We present CyCLeGen, a unified vision-language foundation model capable of both image understanding and image generation within a single autoregressive framework. Unlike existing vision models that depend on separate modules for perception and synthesis, CyCLeGen adopts a fully integrated architecture that enforces cycle-consistent learning through image->layout->image and layout->image->layout generation loops. This unified formulation introduces two key advantages: introspection, enabling the model to reason about its own generations, and data efficiency, allowing self-improvement via synthetic supervision under a reinforcement learning objective guided by cycle consistency. Extensive experiments show that CyCLeGen achieves significant gains across diverse image understanding and generation benchmarks, highlighting the potential of unified vision-language foundation models.
@article{arxiv.2603.14957,
title = {CyCLeGen: Cycle-Consistent Layout Prediction and Image Generation in Vision Foundation Models},
author = {Xiaojun Shan and Haoyu Shen and Yucheng Mao and Xiang Zhang and Abhay Anand and Bingnan Li and Haiyang Xu and Zhuowen Tu},
journal= {arXiv preprint arXiv:2603.14957},
year = {2026}
}