We introduce UniToken, an auto-regressive generation model that encodes visual inputs through a combination of discrete and continuous representations, enabling seamless integration of unified visual understanding and image generation tasks. Unlike previous approaches that rely on unilateral visual representations, our unified visual encoding framework captures both high-level semantics and low-level details, delivering multidimensional information that empowers heterogeneous tasks to selectively assimilate domain-specific knowledge based on their inherent characteristics. Through in-depth experiments, we uncover key principles for developing a unified model capable of both visual understanding and image generation. Extensive evaluations across a diverse range of prominent benchmarks demonstrate that UniToken achieves state-of-the-art performance, surpassing existing approaches. These results establish UniToken as a robust foundation for future research in this domain. The code and models are available atthis https URL.
View on arXiv@article{jiao2025_2504.04423,
title={ UniToken: Harmonizing Multimodal Understanding and Generation through Unified Visual Encoding },
author={ Yang Jiao and Haibo Qiu and Zequn Jie and Shaoxiang Chen and Jingjing Chen and Lin Ma and Yu-Gang Jiang },
journal={arXiv preprint arXiv:2504.04423},
year={ 2025 }
}