Design Your Ad: Personalized Advertising Image and Text Generation with Unified Autoregressive Models

2026-05-12

AI Summary

Existing ad generation methods rely on multiple models and only capture average click preferences, lacking cross-modal awareness and personalization capabilities. This work proposes Uni-AdGen, a unified autoregressive model that achieves end-to-end joint generation of image-text advertisements for the first time. By integrating foreground-aware modeling, instruction fine-tuning, and a coarse-to-fine multimodal user preference understanding mechanism, Uni-AdGen accurately captures individual interests from users’ click histories to guide ad generation. The contributions include constructing PAd1M—the first large-scale personalized ad dataset—introducing the Product Background Similarity (PBS) evaluation metric, and demonstrating significant performance gains over existing approaches in both general and personalized ad generation tasks, yielding results with higher realism and user relevance.

Abstract

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.

Problem

• personalized advertising
• image-text generation
• cross-modal perception
• user preference modeling
• CTR

Innovation

• Unified Autoregressive Model
• Personalized Advertisement Generation
• Cross-modal Perception
• Preference Understanding
• Image-Text Co-generation