ICG: Improving Cover Image Generation via MLLM-based Prompting and Personalized Preference Alignment

• URL: http://arxiv.org/abs/2605.27374v1
• Date: Wed, 08 Apr 2026 06:36:54 GMT
• Title: ICG: Improving Cover Image Generation via MLLM-based Prompting and Personalized Preference Alignment
• Abstract summary: We propose ICG, a framework that integrates MLLM-based prompting with personalized preference alignment to generate contextually relevant covers.<n>ICG extracts semantic features from item titles and reference images via meta tokens, refines them with user embeddings, and injects the resulting personalized context into the diffusion model.<n>Experiments demonstrate that ICG significantly improves image quality, semantic fidelity, and personalization, leading to stronger user appeal and offline recommendation accuracy.
• Score: 70.19758313256503
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recent advances in multimodal large language models (MLLMs) and diffusion models (DMs) have opened new possibilities for AI-generated content. Yet, personalized cover image generation remains underexplored, despite its critical role in boosting user engagement on digital platforms. We propose ICG, a novel framework that integrates MLLM-based prompting with personalized preference alignment to generate high-quality, contextually relevant covers. ICG extracts semantic features from item titles and reference images via meta tokens, refines them with user embeddings, and injects the resulting personalized context into the diffusion model. To address the lack of labeled supervision, we adopt a multi-reward learning strategy that combines public aesthetic and relevance rewards with a personalized preference model trained from user behavior. Unlike prior pipelines relying on handcrafted prompts and disjointed modules, ICG employs an adapter to bridge MLLMs and diffusion models for end-to-end training. Experiments demonstrate that ICG significantly improves image quality, semantic fidelity, and personalization, leading to stronger user appeal and offline recommendation accuracy in downstream tasks. As a plug-and-play adapter bridging MLLMs and diffusion models, ICG is compatible with common checkpoints and requires no ground-truth labels during optimization.

Related papers

• Failure-Informed Image Self-Augmentation for Multimodal Large Language Model Self-Improvement [50.97806700110183]
  Failure-informed Image Self-Augmentation (textbfFISA) is a framework for MLLM self-improvement that constructs augmented images from the model's own failure cases.<n>Our method generates visually challenging yet answer-preserving image complications, verifies their utility through self-examination, and applies dual fidelity filtering to avoid semantic distortion.
  arXiv  Detail & Related papers  (2026-08-04T14:28:42Z)
• Squeezing Capacity from Multimodal Large Language Models for Subject-driven Generation [22.419513267677278]
  Existing approaches often encode text and reference images separately.<n>Recent frameworks that connect multimodal models and diffusion models improve instruction following, but largely overlook identity preservation.<n>We condition diffusion models on Multimodal Large Language Models that jointly encode text and reference images, and augment it with VAE-based identity conditioning.<n>Our approach harmonizes multimodal understanding with identity preservation, mitigates copy-paste issues, and achieves superior performance regarding human preference on subject-driven image generation.
  arXiv  Detail & Related papers  (2026-05-25T17:59:35Z)
• UniCustom: Unified Visual Conditioning for Multi-Reference Image Generation [65.53694602893042]
  We propose a unified visual conditioning framework that fuses ViT and VAE features before VLM encoding.<n>Experiments on two multi-reference generation benchmarks demonstrate that UniCustom consistently improves subject consistency, instruction following, and compositional fidelity.
  arXiv  Detail & Related papers  (2026-05-12T13:10:05Z)
• PrefGen: Multimodal Preference Learning for Preference-Conditioned Image Generation [44.638427866399205]
  Preference-conditioned image generation seeks to adapt generative models to individual users, producing outputs that reflect personal aesthetic choices beyond the given prompt.<n>We propose a framework that leverages multimodal large language models to extract rich user representations and inject them into diffusion-based image generation.<n>Our method substantially outperforms strong baselines in both image quality and preference alignment.
  arXiv  Detail & Related papers  (2025-12-04T02:57:29Z)
• Growing Visual Generative Capacity for Pre-Trained MLLMs [60.826355079902505]
  Bridge is a pure autoregressive unified MLLM that augments pre-trained visual understanding models with generative ability.<n>We propose a semantic-to-pixel discrete representation that integrates compact semantic tokens with fine-grained pixel tokens.
  arXiv  Detail & Related papers  (2025-10-02T00:40:02Z)
• IMG: Calibrating Diffusion Models via Implicit Multimodal Guidance [74.89810064807142]
  Implicit Multimodal Guidance (IMG) is a novel re-generation-based multimodal alignment framework.<n>IMG identifies misalignments and formulates the re-alignment goal into a trainable objective.<n>IMG acts as a flexible plug-and-play adapter, seamlessly enhancing prior finetuning-based alignment methods.
  arXiv  Detail & Related papers  (2025-09-30T13:27:03Z)
• DRC: Enhancing Personalized Image Generation via Disentangled Representation Composition [69.10628479553709]
  We introduce DRC, a novel personalized image generation framework that enhances Large Multimodal Models (LMMs)<n> DRC explicitly extracts user style preferences and semantic intentions from history images and the reference image, respectively.<n>It involves two critical learning stages: 1) Disentanglement learning, which employs a dual-tower disentangler to explicitly separate style and semantic features, optimized via a reconstruction-driven paradigm with difficulty-aware importance sampling; and 2) Personalized modeling, which applies semantic-preserving augmentations to effectively adapt the disentangled representations for robust personalized generation.
  arXiv  Detail & Related papers  (2025-04-24T08:10:10Z)
• Towards Generative Class Prompt Learning for Fine-grained Visual Recognition [5.633314115420456]
  Generative Class Prompt Learning and Contrastive Multi-class Prompt Learning are presented. Generative Class Prompt Learning improves visio-linguistic synergy in class embeddings by conditioning on few-shot exemplars with learnable class prompts. CoMPLe builds on this foundation by introducing a contrastive learning component that encourages inter-class separation.
  arXiv  Detail & Related papers  (2024-09-03T12:34:21Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.