# CODA: Repurposing Continuous VAEs for Discrete Tokenization

Source: [CODA: Repurposing Continuous VAEs for Discrete Tokenization](<https://www.sota2.com/research/paper/68fa7bc31e209131cea8a469>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-28T13:57:22.371Z

Authors: Zeyu Liu, Zanlin Ni, Yeguo Hua, Xin Deng, Xiao Ma, Cheng Zhong, Gao Huang

Published: 2025-03-22T12:59:00.000Z

## Abstract

Discrete visual tokenizers transform images into a sequence of tokens, enabling token-based visual generation akin to language models. However, this process is inherently challenging, as it requires both compressing visual signals into a compact representation and discretizing them into a fixed set of codes. Traditional discrete tokenizers typically learn the two tasks jointly, often leading to unstable training, low codebook utilization, and limited reconstruction quality. In this paper, we introduce \\textbf{CODA}(\\textbf{CO}ntinuous-to-\\textbf{D}iscrete \\textbf{A}daptation), a framework that decouples compression and discretization. Instead of training discrete tokenizers from scratch, CODA adapts off-the-shelf continuous VAEs -- already optimized for perceptual compression -- into discrete tokenizers via a carefully designed discretization process. By primarily focusing on discretization, CODA ensures stable and efficient training while retaining the strong visual fidelity of continuous VAEs. Empirically, with $\\mathbf{6 \\times}$ less training budget than standard VQGAN, our approach achieves a remarkable codebook utilization of 100% and notable reconstruction FID (rFID) of $\\mathbf{0.43}$ and $\\mathbf{1.34}$ for $8 \\times$ and $16 \\times$ compression on ImageNet 256$\\times$ 256 benchmark.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2503.17760>)

[PDF](<https://arxiv.org/pdf/2503.17760.pdf>)
