设计你的广告：基于统一自回归模型的个性化广告图像与文本生成
Design Your Ad: Personalized Advertising Image and Text Generation with Unified Autoregressive Models
把图像与文本放进同一个自回归框架联合生成，并用粗到细的偏好理解模块从噪声多模态历史行为中抽取用户兴趣作为生成条件，为视觉生成中的个性化条件注入提供了可复用的范式；其前景感知模块与产品背景相似度指标也可直接用于电商图像生成的质量控制。
原文依据 employs a single autoregressive framework to produce both advertising images and texts
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论生成真实且符合用户偏好的广告是电子商务中的一项关键挑战。现有方法使用多个由点击率（CTR）驱动的独立模型来可控地生成有吸引力的图像或文本广告。然而，这些流程缺乏跨模态感知，且依赖仅反映平均偏好的点击率。因此，我们探索从历史点击行为中联合生成个性化图文广告。我们首先设计了一个统一广告生成模型（Uni-AdGen），它采用单一自回归框架同时生成广告图像与文本。通过引入前景感知模块与指令微调，Uni-AdGen 提升了生成内容的真实感。为进一步实现广告个性化，我们为 Uni-AdGen 配备了一个粗到细的偏好理解模块，能够从噪声多模态历史行为中有效捕捉用户兴趣，以驱动个性化生成。此外，我们构建了首个大规模个性化广告图文数据集（PAd1M），并提出产品背景相似度（PBS）指标以促进训练与评测。大量实验表明，我们的方法在通用广告生成与个性化广告生成上均优于基线。数据集与代码将在论文录用后发布。
英文原文摘要 1361 字符
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. The dataset and codes will be released after acceptance.