A Simple Baseline for Unifying Understanding, Generation, and Editing via Vanilla Next-token Prediction
📌 核心贡献
这篇论文，就像给AI找了个万能翻译官，只教它“猜下一个词”，结果它就能看懂图片、自己画图，甚至还能修改图片！而且中英文都行，图片大小也不挑。
📖 摘要
In this work, we introduce Wallaroo, a simple autoregressive baseline that leverages next-token prediction to unify multi-modal understanding, image generation, and editing at the same time. Moreover, Wallaroo supports multi-resolution image input and output, as well as bilingual support for both Chinese and English. We decouple the visual encoding into separate pathways and apply a four-stage training strategy to reshape the model’s capabilities. Experiments are conducted on various benchmarks where Wallaroo produces competitive performance or exceeds other unified models, suggesting the great potential of autoregressive models in unifying multi-modality understanding and generation. Our code is available at https://github.com/JiePKU/Wallaroo.
🔍 关键信息
| 字段 | 内容 |
|---|---|
| 发表 | 2026-03-05 |
| 机构 | |
| 分类 | cs.CV |
| 链接 | arXiv |