Codebook Collapse

Follow this topic Ask about this topic

Latest papers

8 papers1 paper in the last four weeks, with none the four weeks before. 0.0% of all new papers.

Transporting Quantiles to Codebook: Scalable Vector Quantization without Codebook Collapse
Oct 26, 2026Yuwei Zeng, Zekun ShiCodebook Collapse Vector Quantization
National University of Singapore · SEA AI Lab
Distributional Matching for Vector Quantization: A Unified Theoretical and Empirical Framework
Jul 17, 2026Xianghong Fang, Litao Guo, Hengchao Chen +8Codebook Collapse Distribution Matching
University of Toronto · The Hong Kong University of Science and Technology · Lehigh University +2
NSVQ: Mitigating Codebook Collapse by Stabilizing Encoder Drift in Vector Quantization
Jun 9, 2026Hao Lu, Yongxin Guo, Onur Koyun +3Codebook Collapse Vector Quantization
Wake Forest University School of Medicine / Advocate Health · Wake Forest University School of Medicine · Advocate Health
Early Quantization Shrinks Codebook: A Simple Fix for Diversity-Preserving Tokenization
Mar 17, 2026Wenhao Zhao, Qiran Zou, Rushi Shah +3Codebook Collapse Vector Quantization
National University of Singapore · Zhejiang University · Shanghai Jiao Tong University
Beyond Stationarity: Rethinking Codebook Collapse in Vector Quantization
Feb 21, 2026Hao Lu, Onur C. Koyun, Yongxin Guo +3Codebook Collapse Vector Quantization
Wake Forest University School of Medicine, Winston-Salem, NC, USA
VP-VAE: Rethinking Vector Quantization via Adaptive Vector Perturbation
Feb 19, 2026Linwei Zhai, Han Ding, Mingzhi Lin +5Codebook Collapse Finite Scalar Quantization
Xi’an Jiaotong University, China
LGQ: Learnable Geometric Quantization for Image Tokenization
Feb 17, 2026Idil Bilge Altun, Mert Onur Cakiroglu, Elham Buxton +2Codebook Collapse Image Tokenization
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
Pushing Toward the Simplex Vertices: A Simple Remedy for Code Collapse in Smoothed Vector Quantization
Sep 26, 2025Takashi MoritaCodebook Collapse Learned Image Compression
Academy of Emerging Sciences, Chubu University · Institute for Advanced Research, Nagoya University

Oct 26, 2026J/K move · Enter open · S save

Transporting Quantiles to Codebook: Scalable Vector Quantization without Codebook Collapse

Yuwei Zeng, Zekun Shi

National University of Singapore · SEA AI Lab

Codebook Collapse Vector Quantization Vector-Quantized Variational Autoencoder Image Tokenization

Open paper AskPDF arXiv

Effective discrete representation learning with VQ-VAE serves as a fundamental component of modern autoregressive generative models. However, it is widely known to suffer from codebook collapse and inefficient code utilization. To address this issue, we propose FlowVQ, a simple yet effective alternative to standard vector quantization by formulating neural quantization as a joint modeling and clustering process. Specifically, we learn the latent space using a lightweight flow matching model alongside training, corresponding to a probability flow ODE that transports an often fixed well-behaved source distribution while preserving probability mass. Based on this, we define the codebook C_1 by transporting even-quantile partitioned prior codes C_0 from the source space through the learned flow, and obtaining the Voronoi centroids under the induced distribution, leading to a structured discretization. We evaluated on image tokenization and generation, as well as on two tasks requiring high-precision tokenization, demonstrating scalability and improved expressivity of the codebook with full utilization.