ICG: Improving Cover Image Generation via MLLM-based Prompting and Personalized Preference Alignment
ICG is a novel framework that integrates MLLM-based prompting with personalized preference alignment to generate high-quality, contextually relevant cover images. It extracts semantic features via meta tokens, refines them with user embeddings, and injects personalized context into diffusion models. A multi-reward learning strategy combines public rewards with a personalized preference model, eliminating the need for labeled supervision. Experiments show improvements in image quality, semantic fidelity, and personalization, boosting user appeal and recommendation accuracy.
Article intelligence
Key points
- ICG integrates MLLM prompting with personalized preference alignment for end-to-end cover image generation.
- Semantic features are extracted via meta tokens and refined with user embeddings for diffusion model injection.
- Multi-reward learning utilizes public rewards and a personalized preference model without labeled data.
- Experiments demonstrate enhanced image quality, semantic fidelity, and personalization.
Why it matters
This matters because ICG integrates MLLM prompting with personalized preference alignment for end-to-end cover image generation.
Technical impact
May affect model selection, inference cost, product capability, and evaluation benchmarks.
[2605.27374] ICG: Improving Cover Image Generation via MLLM-based Prompting and Personalized Preference Alignment
[Submitted on 8 Apr 2026]
Title:ICG: Improving Cover Image Generation via MLLM-based Prompting and Personalized Preference Alignment
View a PDF of the paper titled ICG: Improving Cover Image Generation via MLLM-based Prompting and Personalized Preference Alignment, by Zhipeng Bian and 8 other authors
View PDF HTML (experimental)
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.
Comments: Published in Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, pages 12268-12278, EMNLP 2025. Official version: this https URL
Subjects:
Computation and Language (cs.CL)
ACM classes: I.2.7; I.2.10
Cite as: arXiv:2605.27374 [cs.CL]
(or arXiv:2605.27374v1 [cs.CL] for this version)
https://doi.org/10.48550/arXiv.2605.27374
arXiv-issued DOI via DataCite
Journal reference: Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing (Main Track) EMNLP 2025 12268-12278
Related DOI:
https://doi.org/10.18653/v1/2025.emnlp-main.617
DOI(s) linking to related resources
Submission history
From: Zhipeng Bian [view email] [v1] Wed, 8 Apr 2026 06:36:54 UTC (2,524 KB)
Full-text links:
Access Paper:
View a PDF of the paper titled ICG: Improving Cover Image Generation via MLLM-based Prompting and Personalized Preference Alignment, by Zhipeng Bian and 8 other authors
View PDF
HTML (experimental)
TeX Source
view license
Current browse context:
cs.CL
new | recent | 2026-05
Change to browse by:
cs
References & Citations
NASA ADS
Google Scholar
Semantic Scholar
Loading...
Data provided by:
Bibliographic Tools
Bibliographic and Citation Tools
Bibliographic Explorer Toggle
Bibliographic Explorer (What is the Explorer?)
Connected Papers Toggle
Connected Papers (What is Connected Papers?)
Litmaps Toggle
Litmaps (What is Litmaps?)
scite.ai Toggle
scite Smart Citations (What are Smart Citations?)
Code, Data, Media
Code, Data and Media Associated with this Article
alphaXiv Toggle
alphaXiv (What is alphaXiv?)
Links to Code Toggle
CatalyzeX Code Finder for Papers (What is CatalyzeX?)
DagsHub Toggle
DagsHub (What is DagsHub?)
GotitPub Toggle
Gotit.pub (What is GotitPub?)
Huggingface Toggle
Hugging Face (What is Huggingface?)
ScienceCast Toggle
ScienceCast (What is ScienceCast?)
Demos
Demos
Replicate Toggle
Replicate (What is Replicate?)
Spaces Toggle
Hugging Face Spaces (What is Spaces?)
Spaces Toggle
TXYZ.AI (What is TXYZ.AI?)
Related Papers
Recommenders and Search Tools
Link to Influence Flower
Influence Flower (What are Influence Flowers?)
Core recommender toggle
CORE Recommender (What is CORE?)
Author
Venue
Institution
Topic
About arXivLabs
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)