Show-O: One Single Transformer to Unify Multimodal Understanding and Generation
Abstract
We present a unified transformer, i.e., Show-o, that unifies multimodal understanding and generation. Unlike fully autoregressive models, Show-o unifies autoregressive and (discrete) diffusion modeling to adaptively handle inputs and outputs of various and mixed modalities. The unified model flexibly supports a wide range of vision-language tasks including visual question-answering, text-to-image generation, text-guided inpainting/extrapolation, and mixed-modality generation. Across various benchmarks, it demonstrates comparable or superior performance to existing individual models with an equivalent or larger number of parameters tailored for understanding or generation. This significantly highlights its potential as a next-generation foundation model.
Cite
Text
Xie et al. "Show-O: One Single Transformer to Unify Multimodal Understanding and Generation." International Conference on Learning Representations, 2025.Markdown
[Xie et al. "Show-O: One Single Transformer to Unify Multimodal Understanding and Generation." International Conference on Learning Representations, 2025.](https://mlanthology.org/iclr/2025/xie2025iclr-showo/)BibTeX
@inproceedings{xie2025iclr-showo,
title = {{Show-O: One Single Transformer to Unify Multimodal Understanding and Generation}},
author = {Xie, Jinheng and Mao, Weijia and Bai, Zechen and Zhang, David Junhao and Wang, Weihao and Lin, Kevin Qinghong and Gu, Yuchao and Chen, Zhijie and Yang, Zhenheng and Shou, Mike Zheng},
booktitle = {International Conference on Learning Representations},
year = {2025},
url = {https://mlanthology.org/iclr/2025/xie2025iclr-showo/}
}