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

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Xu, Yexing, Feng, Wei, Zhang, Shen, Wang, Haohan, Qin, Yuxin, Li, Yaoyu, Ma, Ao, Luo, Yuhao, Wang, Lu, Ren, Xudong, Wang, Haoran, Ling, Run, Zhang, Zheng, Lv, Jingjing, Shen, Junjie, Law, Ching, Wang, Longguang, Guo, Yulan
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866911674403913728
author Xu, Yexing
Feng, Wei
Zhang, Shen
Wang, Haohan
Qin, Yuxin
Li, Yaoyu
Ma, Ao
Luo, Yuhao
Wang, Lu
Ren, Xudong
Wang, Haoran
Ling, Run
Zhang, Zheng
Lv, Jingjing
Shen, Junjie
Law, Ching
Wang, Longguang
Guo, Yulan
author_facet Xu, Yexing
Feng, Wei
Zhang, Shen
Wang, Haohan
Qin, Yuxin
Li, Yaoyu
Ma, Ao
Luo, Yuhao
Wang, Lu
Ren, Xudong
Wang, Haoran
Ling, Run
Zhang, Zheng
Lv, Jingjing
Shen, Junjie
Law, Ching
Wang, Longguang
Guo, Yulan
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2605_12138
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Design Your Ad: Personalized Advertising Image and Text Generation with Unified Autoregressive Models
Xu, Yexing
Feng, Wei
Zhang, Shen
Wang, Haohan
Qin, Yuxin
Li, Yaoyu
Ma, Ao
Luo, Yuhao
Wang, Lu
Ren, Xudong
Wang, Haoran
Ling, Run
Zhang, Zheng
Lv, Jingjing
Shen, Junjie
Law, Ching
Wang, Longguang
Guo, Yulan
Computer Vision and Pattern Recognition
Computation and Language
Information Retrieval
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.
title Design Your Ad: Personalized Advertising Image and Text Generation with Unified Autoregressive Models
topic Computer Vision and Pattern Recognition
Computation and Language
Information Retrieval
url https://arxiv.org/abs/2605.12138