Generating realistic and user-preferred advertisements is a key challenge in e-commerce. Existing approaches utilize multiple independent models driven by click-through-rate (CTR) to controllably create attractive image or text advertisements. However, their pipelines lack cross-modal perception and rely on CTR that only reflects average preferences. Therefore, we explore jointly generating personalized image-text advertisements from historical click behaviors. We first design a Unified Advertisement Generative model (Uni-AdGen) that employs a single autoregressive framework to produce both advertising images and texts. By incorporating a foreground perception module and instruction tuning, Uni-AdGen enhances the realism of the generated content. To further personalize advertisements, we equip Uni-AdGen with a coarse-to-fine preference understanding module that effectively captures user interests from noisy multimodal historical behaviors to drive personalized generation. Additionally, we construct the first large-scale Personalized Advertising image-text dataset (PAd1M) and introduce a Product Background Similarity (PBS) metric to facilitate training and evaluation. Extensive experiments show that our method outperforms baselines in general and personalized advertisement generation. Our project is available at https://github.com/JD-GenX/Uni-AdGen.
@article{arxiv.2605.12138,
title = {Design Your Ad: Personalized Advertising Image and Text Generation with Unified Autoregressive Models},
author = {Yexing Xu and Wei Feng and Shen Zhang and Haohan Wang and Yuxin Qin and Yaoyu Li and Ao Ma and Yuhao Luo and Lu Wang and Xudong Ren and Haoran Wang and Run Ling and Zheng Zhang and Jingjing Lv and Junjie Shen and Ching Law and Longguang Wang and Yulan Guo},
journal= {arXiv preprint arXiv:2605.12138},
year = {2026}
}