pipeline_tag: image-feature-extraction
Image Tokenizer Needs Post-Training
This repository contains the official implementation and checkpoints for the paper Image Tokenizer Needs Post-Training.
Project page: https://qiuk2.github.io/works/RobusTok/index.html Code: https://github.com/qiuk2/RobusTok
TL;DR
We present RobusTok, a new image tokenizer with a two-stage training scheme:
Main training → constructs a robust latent space.
Post-training → aligns the generator’s latent distribution with its image space.
Key highlights of Post-Training
- 🚀 Better generative quality: gFID 1.60 → 1.36.
- 🔑 Generalizability: applicable to both autoregressive & diffusion models.
- ⚡ Efficiency: strong results with only ~400M generative models.
Model Zoo
| Generator \ Tokenizer | RobusTok w/o. P.T(weights) | RobusTok w/. P.T (weights) |
|---|---|---|
| Base (weights) | gFID = 1.83 | gFID = 1.60 |
| Large (weights) | gFID = 1.60 | gFID = 1.36 |
Usage
For detailed installation, training, and inference instructions, please refer to the GitHub repository.
Visualization
visualization of 256×256 image generation before (top) and after (bottom) post-training. Three improvements are observed: (a) OOD mitigation, (b) Color fidelity, (c) detail refinement.
Citation
If our work assists your research, feel free to give us a star ⭐ or cite us using
@misc{qiu2025imagetokenizerneedsposttraining,
title={Image Tokenizer Needs Post-Training},
author={Kai Qiu and Xiang Li and Hao Chen and Jason Kuen and Xiaohao Xu and Jiuxiang Gu and Yinyi Luo and Bhiksha Raj and Zhe Lin and Marios Savvides},
year={2025},
eprint={2509.12474},
archivePrefix={arXiv},
primaryClass={cs.CV},
url={https://arxiv.org/abs/2509.12474},
}