高度压缩的标记化器可无需训练生成
摘要
常用的图像标记化器产生一组在二维网格中空间排列的标记。相比之下，所谓的一维图像标记化器将图像表示为高度压缩的一维离散标记序列，最多仅包含32个离散标记。我们发现，具有向量量化的一维标记化器实现的高压缩率，通过对标记进行启发式操作即可实现图像编辑和生成能力， demonstrate that even very crude manipulations -- such as copying and replacing tokens between latent representations of images -- enable fine-grained image editing by transferring appearance and semantic attributes. Motivated by the expressivity of the 1D tokenizer's latent space, we construct an image generation pipeline leveraging gradient-based test-time optimization of tokens with plug-and-play loss functions such as reconstruction or CLIP similarity. Our approach is demonstrated for inpainting and text-guided image editing use cases, and can generate diverse and realistic samples without requiring training of any generative model.
引用
@article{arxiv.2506.08257,
title = {Highly Compressed Tokenizer Can Generate Without Training},
author = {L. Lao Beyer and T. Li and X. Chen and S. Karaman and K. He},
journal= {arXiv preprint arXiv:2506.08257},
year = {2025}
}
备注
Main manuscript: 9 pages, 7 figures. Appendix: 8 pages, 9 figures. To appear in the Proceedings of the 42nd International Conference on Machine Learning