maps with Optimized Latent Positions

    Apr 15, 2026Seiki Ubukata, Akira Notsu, Katsuhiro HondaSelf-Organizing MapsTopological Mapping

    Graduate School of Informatics Osaka Metropolitan University Osaka 599-8531, Japan · Graduate School of Sustainable System Sciences Osaka Metropolitan University Osaka 599-8531, Japan

  11. Differentiable Vector Quantization for Rate-Distortion Optimization of Generative Image Compression

    Apr 12, 2026Shiyin Jiang, Wei Long, Minghao Han +3Generative Image CompressionVector Quantization

    University of Electronic Science and Technology of China · The University of Newcastle, Australia

  12. CodeQuant: Unified Clustering and Quantization for Enhanced Outlier Smoothing in Low-Precision Mixture-of-Experts

    Apr 12, 2026Xiangyang Yin, Xingyu Liu, Tianhua Xia +5Mixture-of-Experts QuantizationNeural Network Quantization

    Courant Institute of Mathematical Sciences, New York University · Tandon School of Engineering, New York University · Cerebras Systems Inc.

  13. Minimal Information Control Invariance via Vector Quantization

    Apr 3, 2026Ege Yuceel, Teodor Tchalakov, Sayan MitraSafety-Critical ControlVector Quantization

    Department of Electrical and Computer Engineering, University of Illinois at Urbana-Champaign, Urbana, IL 61801, USA.

  14. Investigating Permutation-Invariant Discrete Representation Learning for Spatially Aligned Images

    Apr 2, 2026Jamie S. J. Stirling, Noura Al-Moubayed, Hubert P. H. ShumVector QuantizationImage Generation

    Durham University, United Kingdom

  15. IsoQuant: Hardware-Aligned SO(4) Isoclinic Rotations for LLM KV Cache Compression

    Mar 30, 2026Zhongping JiRotation-Based QuantizationKV-Cache Compression

  16. SmaAT-QMix-UNet: A Parameter-Efficient Vector-Quantized UNet for Precipitation Nowcasting

    Mar 23, 2026Nikolas Stavrou, Siamak MehrkanoonPrecipitation NowcastingU-Net

    Department of Information and Computing Sciences, Utrecht University, Utrecht, Netherlands

  17. Early Quantization Shrinks Codebook: A Simple Fix for Diversity-Preserving Tokenization

    Mar 17, 2026Wenhao Zhao, Qiran Zou, Rushi Shah +3Vector QuantizationRepresentation Collapse

    National University of Singapore · Zhejiang University · Shanghai Jiao Tong University

  18. Mitigating Premature Discretization with Progressive Quantization for Robust Vector Tokenization

    Mar 17, 2026Wenhao Zhao, Qiran Zou, Zhouhan Lin +1Vector QuantizationVisual Tokenization

    National University of Singapore, Singapore · Shanghai Jiao Tong University, Shanghai, China

  19. VQKV: High-Fidelity and High-Ratio Cache Compression via Vector-Quantization

    Mar 17, 2026Yixuan Wang, Qingyu Shi, Jiayu Zhou +3KV-Cache CompressionKV-Cache Quantization

    LUMIA Lab, School of Artificial Intelligence, Shanghai Jiao Tong University · Shanghai Innovation Institute · Shanghai Artificial Intelligence Laboratory +2

  20. SNCE: Geometry-Aware Supervision for Scalable Discrete Image Generation

    Mar 16, 2026Shufan Li, Jiuxiang Gu, Kangning Liu +3Image GenerationVector Quantization

    Adobe · UCLA

  21. Leech Lattice Vector Quantization for Efficient LLM Compression

    Mar 11, 2026Tycho F. A. van der Ouderaa, Mart van Baalen, Paul Whatmough +1LLM QuantizationLLM Compression

    Qualcomm AI Research

  22. CONSTANT: Towards High-Quality One-Shot Handwriting Generation with Patch Contrastive Enhancement and Style-Aware Quantization

    Mar 8, 2026Anh-Duy Le, Van-Linh Pham, Thanh-Nam Vo +2Image GenerationDiffusion-Based Image Generation

    Viettel Artificial Intelligence and Data Services Center, Vietnam · Ho Chi Minh City University of Technology, Vietnam

  23. Vector-Quantized Soft Label Compression for Dataset Distillation

    Mar 4, 2026Ali Abbasi, Ashkan Shahbazi, Hamed Pirsiavash +1Dataset DistillationVector Quantization

    Vanderbilt University · University of California, Davis

  24. PCA-VAE: Differentiable Subspace Quantization without Codebook Collapse

    Feb 21, 2026Hao Lu, Onur C. Koyun, Yongxin Guo +3Vector QuantizationVector-Quantized Variational Autoencoder

    Wake Forest University School of Medicine, Winston-Salem, NC, USA

  25. Beyond Stationarity: Rethinking Codebook Collapse in Vector Quantization

    Feb 21, 2026Hao Lu, Onur C. Koyun, Yongxin Guo +3Vector Quantization

    Wake Forest University School of Medicine, Winston-Salem, NC, USA

  26. VP-VAE: Rethinking Vector Quantization via Adaptive Vector Perturbation

    Feb 19, 2026Linwei Zhai, Han Ding, Mingzhi Lin +5Finite Scalar QuantizationVector-Quantized Variational Autoencoder

    Xi’an Jiaotong University, China

  27. LGQ: Learnable Geometric Quantization for Image Tokenization

    Feb 17, 2026Idil Bilge Altun, Mert Onur Cakiroglu, Elham Buxton +2Image TokenizationVector Quantization

    Luddy School of Informatics, Computing, and Engineering, Indiana University Bloomington, Bloomington, IN, USA · Department of Computer Science, University of Illinois Springfield, Springfield, IL, USA · College of Science and Engineering, Hamad Bin Khalifa University, Doha, Qatar

  28. 1-Bit Wonder: Improving QAT Performance in the Low-Bit Regime through K-Means Quantization

    Feb 17, 2026Sohir Maskey, Constantin Eichenberg, Johannes Messner +1QuantizationLLM Quantization

    Aleph Alpha Research · Graphcore Research

  29. Pushing Toward the Simplex Vertices: A Simple Remedy for Code Collapse in Smoothed Vector Quantization

    Sep 26, 2025Takashi MoritaLearned Image CompressionVector Quantization

    Academy of Emerging Sciences, Chubu University · Institute for Advanced Research, Nagoya University

  30. Discrete Tokenization for Multimodal LLMs: A Comprehensive Survey

    Jul 21, 2025Jindong Li, Yali Fu, Jiahong Liu +5Multimodal Large Language ModelsVector Quantization

    Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China · Jilin University, Changchun, China · The Chinese University of Hong Kong, Hong Kong, China +2