# Evolving Creatives with Clicks: CTR-Driven Advertising image Editing via Attribute Disentanglement and Preference Alignment arXiv: https://arxiv.org/abs/2610.13066 ยท HTML: https://mlsanity.com/paper/2610.13066/ ## Key facts - No citing papers in the map yet (data through 14 Oct 2026). - Placed in Diffusion and multimodal model alignment, one of 10 directions in LLM alignment / RLHF / preference optimisation. - Builds on 27 of its 40 references that are in the map. - First posted on arXiv 9 Oct 2026. ## Placed in - LLM alignment / RLHF / preference optimisation / [Diffusion and multimodal model alignment](https://mlsanity.com/alignment/diffusion-and-multimodal-model-alignment/) ## Builds on (most cited first, 27 of 27) - [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020) - [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023) - [Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution](https://mlsanity.com/paper/2409.12191/) (2024) - [LAION-5B: An open large-scale dataset for training next generation image-text models](https://mlsanity.com/paper/2210.08402/) (2022) - [Sigmoid Loss for Language Image Pre-Training](https://mlsanity.com/paper/2303.15343/) (2023) - [DeepFM: A Factorization-Machine based Neural Network for CTR Prediction](https://mlsanity.com/paper/1703.04247/) (2017) - [MagicBrush: A Manually Annotated Dataset for Instruction-Guided Image Editing](https://mlsanity.com/paper/2306.10012/) (2023) - [SWIFT:A Scalable lightWeight Infrastructure for Fine-Tuning](https://mlsanity.com/paper/2408.05517/) (2024) - [Emu Edit: Precise Image Editing via Recognition and Generation Tasks](https://mlsanity.com/paper/2311.10089/) (2023) - [xDeepFM: Combining Explicit and Implicit Feature Interactions for Recommender Systems](https://mlsanity.com/paper/1803.05170/) (2018) - [AnyEdit: Mastering Unified High-Quality Image Editing for Any Idea](https://mlsanity.com/paper/2411.15738/) (2024) - [HQ-Edit: A High-Quality Dataset for Instruction-based Image Editing](https://mlsanity.com/paper/2404.09990/) (2024) - [Provably Robust DPO: Aligning Language Models with Noisy Feedback](https://mlsanity.com/paper/2403.00409/) (2024) - [Pico-Banana-400K: A Large-Scale Dataset for Text-Guided Image Editing](https://mlsanity.com/paper/2510.19808/) (2025) - [Relation-Aware Diffusion Model for Controllable Poster Layout Generation](https://mlsanity.com/paper/2306.09086/) (2023) - [Eliminating Biased Length Reliance of Direct Preference Optimization via Down-Sampled KL Divergence](https://mlsanity.com/paper/2406.10957/) (2024) - [Learning to Create Better Ads: Generation and Ranking Approaches for Ad Creative Refinement](https://mlsanity.com/paper/2008.07467/) (2020) - [A New Creative Generation Pipeline for Click-Through Rate with Stable Diffusion Model](https://mlsanity.com/paper/2401.10934/) (2024) - [On the Limited Generalization Capability of the Implicit Reward Model Induced by Direct Preference Optimization](https://mlsanity.com/paper/2409.03650/) (2024) - [CREATER: CTR-driven Advertising Text Generation with Controlled Pre-Training and Contrastive Fine-Tuning](https://mlsanity.com/paper/2205.08943/) (2022) - [Towards Reliable Advertising Image Generation Using Human Feedback](https://mlsanity.com/paper/2408.00418/) (2024) - [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) - [Instruction-based Image Manipulation by Watching How Things Move](https://mlsanity.com/paper/2412.12087/) (2024) - [Staging E-Commerce Products for Online Advertising using Retrieval Assisted Image Generation](https://mlsanity.com/paper/2307.15326/) (2023) ## Abstract (arXiv) The optimization objective for e-commerce advertising creatives has shifted from aesthetic quality to online business metrics like click-through rate (CTR). Recent methods generate appealing ad images from product images by constructing CTR-based reward signals and refining prompt generation via Reinforcement Learning. Such paradigms equally penalize all attributes within an underperforming image, even though some are actually beneficial to clicks. In this work, we propose Evolving Creatives with Clicks (ECC), which reformulates creative optimization as fine-grained editing rather than generation from scratch. ECC selectively refines attributes that hurt CTR while preserving those that contribute positively. Specifically, faced with a rich attribute space across massive images, ECC first identifies 28 attributes significantly correlated with CTR via ANOVA and Random Forest regression. Based on attribute contrasts between images with disparate CTRs, we instruction-tune a prompt model to generate editing suggestions, then refine it with real click preferences since reference-derived suggestions are not uniformly beneficial. Furthermore, we introduce Consistent Preference Optimization (CPO) as ECC's preference optimization strategy, which enforces consistency across semantically equivalent shuffled suggestions to mitigate DPO overfitting and improve preference generalization. Extensive experiments demonstrate that ECC significantly improves the CTR of ad images, outperforming state-of-the-art models by a substantial margin. The complete data pipeline, including attribute extraction and analysis, the resulting dataset, and source code will be released upon acceptance.