One Size, Many Fits: Aligning Diverse Group-Wise Click Preferences in Large-Scale Advertising Image Generation

TL;DR

This paper introduces a unified framework called OSMF that aligns diverse user group preferences in advertising image generation, improving targeted marketing effectiveness through adaptive grouping, preference-conditioned generation, and preference alignment.

Contribution

The paper presents a novel framework combining adaptive user grouping, a preference-aware multimodal model, and a new dataset for large-scale group-wise preference alignment in advertising images.

Findings

Achieves state-of-the-art offline performance

Improves online CTR for targeted groups

Introduces the first large-scale group preference dataset

Abstract

Advertising image generation has increasingly focused on online metrics like Click-Through Rate (CTR), yet existing approaches adopt a ``one-size-fits-all" strategy that optimizes for overall CTR while neglecting preference diversity among user groups. This leads to suboptimal performance for specific groups, limiting targeted marketing effectiveness. To bridge this gap, we present \textit{One Size, Many Fits} (OSMF), a unified framework that aligns diverse group-wise click preferences in large-scale advertising image generation. OSMF begins with product-aware adaptive grouping, which dynamically organizes users based on their attributes and product characteristics, representing each group with rich collective preference features. Building on these groups, preference-conditioned image generation employs a Group-aware Multimodal Large Language Model (G-MLLM) to generate tailored images for each group. The G-MLLM is pre-trained to simultaneously comprehend group features and generate advertising images. Subsequently, we fine-tune the G-MLLM using our proposed Group-DPO for group-wise preference alignment, which effectively enhances each group's CTR on the generated images. To further advance this field, we introduce the Grouped Advertising Image Preference Dataset (GAIP), the first large-scale public dataset of group-wise image preferences, including around 600K groups built from 40M users. Extensive experiments demonstrate that our framework achieves the state-of-the-art performance in both offline and online settings. Our code and datasets will be released at https://github.com/JD-GenX/OSMF.