# CTR-Driven Advertising Image Generation with Multimodal Large Language Models

arXiv: https://arxiv.org/abs/2502.06823 · HTML: https://mlsanity.com/paper/2502.06823/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Placed in Document understanding and multimodal RAG, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 26 of its 56 references that are in the map.
- First posted on arXiv 5 Feb 2025.

## Placed in

- Multimodal LLMs / vision-language models / [Document understanding and multimodal RAG](https://mlsanity.com/mllm/document-understanding-and-multimodal-rag/)

## Builds on (most cited first, 26 of 26)

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Deep reinforcement learning from human preferences](https://mlsanity.com/paper/1706.03741/) (2017)
- [Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2204.05862/) (2022)
- [LLaVA-OneVision: Easy Visual Task Transfer](https://mlsanity.com/paper/2408.03326/) (2024)
- [Learning to summarize from human feedback](https://mlsanity.com/paper/2009.01325/) (2020)
- [RePaint: Inpainting using Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2201.09865/) (2022)
- [ChatGLM: A Family of Large Language Models from GLM-130B to GLM-4 All Tools](https://mlsanity.com/paper/2406.12793/) (2024)
- [Interactive Learning from Policy-Dependent Human Feedback](https://mlsanity.com/paper/1701.06049/) (2017)
- [Personalizing Reinforcement Learning from Human Feedback with Variational Preference Learning](https://mlsanity.com/paper/2408.10075/) (2024)
- [Distributional Preference Learning: Understanding and Accounting for Hidden Context in RLHF](https://mlsanity.com/paper/2312.08358/) (2023)
- [Relation-Aware Diffusion Model for Controllable Poster Layout Generation](https://mlsanity.com/paper/2306.09086/) (2023)
- [Learning to Create Better Ads: Generation and Ranking Approaches for Ad Creative Refinement](https://mlsanity.com/paper/2008.07467/) (2020)
- [CREATER: CTR-driven Advertising Text Generation with Controlled Pre-Training and Contrastive Fine-Tuning](https://mlsanity.com/paper/2205.08943/) (2022)
- [Generate E-commerce Product Background by Integrating Category Commonality and Personalized Style](https://mlsanity.com/paper/2312.13309/) (2023)
- [A Hybrid Bandit Model with Visual Priors for Creative Ranking in Display Advertising](https://mlsanity.com/paper/2102.04033/) (2021)
- [VirtualModel: Generating Object-ID-retentive Human-object Interaction Image by Diffusion Model for E-commerce Marketing](https://mlsanity.com/paper/2405.09985/) (2024)
- [Automated Creative Optimization for E-Commerce Advertising](https://mlsanity.com/paper/2103.00436/) (2021)
- [Image Matters: Visually modeling user behaviors using Advanced Model Server](https://mlsanity.com/paper/1711.06505/) (2017)
- [Towards Personalized Bundle Creative Generation with Contrastive Non-Autoregressive Decoding](https://mlsanity.com/paper/2205.14970/) (2022)
- [InsertDiffusion: Identity Preserving Visualization of Objects through a Training-Free Diffusion Architecture](https://mlsanity.com/paper/2407.10592/) (2024)

## Built on by (most cited first, 14 of 14)

- [Uni-Layout: Integrating Human Feedback in Unified Layout Generation and Evaluation](https://mlsanity.com/paper/2508.02374/) (2025)
- [BannerAgency: Advertising Banner Design with Multimodal LLM Agents](https://mlsanity.com/paper/2503.11060/) (2025)
- [Lay2Story: Extending Diffusion Transformers for Layout-Togglable Story Generation](https://mlsanity.com/paper/2508.08949/) (2025)
- [One Size, Many Fits: Aligning Diverse Group-Wise Click Preferences in Large-Scale Advertising Image Generation](https://mlsanity.com/paper/2602.02033/) (2026)
- [T2IBias: Uncovering Societal Bias Encoded in the Latent Space of Text-to-Image Generative Models](https://mlsanity.com/paper/2511.10089/) (2025)
- [OMS: On-the-fly, Multi-Objective, Self-Reflective Ad Keyword Generation via LLM Agent](https://mlsanity.com/paper/2507.02353/) (2025)
- [Self-Reasoning Agentic Framework for Narrative Product Grid-Collage Generation](https://mlsanity.com/paper/2604.16958/) (2026)
- [Design Your Ad: Personalized Advertising Image and Text Generation with Unified Autoregressive Models](https://mlsanity.com/paper/2605.12138/) (2026)
- [AI-Generated Content in Cross-Domain Applications: Research Trends, Challenges and Propositions](https://mlsanity.com/paper/2509.11151/) (2025)
- [KD-CVG: A Knowledge-Driven Approach for Creative Video Generation](https://mlsanity.com/paper/2604.21362/) (2026)
- [GeoReward: Mitigating Contextual Variable Overestimation in Vision-Language Models for Cross-Market Preference Prediction](https://mlsanity.com/paper/2608.04504/) (2026)
- [AgenticGen: Reward-Guided Agentic Video Generation for Advertising](https://mlsanity.com/paper/2609.09187/) (2026)
- [KwaiMind Technical Report](https://mlsanity.com/paper/2609.26375/) (2026)
- [How Can Recommendation Feedback Evolve Agent Memory?](https://mlsanity.com/paper/2609.37544/) (2026)

## Abstract (arXiv)

In web data, advertising images are crucial for capturing user attention and improving advertising effectiveness. Most existing methods generate background for products primarily focus on the aesthetic quality, which may fail to achieve satisfactory online performance. To address this limitation, we explore the use of Multimodal Large Language Models (MLLMs) for generating advertising images by optimizing for Click-Through Rate (CTR) as the primary objective. Firstly, we build targeted pre-training tasks, and leverage a large-scale e-commerce multimodal dataset to equip MLLMs with initial capabilities for advertising image generation tasks. To further improve the CTR of generated images, we propose a novel reward model to fine-tune pre-trained MLLMs through Reinforcement Learning (RL), which can jointly utilize multimodal features and accurately reflect user click preferences. Meanwhile, a product-centric preference optimization strategy is developed to ensure that the generated background content aligns with the product characteristics after fine-tuning, enhancing the overall relevance and effectiveness of the advertising images. Extensive experiments have demonstrated that our method achieves state-of-the-art performance in both online and offline metrics. Our code and pre-trained models are publicly available at: https://github.com/Chenguoz/CAIG.